diff --git a/docs/pipelines/gears.md b/docs/pipelines/gears.md
index 6d8d150a05625fb2a1564ea61974e0d91c6bc099..2b2abf7bbf8d78ddd270c70104cb7d1d8c3cf78c 100644
--- a/docs/pipelines/gears.md
+++ b/docs/pipelines/gears.md
@@ -4,49 +4,52 @@
Gears is a metagenomics pipeline. (``GE``nome ``A``nnotation of ``R``esidual ``S``equences). One can use this pipeline to identify contamination in sequencing runs on either raw FastQ files or BAM files.
In case of BAM file as input, it will extract the unaligned read(pair) sequences for analysis.
-Analysis result is reported in a sunburst graph, which is visible and navigatable in a webbrowser.
+Analysis result is reported in a krona graph, which is visible and navigatable in a webbrowser.
Pipeline analysis components include:
- - Kraken, DerrickWood [GitHub](https://github.com/DerrickWood/kraken)
+ - [Kraken, DerrickWood](https://github.com/DerrickWood/kraken)
+ - [Qiime closed reference](http://qiime.org)
+ - [Qiime rtax](http://qiime.org) (**Experimental**)
+ - SeqCount (**Experimental**)
+## Gears
-## Example
+This pipeline is used to analyse a group of samples. This pipeline only accepts fastq files. The fastq files first get trimmed and clipped with [Flexiprep](Flexiprep). This can be disabled with the config flags of [Flexiprep](Flexiprep). The samples can be specified with a sample config file, see [Config](../general/Config)
-To get the help menu:
+### Config
-``` bash
-biopet pipeline Gears -h
-
-... default config ...
-
-Arguments for Gears:
- -R1,--fastqr1 <fastqr1> R1 reads in FastQ format
- -R2,--fastqr2 <fastqr2> R2 reads in FastQ format
- -bam,--bamfile <bamfile> All unmapped reads will be extracted from this bam for analysis
- --outputname <outputname> Undocumented option
- -sample,--sampleid <sampleid> Sample ID
- -library,--libid <libid> Library ID
- -config,--config_file <config_file> JSON / YAML config file(s)
- -cv,--config_value <config_value> Config values, value should be formatted like 'key=value' or
- 'path:path:key=value'
- -DSC,--disablescatter Disable all scatters
+| Key | Type | default | Function |
+| --- | ---- | ------- | -------- |
+| gears_use_kraken | Boolean | true | Run fastq file with kraken |
+| gears_use_qiime_closed | Boolean | false | Run fastq files with qiime with the closed reference module |
+| gears_use_qiime_rtax | Boolean | false | Run fastq files with qiime with the rtax module |
+| gears_use_seq_count | Boolean | false | Produces raw count files |
+
+### Example
+To start the pipeline (remove `-run` for a dry run):
+
+``` bash
+biopet pipeline Gears -run \
+-config mySettings.json -config samples.json
```
-Note that the pipeline also works on unpaired reads where one should only provide R1.
+## GearsSingle
+
+This pipeline can be used to analyse a single sample, this can be fastq files or a bam file. When a bam file is given only the unmapped reads are extracted.
+### Example
To start the pipeline (remove `-run` for a dry run):
``` bash
-biopet pipeline Gears -run \
+biopet pipeline GearsSingle -run \
-R1 myFirstReadPair -R2 mySecondReadPair -sample mySampleName \
-library myLibname -config mySettings.json
```
-
-## Configuration and flags
+### Commandline flags
For technical reasons, single sample pipelines, such as this pipeline do **not** take a sample config.
Input files are in stead given on the command line as a flag.
@@ -58,17 +61,22 @@ Command line flags for Gears are:
| -R2 | --input_r2 | Path (optional) | Path to second read pair fastq file. |
| -bam | --bamfile | Path (optional) | Path to bam file. |
| -sample | --sampleid | String (**required**) | Name of sample |
-| -library | --libid | String (**required**) | Name of library |
+| -library | --libid | String (optional) | Name of library |
If `-R2` is given, the pipeline will assume a paired-end setup. `-bam` is mutualy exclusive with the `-R1` and `-R2` flags. Either specify `-bam` or `-R1` and/or `-R2`.
### Config
+| Key | Type | default | Function |
+| --- | ---- | ------- | -------- |
+| gears_use_kraken | Boolean | true | Run fastq file with kraken |
+| gears_use_qiime_closed | Boolean | false | Run fastq files with qiime with the closed reference module |
+| gears_use_qiime_rtax | Boolean | false | Run fastq files with qiime with the rtax module |
+| gears_use_seq_count | Boolean | false | Produces raw count files |
+### Result files
-## Result files
-
-The results of `Gears` are stored in the following files:
+The results of `GearsSingle` are stored in the following files:
| File suffix | Application | Content | Description |
| ----------- | ----------- | ------- | ----------- |
diff --git a/protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/Shiva.scala b/protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/Shiva.scala
index cff40a548b4545230010ae648ccf93d0081718d6..89b60840715afea2e8f8ff163ddbcd5cc5050ead 100644
--- a/protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/Shiva.scala
+++ b/protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/Shiva.scala
@@ -75,7 +75,7 @@ class Shiva(val root: Configurable) extends QScript with ShivaTrait {
}
}
- override def keepMergedFiles: Boolean = config("keep_merged_files", default = false)
+ override def keepMergedFiles: Boolean = config("keep_merged_files", default = !useIndelRealigner)
override def summarySettings = super.summarySettings + ("use_indel_realigner" -> useIndelRealigner)
diff --git a/public/bammetrics/src/main/resources/nl/lumc/sasc/biopet/pipelines/bammetrics/rnaHistogram.ssp b/public/bammetrics/src/main/resources/nl/lumc/sasc/biopet/pipelines/bammetrics/rnaHistogram.ssp
new file mode 100644
index 0000000000000000000000000000000000000000..9c055ad97492ba782453472a4d7528f92dc28ade
--- /dev/null
+++ b/public/bammetrics/src/main/resources/nl/lumc/sasc/biopet/pipelines/bammetrics/rnaHistogram.ssp
@@ -0,0 +1,93 @@
+#import(nl.lumc.sasc.biopet.utils.summary.Summary)
+#import(nl.lumc.sasc.biopet.core.report.ReportPage)
+#import(nl.lumc.sasc.biopet.pipelines.bammetrics.BammetricsReport)
+#import(java.io.File)
+#import(org.apache.commons.io.FileUtils)
+<%@ var summary: Summary %>
+<%@ var sampleId: Option[String] = None %>
+<%@ var libId: Option[String] = None %>
+<%@ var rootPath: String %>
+<%@ var metricsTag: String = "bammetrics" %>
+<%@ var sampleLevel: Boolean = false %>
+<%@ var outputDir: File %>
+<%@ var fields: List[String] = List("PF_ALIGNED_BASES", "MEDIAN_5PRIME_BIAS", "MEDIAN_3PRIME_BIAS", "MEDIAN_5PRIME_TO_3PRIME_BIAS")%>
+<%@ var showPlot: Boolean = false %>
+<%@ var showTable: Boolean = true %>
+<%@ var showIntro: Boolean = true%>
+#{
+ val samples = sampleId match {
+ case Some(sample) => {
+ List(sample.toString)
+ }
+ case _ => summary.samples.toList
+ }
+}#
+
+#if (showIntro)
+ <br/>
+ <div class="row">
+ <div class="col-md-1"></div>
+ <div class="col-md-6">
+ <p>
+ This Show the relative coverage for all transcripts. De data here is generated by picard CollectRnaMetrics
+ </p>
+ </div>
+ </div>
+#end
+
+#if (showPlot)
+ #{ BammetricsReport.rnaHistogramPlot(outputDir, "rna", summary, !sampleLevel, sampleId = sampleId, libId = libId) }#
+
+ <div class="panel-body">
+ <img src="rna.png" class="img-responsive" />
+ </div>
+ <div class="panel-footer">
+ #if (showTable)
+ <button type="button" class="btn btn-info" data-toggle="collapse" data-target="#rnaTable">Hide table</button>
+ #else
+ <button type="button" class="btn btn-info" data-toggle="collapse" data-target="#rnaTable">Show table</button>
+ #end
+ <i class="glyphicon glyphicon-file"></i> <a href="rna.tsv">tsv file</a>
+ </div>
+#end
+
+<div class="panel-body collapse #if (showTable)in#end" id="rnaTable">
+<!-- Table -->
+<table class="table sortable-theme-bootstrap" data-sortable>
+ <thead><tr>
+ <th data-sorted="true" data-sorted-direction="ascending">Sample</th>
+ #if (!sampleLevel) <th>Library</th> #end
+ #for (field <- fields)
+ <th>${field.replaceAll("_", " ")}</th>
+ #end
+ </tr></thead>
+ <tbody>
+ #for (sample <- samples.toList.sorted)
+ #{
+ val libs = (libId, sampleLevel) match {
+ case (_, true) => List("")
+ case (Some(libId), _) => List(libId.toString)
+ case _ => summary.libraries(sample).toList
+ }
+ }#
+ <tr><td rowspan="${libs.size}"><a href="${rootPath}Samples/${sample}/index.html">${sample}</a></td>
+ #for (libId <- libs)
+ #if (libs.head != libId) <tr> #end
+ #if (!sampleLevel) <td><a href="${rootPath}Samples/${sample}/Libraries/${libId}/index.html">${libId}</a></td> #end
+ #{
+ val prefixPath = List("samples", sample) ::: (if (libId.isEmpty) Nil else List("libraries", libId)) ::: List("bammetrics", "stats")
+
+ val fieldValues = for (field <- fields) yield {
+ summary.getValue((prefixPath ::: List("rna", "metrics", field.toUpperCase)):_*).getOrElse(prefixPath ::: metricsTag :: Nil)
+ }
+ }#
+ #for (value <- fieldValues)
+ <td>${value}</td>
+ #end
+ </tr>
+ #end
+ #end
+ </tbody>
+</table>
+
+</div>
diff --git a/public/bammetrics/src/main/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetrics.scala b/public/bammetrics/src/main/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetrics.scala
index 01fd32ab2aef9de5a55d8e726fd4334980888b32..78bf5f309f77ea2916715a0681640b4d1400cd72 100644
--- a/public/bammetrics/src/main/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetrics.scala
+++ b/public/bammetrics/src/main/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetrics.scala
@@ -17,6 +17,7 @@ package nl.lumc.sasc.biopet.pipelines.bammetrics
import java.io.File
+import nl.lumc.sasc.biopet.core.annotations.{ RibosomalRefFlat, AnnotationRefFlat }
import nl.lumc.sasc.biopet.utils.config.Configurable
import nl.lumc.sasc.biopet.core.summary.SummaryQScript
import nl.lumc.sasc.biopet.core.{ Reference, BiopetFifoPipe, PipelineCommand, SampleLibraryTag }
@@ -31,16 +32,15 @@ class BamMetrics(val root: Configurable) extends QScript
with SummaryQScript
with SampleLibraryTag
with Reference
- with TargetRegions {
+ with TargetRegions
+ with AnnotationRefFlat
+ with RibosomalRefFlat {
def this() = this(null)
@Input(doc = "Bam File", shortName = "BAM", required = true)
var inputBam: File = _
- /** Settings for CollectRnaSeqMetrics */
- var transcriptRefFlatFile: Option[File] = config("transcript_refflat")
-
/** return location of summary file */
def summaryFile = (sampleId, libId) match {
case (Some(s), Some(l)) => new File(outputDir, s + "-" + l + ".BamMetrics.summary.json")
@@ -92,7 +92,7 @@ class BamMetrics(val root: Configurable) extends QScript
add(gcBiasMetrics)
addSummarizable(gcBiasMetrics, "gc_bias")
- if (transcriptRefFlatFile.isEmpty) {
+ if (config("wgs_metrics", default = true)) {
val wgsMetrics = new CollectWgsMetrics(this)
wgsMetrics.input = inputBam
wgsMetrics.output = swapExt(outputDir, inputBam, ".bam", ".wgs.metrics")
@@ -100,12 +100,13 @@ class BamMetrics(val root: Configurable) extends QScript
addSummarizable(wgsMetrics, "wgs")
}
- if (transcriptRefFlatFile.isDefined) {
+ if (config("rna_metrics", default = false)) {
val rnaMetrics = new CollectRnaSeqMetrics(this)
rnaMetrics.input = inputBam
rnaMetrics.output = swapExt(outputDir, inputBam, ".bam", ".rna.metrics")
rnaMetrics.chartOutput = Some(swapExt(outputDir, inputBam, ".bam", ".rna.metrics.pdf"))
- rnaMetrics.refFlat = transcriptRefFlatFile.get
+ rnaMetrics.refFlat = annotationRefFlat()
+ rnaMetrics.ribosomalIntervals = ribosomalRefFlat()
add(rnaMetrics)
addSummarizable(rnaMetrics, "rna")
}
diff --git a/public/bammetrics/src/main/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BammetricsReport.scala b/public/bammetrics/src/main/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BammetricsReport.scala
index 4da9ec9e5f878262e66473d559cc209580674992..d214860778f986461206fa8d757b2b6c95cdfe0a 100644
--- a/public/bammetrics/src/main/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BammetricsReport.scala
+++ b/public/bammetrics/src/main/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BammetricsReport.scala
@@ -57,9 +57,19 @@ object BammetricsReport extends ReportBuilder {
sampleId: Option[String],
libId: Option[String],
metricsTag: String = "bammetrics") = {
+
+ val wgsExecuted = summary.getValue(sampleId, libId, metricsTag, "stats", "wgs").isDefined
+ val rnaExecuted = summary.getValue(sampleId, libId, metricsTag, "stats", "rna").isDefined
+
+ val insertsizeMetrics = summary.getValue(sampleId, libId, metricsTag, "stats", "CollectInsertSizeMetrics", "metrics") match {
+ case Some(None) => false
+ case Some(_) => true
+ case _ => false
+ }
+
val targets = (
- summary.getValue(sampleId, libId, "bammetrics", "settings", "amplicon_name"),
- summary.getValue(sampleId, libId, "bammetrics", "settings", "roi_name")
+ summary.getValue(sampleId, libId, metricsTag, "settings", "amplicon_name"),
+ summary.getValue(sampleId, libId, metricsTag, "settings", "roi_name")
) match {
case (Some(amplicon: String), Some(roi: List[_])) => amplicon :: roi.map(_.toString)
case (_, Some(roi: List[_])) => roi.map(_.toString)
@@ -73,10 +83,15 @@ object BammetricsReport extends ReportBuilder {
targets.map(t => t -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/covstatsPlot.ssp", Map("target" -> Some(t)))),
Map())),
List(
- "Summary" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp"),
- "Insert Size" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/insertSize.ssp", Map("showPlot" -> true)),
- "Whole genome coverage" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/wgsHistogram.ssp", Map("showPlot" -> true))
- ),
+ "Summary" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp")) ++
+ (if (insertsizeMetrics) List("Insert Size" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/insertSize.ssp", Map("showPlot" -> true))
+ )
+ else Nil) ++ (if (wgsExecuted) List("Whole genome coverage" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/wgsHistogram.ssp",
+ Map("showPlot" -> true)))
+ else Nil) ++
+ (if (rnaExecuted) List("Rna coverage" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/rnaHistogram.ssp",
+ Map("showPlot" -> true)))
+ else Nil),
Map("metricsTag" -> metricsTag)
)
}
@@ -321,4 +336,94 @@ object BammetricsReport extends ReportBuilder {
plot.title = Some("Whole genome coverage")
plot.runLocal()
}
+
+ /**
+ * Generate a line plot for rna coverage
+ * @param outputDir OutputDir for the tsv and png file
+ * @param prefix Prefix of the tsv and png file
+ * @param summary Summary class
+ * @param libraryLevel Default false, when set true plot will be based on library stats instead of sample stats
+ * @param sampleId Default it selects all sampples, when sample is giving it limits to selected sample
+ */
+ def rnaHistogramPlot(outputDir: File,
+ prefix: String,
+ summary: Summary,
+ libraryLevel: Boolean = false,
+ sampleId: Option[String] = None,
+ libId: Option[String] = None): Unit = {
+ val tsvFile = new File(outputDir, prefix + ".tsv")
+ val pngFile = new File(outputDir, prefix + ".png")
+ val tsvWriter = new PrintWriter(tsvFile)
+ if (libraryLevel) {
+ tsvWriter.println((for (
+ sample <- summary.samples if sampleId.isEmpty || sampleId.get == sample;
+ lib <- summary.libraries(sample) if libId.isEmpty || libId.get == lib
+ ) yield s"$sample-$lib")
+ .mkString("library\t", "\t", ""))
+ } else {
+ sampleId match {
+ case Some(sample) => tsvWriter.println("\t" + sample)
+ case _ => tsvWriter.println(summary.samples.mkString("Sample\t", "\t", ""))
+ }
+ }
+
+ var map: Map[Int, Map[String, Double]] = Map()
+
+ def fill(sample: String, lib: Option[String]): Unit = {
+
+ val insertSize = new SummaryValue(List("bammetrics", "stats", "rna", "histogram", "normalized_position"),
+ summary, Some(sample), lib).value.getOrElse(List())
+ val counts = new SummaryValue(List("bammetrics", "stats", "rna", "histogram", "All_Reads.normalized_coverage"),
+ summary, Some(sample), lib).value.getOrElse(List())
+
+ (insertSize, counts) match {
+ case (l: List[_], l2: List[_]) =>
+ l.zip(l2).foreach(i => {
+ val insertSize = i._1.toString.toInt
+ val count = i._2.toString.toDouble
+ val old = map.getOrElse(insertSize, Map())
+ if (libraryLevel) map += insertSize -> (old + ((s"$sample-" + lib.get) -> count))
+ else map += insertSize -> (old + (sample -> count))
+ })
+ case _ => throw new IllegalStateException("Must be a list")
+ }
+ }
+
+ if (libraryLevel) {
+ for (
+ sample <- summary.samples if sampleId.isEmpty || sampleId.get == sample;
+ lib <- summary.libraries(sample) if libId.isEmpty || libId.get == lib
+ ) fill(sample, Some(lib))
+ } else if (sampleId.isDefined) fill(sampleId.get, None)
+ else summary.samples.foreach(fill(_, None))
+
+ for ((insertSize, counts) <- map) {
+ tsvWriter.print(insertSize)
+ if (libraryLevel) {
+ for (
+ sample <- summary.samples if sampleId.isEmpty || sampleId.get == sample;
+ lib <- summary.libraries(sample) if libId.isEmpty || libId.get == lib
+ ) {
+ tsvWriter.print("\t" + counts.getOrElse(s"$sample-$lib", "0"))
+ }
+ } else {
+ for (sample <- summary.samples if sampleId.isEmpty || sampleId.get == sample) {
+ tsvWriter.print("\t" + counts.getOrElse(sample, "0"))
+ }
+ }
+ tsvWriter.println()
+ }
+
+ tsvWriter.close()
+
+ val plot = new LinePlot(null)
+ plot.input = tsvFile
+ plot.output = pngFile
+ plot.xlabel = Some("Reletive position")
+ plot.ylabel = Some("Coverage")
+ plot.width = Some(1200)
+ plot.removeZero = true
+ plot.title = Some("Rna coverage")
+ plot.runLocal()
+ }
}
diff --git a/public/bammetrics/src/test/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetricsTest.scala b/public/bammetrics/src/test/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetricsTest.scala
index 744988cbadd378eb1aef85eef95b8961261f8d56..4b0b2dad9172b5d8221a4438070255587ebc4e91 100644
--- a/public/bammetrics/src/test/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetricsTest.scala
+++ b/public/bammetrics/src/test/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetricsTest.scala
@@ -50,22 +50,22 @@ class BamMetricsTest extends TestNGSuite with Matchers {
@DataProvider(name = "bammetricsOptions")
def bammetricsOptions = {
val rois = Array(0, 1, 2, 3)
- val amplicon = Array(true, false)
- val rna = Array(true, false)
+ val bool = Array(true, false)
for (
rois <- rois;
- amplicon <- amplicon;
- rna <- rna
- ) yield Array(rois, amplicon, rna)
+ amplicon <- bool;
+ rna <- bool;
+ wgs <- bool
+ ) yield Array(rois, amplicon, rna, wgs)
}
@Test(dataProvider = "bammetricsOptions")
- def testBamMetrics(rois: Int, amplicon: Boolean, rna: Boolean) = {
- val map = ConfigUtils.mergeMaps(Map("output_dir" -> BamMetricsTest.outputDir),
+ def testBamMetrics(rois: Int, amplicon: Boolean, rna: Boolean, wgs: Boolean) = {
+ val map = ConfigUtils.mergeMaps(Map("output_dir" -> BamMetricsTest.outputDir, "rna_metrics" -> rna, "wgs_metrics" -> wgs),
Map(BamMetricsTest.executables.toSeq: _*)) ++
(if (amplicon) Map("amplicon_bed" -> "amplicon.bed") else Map()) ++
- (if (rna) Map("transcript_refflat" -> "transcripts.refFlat") else Map()) ++
+ (if (rna) Map("annotation_refflat" -> "transcripts.refFlat") else Map()) ++
Map("regions_of_interest" -> (1 to rois).map("roi_" + _ + ".bed").toList)
val bammetrics: BamMetrics = initPipeline(map)
@@ -77,7 +77,7 @@ class BamMetricsTest extends TestNGSuite with Matchers {
var regions: Int = rois + (if (amplicon) 1 else 0)
bammetrics.functions.count(_.isInstanceOf[CollectRnaSeqMetrics]) shouldBe (if (rna) 1 else 0)
- bammetrics.functions.count(_.isInstanceOf[CollectWgsMetrics]) shouldBe (if (rna) 0 else 1)
+ bammetrics.functions.count(_.isInstanceOf[CollectWgsMetrics]) shouldBe (if (wgs) 1 else 0)
bammetrics.functions.count(_.isInstanceOf[CollectMultipleMetrics]) shouldBe 1
bammetrics.functions.count(_.isInstanceOf[CalculateHsMetrics]) shouldBe (if (amplicon) 1 else 0)
bammetrics.functions.count(_.isInstanceOf[CollectTargetedPcrMetrics]) shouldBe (if (amplicon) 1 else 0)
diff --git a/public/biopet-core/src/main/resources/nl/lumc/sasc/biopet/core/report/krona.ssp b/public/biopet-core/src/main/resources/nl/lumc/sasc/biopet/core/report/krona.ssp
new file mode 100644
index 0000000000000000000000000000000000000000..8c5f1e5d0c91e09415c837162a009eb5dd3c7dec
--- /dev/null
+++ b/public/biopet-core/src/main/resources/nl/lumc/sasc/biopet/core/report/krona.ssp
@@ -0,0 +1,24 @@
+#import(java.io.File)
+#import(scala.io.Source)
+<%@ var rootPath: String %>
+<%@ var kronaXml: File %>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+<head>
+<meta charset="utf-8"/>
+<link rel="shortcut icon" href="${rootPath}ext/img/krona/favicon.ico"/>
+<!--<script id="notfound">window.onload=function(){document.body.innerHTML="Could not get resources from \"http://krona.sourceforge.net\"."}</script>-->
+<script src="${rootPath}ext/js/krona-2.0.js"></script>
+</head>
+<body>
+<img id="hiddenImage" src="${rootPath}ext/img/krona/hidden.png" style="display:none"/>
+<img id="loadingImage" src="${rootPath}ext/img/krona/loading.gif" style="display:none"/>
+<noscript>Javascript must be enabled to view this page.</noscript>
+<div style="display:none">
+<%
+ val reader = Source.fromFile(kronaXml)
+ val xml = reader.getLines().mkString("\n")
+ reader.close()
+%>
+${unescape(xml)}
+</div></body></html>
diff --git a/public/biopet-core/src/main/resources/nl/lumc/sasc/biopet/core/report/main.ssp b/public/biopet-core/src/main/resources/nl/lumc/sasc/biopet/core/report/main.ssp
index 7102c5ef76a3e3e5694b188164b72a031a0d47f3..356ddc00ecd606bdf3753d078d9eb58f36bad4fe 100644
--- a/public/biopet-core/src/main/resources/nl/lumc/sasc/biopet/core/report/main.ssp
+++ b/public/biopet-core/src/main/resources/nl/lumc/sasc/biopet/core/report/main.ssp
@@ -148,7 +148,7 @@
${name}
</h3>
</div>
- ${unescape(section.render(args))}
+ ${unescape(section.render(args ++ Map("args" -> args)))}
</div>
#end
</div>
diff --git a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/BiopetQScript.scala b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/BiopetQScript.scala
index c95299b0d4c47ef189a22fce2fcd1dfaff9183f8..5fe30c554d3c9ba40efb687629d50fff1c6a235c 100644
--- a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/BiopetQScript.scala
+++ b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/BiopetQScript.scala
@@ -23,9 +23,7 @@ import nl.lumc.sasc.biopet.core.report.ReportBuilderExtension
import nl.lumc.sasc.biopet.utils.Logging
import org.broadinstitute.gatk.queue.{ QScript, QSettings }
import org.broadinstitute.gatk.queue.function.QFunction
-import org.broadinstitute.gatk.queue.function.scattergather.ScatterGatherableFunction
import org.broadinstitute.gatk.queue.util.{ Logging => GatkLogging }
-import org.broadinstitute.gatk.utils.commandline.Argument
/** Base for biopet pipeline */
trait BiopetQScript extends Configurable with GatkLogging { qscript: QScript =>
@@ -99,12 +97,13 @@ trait BiopetQScript extends Configurable with GatkLogging { qscript: QScript =>
inputFiles.foreach { i =>
if (!i.file.exists()) Logging.addError(s"Input file does not exist: ${i.file}")
- else if (!i.file.canRead) Logging.addError(s"Input file can not be read: ${i.file}")
+ if (!i.file.canRead) Logging.addError(s"Input file can not be read: ${i.file}")
+ if (!i.file.isAbsolute) Logging.addError(s"Input file should be an absulute path: ${i.file}")
}
functions.filter(_.jobOutputFile == null).foreach(f => {
try {
- f.jobOutputFile = new File(f.firstOutput.getAbsoluteFile.getParent, "." + f.firstOutput.getName + "." + configName + ".out")
+ f.jobOutputFile = new File(f.firstOutput.getAbsoluteFile.getParent, "." + f.firstOutput.getName + "." + f.getClass.getSimpleName + ".out")
} catch {
case e: NullPointerException => logger.warn(s"Can't generate a jobOutputFile for $f")
}
diff --git a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/PipelineCommand.scala b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/PipelineCommand.scala
index a33223019ce1eb7c3fce24ed3891f0ccd6183b5c..f7ecc8bf1e612bb104d3eb567978c30b63183455 100644
--- a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/PipelineCommand.scala
+++ b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/PipelineCommand.scala
@@ -94,7 +94,7 @@ trait PipelineCommand extends MainCommand with GatkLogging with ImplicitConversi
}
if (!args.contains("-retry") && !args.contains("--retry_failed")) {
val retry: Int = globalConfig(pipelineName, Nil, "retry", default = 5)
- logger.info("No retry flag found, ")
+ logger.info(s"No retry flag found, set to default value of '$retry'")
argv ++= List("-retry", retry.toString)
}
BiopetQCommandLine.main(argv)
diff --git a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/Reference.scala b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/Reference.scala
index 11ebe1c79158bed3acd8bd714476615851ee4566..ee5f9b661584697d3c81cdb43956681e779246fe 100644
--- a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/Reference.scala
+++ b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/Reference.scala
@@ -71,7 +71,7 @@ trait Reference extends Configurable {
val file: File = config("reference_fasta")
checkFasta(file)
- val dict = new File(file.getAbsolutePath.stripSuffix(".fa").stripSuffix(".fasta") + ".dict")
+ val dict = new File(file.getAbsolutePath.stripSuffix(".fa").stripSuffix(".fasta").stripSuffix(".fna") + ".dict")
val fai = new File(file.getAbsolutePath + ".fai")
this match {
diff --git a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/WriteDependencies.scala b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/WriteDependencies.scala
index 232954b7d8be7bf99cd4b354fb72d570ed1ebddc..108ee694e54fc4dd126dfc82f90adb7470602cde 100644
--- a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/WriteDependencies.scala
+++ b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/WriteDependencies.scala
@@ -80,7 +80,7 @@ object WriteDependencies extends Logging with Configurable {
"intermediate" -> isIntermediate,
"output_jobs" -> outputJobNames,
"input_jobs" -> inputJobNames,
- "exist_at_start" -> fileExist,
+ "exists_at_start" -> fileExist,
"pipeline_input" -> outputJobs.isEmpty
)
}
@@ -114,9 +114,9 @@ object WriteDependencies extends Logging with Configurable {
case cmd: CommandLineFunction => cmd.commandLine
case _ => None
}), "intermediate" -> f.isIntermediate,
- "depens_on_intermediate" -> f.inputs.exists(files(_).isIntermediate),
- "depens_on_jobs" -> f.inputs.toList.flatMap(files(_).outputJobNames).distinct,
- "ouput_used_by_jobs" -> outputFiles(f).toList.flatMap(files(_).inputJobNames).distinct,
+ "depends_on_intermediate" -> f.inputs.exists(files(_).isIntermediate),
+ "depends_on_jobs" -> f.inputs.toList.flatMap(files(_).outputJobNames).distinct,
+ "output_used_by_jobs" -> outputFiles(f).toList.flatMap(files(_).inputJobNames).distinct,
"outputs" -> outputFiles(f).toList,
"inputs" -> f.inputs.toList,
"done_at_start" -> f.isDone,
diff --git a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/annotations/Annotations.scala b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/annotations/Annotations.scala
new file mode 100644
index 0000000000000000000000000000000000000000..c2f688804cd7917bbe73cae1fd05d282fa61b30a
--- /dev/null
+++ b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/annotations/Annotations.scala
@@ -0,0 +1,39 @@
+package nl.lumc.sasc.biopet.core.annotations
+
+import nl.lumc.sasc.biopet.core.BiopetQScript
+import nl.lumc.sasc.biopet.core.BiopetQScript.InputFile
+import nl.lumc.sasc.biopet.utils.LazyCheck
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by pjvan_thof on 1/12/16.
+ */
+trait AnnotationGtf extends BiopetQScript { qscript: QScript =>
+ /** GTF reference file */
+ lazy val annotationGtf: File = {
+ val file: File = config("annotation_gtf", freeVar = true)
+ inputFiles :+ InputFile(file, config("annotation_gtf_md5", freeVar = true))
+ file
+ }
+}
+
+trait AnnotationRefFlat extends BiopetQScript { qscript: QScript =>
+ /** GTF reference file */
+ lazy val annotationRefFlat = new LazyCheck({
+ val file: File = config("annotation_refflat", freeVar = true)
+ inputFiles :+ InputFile(file, config("annotation_refflat_md5", freeVar = true))
+ file
+ })
+}
+
+trait RibosomalRefFlat extends BiopetQScript { qscript: QScript =>
+ /** GTF reference file */
+ lazy val ribosomalRefFlat = new LazyCheck({
+ val file: Option[File] = config("ribosome_refflat", freeVar = true)
+ file match {
+ case Some(f) => inputFiles :+ InputFile(f, config("ribosome_refflat_md5", freeVar = true))
+ case _ =>
+ }
+ file
+ })
+}
diff --git a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/extensions/RscriptCommandLineFunction.scala b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/extensions/RscriptCommandLineFunction.scala
index c773de6155b5a771f242dbbe83a4a21f98089eaa..24e51c7636d321f1dccf24910a6a411c5701b0f5 100644
--- a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/extensions/RscriptCommandLineFunction.scala
+++ b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/extensions/RscriptCommandLineFunction.scala
@@ -15,13 +15,11 @@
*/
package nl.lumc.sasc.biopet.core.extensions
-import java.io.{ File, FileOutputStream }
+import java.io.File
import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
import nl.lumc.sasc.biopet.utils.rscript.Rscript
-import scala.sys.process._
-
/**
* General rscript extension
*
@@ -32,7 +30,7 @@ trait RscriptCommandLineFunction extends BiopetCommandLineFunction with Rscript
executable = rscriptExecutable
override def beforeGraph(): Unit = {
- checkScript(Some(jobTempDir))
+ checkScript(Some(new File(".queue" + File.separator + "tmp")))
}
def cmdLine: String = repeat(cmd)
diff --git a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/summary/WriteSummary.scala b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/summary/WriteSummary.scala
index 02c860fdb1719c8c4635d467bea752b74745f9b2..bb6e1bf5606f21e99ceb7d557a93b68b690c0c3d 100644
--- a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/summary/WriteSummary.scala
+++ b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/summary/WriteSummary.scala
@@ -184,6 +184,7 @@ class WriteSummary(val root: Configurable) extends InProcessFunction with Config
map.toMap
}
}
+
object WriteSummary {
/** Retrive checksum from file */
def parseChecksum(checksumFile: File): String = {
diff --git a/public/biopet-core/src/test/scala/nl/lumc/sasc/biopet/core/ReferenceTest.scala b/public/biopet-core/src/test/scala/nl/lumc/sasc/biopet/core/ReferenceTest.scala
index 31b70db9d1595f2dd5614c9abe4a5fa1047ed834..79741a2c2eb73a39cce67d8ad48b5680ba939163 100644
--- a/public/biopet-core/src/test/scala/nl/lumc/sasc/biopet/core/ReferenceTest.scala
+++ b/public/biopet-core/src/test/scala/nl/lumc/sasc/biopet/core/ReferenceTest.scala
@@ -19,6 +19,7 @@ class ReferenceTest extends TestNGSuite with Matchers with MockitoSugar {
@Test
def testDefault: Unit = {
+ Logging.errors.clear()
make(config :: testReferenceNoIndex :: Nil).referenceFasta()
Logging.checkErrors(true)
diff --git a/public/biopet-core/src/test/scala/nl/lumc/sasc/biopet/core/summary/SummarizableTest.scala b/public/biopet-core/src/test/scala/nl/lumc/sasc/biopet/core/summary/SummarizableTest.scala
new file mode 100644
index 0000000000000000000000000000000000000000..1be487ff6d1309685d004d4b2f8f8b5523a93d75
--- /dev/null
+++ b/public/biopet-core/src/test/scala/nl/lumc/sasc/biopet/core/summary/SummarizableTest.scala
@@ -0,0 +1,32 @@
+package nl.lumc.sasc.biopet.core.summary
+
+import java.io.File
+
+import org.scalatest.Matchers
+import org.scalatest.testng.TestNGSuite
+import org.testng.annotations.Test
+
+/**
+ * Created by pjvanthof on 14/01/16.
+ */
+class SummarizableTest extends TestNGSuite with Matchers {
+ @Test
+ def testDefaultMerge: Unit = {
+ val summarizable = new Summarizable {
+ def summaryFiles: Map[String, File] = ???
+ def summaryStats: Any = ???
+ }
+ intercept[IllegalStateException] {
+ summarizable.resolveSummaryConflict("1", "1", "key")
+ }
+ }
+
+ def testOverrideMerge: Unit = {
+ val summarizable = new Summarizable {
+ def summaryFiles: Map[String, File] = ???
+ def summaryStats: Any = ???
+ override def resolveSummaryConflict(v1: Any, v2: Any, key: String) = v1
+ }
+ summarizable.resolveSummaryConflict("1", "1", "key") shouldBe "1"
+ }
+}
diff --git a/public/biopet-core/src/test/scala/nl/lumc/sasc/biopet/core/summary/SummaryQScriptTest.scala b/public/biopet-core/src/test/scala/nl/lumc/sasc/biopet/core/summary/SummaryQScriptTest.scala
new file mode 100644
index 0000000000000000000000000000000000000000..a53fe068f9537cdce91a75f45ef9393631377d0d
--- /dev/null
+++ b/public/biopet-core/src/test/scala/nl/lumc/sasc/biopet/core/summary/SummaryQScriptTest.scala
@@ -0,0 +1,126 @@
+package nl.lumc.sasc.biopet.core.summary
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.BiopetQScript.InputFile
+import nl.lumc.sasc.biopet.core.extensions.Md5sum
+import nl.lumc.sasc.biopet.utils.config.{ Config, Configurable }
+import org.broadinstitute.gatk.queue.QScript
+import org.scalatest.Matchers
+import org.scalatest.testng.TestNGSuite
+import org.testng.annotations.Test
+import SummaryQScriptTest._
+
+/**
+ * Created by pjvanthof on 14/01/16.
+ */
+class SummaryQScriptTest extends TestNGSuite with Matchers {
+ @Test
+ def testNoJobs: Unit = {
+ SummaryQScript.md5sumCache.clear()
+ val script = makeQscript()
+ script.addSummaryJobs()
+ SummaryQScript.md5sumCache shouldBe empty
+ }
+
+ @Test
+ def testFiles: Unit = {
+ SummaryQScript.md5sumCache.clear()
+ val file = new File(s".${File.separator}bla")
+ val script = makeQscript(files = Map("file" -> file))
+ script.addSummaryJobs()
+ SummaryQScript.md5sumCache should not be empty
+ SummaryQScript.md5sumCache.toMap shouldBe Map(
+ new File(s".${File.separator}bla") -> new File(s".${File.separator}bla.md5"))
+ script.functions.size shouldBe 2
+ assert(script.functions
+ .filter(_.isInstanceOf[Md5sum])
+ .map(_.asInstanceOf[Md5sum])
+ .exists(_.cmdLine.contains(" || ")))
+ }
+
+ @Test
+ def testDuplicateFiles: Unit = {
+ SummaryQScript.md5sumCache.clear()
+ val file = new File(s".${File.separator}bla")
+ val script = makeQscript(files = Map("file" -> file, "file2" -> file))
+ script.addSummaryJobs()
+ SummaryQScript.md5sumCache should not be empty
+ SummaryQScript.md5sumCache.toMap shouldBe Map(
+ new File(s".${File.separator}bla") -> new File(s".${File.separator}bla.md5"))
+ script.functions.size shouldBe 2
+ assert(script.functions
+ .filter(_.isInstanceOf[Md5sum])
+ .map(_.asInstanceOf[Md5sum])
+ .exists(_.cmdLine.contains(" || ")))
+ }
+
+ @Test
+ def testAddSummarizable: Unit = {
+ SummaryQScript.md5sumCache.clear()
+ val file = new File(s".${File.separator}bla")
+ val script = makeQscript()
+ script.addSummarizable(makeSummarizable(files = Map("file" -> file, "file2" -> file)), "test")
+ script.summarizables.size shouldBe 1
+ script.addSummaryJobs()
+ SummaryQScript.md5sumCache should not be empty
+ SummaryQScript.md5sumCache.toMap shouldBe Map(
+ new File(s".${File.separator}bla") -> new File(s".${File.separator}bla.md5"))
+ script.functions.size shouldBe 2
+ assert(script.functions
+ .filter(_.isInstanceOf[Md5sum])
+ .map(_.asInstanceOf[Md5sum])
+ .exists(_.cmdLine.contains(" || ")))
+ }
+
+ @Test
+ def testInputFile: Unit = {
+ SummaryQScript.md5sumCache.clear()
+ val file = new File(s".${File.separator}bla")
+ val script = makeQscript()
+ script.addSummarizable(makeSummarizable(files = Map("file" -> file, "file2" -> file)), "test")
+ script.summarizables.size shouldBe 1
+ script.inputFiles :+= InputFile(file, Some("md5sum"))
+ script.inputFiles :+= InputFile(file, None)
+ script.addSummaryJobs()
+ SummaryQScript.md5sumCache should not be empty
+ SummaryQScript.md5sumCache.toMap shouldBe Map(
+ new File(s".${File.separator}bla") -> new File(s".${File.separator}bla.md5"))
+ script.functions.size shouldBe 3
+ assert(script.functions
+ .filter(_.isInstanceOf[Md5sum])
+ .map(_.asInstanceOf[Md5sum])
+ .exists(_.cmdLine.contains(" || ")))
+ }
+
+ @Test
+ def testAddQscript: Unit = {
+ SummaryQScript.md5sumCache.clear()
+ val script = makeQscript()
+ script.addSummaryQScript(script)
+ script.summaryQScripts.head shouldBe script
+ }
+}
+
+object SummaryQScriptTest {
+ def makeQscript(settings: Map[String, Any] = Map(),
+ files: Map[String, File] = Map(),
+ c: Map[String, Any] = Map()) =
+ new SummaryQScript with QScript {
+ outputDir = new File(".")
+ override def globalConfig = new Config(c)
+ def summarySettings: Map[String, Any] = settings
+ def summaryFiles: Map[String, File] = files
+ val tempFile = File.createTempFile("summary", ".json")
+ tempFile.deleteOnExit()
+ def summaryFile: File = tempFile
+ def init(): Unit = ???
+ def biopetScript(): Unit = ???
+ def root: Configurable = null
+ }
+
+ def makeSummarizable(files: Map[String, File] = Map(), stats: Map[String, Any] = Map()) = new Summarizable {
+ def summaryFiles: Map[String, File] = files
+ def summaryStats: Any = stats
+ }
+}
\ No newline at end of file
diff --git a/public/biopet-core/src/test/scala/nl/lumc/sasc/biopet/core/summary/WriteSummaryTest.scala b/public/biopet-core/src/test/scala/nl/lumc/sasc/biopet/core/summary/WriteSummaryTest.scala
new file mode 100644
index 0000000000000000000000000000000000000000..4bb196c162ddb93c85b19d1364d34789fb77e8b9
--- /dev/null
+++ b/public/biopet-core/src/test/scala/nl/lumc/sasc/biopet/core/summary/WriteSummaryTest.scala
@@ -0,0 +1,346 @@
+package nl.lumc.sasc.biopet.core.summary
+
+import java.io.{ PrintWriter, File }
+
+import com.google.common.io.Files
+import nl.lumc.sasc.biopet.core._
+import nl.lumc.sasc.biopet.utils.config.{ Config, Configurable }
+import nl.lumc.sasc.biopet.utils.summary.Summary
+import org.broadinstitute.gatk.queue.function.CommandLineFunction
+import org.broadinstitute.gatk.queue.{ QScript, QSettings }
+import org.scalatest.Matchers
+import org.scalatest.testng.TestNGSuite
+import WriteSummaryTest._
+import org.testng.annotations.Test
+
+import scala.util.matching.Regex
+
+/**
+ * Created by pjvanthof on 15/01/16.
+ */
+class WriteSummaryTest extends TestNGSuite with Matchers {
+
+ @Test
+ def testWrongRoot(): Unit = {
+ intercept[IllegalArgumentException] {
+ makeWriter(null)
+ }
+ }
+
+ /** This is a basic summary test, no matter the content this should always be true */
+ def basicSummaryTest(summary: Summary,
+ name: String,
+ sampleId: Option[String] = None,
+ libId: Option[String] = None): Unit = {
+ summary.getValue(sampleId, libId, name) should not be None
+ summary.getValue(sampleId, libId, name, "files", "pipeline").get shouldBe a[Map[_, _]]
+ summary.getValue(sampleId, libId, name, "settings").get shouldBe a[Map[_, _]]
+ summary.getValue(sampleId, libId, name, "executables").get shouldBe a[Map[_, _]]
+
+ summary.getValue("meta") should not be None
+ summary.getValue("meta", "pipeline_name") shouldBe Some(name)
+ summary.getValue("meta", "last_commit_hash") shouldBe Some(nl.lumc.sasc.biopet.LastCommitHash)
+ summary.getValue("meta", "pipeline_version") shouldBe Some(nl.lumc.sasc.biopet.Version)
+ summary.getValue("meta", "output_dir") shouldBe Some(new File(".").getAbsolutePath)
+ summary.getValue("meta", "summary_creation") should not be None
+ }
+
+ def createFakeCheckSum(file: File): Unit = {
+ file.getParentFile.mkdirs()
+ val writer = new PrintWriter(file)
+ writer.println("checksum file")
+ writer.close()
+ file.deleteOnExit()
+ }
+
+ @Test
+ def testEmpty(): Unit = {
+ val qscript = makeQscript(name = "test")
+ val writer = makeWriter(qscript)
+ writer.freezeFieldValues()
+ writer.deps shouldBe empty
+ writer.run()
+
+ val summary = new Summary(writer.out)
+ basicSummaryTest(summary, "test")
+ }
+
+ @Test
+ def testMergeQscript(): Unit = {
+ val qscript = makeQscript(name = "test")
+ val qscript2 = makeQscript(name = "test2")
+ qscript.addSummaryQScript(qscript2)
+ val summaryWriter = new PrintWriter(qscript2.summaryFile)
+ summaryWriter.println("""{ "test2": "value" }""")
+ summaryWriter.close()
+ val writer = makeWriter(qscript)
+ writer.freezeFieldValues()
+ writer.run()
+
+ val summary = new Summary(writer.out)
+ basicSummaryTest(summary, "test")
+ summary.getValue("test2") shouldBe Some("value")
+ }
+
+ @Test
+ def testSingleJob(): Unit = {
+ val qscript = makeQscript("test")
+ val writer = makeWriter(qscript)
+ val summarizable = makeSummarizable(files = Map("file_1" -> new File("bla")), stats = Map("key" -> "value"))
+ qscript.addSummarizable(summarizable, "tool_1")
+ qscript.addSummaryJobs()
+ createFakeCheckSum(SummaryQScript.md5sumCache(new File("bla")))
+ writer.freezeFieldValues()
+ writer.run()
+
+ val summary = new Summary(writer.out)
+ basicSummaryTest(summary, "test")
+ summary.getValue("test", "stats", "tool_1", "key") shouldBe Some("value")
+ summary.getValue("test", "files", "tool_1", "file_1", "md5") shouldBe Some("checksum")
+ }
+
+ @Test
+ def testSingleJavaJob(): Unit = {
+ val qscript = makeQscript("test")
+ val writer = makeWriter(qscript)
+ val summarizable = makeJavaCommand(files = Map("file_1" -> new File("bla")), stats = Map("key" -> "value"))
+ qscript.add(summarizable)
+ qscript.addSummarizable(summarizable, "tool_1")
+ qscript.addSummaryJobs()
+ createFakeCheckSum(SummaryQScript.md5sumCache(new File("bla")))
+ writer.freezeFieldValues()
+ writer.run()
+
+ val summary = new Summary(writer.out)
+ basicSummaryTest(summary, "test")
+ summary.getValue("test", "stats", "tool_1", "key") shouldBe Some("value")
+ summary.getValue("test", "files", "tool_1", "file_1", "md5") shouldBe Some("checksum")
+ summary.getValue("test", "executables", "java_command", "version") shouldBe Some("test version")
+ }
+
+ @Test
+ def testVersion(): Unit = {
+ val qscript = makeQscript("test")
+ val writer = makeWriter(qscript)
+ val summarizable = makeVersionSummarizable(files = Map("file_1" -> new File("bla")), stats = Map("key" -> "value"))
+ qscript.add(summarizable)
+ qscript.addSummarizable(summarizable, "tool_1")
+ qscript.addSummaryJobs()
+ createFakeCheckSum(SummaryQScript.md5sumCache(new File("bla")))
+ writer.freezeFieldValues()
+ writer.run()
+
+ val summary = new Summary(writer.out)
+ basicSummaryTest(summary, "test")
+ summary.getValue("test", "stats", "tool_1", "key") shouldBe Some("value")
+ summary.getValue("test", "files", "tool_1", "file_1", "md5") shouldBe Some("checksum")
+ summary.getValue("test", "executables", "version_command", "version") shouldBe Some("test version")
+ }
+
+ @Test
+ def testSampleLibrary(): Unit = {
+ val qscript = makeSampleLibraryQscript("test", s = Some("sampleName"), l = Some("libName"))
+ val writer = makeWriter(qscript)
+ val summarizable = makeSummarizable(files = Map("file_1" -> new File("bla")), stats = Map("key" -> "value"))
+ qscript.addSummarizable(summarizable, "tool_1")
+ qscript.addSummaryJobs()
+ createFakeCheckSum(SummaryQScript.md5sumCache(new File("bla")))
+ writer.freezeFieldValues()
+ writer.deps shouldBe empty
+ writer.run()
+
+ val summary = new Summary(writer.out)
+ basicSummaryTest(summary, "test", sampleId = Some("sampleName"), libId = Some("libName"))
+ summary.getValue(Some("sampleName"), Some("libName"), "test", "stats", "tool_1", "key") shouldBe Some("value")
+ summary.getValue(Some("sampleName"), Some("libName"), "test", "files", "tool_1", "file_1", "md5") shouldBe Some("checksum")
+ }
+
+ @Test
+ def testSample(): Unit = {
+ val qscript = makeSampleLibraryQscript("test", s = Some("sampleName"))
+ val writer = makeWriter(qscript)
+ val summarizable = makeSummarizable(files = Map("file_1" -> new File("bla")), stats = Map("key" -> "value"))
+ qscript.addSummarizable(summarizable, "tool_1")
+ qscript.addSummaryJobs()
+ createFakeCheckSum(SummaryQScript.md5sumCache(new File("bla")))
+ writer.freezeFieldValues()
+ writer.deps shouldBe empty
+ writer.run()
+
+ val summary = new Summary(writer.out)
+ basicSummaryTest(summary, "test", sampleId = Some("sampleName"), libId = None)
+ summary.getValue(Some("sampleName"), None, "test", "stats", "tool_1", "key") shouldBe Some("value")
+ summary.getValue(Some("sampleName"), None, "test", "files", "tool_1", "file_1", "md5") shouldBe Some("checksum")
+ }
+
+ @Test
+ def testMultisampleQscript(): Unit = {
+ val qscript = makeMultisampleQscript("test", multisampleConfig)
+ val writer = makeWriter(qscript)
+ val summarizable = makeSummarizable(files = Map("file_1" -> new File("bla")), stats = Map("key" -> "value"))
+ qscript.addSummarizable(summarizable, "tool_1")
+ qscript.addSummaryJobs()
+ createFakeCheckSum(SummaryQScript.md5sumCache(new File("bla")))
+ writer.freezeFieldValues()
+ writer.deps shouldBe empty
+ writer.run()
+
+ val summary = new Summary(writer.out)
+ basicSummaryTest(summary, "test")
+ summary.getValue("test", "stats", "tool_1", "key") shouldBe Some("value")
+ summary.getValue("test", "files", "tool_1", "file_1", "md5") shouldBe Some("checksum")
+
+ summary.getValue(Some("sampleName"), Some("libName"), "test") should not be None
+ }
+
+}
+
+object WriteSummaryTest {
+ def makeWriter(root: Configurable, c: Map[String, Any] = Map()) = new WriteSummary(root) {
+ override def globalConfig = new Config(c)
+ override def outputs = Seq()
+ override def inputs = Seq()
+ qSettings = new QSettings {
+ jobName = "test"
+ jobTempDir = Files.createTempDir()
+ jobTempDir.deleteOnExit()
+ jobPriority = Some(1)
+ }
+ override def absoluteCommandDirectory() {}
+ }
+
+ def makeQscript(name: String,
+ settings: Map[String, Any] = Map(),
+ files: Map[String, File] = Map(),
+ c: Map[String, Any] = Map()) =
+ new SummaryQScript with QScript {
+ summaryName = name
+ outputDir = new File(".").getAbsoluteFile
+ override def globalConfig = new Config(c)
+ def summarySettings: Map[String, Any] = settings
+ def summaryFiles: Map[String, File] = files
+ val tempFile = File.createTempFile("summary", ".json")
+ tempFile.deleteOnExit()
+ def summaryFile: File = tempFile
+ def init(): Unit = {}
+ def biopetScript(): Unit = {}
+ def root: Configurable = null
+ }
+
+ def makeSampleLibraryQscript(name: String,
+ settings: Map[String, Any] = Map(),
+ files: Map[String, File] = Map(),
+ c: Map[String, Any] = Map(),
+ s: Option[String] = None,
+ l: Option[String] = None) =
+ new SummaryQScript with QScript with SampleLibraryTag {
+ sampleId = s
+ libId = l
+ summaryName = "test"
+ outputDir = new File(".").getAbsoluteFile
+ override def globalConfig = new Config(c)
+ def summarySettings: Map[String, Any] = settings
+ def summaryFiles: Map[String, File] = files
+ val tempFile = File.createTempFile("summary", ".json")
+ tempFile.deleteOnExit()
+ def summaryFile: File = tempFile
+ def init(): Unit = {}
+ def biopetScript(): Unit = {}
+ def root: Configurable = null
+ }
+
+ def makeMultisampleQscript(name: String,
+ c: Map[String, Any],
+ settings: Map[String, Any] = Map(),
+ files: Map[String, File] = Map()) =
+ new MultiSampleQScript with QScript {
+ summaryName = "test"
+ outputDir = new File(".").getAbsoluteFile
+ override def globalConfig = new Config(c)
+ def summarySettings: Map[String, Any] = settings
+ def summaryFiles: Map[String, File] = files
+ val tempFile = File.createTempFile("summary", ".json")
+ tempFile.deleteOnExit()
+ def summaryFile: File = tempFile
+ def init(): Unit = {}
+ def biopetScript(): Unit = {}
+ def root: Configurable = null
+
+ class Sample(id: String) extends AbstractSample(id) {
+ class Library(id: String) extends AbstractLibrary(id) {
+ protected def addJobs(): Unit = {}
+ def summaryFiles: Map[String, File] = files
+ def summaryStats: Any = Map()
+ }
+
+ def makeLibrary(id: String): Library = new Library(id)
+ protected def addJobs(): Unit = {}
+ def summaryFiles: Map[String, File] = files
+ def summaryStats: Any = Map()
+ }
+
+ def makeSample(id: String): Sample = new Sample(id)
+
+ def addMultiSampleJobs(): Unit = {}
+ }
+
+ val multisampleConfig = Map("samples" -> Map("sampleName" -> Map("libraries" -> Map("libName" -> Map()))))
+
+ def makeSummarizable(files: Map[String, File] = Map(), stats: Map[String, Any] = Map()) = new Summarizable {
+ def summaryFiles: Map[String, File] = files
+ def summaryStats: Any = stats
+ }
+
+ def makeJavaCommand(files: Map[String, File] = Map(),
+ stats: Map[String, Any] = Map(),
+ c: Map[String, Any] = Map()) = new BiopetJavaCommandLineFunction with Summarizable with Version {
+ override def globalConfig = new Config(c)
+ override def configName = "java_command"
+ def root: Configurable = null
+ def summaryStats: Map[String, Any] = stats
+ def summaryFiles: Map[String, File] = files
+
+ def versionCommand: String = "echo test version"
+ def versionRegex: Regex = """(.*)""".r
+ override def getVersion = Some("test version")
+
+ override def outputs = Seq()
+ override def inputs = Seq()
+ qSettings = new QSettings {
+ jobName = "test"
+ jobTempDir = Files.createTempDir()
+ jobTempDir.deleteOnExit()
+ jobPriority = Some(1)
+ }
+ override def absoluteCommandDirectory() {}
+ }
+
+ def makeVersionSummarizable(files: Map[String, File] = Map(),
+ stats: Map[String, Any] = Map(),
+ c: Map[String, Any] = Map()) =
+ new CommandLineFunction with Configurable with Summarizable with Version {
+ override def globalConfig = new Config(c)
+ override def configName = "version_command"
+ def root: Configurable = null
+
+ def summaryFiles: Map[String, File] = files
+ def summaryStats: Any = stats
+
+ def versionCommand: String = "echo test version"
+ def versionRegex: Regex = """(.*)""".r
+ override def getVersion = Some("test version")
+
+ def commandLine: String = ""
+
+ override def outputs = Seq()
+ override def inputs = Seq()
+ qSettings = new QSettings {
+ jobName = "test"
+ jobTempDir = Files.createTempDir()
+ jobTempDir.deleteOnExit()
+ jobPriority = Some(1)
+ }
+ override def absoluteCommandDirectory() {}
+ }
+
+}
\ No newline at end of file
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/fix_mpileup.py b/public/biopet-extensions/src/main/resources/nl/lumc/sasc/biopet/extensions/varscan/fix_mpileup.py
similarity index 94%
rename from public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/fix_mpileup.py
rename to public/biopet-extensions/src/main/resources/nl/lumc/sasc/biopet/extensions/varscan/fix_mpileup.py
index 3cbaf06412488bece8e795ef097c2582130920a3..3def5be1542873c7f5b6f50f2df36c4db7fc00d1 100644
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/fix_mpileup.py
+++ b/public/biopet-extensions/src/main/resources/nl/lumc/sasc/biopet/extensions/varscan/fix_mpileup.py
@@ -21,6 +21,9 @@ from __future__ import print_function
__author__="Wai Yi Leung"
import sys
+import re
+
+upacPatern = re.compile(r'[RYKMSWBDHV]')
if __name__ == "__main__":
"""
@@ -46,4 +49,5 @@ if __name__ == "__main__":
if new_size == 0:
l[5] = ""
+ l[2] = upacPatern.sub("N", l[2])
print("\t".join(map(str, l)))
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Bgzip.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Bgzip.scala
index 321cb8b9c5960936da9d8f5bcac0d2fdb9937627..a43fc4734852642b92e7924e2209073616197f6c 100644
--- a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Bgzip.scala
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Bgzip.scala
@@ -36,5 +36,5 @@ class Bgzip(val root: Configurable) extends BiopetCommandLineFunction {
def cmdLine = required(executable) +
conditional(f, "-f") +
" -c " + repeat(input) +
- " > " + required(output)
+ (if (outputAsStsout) "" else " > " + required(output))
}
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Cutadapt.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Cutadapt.scala
index 6e06894f916a5206bcac748d924eb8f3a9f51c53..80743e00d167dd7a37ae9ec5d208cf0a83c7be97 100644
--- a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Cutadapt.scala
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Cutadapt.scala
@@ -26,18 +26,19 @@ import scala.collection.mutable
import scala.io.Source
/**
- * Extension for cutadept
- * Based on version 1.5
+ * Extension for cutadapt
+ * Started with version 1.5
+ * Updated to version 1.9 (18-01-2016 by wyleung)
*/
class Cutadapt(val root: Configurable) extends BiopetCommandLineFunction with Summarizable with Version {
@Input(doc = "Input fastq file")
- var fastq_input: File = _
+ var fastqInput: File = _
@Output
- var fastq_output: File = _
+ var fastqOutput: File = _
@Output(doc = "Output statistics file")
- var stats_output: File = _
+ var statsOutput: File = _
executable = config("exe", default = "cutadapt")
def versionCommand = executable + " --version"
@@ -46,28 +47,121 @@ class Cutadapt(val root: Configurable) extends BiopetCommandLineFunction with Su
/** Name of the key containing clipped adapters information in the summary stats. */
def adaptersStatsName = "adapters"
- var default_clip_mode: String = config("default_clip_mode", default = "3")
- var opt_adapter: Set[String] = config("adapter", default = Nil)
- var opt_anywhere: Set[String] = config("anywhere", default = Nil)
- var opt_front: Set[String] = config("front", default = Nil)
-
- var opt_discard: Boolean = config("discard", default = false)
- var opt_minimum_length: Int = config("minimum_length", 1)
- var opt_maximum_length: Option[Int] = config("maximum_length")
+ var defaultClipMode: String = config("default_clip_mode", default = "3")
+ var adapter: Set[String] = config("adapter", default = Nil)
+ var anywhere: Set[String] = config("anywhere", default = Nil)
+ var front: Set[String] = config("front", default = Nil)
+
+ var errorRate: Option[Double] = config("error_rate")
+ var noIndels: Boolean = config("no_indels", default = false)
+ var times: Option[Int] = config("times")
+ var overlap: Option[Int] = config("overlap")
+ var matchReadWildcards: Boolean = config("match_read_wildcards", default = false)
+ var noMatchAdapterWildcards: Boolean = config("no_match_adapter_wildcards", default = false) // specific for 1.9
+
+ /** Options for filtering of processed reads */
+ var discard: Boolean = config("discard", default = false)
+ var trimmedOnly: Boolean = config("trimmed_only", default = false)
+ var minimumLength: Int = config("minimum_length", 1)
+ var maximumLength: Option[Int] = config("maximum_length")
+ var noTrim: Boolean = config("no_trim", default = false)
+ var maxN: Option[Int] = config("max_n") // specific for 1.9
+ var maskAdapter: Boolean = config("mask_adapter", default = false)
+
+ /** Options that influence what gets output to where */
+ var quiet: Boolean = config("quiet", default = false)
+ // var output: File // see up @Output
+ var infoFile: Option[File] = config("info_file")
+ var restFile: Option[File] = config("rest_file")
+ var wildcardFile: Option[File] = config("wildcard_file")
+ var tooShortOutput: Option[File] = config("too_short_output")
+ var tooLongOutput: Option[File] = config("too_long_output")
+ var untrimmedOutput: Option[File] = config("untrimmed_output")
+
+ /** Additional read modifications */
+ var cut: Option[Int] = config("cut")
+ var qualityCutoff: Option[String] = config("quality_cutoff")
+ var qualityBase: Option[Int] = config("quality_base")
+ var trimN: Boolean = config("trim_n", default = false)
+ var prefix: Option[String] = config("prefix")
+ var suffix: Option[String] = config("suffix")
+ var stripSuffix: Set[String] = config("strip_suffix")
+ var lengthTag: Option[String] = config("length_tag")
+
+ /** Colorspace options */
+ var colorspace: Boolean = config("colorspace", default = false)
+ var doubleEncode: Boolean = config("double_encode", default = false)
+ var trimPrimer: Boolean = config("trim_primer", default = false)
+ var stripF3: Boolean = config("strip_f3", default = false)
+ var maq: Boolean = config("maq", default = false)
+ var bwa: Boolean = config("bwa", default = false, freeVar = false)
+ var noZeroCap: Boolean = config("no_zero_cap", default = false)
+ var zeroCap: Boolean = config("zero_cap", default = false)
+
+ /** Paired end options */
+ var peAdapter: Set[String] = config("pe_adapter", default = Nil)
+ var peAdapterFront: Set[String] = config("pe_adapter_front", default = Nil)
+ var peAdapterBoth: Set[String] = config("pe_adapter_both", default = Nil)
+ var peCut: Boolean = config("pe_cut", default = false)
+ var pairedOutput: Option[File] = config("paired_output")
+ var interleaved: Boolean = config("interleaved", default = false)
+ var untrimmedPairedOutput: Option[File] = config("untrimmed_paired_output")
/** return commandline to execute */
def cmdLine = required(executable) +
- // options
- repeat("-a", opt_adapter) +
- repeat("-b", opt_anywhere) +
- repeat("-g", opt_front) +
- conditional(opt_discard, "--discard") +
- optional("-m", opt_minimum_length) +
- optional("-M", opt_maximum_length) +
+ // Options that influence how the adapters are found
+ repeat("-a", adapter) +
+ repeat("-b", anywhere) +
+ repeat("-g", front) +
+ optional("--error-rate", errorRate) +
+ conditional(noIndels, "--no-indels") +
+ optional("--times", times) +
+ optional("--overlap", overlap) +
+ conditional(matchReadWildcards, "--match-read-wildcards") +
+ conditional(noMatchAdapterWildcards, "--no-match-adapter-wildcards") +
+ // Options for filtering of processed reads
+ conditional(discard, "--discard") +
+ conditional(trimmedOnly, "--trimmed-only") +
+ optional("-m", minimumLength) +
+ optional("-M", maximumLength) +
+ conditional(noTrim, "--no-trim") +
+ optional("--max-n", maxN) +
+ conditional(maskAdapter, "--mask-adapter") +
+ conditional(quiet, "--quiet") +
+ optional("--info-file", infoFile) +
+ optional("--rest-file", restFile) +
+ optional("--wildcard-file", wildcardFile) +
+ optional("--too-short-output", tooShortOutput) +
+ optional("--too-long-output", tooLongOutput) +
+ optional("--untrimmed-output", untrimmedOutput) +
+ // Additional read modifications
+ optional("--cut", cut) +
+ optional("--quality-cutoff", qualityCutoff) +
+ conditional(trimN, "--trim-n") +
+ optional("--prefix", prefix) +
+ optional("--suffix", suffix) +
+ optional("--strip-suffix", stripSuffix) +
+ optional("--length-tag", lengthTag) +
+ // Colorspace options
+ conditional(colorspace, "--colorspace") +
+ conditional(doubleEncode, "--double-encode") +
+ conditional(trimPrimer, "--trim-primer") +
+ conditional(stripF3, "--strip-f3") +
+ conditional(maq, "--maq") +
+ conditional(bwa, "--bwa") +
+ conditional(noZeroCap, "--no-zero-cap") +
+ conditional(zeroCap, "--zero-cap") +
+ // Paired-end options
+ repeat("-A", peAdapter) +
+ repeat("-G", peAdapterFront) +
+ repeat("-B", peAdapterBoth) +
+ conditional(interleaved, "--interleaved") +
+ optional("--paired-output", pairedOutput) +
+ optional("--untrimmed-paired-output", untrimmedPairedOutput) +
// input / output
- required(fastq_input) +
- (if (outputAsStsout) "" else required("--output", fastq_output) +
- " > " + required(stats_output))
+ required(fastqInput) +
+ (if (outputAsStsout) "" else required("--output", fastqOutput) +
+ " > " + required(statsOutput))
/** Output summary stats */
def summaryStats: Map[String, Any] = {
@@ -79,7 +173,7 @@ class Cutadapt(val root: Configurable) extends BiopetCommandLineFunction with Su
val stats: mutable.Map[String, Int] = mutable.Map("trimmed" -> 0, "tooshort" -> 0, "toolong" -> 0)
val adapter_stats: mutable.Map[String, Int] = mutable.Map()
- if (stats_output.exists) for (line <- Source.fromFile(stats_output).getLines()) {
+ if (statsOutput.exists) for (line <- Source.fromFile(statsOutput).getLines()) {
line match {
case trimR(m) => stats += ("trimmed" -> m.toInt)
case tooShortR(m) => stats += ("tooshort" -> m.toInt)
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Flash.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Flash.scala
new file mode 100644
index 0000000000000000000000000000000000000000..4013b8aeada8962ebe5893bed017e95056715317
--- /dev/null
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Flash.scala
@@ -0,0 +1,88 @@
+package nl.lumc.sasc.biopet.extensions
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.{ Version, BiopetCommandLineFunction }
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.Input
+
+import scala.util.matching.Regex
+
+/**
+ * Created by pjvanthof on 16/12/15.
+ */
+class Flash(val root: Configurable) extends BiopetCommandLineFunction with Version {
+ executable = config("exe", default = "flash", freeVar = false)
+
+ /** Command to get version of executable */
+ def versionCommand: String = executable + " --version"
+
+ /** Regex to get version from version command output */
+ def versionRegex: Regex = """FLASH (v.*)""".r
+
+ @Input(required = true)
+ var fastqR1: File = _
+
+ @Input(required = true)
+ var fastqR2: File = _
+
+ var minOverlap: Option[Int] = config("min_overlap")
+ var maxOverlap: Option[Int] = config("max_overlap")
+ var maxMismatchDensity: Option[Double] = config("max_mismatch_density")
+ var allowOuties: Boolean = config("allow_outies", default = false)
+ var phredOffset: Option[Int] = config("phred_offset")
+ var readLen: Option[Int] = config("read_len")
+ var fragmentLen: Option[Int] = config("fragment_len")
+ var fragmentLenStddev: Option[Int] = config("fragment_len_stddev")
+ var capMismatchQuals: Boolean = config("cap_mismatch_quals", default = false)
+ var interleavedInput: Boolean = config("interleaved-input", default = false)
+ var interleavedOutput: Boolean = config("interleaved_output", default = false)
+ var interleaved: Boolean = config("interleaved", default = false)
+ var tabDelimitedInput: Boolean = config("tab_delimited_input", default = false)
+ var tabDelimitedOutput: Boolean = config("tab_delimited_output", default = false)
+ var outputPrefix: String = config("output_prefix", default = "out")
+ var outputDirectory: File = _
+ var compress: Boolean = config("compress", default = false)
+ var compressProg: Option[String] = config("compress_prog")
+ var compressProgArgs: Option[String] = config("compress_prog_args")
+ var outputSuffix: Option[String] = config("output_suffix")
+
+ private def suffix = outputSuffix.getOrElse("fastq") + (if (compress) ".gz" else "")
+
+ def combinedFastq = new File(outputDirectory, s"$outputPrefix.extendedFrags.$suffix")
+ def notCombinedR1 = new File(outputDirectory, s"$outputPrefix.notCombined_1.$suffix")
+ def notCombinedR2 = new File(outputDirectory, s"$outputPrefix.notCombined_2.$suffix")
+ def outputHistogramTable = new File(outputDirectory, s"$outputPrefix.hist")
+ def outputHistogram = new File(outputDirectory, s"$outputPrefix.histogram")
+
+ override def beforeGraph(): Unit = {
+ super.beforeGraph()
+ outputFiles :::= combinedFastq :: notCombinedR1 ::
+ notCombinedR2 :: outputHistogramTable :: outputHistogram :: Nil
+ }
+
+ def cmdLine = executable +
+ optional("-m", minOverlap) +
+ optional("-M", maxOverlap) +
+ optional("-x", maxMismatchDensity) +
+ conditional(allowOuties, "--allow-outies") +
+ optional("--phred-offset", phredOffset) +
+ optional("--read-len", readLen) +
+ optional("--fragment-len", fragmentLen) +
+ optional("--fragment-len-stddev", fragmentLenStddev) +
+ conditional(capMismatchQuals, "--cap-mismatch-quals") +
+ conditional(interleavedInput, "--interleaved-input") +
+ conditional(interleavedOutput, "--interleaved-output") +
+ conditional(interleaved, "--interleaved") +
+ conditional(tabDelimitedInput, "--tab-delimited-input") +
+ conditional(tabDelimitedOutput, "--tab-delimited-output") +
+ optional("--output-prefix", outputPrefix) +
+ required("--output-directory", outputDirectory) +
+ conditional(compress, "--compress") +
+ optional("--compress-prog", compressProg) +
+ optional("--compress-prog-args", compressProgArgs) +
+ optional("--output-suffix", outputSuffix) +
+ optional("--threads", threads) +
+ required(fastqR1) +
+ required(fastqR2)
+}
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Ln.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Ln.scala
index 951d667dad32ab2db616c53f11347db0da6e99b9..a182c41f632042a7f8e461253b9d747679944252 100644
--- a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Ln.scala
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Ln.scala
@@ -49,52 +49,32 @@ class Ln(val root: Configurable) extends InProcessFunction with Configurable {
/** return commandline to execute */
lazy val cmd: String = {
- lazy val inCanonical: String = {
+ val inCanonical: String = {
// need to remove "/~" to correctly expand path with tilde
input.getAbsolutePath.replace("/~", "")
}
- lazy val outCanonical: String = output.getAbsolutePath.replace("/~", "")
+ val outCanonical: String = output.getAbsolutePath.replace("/~", "")
- lazy val inToks: Array[String] = inCanonical.split(File.separator)
+ if (relative) {
+ val inToks: Array[String] = inCanonical.split(File.separator)
- lazy val outToks: Array[String] = outCanonical.split(File.separator)
+ val outToks: Array[String] = outCanonical.split(File.separator)
- lazy val commonPrefixLength: Int = {
- val maxLength = scala.math.min(inToks.length, outToks.length)
- var i: Int = 0
- while (i < maxLength && inToks(i) == outToks(i)) i += 1
- i
- }
+ val commonPrefixLength: Int = {
+ val maxLength = scala.math.min(inToks.length, outToks.length)
+ var i: Int = 0
+ while (i < maxLength && inToks(i) == outToks(i)) i += 1
+ i
+ }
- lazy val inUnique: String = {
- inToks.slice(commonPrefixLength, inToks.length).mkString(File.separator)
- }
+ val inUnique = inToks.slice(commonPrefixLength, inToks.length)
- lazy val outUnique: String = {
- outToks.slice(commonPrefixLength, outToks.length).mkString(File.separator)
- }
+ val outUnique = outToks.slice(commonPrefixLength, outToks.length)
- lazy val inRelative: String = {
- // calculate 'distance' from output directory to input
- // which is the number of directory walks required to get to the inUnique directory from outDir
- val dist =
- // relative path differs depending on which of the input or target is in the 'higher' directory
- if (inToks.length > outToks.length)
- scala.math.max(0, inUnique.split(File.separator).length - 1)
- else
- scala.math.max(0, outUnique.split(File.separator).length - 1)
-
- val result =
- if (dist == 0 || inToks.length > outToks.length)
- inUnique
- else
- ((".." + File.separator) * dist) + inUnique
-
- result
- }
+ val inRelative: String =
+ ((".." + File.separator) * (outUnique.length - 1)) + inUnique.mkString(File.separator)
- if (relative) {
// workaround until we have `ln` that works with relative path (i.e. `ln -r`)
"ln -s " + inRelative + " " + outCanonical
} else {
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Zcat.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Zcat.scala
index da330a14c36e4a2a8ccbeab9095371a0a01de729..38efdf63a569935aac5a5385460c146e60613eca 100644
--- a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Zcat.scala
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Zcat.scala
@@ -54,10 +54,10 @@ object Zcat {
zcat
}
- def apply(root: Configurable, input: List[File], output: File): Zcat = {
+ def apply(root: Configurable, input: List[File], output: File = null): Zcat = {
val zcat = new Zcat(root)
zcat.input = input
- zcat.output = output
+ if (output != null) zcat.output = output
zcat
}
}
\ No newline at end of file
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/kraken/Kraken.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/kraken/Kraken.scala
index 86df5c4151d114fcb2b654cbf7b0c28bb78b9bcf..e6b94712f2113abee03311c8082580677b7d06a0 100644
--- a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/kraken/Kraken.scala
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/kraken/Kraken.scala
@@ -53,7 +53,7 @@ class Kraken(val root: Configurable) extends BiopetCommandLineFunction with Vers
def versionCommand = executable + " --version"
- override def defaultCoreMemory = 8.0
+ override def defaultCoreMemory = 15.0
override def defaultThreads = 4
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/kraken/KrakenReport.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/kraken/KrakenReport.scala
index 0919728a08ccbd466f7dc1ae1d3f385e49294162..aa6e825bbed68c2724e98849019095d5d9ac71ec 100644
--- a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/kraken/KrakenReport.scala
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/kraken/KrakenReport.scala
@@ -32,7 +32,11 @@ class KrakenReport(val root: Configurable) extends BiopetCommandLineFunction wit
override def defaultCoreMemory = 4.0
override def defaultThreads = 1
- def versionCommand = new File(new File(executable).getParent, "kraken").getAbsolutePath + " --version"
+ def versionCommand = {
+ val exe = new File(new File(executable).getParent, "kraken")
+ if (exe.exists()) exe.getAbsolutePath + " --version"
+ else executable + " --version"
+ }
var db: File = config("db")
var show_zeros: Boolean = config("show_zeros", default = false)
@@ -43,10 +47,9 @@ class KrakenReport(val root: Configurable) extends BiopetCommandLineFunction wit
@Output(doc = "Output path kraken report")
var output: File = _
- def cmdLine: String = {
- val cmd: String = required(executable) + "--db " + required(db) +
- conditional(show_zeros, "--show-zeros") +
- required(input.getAbsolutePath) + " > " + required(output.getAbsolutePath)
- cmd
- }
+ def cmdLine: String = required(executable) +
+ required("--db", db) +
+ conditional(show_zeros, "--show-zeros") +
+ required(input) +
+ " > " + required(output)
}
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/CollectRnaSeqMetrics.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/CollectRnaSeqMetrics.scala
index 2aca96da6ebe993381766f50fc699c1c04233b0d..29c3ef7aab59aca13f741504a7ca736788d0b6db 100644
--- a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/CollectRnaSeqMetrics.scala
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/CollectRnaSeqMetrics.scala
@@ -36,7 +36,7 @@ class CollectRnaSeqMetrics(val root: Configurable) extends Picard with Summariza
var refFlat: File = null
@Input(doc = "Location of rRNA sequences in interval list format", required = false)
- var ribosomalIntervals: Option[File] = config("ribosomal_intervals")
+ var ribosomalIntervals: Option[File] = None
@Output(doc = "Output metrics file", required = true)
var output: File = null
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/AssignTaxonomy.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/AssignTaxonomy.scala
new file mode 100644
index 0000000000000000000000000000000000000000..b41dbfd0dcc524f4029da66a4b1d8a6724514399
--- /dev/null
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/AssignTaxonomy.scala
@@ -0,0 +1,87 @@
+package nl.lumc.sasc.biopet.extensions.qiime
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.{ Version, BiopetCommandLineFunction }
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.Input
+
+/**
+ * Created by pjvan_thof on 12/4/15.
+ */
+class AssignTaxonomy(val root: Configurable) extends BiopetCommandLineFunction with Version {
+ executable = config("exe", default = "assign_taxonomy.py")
+
+ @Input(required = true)
+ var inputFasta: File = _
+
+ @Input(required = false)
+ var read_1_seqs_fp: Option[File] = None
+
+ @Input(required = false)
+ var read_2_seqs_fp: Option[File] = None
+
+ @Input(required = false)
+ var id_to_taxonomy_fp: Option[File] = config("id_to_taxonomy_fp")
+
+ @Input(required = false)
+ var reference_seqs_fp: Option[File] = config("reference_seqs_fp")
+
+ @Input(required = false)
+ var training_data_properties_fp: Option[File] = config("training_data_properties_fp")
+
+ var single_ok: Boolean = config("single_ok", default = false)
+ var no_single_ok_generic: Boolean = config("no_single_ok_generic", default = false)
+
+ var amplicon_id_regex: Option[String] = config("amplicon_id_regex")
+ var header_id_regex: Option[String] = config("header_id_regex")
+ var assignment_method: Option[String] = config("assignment_method")
+ var sortmerna_db: Option[String] = config("sortmerna_db")
+ var sortmerna_e_value: Option[String] = config("sortmerna_e_value")
+ var sortmerna_coverage: Option[String] = config("sortmerna_coverage")
+ var sortmerna_best_N_alignments: Option[String] = config("sortmerna_best_N_alignments")
+ var sortmerna_threads: Option[String] = config("sortmerna_threads")
+ var blast_db: Option[String] = config("blast_db")
+ var confidence: Option[String] = config("confidence")
+ var min_consensus_fraction: Option[String] = config("min_consensus_fraction")
+ var similarity: Option[String] = config("similarity")
+ var uclust_max_accepts: Option[String] = config("uclust_max_accepts")
+ var rdp_max_memory: Option[String] = config("rdp_max_memory")
+ var blast_e_value: Option[String] = config("blast_e_value")
+ var outputDir: File = _
+
+ def versionCommand = executable + " --version"
+ def versionRegex = """Version: (.*)""".r
+ override def defaultCoreMemory = 4.0
+
+ override def beforeGraph(): Unit = {
+ super.beforeGraph()
+ require(outputDir != null)
+ }
+
+ def cmdLine = executable +
+ required("-i", inputFasta) +
+ optional("--read_1_seqs_fp", read_1_seqs_fp) +
+ optional("--read_2_seqs_fp", read_2_seqs_fp) +
+ optional("-t", id_to_taxonomy_fp) +
+ optional("-r", reference_seqs_fp) +
+ optional("-p", training_data_properties_fp) +
+ optional("--amplicon_id_regex", amplicon_id_regex) +
+ optional("--header_id_regex", header_id_regex) +
+ optional("--assignment_method", assignment_method) +
+ optional("--sortmerna_db", sortmerna_db) +
+ optional("--sortmerna_e_value", sortmerna_e_value) +
+ optional("--sortmerna_coverage", sortmerna_coverage) +
+ optional("--sortmerna_best_N_alignments", sortmerna_best_N_alignments) +
+ optional("--sortmerna_threads", sortmerna_threads) +
+ optional("--blast_db", blast_db) +
+ optional("--confidence", confidence) +
+ optional("--min_consensus_fraction", min_consensus_fraction) +
+ optional("--similarity", similarity) +
+ optional("--uclust_max_accepts", uclust_max_accepts) +
+ optional("--rdp_max_memory", rdp_max_memory) +
+ optional("--blast_e_value", blast_e_value) +
+ required("--output_dir", outputDir) +
+ conditional(single_ok, "--single_ok") +
+ conditional(no_single_ok_generic, "--no_single_ok_generic")
+}
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/MergeOtuMaps.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/MergeOtuMaps.scala
new file mode 100644
index 0000000000000000000000000000000000000000..a538e97a1c281256b007ee37e115da48bfb0e393
--- /dev/null
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/MergeOtuMaps.scala
@@ -0,0 +1,39 @@
+package nl.lumc.sasc.biopet.extensions.qiime
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.{ BiopetCommandLineFunction, Version }
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
+
+/**
+ * Created by pjvan_thof on 12/10/15.
+ */
+class MergeOtuMaps(val root: Configurable) extends BiopetCommandLineFunction with Version {
+ executable = config("exe", default = "merge_otu_maps.py")
+
+ def versionCommand = executable + " --version"
+ def versionRegex = """Version: (.*)""".r
+
+ @Input(required = true)
+ var input: List[File] = Nil
+
+ @Output(required = true)
+ var outputFile: File = _
+
+ var failures_fp: Option[File] = None
+
+ override def beforeGraph(): Unit = {
+ super.beforeGraph()
+ require(input.nonEmpty)
+ require(outputFile != null)
+ }
+
+ def cmdLine = executable +
+ (input match {
+ case l: List[_] if l.nonEmpty => required("-i", l.mkString(","))
+ case _ => ""
+ }) +
+ required("-o", outputFile) +
+ optional("--failures_fp", failures_fp)
+}
\ No newline at end of file
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/MergeOtuTables.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/MergeOtuTables.scala
new file mode 100644
index 0000000000000000000000000000000000000000..ae3d4edd29793327a5621339cf7463c288a8ae08
--- /dev/null
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/MergeOtuTables.scala
@@ -0,0 +1,36 @@
+package nl.lumc.sasc.biopet.extensions.qiime
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.{ BiopetCommandLineFunction, Version }
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.{ Output, Input }
+
+/**
+ * Created by pjvan_thof on 12/10/15.
+ */
+class MergeOtuTables(val root: Configurable) extends BiopetCommandLineFunction with Version {
+ executable = config("exe", default = "merge_otu_tables.py")
+
+ def versionCommand = executable + " --version"
+ def versionRegex = """Version: (.*)""".r
+
+ @Input(required = true)
+ var input: List[File] = Nil
+
+ @Output(required = true)
+ var outputFile: File = _
+
+ override def beforeGraph(): Unit = {
+ super.beforeGraph()
+ require(input.nonEmpty)
+ require(outputFile != null)
+ }
+
+ def cmdLine = executable +
+ (input match {
+ case l: List[_] if l.nonEmpty => required("-i", l.mkString(","))
+ case _ => ""
+ }) +
+ required("-o", outputFile)
+}
\ No newline at end of file
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/PickClosedReferenceOtus.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/PickClosedReferenceOtus.scala
new file mode 100644
index 0000000000000000000000000000000000000000..265a6d21f941bfae7bc3c6b7c742993b9638e6c3
--- /dev/null
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/PickClosedReferenceOtus.scala
@@ -0,0 +1,61 @@
+package nl.lumc.sasc.biopet.extensions.qiime
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.{ BiopetCommandLineFunction, Version }
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.Input
+
+/**
+ * Created by pjvan_thof on 12/4/15.
+ */
+class PickClosedReferenceOtus(val root: Configurable) extends BiopetCommandLineFunction with Version {
+ executable = config("exe", default = "pick_closed_reference_otus.py")
+
+ @Input(required = true)
+ var inputFasta: File = _
+
+ var outputDir: File = null
+
+ override def defaultThreads = 2
+ override def defaultCoreMemory = 10.0
+ def versionCommand = executable + " --version"
+ def versionRegex = """Version: (.*)""".r
+
+ @Input(required = false)
+ var parameter_fp: Option[File] = config("parameter_fp")
+
+ @Input(required = false)
+ var reference_fp: Option[File] = config("reference_fp")
+
+ @Input(required = false)
+ var taxonomy_fp: Option[File] = config("taxonomy_fp")
+
+ var assign_taxonomy: Boolean = config("assign_taxonomy", default = false)
+ var force: Boolean = config("force", default = false)
+ var print_only: Boolean = config("print_only", default = false)
+ var suppress_taxonomy_assignment: Boolean = config("suppress_taxonomy_assignment", default = false)
+
+ def otuTable = new File(outputDir, "otu_table.biom")
+ def otuMap = new File(outputDir, "uclust_ref_picked_otus" + File.separator + "seqs_otus.txt")
+
+ override def beforeGraph(): Unit = {
+ super.beforeGraph()
+ jobOutputFile = new File(outputDir, ".std.out")
+ outputFiles ::= otuTable
+ outputFiles ::= otuMap
+ }
+
+ def cmdLine = executable + required("-f") +
+ required("-i", inputFasta) +
+ required("-o", outputDir) +
+ optional("--reference_fp", reference_fp) +
+ optional("--parameter_fp", parameter_fp) +
+ optional("--taxonomy_fp", taxonomy_fp) +
+ conditional(assign_taxonomy, "--assign_taxonomy") +
+ conditional(force, "--force") +
+ conditional(print_only, "--print_only") +
+ conditional(suppress_taxonomy_assignment, "--suppress_taxonomy_assignment") +
+ (if (threads > 1) required("-a") + required("-O", threads) else "")
+
+}
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/PickOtus.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/PickOtus.scala
new file mode 100644
index 0000000000000000000000000000000000000000..f83c59aa9dc61ad74297e707f2a1a6452780b9a2
--- /dev/null
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/PickOtus.scala
@@ -0,0 +1,151 @@
+package nl.lumc.sasc.biopet.extensions.qiime
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.{ Version, BiopetCommandLineFunction }
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.Input
+
+/**
+ * Created by pjvan_thof on 12/4/15.
+ */
+class PickOtus(val root: Configurable) extends BiopetCommandLineFunction with Version {
+ executable = config("exe", default = "pick_otus.py")
+
+ @Input(required = true)
+ var inputFasta: File = _
+
+ var outputDir: File = null
+
+ override def defaultThreads = 2
+ override def defaultCoreMemory = 5.0
+ def versionCommand = executable + " --version"
+ def versionRegex = """Version: (.*)""".r
+
+ var otu_picking_method: Option[String] = config("otu_picking_method")
+ var clustering_algorithm: Option[String] = config("clustering_algorithm")
+ var max_cdhit_memory: Option[Int] = config("max_cdhit_memory")
+ var refseqs_fp: Option[String] = config("refseqs_fp")
+ var blast_db: Option[String] = config("blast_db")
+ var max_e_value_blast: Option[String] = config("max_e_value_blast")
+ var sortmerna_db: Option[String] = config("sortmerna_db")
+ var sortmerna_e_value: Option[Double] = config("sortmerna_e_value")
+ var sortmerna_coverage: Option[Double] = config("sortmerna_coverage")
+ var sortmerna_tabular: Boolean = config("sortmerna_tabular", default = false)
+ var sortmerna_best_N_alignments: Option[Int] = config("sortmerna_best_N_alignments")
+ var sortmerna_max_pos: Option[Int] = config("sortmerna_max_pos")
+ var min_aligned_percent: Option[Double] = config("min_aligned_percent")
+ var similarity: Option[Double] = config("similarity")
+ var sumaclust_exact: Option[String] = config("sumaclust_exact")
+ var sumaclust_l: Boolean = config("sumaclust_l", default = false)
+ var denovo_otu_id_prefix: Option[String] = config("denovo_otu_id_prefix")
+ var swarm_resolution: Option[String] = config("swarm_resolution")
+ var trie_reverse_seqs: Boolean = config("trie_reverse_seqs", default = false)
+ var prefix_prefilter_length: Option[String] = config("prefix_prefilter_length")
+ var trie_prefilter: Option[String] = config("trie_prefilter")
+ var prefix_length: Option[String] = config("prefix_length")
+ var suffix_length: Option[String] = config("suffix_length")
+ var enable_rev_strand_match: Boolean = config("enable_rev_strand_match", default = false)
+ var suppress_presort_by_abundance_uclust: Boolean = config("suppress_presort_by_abundance_uclust", default = false)
+ var optimal_uclust: Boolean = config("optimal_uclust", default = false)
+ var exact_uclust: Boolean = config("exact_uclust", default = false)
+ var user_sort: Boolean = config("user_sort", default = false)
+ var suppress_new_clusters: Boolean = config("suppress_new_clusters", default = false)
+ var max_accepts: Option[String] = config("max_accepts")
+ var max_rejects: Option[String] = config("max_rejects")
+ var stepwords: Option[String] = config("stepwords")
+ var word_length: Option[String] = config("word_length")
+ var suppress_uclust_stable_sort: Boolean = config("suppress_uclust_stable_sort", default = false)
+ var suppress_prefilter_exact_match: Boolean = config("suppress_prefilter_exact_match", default = false)
+ var save_uc_files: Boolean = config("save_uc_files", default = false)
+ var percent_id_err: Option[String] = config("percent_id_err")
+ var minsize: Option[String] = config("minsize")
+ var abundance_skew: Option[String] = config("abundance_skew")
+ var db_filepath: Option[String] = config("db_filepath")
+ var perc_id_blast: Option[String] = config("perc_id_blast")
+ var de_novo_chimera_detection: Boolean = config("de_novo_chimera_detection", default = false)
+ var suppress_de_novo_chimera_detection: Boolean = config("suppress_de_novo_chimera_detection", default = false)
+ var reference_chimera_detection: Option[String] = config("reference_chimera_detection")
+ var suppress_reference_chimera_detection: Option[String] = config("suppress_reference_chimera_detection")
+ var cluster_size_filtering: Option[String] = config("cluster_size_filtering")
+ var suppress_cluster_size_filtering: Option[String] = config("suppress_cluster_size_filtering")
+ var remove_usearch_logs: Boolean = config("remove_usearch_logs", default = false)
+ var derep_fullseq: Boolean = config("derep_fullseq", default = false)
+ var non_chimeras_retention: Option[String] = config("non_chimeras_retention")
+ var minlen: Option[String] = config("minlen")
+ var usearch_fast_cluster: Boolean = config("usearch_fast_cluster", default = false)
+ var usearch61_sort_method: Option[String] = config("usearch61_sort_method")
+ var sizeorder: Boolean = config("sizeorder", default = false)
+
+ private lazy val name = inputFasta.getName.stripSuffix(".fasta").stripSuffix(".fa").stripSuffix(".fna")
+
+ def clustersFile = new File(outputDir, s"${name}_clusters.uc")
+ def logFile = new File(outputDir, s"${name}_otus.log")
+ def otusTxt = new File(outputDir, s"${name}_otus.txt")
+
+ override def beforeGraph(): Unit = {
+ super.beforeGraph()
+ outputFiles :+= clustersFile
+ outputFiles :+= logFile
+ outputFiles :+= otusTxt
+ }
+
+ def cmdLine = executable +
+ required("-i", inputFasta) +
+ required("-o", outputDir) +
+ optional("-m", otu_picking_method) +
+ optional("-c", clustering_algorithm) +
+ optional("-M", max_cdhit_memory) +
+ optional("-r", refseqs_fp) +
+ optional("-b", blast_db) +
+ optional("-e", max_e_value_blast) +
+ optional("--sortmerna_db", sortmerna_db) +
+ optional("--sortmerna_e_value", sortmerna_e_value) +
+ optional("--sortmerna_coverage", sortmerna_coverage) +
+ conditional(sortmerna_tabular, "--sortmerna_tabular") +
+ optional("--sortmerna_best_N_alignments", sortmerna_best_N_alignments) +
+ optional("--sortmerna_max_pos", sortmerna_max_pos) +
+ optional("--min_aligned_percent", min_aligned_percent) +
+ optional("--similarity", similarity) +
+ optional("--sumaclust_exact", sumaclust_exact) +
+ conditional(sumaclust_l, "--sumaclust_l") +
+ optional("--denovo_otu_id_prefix", denovo_otu_id_prefix) +
+ optional("--swarm_resolution", swarm_resolution) +
+ conditional(trie_reverse_seqs, "--trie_reverse_seqs") +
+ optional("--prefix_prefilter_length", prefix_prefilter_length) +
+ optional("--trie_prefilter", trie_prefilter) +
+ optional("--prefix_length", prefix_length) +
+ optional("--suffix_length", suffix_length) +
+ conditional(enable_rev_strand_match, "--enable_rev_strand_match") +
+ conditional(suppress_presort_by_abundance_uclust, "--suppress_presort_by_abundance_uclust") +
+ conditional(optimal_uclust, "--optimal_uclust") +
+ conditional(exact_uclust, "--exact_uclust") +
+ conditional(user_sort, "--user_sort") +
+ conditional(suppress_new_clusters, "--suppress_new_clusters") +
+ optional("--max_accepts", max_accepts) +
+ optional("--max_rejects", max_rejects) +
+ optional("--stepwords", stepwords) +
+ optional("--word_length", word_length) +
+ conditional(suppress_uclust_stable_sort, "--suppress_uclust_stable_sort") +
+ conditional(suppress_prefilter_exact_match, "--suppress_prefilter_exact_match") +
+ conditional(save_uc_files, "--save_uc_files") +
+ optional("--percent_id_err", percent_id_err) +
+ optional("--minsize", minsize) +
+ optional("--abundance_skew", abundance_skew) +
+ optional("--db_filepath", db_filepath) +
+ optional("--perc_id_blast", perc_id_blast) +
+ conditional(de_novo_chimera_detection, "--de_novo_chimera_detection") +
+ conditional(suppress_de_novo_chimera_detection, "--suppress_de_novo_chimera_detection") +
+ optional("--reference_chimera_detection", reference_chimera_detection) +
+ optional("--suppress_reference_chimera_detection", suppress_reference_chimera_detection) +
+ optional("--cluster_size_filtering", cluster_size_filtering) +
+ optional("--suppress_cluster_size_filtering", suppress_cluster_size_filtering) +
+ conditional(remove_usearch_logs, "--remove_usearch_logs") +
+ conditional(derep_fullseq, "--derep_fullseq") +
+ optional("--non_chimeras_retention", non_chimeras_retention) +
+ optional("--minlen", minlen) +
+ conditional(usearch_fast_cluster, "--usearch_fast_cluster") +
+ optional("--usearch61_sort_method", usearch61_sort_method) +
+ conditional(sizeorder, "--sizeorder") +
+ optional("--threads", threads)
+}
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/PickRepSet.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/PickRepSet.scala
new file mode 100644
index 0000000000000000000000000000000000000000..5496c673cf515df6d735c406ed46cb145d49f389
--- /dev/null
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/PickRepSet.scala
@@ -0,0 +1,45 @@
+package nl.lumc.sasc.biopet.extensions.qiime
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.{ Version, BiopetCommandLineFunction }
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.{ Output, Input }
+
+/**
+ * Created by pjvan_thof on 12/4/15.
+ */
+class PickRepSet(val root: Configurable) extends BiopetCommandLineFunction with Version {
+ executable = config("exe", default = "pick_rep_set.py")
+
+ @Input(required = true)
+ var inputFile: File = _
+
+ @Output
+ var outputFasta: Option[File] = None
+
+ @Output
+ var logFile: Option[File] = None
+
+ @Input(required = false)
+ var reference_seqs_fp: Option[File] = config("reference_seqs_fp")
+
+ @Input(required = false)
+ var fastaInput: Option[File] = None
+
+ var sortBy: Option[String] = config("sort_by")
+
+ def versionCommand = executable + " --version"
+ def versionRegex = """Version: (.*)""".r
+
+ var rep_set_picking_method: Option[String] = config("rep_set_picking_method")
+
+ def cmdLine = executable +
+ required("-i", inputFile) +
+ required("-o", outputFasta) +
+ optional("-m", rep_set_picking_method) +
+ optional("-f", fastaInput) +
+ optional("-l", logFile) +
+ optional("-s", sortBy) +
+ optional("-r", reference_seqs_fp)
+}
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/SplitLibrariesFastq.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/SplitLibrariesFastq.scala
new file mode 100644
index 0000000000000000000000000000000000000000..25db2dd9ae2347e4439ac482627d547f6a54e310
--- /dev/null
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/SplitLibrariesFastq.scala
@@ -0,0 +1,79 @@
+package nl.lumc.sasc.biopet.extensions.qiime
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.{ Version, BiopetCommandLineFunction }
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.Input
+
+/**
+ * Created by pjvan_thof on 12/10/15.
+ */
+class SplitLibrariesFastq(val root: Configurable) extends BiopetCommandLineFunction with Version {
+ executable = config("exe", default = "split_libraries_fastq.py")
+
+ def versionCommand = executable + " --version"
+ def versionRegex = """Version: (.*)""".r
+
+ @Input
+ var input: List[File] = Nil
+ var outputDir: File = _
+
+ var v: Option[String] = config("v")
+ var m: Option[String] = config("m")
+ var b: Option[String] = config("b")
+ var store_qual_scores: Boolean = config("store_qual_scores", default = false)
+ var sample_ids: List[String] = Nil
+ var store_demultiplexed_fastq: Boolean = config("store_demultiplexed_fastq", default = false)
+ var retain_unassigned_reads: Boolean = config("retain_unassigned_reads", default = false)
+ var r: Option[Int] = config("r")
+ var p: Option[Double] = config("p")
+ var n: Option[Int] = config("n")
+ var s: Option[Int] = config("s")
+ var rev_comp_barcode: Boolean = config("rev_comp_barcode", default = false)
+ var rev_comp_mapping_barcodes: Boolean = config("rev_comp_mapping_barcodes", default = false)
+ var rev_comp: Boolean = config("rev_comp", default = false)
+ var q: Option[Int] = config("q")
+ var last_bad_quality_char: Option[String] = config("last_bad_quality_char")
+ var barcode_type: Option[String] = config("barcode_type")
+ var max_barcode_errors: Option[Double] = config("max_barcode_errors")
+ var phred_offset: Option[String] = config("phred_offset")
+
+ def outputSeqs = new File(outputDir, "seqs.fna")
+
+ override def beforeGraph(): Unit = {
+ super.beforeGraph()
+ require(input.nonEmpty)
+ require(outputDir != null)
+ outputFiles :+= outputSeqs
+ }
+
+ def cmdLine = executable +
+ optional("-v", v) +
+ optional("-m", m) +
+ optional("-b", b) +
+ conditional(store_qual_scores, "--store_qual_scores") +
+ (sample_ids match {
+ case l: List[_] if l.nonEmpty => optional("--sample_ids", l.mkString(","))
+ case _ => ""
+ }) +
+ conditional(store_demultiplexed_fastq, "--store_demultiplexed_fastq") +
+ conditional(retain_unassigned_reads, "--retain_unassigned_reads") +
+ optional("-r", r) +
+ optional("-p", p) +
+ optional("-n", n) +
+ optional("-s", s) +
+ conditional(rev_comp_barcode, "--rev_comp_barcode") +
+ conditional(rev_comp_mapping_barcodes, "--rev_comp_mapping_barcodes") +
+ conditional(rev_comp, "--rev_comp") +
+ optional("-q", q) +
+ optional("--last_bad_quality_char", last_bad_quality_char) +
+ optional("--barcode_type", barcode_type) +
+ optional("--max_barcode_errors", max_barcode_errors) +
+ optional("--phred_offset", phred_offset) +
+ (input match {
+ case l: List[_] if l.nonEmpty => required("-i", l.mkString(","))
+ case _ => ""
+ }) +
+ optional("-o", outputDir)
+}
\ No newline at end of file
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/varscan/FixMpileup.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/varscan/FixMpileup.scala
new file mode 100644
index 0000000000000000000000000000000000000000..827da73e3779003746a8ec16044c7726faa03337
--- /dev/null
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/varscan/FixMpileup.scala
@@ -0,0 +1,12 @@
+package nl.lumc.sasc.biopet.extensions.varscan
+
+import nl.lumc.sasc.biopet.core.extensions.PythonCommandLineFunction
+import nl.lumc.sasc.biopet.utils.config.Configurable
+
+/**
+ * Created by sajvanderzeeuw on 19-1-16.
+ */
+class FixMpileup(val root: Configurable) extends PythonCommandLineFunction {
+ setPythonScript("fix_mpileup.py", "/nl/lumc/sasc/biopet/extensions/varscan/")
+ def cmdLine = getPythonCommand
+}
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/varscan/Varscan.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/varscan/Varscan.scala
index f3d8585de87216b872bee7235e364df29514710a..67d3d34ee7be4dbd7e77fe030ee9914674522348 100644
--- a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/varscan/Varscan.scala
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/varscan/Varscan.scala
@@ -15,20 +15,15 @@
*/
package nl.lumc.sasc.biopet.extensions.varscan
-import nl.lumc.sasc.biopet.core.BiopetJavaCommandLineFunction
+import nl.lumc.sasc.biopet.core.{ Version, BiopetJavaCommandLineFunction }
-abstract class Varscan extends BiopetJavaCommandLineFunction {
+abstract class Varscan extends BiopetJavaCommandLineFunction with Version {
override def subPath = "varscan" :: super.subPath
jarFile = config("varscan_jar")
- /**
- * TODO: test version
- * override def versionCommand = super.commandLine
- * override val versionRegex = """VarScan v(.*)""".r
- */
-
- override def defaultCoreMemory = 5.0
+ def versionCommand = s"$executable -jar $jarFile"
+ def versionRegex = """VarScan v(.*)""".r
}
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/varscan/Mpileup2cns.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/varscan/VarscanMpileup2cns.scala
similarity index 74%
rename from public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/varscan/Mpileup2cns.scala
rename to public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/varscan/VarscanMpileup2cns.scala
index 0379c36d9ace680b7833bf226912504bb619f8e2..a7d382733c92fa74b736101793645cfa97aab655 100644
--- a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/varscan/Mpileup2cns.scala
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/varscan/VarscanMpileup2cns.scala
@@ -20,7 +20,7 @@ import java.io.File
import nl.lumc.sasc.biopet.utils.config.Configurable
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
-class Mpileup2cns(val root: Configurable) extends Varscan {
+class VarscanMpileup2cns(val root: Configurable) extends Varscan {
@Input(doc = "Input mpileup file", required = false) // if not defined, input is stdin
var input: Option[File] = None
@@ -39,6 +39,8 @@ class Mpileup2cns(val root: Configurable) extends Varscan {
var vcfSampleList: Option[File] = config("vcf_sample_list")
var variants: Option[Int] = config("variants")
+ override def defaultCoreMemory = 8.0
+
override def beforeGraph(): Unit = {
val validValues: Set[Int] = Set(0, 1)
// check for boolean vars that are passed as ints
@@ -47,22 +49,17 @@ class Mpileup2cns(val root: Configurable) extends Varscan {
variants.foreach { case v => require(validValues.contains(v), "variants value must be either 0 or 1") }
}
- override def cmdLine = {
- val baseCommand = super.cmdLine + required("mpileup2cns") +
- required("", input) +
- required("--min-coverage", minCoverage) +
- required("--min-reads2", minReads2) +
- required("--min-avg-qual", minAvgQual) +
- required("--min-var-freq", minVarFreq) +
- required("--min-freq-for-hom", minFreqForHom) +
- required("--p-value", pValue) +
- required("--strand-filter", strandFilter) +
- required("--output-vcf", outputVcf) +
- required("--vcf-sample-list", vcfSampleList) +
- required("--variants", variants)
-
- if (output.isDefined) baseCommand + " > " + required(output)
- else baseCommand
- }
-
+ override def cmdLine = super.cmdLine + required("mpileup2cns") +
+ required(input) +
+ optional("--min-coverage", minCoverage) +
+ optional("--min-reads2", minReads2) +
+ optional("--min-avg-qual", minAvgQual) +
+ optional("--min-var-freq", minVarFreq) +
+ optional("--min-freq-for-hom", minFreqForHom) +
+ optional("--p-value", pValue) +
+ optional("--strand-filter", strandFilter) +
+ optional("--output-vcf", outputVcf) +
+ optional("--vcf-sample-list", vcfSampleList) +
+ optional("--variants", variants) +
+ (if (outputAsStsout) "" else " > " + required(output))
}
diff --git a/public/biopet-extensions/src/test/scala/nl/lumc/sasc/biopet/extensions/LnTest.scala b/public/biopet-extensions/src/test/scala/nl/lumc/sasc/biopet/extensions/LnTest.scala
index 1f7f7b542438de2cce87f4ccd31d16e0601787c5..8083e46e16b27e2f5ce8f6553091fbccddcf1a95 100644
--- a/public/biopet-extensions/src/test/scala/nl/lumc/sasc/biopet/extensions/LnTest.scala
+++ b/public/biopet-extensions/src/test/scala/nl/lumc/sasc/biopet/extensions/LnTest.scala
@@ -59,6 +59,42 @@ class LnTest extends TestNGSuite with Matchers {
ln.cmd should ===("ln -s ../another_nested/target.txt /dir/nested/link.txt")
}
+ @Test(description = "Target is a child of a directory multi level above link, relative set to true")
+ def testTargetMultiLevelAboveChildRelative1() {
+ val ln = new Ln(null)
+ ln.relative = true
+ ln.input = new File("/dir/another_nested/1/2/3/4/target.txt")
+ ln.output = new File("/dir/nested/link.txt")
+ ln.cmd should ===("ln -s ../another_nested/1/2/3/4/target.txt /dir/nested/link.txt")
+ }
+
+ @Test(description = "Target is a child of a directory multi level above link, relative set to true")
+ def testTargetMultiLevelAboveChildRelative2() {
+ val ln = new Ln(null)
+ ln.relative = true
+ ln.input = new File("/dir/another_nested/1/2/3/4/target.txt")
+ ln.output = new File("/dir/nested/2/link.txt")
+ ln.cmd should ===("ln -s ../../another_nested/1/2/3/4/target.txt /dir/nested/2/link.txt")
+ }
+
+ @Test(description = "Source is a child of a directory multi level above link, relative set to true")
+ def testSourceMultiLevelAboveChildRelative() {
+ val ln = new Ln(null)
+ ln.relative = true
+ ln.output = new File("/dir/another_nested/1/2/3/4/link.txt")
+ ln.input = new File("/dir/nested/2/output.txt")
+ ln.cmd should ===("ln -s ../../../../../nested/2/output.txt /dir/another_nested/1/2/3/4/link.txt")
+ }
+
+ @Test(description = "Target is a child of a directory multi level above link, relative set to false")
+ def testTargetMultiLevelAboveChild() {
+ val ln = new Ln(null)
+ ln.relative = false
+ ln.input = new File("/dir/another_nested/1/2/3/4/target.txt")
+ ln.output = new File("/dir/nested/link.txt")
+ ln.cmd should ===("ln -s /dir/another_nested/1/2/3/4/target.txt /dir/nested/link.txt")
+ }
+
@Test(description = "Target is one level below link, relative set to true")
def testTargetOneLevelBelowRelative() {
val ln = new Ln(null)
diff --git a/public/biopet-public-package/pom.xml b/public/biopet-public-package/pom.xml
index 98945e3a22206579af807c6d2fbe4682ff75bd6c..32fb4e48b804c665e8abcafd552079a904a3f971 100644
--- a/public/biopet-public-package/pom.xml
+++ b/public/biopet-public-package/pom.xml
@@ -111,6 +111,11 @@
<artifactId>Basty</artifactId>
<version>${project.version}</version>
</dependency>
+ <dependency>
+ <groupId>nl.lumc.sasc</groupId>
+ <artifactId>BiopetToolsPackage</artifactId>
+ <version>${project.version}</version>
+ </dependency>
</dependencies>
<build>
<plugins>
diff --git a/public/biopet-public-package/src/main/scala/nl/lumc/sasc/biopet/BiopetExecutablePublic.scala b/public/biopet-public-package/src/main/scala/nl/lumc/sasc/biopet/BiopetExecutablePublic.scala
index 1b22370dc0dfa1d8a992a5dca6b7432a9836b63c..161a818900de16c86d4821fec774f099d8c0f8c3 100644
--- a/public/biopet-public-package/src/main/scala/nl/lumc/sasc/biopet/BiopetExecutablePublic.scala
+++ b/public/biopet-public-package/src/main/scala/nl/lumc/sasc/biopet/BiopetExecutablePublic.scala
@@ -30,6 +30,7 @@ object BiopetExecutablePublic extends BiopetExecutable {
nl.lumc.sasc.biopet.pipelines.carp.Carp,
nl.lumc.sasc.biopet.pipelines.toucan.Toucan,
nl.lumc.sasc.biopet.pipelines.shiva.ShivaSvCalling,
+ nl.lumc.sasc.biopet.pipelines.gears.GearsSingle,
nl.lumc.sasc.biopet.pipelines.gears.Gears
)
@@ -39,29 +40,5 @@ object BiopetExecutablePublic extends BiopetExecutable {
nl.lumc.sasc.biopet.pipelines.basty.Basty
) ::: publicPipelines
- def tools: List[MainCommand] = List(
- nl.lumc.sasc.biopet.tools.MergeTables,
- nl.lumc.sasc.biopet.tools.WipeReads,
- nl.lumc.sasc.biopet.tools.ExtractAlignedFastq,
- nl.lumc.sasc.biopet.tools.FastqSync,
- nl.lumc.sasc.biopet.tools.BiopetFlagstat,
- nl.lumc.sasc.biopet.tools.CheckAllelesVcfInBam,
- nl.lumc.sasc.biopet.tools.VcfToTsv,
- nl.lumc.sasc.biopet.tools.VcfFilter,
- nl.lumc.sasc.biopet.tools.VcfStats,
- nl.lumc.sasc.biopet.tools.FindRepeatsPacBio,
- nl.lumc.sasc.biopet.tools.MpileupToVcf,
- nl.lumc.sasc.biopet.tools.FastqSplitter,
- nl.lumc.sasc.biopet.tools.BedtoolsCoverageToCounts,
- nl.lumc.sasc.biopet.tools.SageCountFastq,
- nl.lumc.sasc.biopet.tools.SageCreateLibrary,
- nl.lumc.sasc.biopet.tools.SageCreateTagCounts,
- nl.lumc.sasc.biopet.tools.BastyGenerateFasta,
- nl.lumc.sasc.biopet.tools.MergeAlleles,
- nl.lumc.sasc.biopet.tools.SamplesTsvToJson,
- nl.lumc.sasc.biopet.tools.SeqStat,
- nl.lumc.sasc.biopet.tools.VepNormalizer,
- nl.lumc.sasc.biopet.tools.AnnotateVcfWithBed,
- nl.lumc.sasc.biopet.tools.VcfWithVcf,
- nl.lumc.sasc.biopet.tools.KrakenReportToJson)
+ def tools: List[MainCommand] = BiopetToolsExecutable.tools
}
diff --git a/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/BaseCounter.scala b/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/BaseCounter.scala
new file mode 100644
index 0000000000000000000000000000000000000000..d15d26a368f25080e7c0e54f668a2af1b2831699
--- /dev/null
+++ b/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/BaseCounter.scala
@@ -0,0 +1,102 @@
+/**
+ * Biopet is built on top of GATK Queue for building bioinformatic
+ * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
+ * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
+ * should also be able to execute Biopet tools and pipelines.
+ *
+ * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
+ *
+ * Contact us at: sasc@lumc.nl
+ *
+ * A dual licensing mode is applied. The source code within this project that are
+ * not part of GATK Queue is freely available for non-commercial use under an AGPL
+ * license; For commercial users or users who do not want to follow the AGPL
+ * license, please contact us to obtain a separate license.
+ */
+package nl.lumc.sasc.biopet.extensions.tools
+
+import java.io.{ PrintWriter, File }
+
+import nl.lumc.sasc.biopet.core.ToolCommandFunction
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
+
+/**
+ *
+ */
+class BaseCounter(val root: Configurable) extends ToolCommandFunction {
+ def toolObject = nl.lumc.sasc.biopet.tools.BaseCounter
+
+ @Input(doc = "Input Bed file", required = true)
+ var refFlat: File = _
+
+ @Input(doc = "Bam File", required = true)
+ var bamFile: File = _
+
+ var outputDir: File = _
+
+ var prefix: String = "output"
+
+ override def defaultCoreMemory = 3.0
+ override def defaultThreads = 4
+
+ def transcriptTotalCounts = new File(outputDir, s"$prefix.base.transcript.counts")
+ def transcriptTotalSenseCounts = new File(outputDir, s"$prefix.base.transcript.sense.counts")
+ def transcriptTotalAntiSenseCounts = new File(outputDir, s"$prefix.base.transcript.antisense.counts")
+ def transcriptExonicCounts = new File(outputDir, s"$prefix.base.transcript.exonic.counts")
+ def transcriptExonicSenseCounts = new File(outputDir, s"$prefix.base.transcript.exonic.sense.counts")
+ def transcriptExonicAntiSenseCounts = new File(outputDir, s"$prefix.base.transcript.exonic.antisense.counts")
+ def transcriptIntronicCounts = new File(outputDir, s"$prefix.base.transcript.intronic.counts")
+ def transcriptIntronicSenseCounts = new File(outputDir, s"$prefix.base.transcript.intronic.sense.counts")
+ def transcriptIntronicAntiSenseCounts = new File(outputDir, s"$prefix.base.transcript.intronic.antisense.counts")
+ def exonCounts = new File(outputDir, s"$prefix.base.exon.counts")
+ def exonSenseCounts = new File(outputDir, s"$prefix.base.exon.sense.counts")
+ def exonAntiSenseCounts = new File(outputDir, s"$prefix.base.exon.antisense.counts")
+ def intronCounts = new File(outputDir, s"$prefix.base.intron.counts")
+ def intronSenseCounts = new File(outputDir, s"$prefix.base.intron.sense.counts")
+ def intronAntiSenseCounts = new File(outputDir, s"$prefix.base.intron.antisense.counts")
+ def geneTotalCounts = new File(outputDir, s"$prefix.base.gene.counts")
+ def geneTotalSenseCounts = new File(outputDir, s"$prefix.base.gene.sense.counts")
+ def geneTotalAntiSenseCounts = new File(outputDir, s"$prefix.base.gene.antisense.counts")
+ def geneExonicCounts = new File(outputDir, s"$prefix.base.gene.exonic.counts")
+ def geneExonicSenseCounts = new File(outputDir, s"$prefix.base.gene.exonic.sense.counts")
+ def geneExonicAntiSenseCounts = new File(outputDir, s"$prefix.base.gene.exonic.antisense.counts")
+ def geneIntronicCounts = new File(outputDir, s"$prefix.base.gene.intronic.counts")
+ def geneIntronicSenseCounts = new File(outputDir, s"$prefix.base.gene.intronic.sense.counts")
+ def geneIntronicAntiSenseCounts = new File(outputDir, s"$prefix.base.gene.intronic.antisense.counts")
+ def mergeExonCounts = new File(outputDir, s"$prefix.base.exon.merge.counts")
+ def mergeExonSenseCounts = new File(outputDir, s"$prefix.base.exon.merge.sense.counts")
+ def mergeExonAntiSenseCounts = new File(outputDir, s"$prefix.base.exon.merge.antisense.counts")
+ def mergeIntronCounts = new File(outputDir, s"$prefix.base.intron.merge.counts")
+ def mergeIntronSenseCounts = new File(outputDir, s"$prefix.base.intron.merge.sense.counts")
+ def mergeIntronAntiSenseCounts = new File(outputDir, s"$prefix.base.intron.merge.antisense.counts")
+ def nonStrandedMetaExonCounts = new File(outputDir, s"$prefix.base.metaexons.non_stranded.counts")
+ def strandedMetaExonCounts = new File(outputDir, s"$prefix.base.metaexons.stranded.counts")
+ def strandedSenseMetaExonCounts = new File(outputDir, s"$prefix.base.metaexons.stranded.sense.counts")
+ def strandedAntiSenseMetaExonCounts = new File(outputDir, s"$prefix.base.metaexons.stranded.antisense.counts")
+
+ override def beforeGraph(): Unit = {
+ outputFiles ++= List(transcriptTotalCounts, transcriptTotalSenseCounts, transcriptTotalAntiSenseCounts,
+ transcriptExonicCounts, transcriptExonicSenseCounts, transcriptExonicAntiSenseCounts,
+ transcriptIntronicCounts, transcriptIntronicSenseCounts, transcriptIntronicAntiSenseCounts,
+ exonCounts, exonSenseCounts, exonAntiSenseCounts,
+ intronCounts, intronSenseCounts, intronAntiSenseCounts,
+ geneTotalCounts, geneTotalSenseCounts, geneTotalAntiSenseCounts,
+ geneExonicCounts, geneExonicSenseCounts, geneExonicAntiSenseCounts,
+ geneIntronicCounts, geneIntronicSenseCounts, geneIntronicAntiSenseCounts,
+ mergeExonCounts, mergeExonSenseCounts, mergeExonAntiSenseCounts,
+ mergeIntronCounts, mergeIntronSenseCounts, mergeIntronAntiSenseCounts,
+ nonStrandedMetaExonCounts,
+ strandedMetaExonCounts, strandedSenseMetaExonCounts, strandedAntiSenseMetaExonCounts)
+ jobOutputFile = new File(outputDir, s".$prefix.basecounter.out")
+ super.beforeGraph()
+
+ }
+
+ override def cmdLine = super.cmdLine +
+ required("--refFlat", refFlat) +
+ required("-b", bamFile) +
+ required("-o", outputDir) +
+ optional("--prefix", prefix)
+}
+
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/PlotPca.scala b/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/MergeOtuMaps.scala
similarity index 54%
rename from public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/PlotPca.scala
rename to public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/MergeOtuMaps.scala
index dd13421069fd331c819653a9fcf2cb4cf3b7c851..70f452b2537ce6943fd164d7dc1963d8c611f450 100644
--- a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/PlotPca.scala
+++ b/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/MergeOtuMaps.scala
@@ -13,33 +13,28 @@
* license; For commercial users or users who do not want to follow the AGPL
* license, please contact us to obtain a separate license.
*/
-package nl.lumc.sasc.biopet.pipelines.gentrap.scripts
+package nl.lumc.sasc.biopet.extensions.tools
import java.io.File
+import nl.lumc.sasc.biopet.core.ToolCommandFunction
+import nl.lumc.sasc.biopet.core.summary.Summarizable
+import nl.lumc.sasc.biopet.utils.ConfigUtils
import nl.lumc.sasc.biopet.utils.config.Configurable
-import nl.lumc.sasc.biopet.pipelines.gentrap.extensions.RScriptCommandLineFunction
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
-/**
- * Wrapper for the plot_pca.R script, used internally in Gentrap
- */
-class PlotPca(val root: Configurable) extends RScriptCommandLineFunction {
+class MergeOtuMaps(val root: Configurable) extends ToolCommandFunction {
+ def toolObject = nl.lumc.sasc.biopet.tools.MergeOtuMaps
- setRScript("plot_pca.R", "/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/")
+ @Input(doc = "Input", shortName = "input", required = true)
+ var input: List[File] = Nil
- @Input(doc = "Input table", required = true)
- var input: File = null
+ @Output(doc = "Output", shortName = "output", required = true)
+ var output: File = _
- @Output(doc = "Output plot", required = false)
- var output: File = null
+ override def defaultCoreMemory = 6.0
- var tmmNormalize: Boolean = config("tmm_normalize", default = false)
+ override def cmdLine = super.cmdLine + repeat("-I", input) + required("-o", output)
- def cmdLine = {
- RScriptCommand +
- conditional(tmmNormalize, "-T") +
- required("-I", input) +
- required("-O", output)
- }
}
+
diff --git a/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/MergeTables.scala b/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/MergeTables.scala
index f4e0946588d94fed1b9829ce1f66935a0530c532..96abaf1edb0725c21f8e1d41a698438b13f74d4f 100644
--- a/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/MergeTables.scala
+++ b/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/MergeTables.scala
@@ -77,3 +77,24 @@ class MergeTables(val root: Configurable) extends ToolCommandFunction {
required("-o", output) +
required("", repeat(inputTables), escape = false)
}
+
+object MergeTables {
+ def apply(root: Configurable,
+ tables: List[File],
+ outputFile: File,
+ idCols: List[Int],
+ valCol: Int,
+ numHeaderLines: Int = 0,
+ fallback: String = "-",
+ fileExtension: Option[String] = None): MergeTables = {
+ val job = new MergeTables(root)
+ job.inputTables = tables
+ job.output = outputFile
+ job.idColumnIndices = idCols.map(_.toString)
+ job.valueColumnIndex = valCol
+ job.fallbackString = Option(fallback)
+ job.numHeaderLines = Option(numHeaderLines)
+ job.fileExtension = fileExtension
+ job
+ }
+}
\ No newline at end of file
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/Hist2Count.scala b/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/ValidateFastq.scala
similarity index 51%
rename from public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/Hist2Count.scala
rename to public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/ValidateFastq.scala
index 4a8002c9defcf843bfeb6f69b062d68dc6d3b7b6..7fccf3eed249c749a89889ea4454e97d771aaeb1 100644
--- a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/Hist2Count.scala
+++ b/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/ValidateFastq.scala
@@ -13,34 +13,24 @@
* license; For commercial users or users who do not want to follow the AGPL
* license, please contact us to obtain a separate license.
*/
-package nl.lumc.sasc.biopet.pipelines.gentrap.scripts
+package nl.lumc.sasc.biopet.extensions.tools
import java.io.File
+import nl.lumc.sasc.biopet.core.{ Reference, ToolCommandFunction }
import nl.lumc.sasc.biopet.utils.config.Configurable
-import nl.lumc.sasc.biopet.core.extensions.PythonCommandLineFunction
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
-/**
- * Wrapper for the hist2count.py script, used internally in Gentrap
- */
-class Hist2Count(val root: Configurable) extends PythonCommandLineFunction {
-
- setPythonScript("hist2count.py")
-
- @Input(doc = "Input histogram file (generated by bedtools coverage -hist)", required = true)
- var input: File = null
+class ValidateFastq(val root: Configurable) extends ToolCommandFunction {
+ def toolObject = nl.lumc.sasc.biopet.tools.ValidateFastq
- @Output(doc = "Output count file", required = false)
- var outputGeneLevelCount: File = null
+ @Input(doc = "Input R1 fastq file", required = true)
+ var r1Fastq: File = _
- /** index of column to copy to output file from input file */
- var copyColumn: List[Int] = List.empty[Int]
+ @Input(doc = "Input R1 fastq file", required = false)
+ var r2Fastq: Option[File] = None
- def cmdLine = {
- getPythonCommand +
- required("-i", input) +
- required("-o", outputGeneLevelCount) +
- optional("-c", repeat(copyColumn), escape = false)
- }
+ override def cmdLine = super.cmdLine +
+ required("-i", r1Fastq) +
+ optional("-j", r2Fastq)
}
diff --git a/public/biopet-tools-package/src/main/scala/nl/lumc/sasc/biopet/BiopetToolsExecutable.scala b/public/biopet-tools-package/src/main/scala/nl/lumc/sasc/biopet/BiopetToolsExecutable.scala
index f3eae932c03aee22aa3867c243d93eeda479dcc5..a4d187c963f8d7417400fded53f2ce971288df5f 100644
--- a/public/biopet-tools-package/src/main/scala/nl/lumc/sasc/biopet/BiopetToolsExecutable.scala
+++ b/public/biopet-tools-package/src/main/scala/nl/lumc/sasc/biopet/BiopetToolsExecutable.scala
@@ -44,5 +44,7 @@ object BiopetToolsExecutable extends BiopetExecutable {
nl.lumc.sasc.biopet.tools.SeqStat,
nl.lumc.sasc.biopet.tools.VepNormalizer,
nl.lumc.sasc.biopet.tools.AnnotateVcfWithBed,
- nl.lumc.sasc.biopet.tools.VcfWithVcf)
+ nl.lumc.sasc.biopet.tools.VcfWithVcf,
+ nl.lumc.sasc.biopet.tools.ValidateFastq,
+ nl.lumc.sasc.biopet.tools.KrakenReportToJson)
}
diff --git a/public/biopet-tools/pom.xml b/public/biopet-tools/pom.xml
index cbd59820cef99e2fed1d3bb6a5da137ce90f5e74..c161ecff49f337a16954b0908405e66bd9eca1ea 100644
--- a/public/biopet-tools/pom.xml
+++ b/public/biopet-tools/pom.xml
@@ -70,5 +70,10 @@
<artifactId>biojava3-sequencing</artifactId>
<version>3.1.0</version>
</dependency>
+ <dependency>
+ <groupId>com.github.broadinstitute</groupId>
+ <artifactId>picard</artifactId>
+ <version>1.141</version>
+ </dependency>
</dependencies>
</project>
\ No newline at end of file
diff --git a/public/biopet-tools/src/main/resources/log4j.properties b/public/biopet-tools/src/main/resources/log4j.properties
new file mode 100644
index 0000000000000000000000000000000000000000..82aef1c853b2047cc3376ccfadd7f0465a990695
--- /dev/null
+++ b/public/biopet-tools/src/main/resources/log4j.properties
@@ -0,0 +1,26 @@
+#
+# Biopet is built on top of GATK Queue for building bioinformatic
+# pipelines. It is mainly intended to support LUMC SHARK cluster which is running
+# SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
+# should also be able to execute Biopet tools and pipelines.
+#
+# Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
+#
+# Contact us at: sasc@lumc.nl
+#
+# A dual licensing mode is applied. The source code within this project that are
+# not part of GATK Queue is freely available for non-commercial use under an AGPL
+# license; For commercial users or users who do not want to follow the AGPL
+# license, please contact us to obtain a separate license.
+#
+
+# Set root logger level to DEBUG and its only appender to A1.
+log4j.rootLogger=INFO, A1
+
+# A1 is set to be a ConsoleAppender.
+log4j.appender.A1=org.apache.log4j.ConsoleAppender
+log4j.appender.A1.Target=System.err
+
+# A1 uses PatternLayout.
+log4j.appender.A1.layout=org.apache.log4j.PatternLayout
+log4j.appender.A1.layout.ConversionPattern=%-5p [%d] [%C{1}] - %m%n
\ No newline at end of file
diff --git a/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/BaseCounter.scala b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/BaseCounter.scala
new file mode 100644
index 0000000000000000000000000000000000000000..7a2b0907f83cac2c0c65fe070bf3270b4e395775
--- /dev/null
+++ b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/BaseCounter.scala
@@ -0,0 +1,423 @@
+package nl.lumc.sasc.biopet.tools
+
+import java.io.{ PrintWriter, File }
+
+import htsjdk.samtools.{ SAMRecord, SamReaderFactory }
+import nl.lumc.sasc.biopet.utils.ToolCommand
+import nl.lumc.sasc.biopet.utils.intervals.{ BedRecordList, BedRecord }
+import picard.annotation.{ Gene, GeneAnnotationReader }
+
+import scala.collection.JavaConversions._
+
+/**
+ * This tool will generate Base count based on a bam file and a refflat file
+ *
+ * Created by pjvanthof on 22/01/16.
+ */
+object BaseCounter extends ToolCommand {
+
+ case class Args(refFlat: File = null,
+ outputDir: File = null,
+ bamFile: File = null,
+ prefix: String = "output") extends AbstractArgs
+
+ class OptParser extends AbstractOptParser {
+ opt[File]('r', "refFlat") required () valueName "<file>" action { (x, c) =>
+ c.copy(refFlat = x)
+ }
+ opt[File]('o', "outputDir") required () valueName "<directory>" action { (x, c) =>
+ c.copy(outputDir = x)
+ }
+ opt[File]('b', "bam") required () valueName "<file>" action { (x, c) =>
+ c.copy(bamFile = x)
+ }
+ opt[String]('p', "prefix") valueName "<prefix>" action { (x, c) =>
+ c.copy(prefix = x)
+ }
+ }
+
+ def main(args: Array[String]): Unit = {
+ val argsParser = new OptParser
+ val cmdArgs: Args = argsParser.parse(args, Args()) match {
+ case Some(x) => x
+ case _ => throw new IllegalArgumentException
+ }
+
+ //Sets picard logging level
+ htsjdk.samtools.util.Log.setGlobalLogLevel(htsjdk.samtools.util.Log.LogLevel.valueOf(logger.getLevel.toString))
+
+ logger.info("Start reading RefFlat file")
+ val bamReader = SamReaderFactory.makeDefault().open(cmdArgs.bamFile)
+ val geneReader = GeneAnnotationReader.loadRefFlat(cmdArgs.refFlat, bamReader.getFileHeader.getSequenceDictionary)
+ bamReader.close()
+ logger.info("Done reading RefFlat file")
+
+ logger.info("Finding overlapping genes")
+ val overlapGenes = groupGenesOnOverlap(geneReader.getAll)
+
+ logger.info("Start reading bamFile")
+ val counts = (for (genes <- overlapGenes.values.flatten.par) yield runThread(cmdArgs.bamFile, genes)).toList
+ logger.info("Done reading bamFile")
+
+ writeGeneCounts(counts.flatMap(_.geneCounts), cmdArgs.outputDir, cmdArgs.prefix)
+ writeMergeExonCount(counts.flatMap(_.geneCounts), cmdArgs.outputDir, cmdArgs.prefix)
+ writeMergeIntronCount(counts.flatMap(_.geneCounts), cmdArgs.outputDir, cmdArgs.prefix)
+ writeTranscriptCounts(counts.flatMap(_.geneCounts), cmdArgs.outputDir, cmdArgs.prefix)
+ writeExonCount(counts.flatMap(_.geneCounts), cmdArgs.outputDir, cmdArgs.prefix)
+ writeIntronCount(counts.flatMap(_.geneCounts), cmdArgs.outputDir, cmdArgs.prefix)
+ writeNonStrandedMetaExonsCount(counts.flatMap(_.nonStrandedMetaExonCounts), cmdArgs.outputDir, cmdArgs.prefix)
+ writeStrandedMetaExonsCount(counts.flatMap(_.strandedMetaExonCounts), cmdArgs.outputDir, cmdArgs.prefix)
+ }
+
+ /**
+ * This function will write all counts that are concatenated on transcript level. Each line is 1 transcript.
+ * Exonic: then it's seen as an exon on 1 of the transcripts
+ * Intronic: then it's not seen as an exon on 1 of the transcripts
+ * Exonic + Intronic = Total
+ */
+ def writeTranscriptCounts(genes: List[GeneCount], outputDir: File, prefix: String): Unit = {
+ val transcriptTotalWriter = new PrintWriter(new File(outputDir, s"$prefix.base.transcript.counts"))
+ val transcriptTotalSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.transcript.sense.counts"))
+ val transcriptTotalAntiSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.transcript.antisense.counts"))
+ val transcriptExonicWriter = new PrintWriter(new File(outputDir, s"$prefix.base.transcript.exonic.counts"))
+ val transcriptExonicSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.transcript.exonic.sense.counts"))
+ val transcriptExonicAntiSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.transcript.exonic.antisense.counts"))
+ val transcriptIntronicWriter = new PrintWriter(new File(outputDir, s"$prefix.base.transcript.intronic.counts"))
+ val transcriptIntronicSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.transcript.intronic.sense.counts"))
+ val transcriptIntronicAntiSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.transcript.intronic.antisense.counts"))
+
+ genes.flatMap(_.transcripts).sortBy(_.transcript.name).foreach { transcriptCount =>
+ transcriptTotalWriter.println(transcriptCount.transcript.name + "\t" + transcriptCount.counts.totalBases)
+ transcriptTotalSenseWriter.println(transcriptCount.transcript.name + "\t" + transcriptCount.counts.senseBases)
+ transcriptTotalAntiSenseWriter.println(transcriptCount.transcript.name + "\t" + transcriptCount.counts.antiSenseBases)
+ transcriptExonicWriter.println(transcriptCount.transcript.name + "\t" + transcriptCount.exonCounts.map(_.counts.totalBases).sum)
+ transcriptExonicSenseWriter.println(transcriptCount.transcript.name + "\t" + transcriptCount.exonCounts.map(_.counts.senseBases).sum)
+ transcriptExonicAntiSenseWriter.println(transcriptCount.transcript.name + "\t" + transcriptCount.exonCounts.map(_.counts.antiSenseBases).sum)
+ transcriptIntronicWriter.println(transcriptCount.transcript.name + "\t" + transcriptCount.intronCounts.map(_.counts.totalBases).sum)
+ transcriptIntronicSenseWriter.println(transcriptCount.transcript.name + "\t" + transcriptCount.intronCounts.map(_.counts.senseBases).sum)
+ transcriptIntronicAntiSenseWriter.println(transcriptCount.transcript.name + "\t" + transcriptCount.intronCounts.map(_.counts.antiSenseBases).sum)
+ }
+
+ transcriptTotalWriter.close()
+ transcriptTotalSenseWriter.close()
+ transcriptTotalAntiSenseWriter.close()
+ transcriptExonicWriter.close()
+ transcriptExonicSenseWriter.close()
+ transcriptExonicAntiSenseWriter.close()
+ transcriptIntronicWriter.close()
+ transcriptIntronicSenseWriter.close()
+ transcriptIntronicAntiSenseWriter.close()
+ }
+
+ /** This will write counts on each exon */
+ def writeExonCount(genes: List[GeneCount], outputDir: File, prefix: String): Unit = {
+ val exonWriter = new PrintWriter(new File(outputDir, s"$prefix.base.exon.counts"))
+ val exonSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.exon.sense.counts"))
+ val exonAntiSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.exon.antisense.counts"))
+
+ genes.flatMap(_.transcripts).sortBy(_.transcript.name).foreach { transcriptCount =>
+ transcriptCount.exonCounts.foreach { exonCount =>
+ exonWriter.println(transcriptCount.transcript.name + s"_exon:${exonCount.start}-${exonCount.end}\t" + exonCount.counts.totalBases)
+ exonSenseWriter.println(transcriptCount.transcript.name + s"_exon:${exonCount.start}-${exonCount.end}\t" + exonCount.counts.senseBases)
+ exonAntiSenseWriter.println(transcriptCount.transcript.name + s"_exon:${exonCount.start}-${exonCount.end}\t" + exonCount.counts.antiSenseBases)
+ }
+ }
+
+ exonWriter.close()
+ exonSenseWriter.close()
+ exonAntiSenseWriter.close()
+ }
+
+ /** This will write counts on each intron */
+ def writeIntronCount(genes: List[GeneCount], outputDir: File, prefix: String): Unit = {
+ val intronWriter = new PrintWriter(new File(outputDir, s"$prefix.base.intron.counts"))
+ val intronSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.intron.sense.counts"))
+ val intronAntiSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.intron.antisense.counts"))
+
+ genes.flatMap(_.transcripts).sortBy(_.transcript.name).foreach { transcriptCount =>
+ transcriptCount.intronCounts.foreach { intronCount =>
+ intronWriter.println(transcriptCount.transcript.name + s"_intron:${intronCount.start}-${intronCount.end}\t" + intronCount.counts.totalBases)
+ intronSenseWriter.println(transcriptCount.transcript.name + s"_intron:${intronCount.start}-${intronCount.end}\t" + intronCount.counts.senseBases)
+ intronAntiSenseWriter.println(transcriptCount.transcript.name + s"_intron:${intronCount.start}-${intronCount.end}\t" + intronCount.counts.antiSenseBases)
+ }
+ }
+
+ intronWriter.close()
+ intronSenseWriter.close()
+ intronAntiSenseWriter.close()
+ }
+
+ /**
+ * This function will write all counts that are concatenated on gene level. Each line is 1 gene.
+ * Exonic: then it's seen as an exon on 1 of the transcripts
+ * Intronic: then it's not seen as an exon on 1 of the transcripts
+ * Exonic + Intronic = Total
+ */
+ def writeGeneCounts(genes: List[GeneCount], outputDir: File, prefix: String): Unit = {
+ val geneTotalWriter = new PrintWriter(new File(outputDir, s"$prefix.base.gene.counts"))
+ val geneTotalSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.gene.sense.counts"))
+ val geneTotalAntiSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.gene.antisense.counts"))
+ val geneExonicWriter = new PrintWriter(new File(outputDir, s"$prefix.base.gene.exonic.counts"))
+ val geneExonicSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.gene.exonic.sense.counts"))
+ val geneExonicAntiSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.gene.exonic.antisense.counts"))
+ val geneIntronicWriter = new PrintWriter(new File(outputDir, s"$prefix.base.gene.intronic.counts"))
+ val geneIntronicSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.gene.intronic.sense.counts"))
+ val geneIntronicAntiSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.gene.intronic.antisense.counts"))
+
+ genes.sortBy(_.gene.getName).foreach { geneCount =>
+ geneTotalWriter.println(geneCount.gene.getName + "\t" + geneCount.counts.totalBases)
+ geneTotalSenseWriter.println(geneCount.gene.getName + "\t" + geneCount.counts.senseBases)
+ geneTotalAntiSenseWriter.println(geneCount.gene.getName + "\t" + geneCount.counts.antiSenseBases)
+ geneExonicWriter.println(geneCount.gene.getName + "\t" + geneCount.exonCounts.map(_.counts.totalBases).sum)
+ geneExonicSenseWriter.println(geneCount.gene.getName + "\t" + geneCount.exonCounts.map(_.counts.senseBases).sum)
+ geneExonicAntiSenseWriter.println(geneCount.gene.getName + "\t" + geneCount.exonCounts.map(_.counts.antiSenseBases).sum)
+ geneIntronicWriter.println(geneCount.gene.getName + "\t" + geneCount.intronCounts.map(_.counts.totalBases).sum)
+ geneIntronicSenseWriter.println(geneCount.gene.getName + "\t" + geneCount.intronCounts.map(_.counts.senseBases).sum)
+ geneIntronicAntiSenseWriter.println(geneCount.gene.getName + "\t" + geneCount.intronCounts.map(_.counts.antiSenseBases).sum)
+ }
+
+ geneTotalWriter.close()
+ geneTotalSenseWriter.close()
+ geneTotalAntiSenseWriter.close()
+ geneExonicWriter.close()
+ geneExonicSenseWriter.close()
+ geneExonicAntiSenseWriter.close()
+ geneIntronicWriter.close()
+ geneIntronicSenseWriter.close()
+ geneIntronicAntiSenseWriter.close()
+ }
+
+ /**
+ * This function will print all counts that exist on exonic regions,
+ * each base withing the gene is only represented once but all regions are separated
+ */
+ def writeMergeExonCount(genes: List[GeneCount], outputDir: File, prefix: String): Unit = {
+ val exonWriter = new PrintWriter(new File(outputDir, s"$prefix.base.exon.merge.counts"))
+ val exonSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.exon.merge.sense.counts"))
+ val exonAntiSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.exon.merge.antisense.counts"))
+
+ genes.sortBy(_.gene.getName).foreach { geneCount =>
+ geneCount.exonCounts.foreach { exonCount =>
+ exonWriter.println(geneCount.gene.getName + s"_exon:${exonCount.start}-${exonCount.end}\t" + exonCount.counts.totalBases)
+ exonSenseWriter.println(geneCount.gene.getName + s"_exon:${exonCount.start}-${exonCount.end}\t" + exonCount.counts.senseBases)
+ exonAntiSenseWriter.println(geneCount.gene.getName + s"_exon:${exonCount.start}-${exonCount.end}\t" + exonCount.counts.antiSenseBases)
+ }
+ }
+
+ exonWriter.close()
+ exonSenseWriter.close()
+ exonAntiSenseWriter.close()
+ }
+
+ /**
+ * This function will print all counts that does *not* exist on exonic regions,
+ * each base withing the gene is only represented once but all regions are separated
+ */
+ def writeMergeIntronCount(genes: List[GeneCount], outputDir: File, prefix: String): Unit = {
+ val intronWriter = new PrintWriter(new File(outputDir, s"$prefix.base.intron.merge.counts"))
+ val intronSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.intron.merge.sense.counts"))
+ val intronAntiSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.intron.merge.antisense.counts"))
+
+ genes.sortBy(_.gene.getName).foreach { geneCount =>
+ geneCount.intronCounts.foreach { intronCount =>
+ intronWriter.println(geneCount.gene.getName + s"_intron:${intronCount.start}-${intronCount.end}\t" + intronCount.counts.totalBases)
+ intronSenseWriter.println(geneCount.gene.getName + s"_intron:${intronCount.start}-${intronCount.end}\t" + intronCount.counts.senseBases)
+ intronAntiSenseWriter.println(geneCount.gene.getName + s"_intron:${intronCount.start}-${intronCount.end}\t" + intronCount.counts.antiSenseBases)
+ }
+ }
+
+ intronWriter.close()
+ intronSenseWriter.close()
+ intronAntiSenseWriter.close()
+ }
+
+ /**
+ * This function will print all counts for meta exons
+ */
+ def writeNonStrandedMetaExonsCount(metaCounts: List[(String, RegionCount)],
+ outputDir: File, prefix: String): Unit = {
+ val nonStrandedWriter = new PrintWriter(new File(outputDir, s"$prefix.base.metaexons.non_stranded.counts"))
+
+ metaCounts.foreach {
+ case (name, counts) =>
+ nonStrandedWriter.println(s"${name}_intron:${counts.start}-${counts.end}\t${counts.counts.totalBases}")
+ }
+
+ nonStrandedWriter.close()
+ }
+
+ /**
+ * This function will print all counts for meta exons
+ */
+ def writeStrandedMetaExonsCount(metaCounts: List[(String, RegionCount)],
+ outputDir: File, prefix: String): Unit = {
+ val strandedWriter = new PrintWriter(new File(outputDir, s"$prefix.base.metaexons.stranded.counts"))
+ val strandedSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.metaexons.stranded.sense.counts"))
+ val strandedAntiSenseWriter = new PrintWriter(new File(outputDir, s"$prefix.base.metaexons.stranded.antisense.counts"))
+
+ metaCounts.foreach {
+ case (name, counts) =>
+ strandedWriter.println(s"${name}_intron:${counts.start}-${counts.end}\t${counts.counts.totalBases}")
+ strandedSenseWriter.println(s"${name}_intron:${counts.start}-${counts.end}\t${counts.counts.senseBases}")
+ strandedAntiSenseWriter.println(s"${name}_intron:${counts.start}-${counts.end}\t${counts.counts.antiSenseBases}")
+ }
+
+ strandedWriter.close()
+ strandedSenseWriter.close()
+ strandedAntiSenseWriter.close()
+ }
+
+ def samRecordStrand(samRecord: SAMRecord, gene: Gene): Boolean = {
+ samRecordStrand(samRecord, gene.isPositiveStrand)
+ }
+
+ def samRecordStrand(samRecord: SAMRecord, strand: Boolean): Boolean = {
+ if (samRecord.getReadPairedFlag && samRecord.getSecondOfPairFlag)
+ samRecord.getReadNegativeStrandFlag != strand
+ else samRecord.getReadNegativeStrandFlag == strand
+ }
+
+ private[tools] case class ThreadOutput(geneCounts: List[GeneCount],
+ nonStrandedMetaExonCounts: List[(String, RegionCount)],
+ strandedMetaExonCounts: List[(String, RegionCount)])
+
+ private[tools] def runThread(bamFile: File, genes: List[Gene]): ThreadOutput = {
+ val counts = genes.map(gene => gene -> new GeneCount(gene)).toMap
+ val bamReader = SamReaderFactory.makeDefault().open(bamFile)
+
+ val metaExons = createMetaExonCounts(genes)
+ val plusMetaExons = createMetaExonCounts(genes.filter(_.isPositiveStrand))
+ val minMetaExons = createMetaExonCounts(genes.filter(_.isNegativeStrand))
+
+ val start = genes.map(_.getStart).min
+ val end = genes.map(_.getEnd).max
+
+ for (record <- bamReader.queryOverlapping(genes.head.getContig, start, end) if !record.getNotPrimaryAlignmentFlag) {
+ counts.foreach { case (gene, count) => count.addRecord(record, samRecordStrand(record, gene)) }
+ metaExons.foreach(_._2.addRecord(record, sense = true))
+ plusMetaExons.foreach(_._2.addRecord(record, samRecordStrand(record, strand = true)))
+ minMetaExons.foreach(_._2.addRecord(record, samRecordStrand(record, strand = false)))
+ }
+
+ bamReader.close()
+ ThreadOutput(counts.values.toList, metaExons, plusMetaExons ::: minMetaExons)
+ }
+
+ def createMetaExonCounts(genes: List[Gene]): List[(String, RegionCount)] = {
+ if (genes.nonEmpty) {
+ val regions = genes.map(gene => gene.getName -> generateMergedExonRegions(gene).sorted)
+ val chr = genes.head.getContig
+ val begin = regions.map(_._2.allRecords.head.start).min
+ val end = regions.map(_._2.allRecords.last.end).max
+
+ val posibleEnds = (regions.flatMap(_._2.allRecords.map(_.end)) ++ regions.flatMap(_._2.allRecords.map(_.start))).distinct.sorted
+
+ def mergeRegions(newBegin: Int, output: List[(String, RegionCount)] = Nil): List[(String, RegionCount)] = {
+ val newEnds = posibleEnds.filter(_ > newBegin)
+ if (newBegin > end || newEnds.isEmpty) output
+ else {
+ val newEnd = newEnds.min
+ val record = BedRecord(chr, newBegin, newEnd)
+ val names = regions.filter(_._2.overlapWith(record).nonEmpty).map(_._1)
+ if (names.nonEmpty) mergeRegions(newEnd, (names.mkString(","), new RegionCount(record.start + 1, record.end)) :: output)
+ else mergeRegions(newEnd, output)
+ }
+ }
+ mergeRegions(begin)
+ } else Nil
+ }
+
+ def bamRecordBasesOverlap(samRecord: SAMRecord, start: Int, end: Int): Int = {
+ samRecord.getAlignmentBlocks
+ .map { block =>
+ val blockStart = block.getReferenceStart
+ val blockEnd = blockStart + block.getLength - 1
+ if (start <= blockEnd && end >= blockStart) {
+ (if (end < blockEnd) end else blockEnd) - (if (start > blockStart) start else blockStart) + 1
+ } else 0
+ }.sum
+ }
+
+ def bamRecordBasesOverlap(samRecord: SAMRecord, start: Int, end: Int, counts: Counts, sense: Boolean): Int = {
+ val overlap = bamRecordBasesOverlap(samRecord, start, end)
+ if (overlap > 0) {
+ if (sense) {
+ counts.senseBases += overlap
+ counts.senseReads += 1
+ } else {
+ counts.antiSenseBases += overlap
+ counts.antiSenseReads += 1
+ }
+ }
+ overlap
+ }
+
+ def groupGenesOnOverlap(genes: Iterable[Gene]) = {
+ genes.groupBy(_.getContig)
+ .map {
+ case (contig, g) => contig -> g.toList
+ .sortBy(_.getStart).foldLeft(List[List[Gene]]()) { (list, gene) =>
+ if (list.isEmpty) List(List(gene))
+ else if (list.head.exists(_.getEnd >= gene.getStart)) (gene :: list.head) :: list.tail
+ else List(gene) :: list
+ }
+ }
+ }
+
+ class Counts {
+ var senseBases = 0L
+ var antiSenseBases = 0L
+ def totalBases = senseBases + antiSenseBases
+ var senseReads = 0L
+ var antiSenseReads = 0L
+ def totalReads = senseReads + antiSenseReads
+ }
+
+ def generateMergedExonRegions(gene: Gene) =
+ BedRecordList.fromList(gene.iterator()
+ .flatMap(_.exons)
+ .map(e => BedRecord(gene.getContig, e.start - 1, e.end))
+ ).combineOverlap
+
+ class GeneCount(val gene: Gene) {
+ val counts = new Counts
+ val transcripts = gene.iterator().map(new TranscriptCount(_)).toList
+ def intronRegions = BedRecordList.fromList(BedRecord(gene.getContig, gene.getStart - 1, gene.getEnd) :: generateMergedExonRegions(gene).allRecords.toList)
+ .squishBed(strandSensitive = false, nameSensitive = false)
+
+ val exonCounts = generateMergedExonRegions(gene).allRecords.map(e => new RegionCount(e.start + 1, e.end))
+ val intronCounts = intronRegions.allRecords.map(e => new RegionCount(e.start + 1, e.end))
+
+ def addRecord(samRecord: SAMRecord, sense: Boolean): Unit = {
+ bamRecordBasesOverlap(samRecord, gene.getStart, gene.getEnd, counts, sense)
+ transcripts.foreach(_.addRecord(samRecord, sense))
+ exonCounts.foreach(_.addRecord(samRecord, sense))
+ intronCounts.foreach(_.addRecord(samRecord, sense))
+ }
+ }
+
+ class TranscriptCount(val transcript: Gene#Transcript) {
+ val counts = new Counts
+ def intronRegions = BedRecordList.fromList(BedRecord(transcript.getGene.getContig, transcript.start() - 1, transcript.end()) ::
+ transcript.exons.map(e => BedRecord(transcript.getGene.getContig, e.start - 1, e.end)).toList)
+ .squishBed(strandSensitive = false, nameSensitive = false)
+
+ val exonCounts = transcript.exons.map(new RegionCount(_))
+ val intronCounts = if (transcript.exons.size > 1)
+ intronRegions.allRecords.map(e => new RegionCount(e.start + 1, e.end)).toList
+ else Nil
+ def addRecord(samRecord: SAMRecord, sense: Boolean): Unit = {
+ bamRecordBasesOverlap(samRecord, transcript.start, transcript.end, counts, sense)
+ exonCounts.foreach(_.addRecord(samRecord, sense))
+ intronCounts.foreach(_.addRecord(samRecord, sense))
+ }
+ }
+
+ class RegionCount(val start: Int, val end: Int) {
+ def this(exon: Gene#Transcript#Exon) = this(exon.start, exon.end)
+ val counts = new Counts
+ def addRecord(samRecord: SAMRecord, sense: Boolean): Unit = {
+ bamRecordBasesOverlap(samRecord, start, end, counts, sense)
+ }
+ }
+}
\ No newline at end of file
diff --git a/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/MergeOtuMaps.scala b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/MergeOtuMaps.scala
new file mode 100644
index 0000000000000000000000000000000000000000..78bc62cfe7d55e6a3e01b92a4a0bae663e997e56
--- /dev/null
+++ b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/MergeOtuMaps.scala
@@ -0,0 +1,49 @@
+package nl.lumc.sasc.biopet.tools
+
+import java.io.{ PrintWriter, File }
+
+import nl.lumc.sasc.biopet.utils.ToolCommand
+
+import scala.io.Source
+
+/**
+ * Created by pjvan_thof on 12/18/15.
+ */
+object MergeOtuMaps extends ToolCommand {
+ case class Args(inputFiles: List[File] = Nil, outputFile: File = null) extends AbstractArgs
+
+ class OptParser extends AbstractOptParser {
+ opt[File]('I', "input") minOccurs 2 required () unbounded () valueName "<file>" action { (x, c) =>
+ c.copy(inputFiles = x :: c.inputFiles)
+ }
+ opt[File]('o', "output") required () unbounded () maxOccurs 1 valueName "<file>" action { (x, c) =>
+ c.copy(outputFile = x)
+ }
+ }
+
+ /**
+ * @param args the command line arguments
+ */
+ def main(args: Array[String]): Unit = {
+ val argsParser = new OptParser
+ val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
+
+ var map: Map[Long, String] = Map()
+
+ for (inputFile <- commandArgs.inputFiles) {
+ logger.info(s"Start reading $inputFile")
+ val reader = Source.fromFile(inputFile)
+ reader.getLines().foreach { line =>
+ val values = line.split("\t", 2)
+ val key = values.head.toLong
+ map += key -> (line.stripPrefix(s"$key") + map.getOrElse(key, ""))
+ }
+ reader.close()
+ }
+
+ logger.info(s"Start writing to ${commandArgs.outputFile}")
+ val writer = new PrintWriter(commandArgs.outputFile)
+ map.foreach { case (key, list) => writer.println(key + list) }
+ writer.close()
+ }
+}
diff --git a/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/MergeTables.scala b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/MergeTables.scala
index 680cba33443e7efbcda4e2acb5b42809a12b3f5c..426043c4b92ff49a1f987c418658ffd4180ba702 100644
--- a/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/MergeTables.scala
+++ b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/MergeTables.scala
@@ -108,6 +108,7 @@ object MergeTables extends ToolCommand {
idColumnIndices: Seq[Int] = Seq.empty[Int],
valueColumnIndex: Int = -1,
fileExtension: String = "",
+ columnNames: Option[Seq[String]] = None,
numHeaderLines: Int = 0,
fallbackString: String = "-",
delimiter: Char = '\t',
@@ -146,6 +147,10 @@ object MergeTables extends ToolCommand {
c.copy(idColumnName = x)
} text "Name of feature ID column in the output merged file (default: feature)"
+ opt[String]('N', "column_names") optional () valueName "<name>" action { (x, c) =>
+ c.copy(columnNames = Some(x.split(",")))
+ } text "Name of feature ID column in the output merged file (default: feature)"
+
opt[String]('e', "strip_extension") optional () valueName "<ext>" action { (x, c) =>
c.copy(fileExtension = x)
} text "Common extension of all input tables to strip (default: empty string)"
@@ -186,10 +191,17 @@ object MergeTables extends ToolCommand {
.getOrElse(sys.exit(1))
/** Transforms the input file seq into a seq of [[InputTable]] objects */
- def prepInput(inFiles: Seq[File], ext: String = ""): Seq[InputTable] = {
- require(inFiles.map(_.getName.stripSuffix(ext)).distinct.size == inFiles.size, "Duplicate samples exist in inputs")
- inFiles
- .map(tableFile => InputTable(tableFile.getName.stripSuffix(ext), Source.fromFile(tableFile)))
+ def prepInput(inFiles: Seq[File], ext: String, columnNames: Option[Seq[String]]): Seq[InputTable] = {
+ (ext, columnNames) match {
+ case (_, Some(names)) =>
+ require(names.size == inFiles.size, "columnNames are not the same number as input Files")
+ names.zip(inFiles).map { case (name, tableFile) => InputTable(name, Source.fromFile(tableFile)) }
+ case _ =>
+ require(inFiles.map(_.getName.stripSuffix(ext)).distinct.size == inFiles.size,
+ "Duplicate samples exist in inputs")
+ inFiles
+ .map(tableFile => InputTable(tableFile.getName.stripSuffix(ext), Source.fromFile(tableFile)))
+ }
}
/** Creates the output writer object */
@@ -205,7 +217,7 @@ object MergeTables extends ToolCommand {
import commandArgs._
val outStream = prepOutput(out)
- val merged = mergeTables(prepInput(inputTables, fileExtension),
+ val merged = mergeTables(prepInput(inputTables, fileExtension, columnNames),
idColumnIndices, valueColumnIndex, numHeaderLines, delimiter)
writeOutput(merged, outStream, fallbackString, idColumnName)
outStream.close()
diff --git a/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/SageCountFastq.scala b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/SageCountFastq.scala
index 2049a337670655d56c0846e3e64eb6274d6f8d7a..e559f22216b5f08fd625b24931251694733a81c4 100644
--- a/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/SageCountFastq.scala
+++ b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/SageCountFastq.scala
@@ -15,10 +15,12 @@
*/
package nl.lumc.sasc.biopet.tools
-import java.io.{ File, FileReader, PrintWriter }
+import java.io.{ File, PrintWriter }
+import htsjdk.samtools.fastq.FastqReader
import nl.lumc.sasc.biopet.utils.ToolCommand
-import org.biojava3.sequencing.io.fastq.{ Fastq, StreamListener, SangerFastqReader }
+
+import scala.collection.JavaConversions._
import scala.collection.{ SortedMap, mutable }
@@ -44,19 +46,19 @@ object SageCountFastq extends ToolCommand {
if (!commandArgs.input.exists) throw new IllegalStateException("Input file not found, file: " + commandArgs.input)
val counts: mutable.Map[String, Long] = mutable.Map()
- val reader = new SangerFastqReader
+ val reader: FastqReader = new FastqReader(commandArgs.input)
var count = 0
logger.info("Reading fastq file: " + commandArgs.input)
- val fileReader = new FileReader(commandArgs.input)
- reader.stream(fileReader, new StreamListener {
- def fastq(fastq: Fastq) {
- val seq = fastq.getSequence
- if (counts.contains(seq)) counts(seq) += 1
- else counts += (seq -> 1)
- count += 1
- if (count % 1000000 == 0) logger.info(count + " sequences done")
- }
- })
+
+ for (read <- reader.iterator()) {
+ val seq = read.getReadString
+ if (counts.contains(seq)) counts(seq) += 1
+ else counts += (seq -> 1)
+ count += 1
+ if (count % 1000000 == 0) logger.info(count + " sequences done")
+ }
+
+ reader.close()
logger.info(count + " sequences done")
logger.info("Sorting")
@@ -64,9 +66,7 @@ object SageCountFastq extends ToolCommand {
logger.info("Writting outputfile: " + commandArgs.output)
val writer = new PrintWriter(commandArgs.output)
- for ((seq, count) <- sortedCounts) {
- writer.println(seq + "\t" + count)
- }
+ sortedCounts.foreach { case (s, c) => writer.println(s + "\t" + c) }
writer.close()
}
}
\ No newline at end of file
diff --git a/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/ValidateFastq.scala b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/ValidateFastq.scala
new file mode 100644
index 0000000000000000000000000000000000000000..ab768899eea79530e3a76e04a2a60e8140e25a90
--- /dev/null
+++ b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/ValidateFastq.scala
@@ -0,0 +1,179 @@
+package nl.lumc.sasc.biopet.tools
+
+import java.io.File
+
+import htsjdk.samtools.fastq.{ FastqRecord, FastqReader }
+import nl.lumc.sasc.biopet.utils.ToolCommand
+
+import scala.collection.JavaConversions._
+import scala.collection.mutable.ListBuffer
+
+/**
+ * Created by sajvanderzeeuw on 2-2-16.
+ */
+object ValidateFastq extends ToolCommand {
+ /**
+ * Args for commandline program
+ * @param input input first fastq file (R1) (can be zipped)
+ * @param input2 input second fastq file (R2) (can be zipped)
+ */
+
+ case class Args(input: File = null, input2: Option[File] = None) extends AbstractArgs
+
+ class OptParser extends AbstractOptParser {
+ opt[File]('i', "fastq1") required () maxOccurs 1 valueName "<file>" action { (x, c) =>
+ c.copy(input = x)
+ }
+ opt[File]('j', "fastq2") maxOccurs 1 valueName "<file>" action { (x, c) =>
+ c.copy(input2 = Some(x))
+ }
+ }
+
+ def main(args: Array[String]): Unit = {
+ //Start analyses of fastq files
+ logger.info("Start")
+
+ //parse all possible options into OptParser
+ val argsParser = new OptParser
+ val cmdArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
+
+ //read in fastq file 1 and if present fastq file 2
+ val readFq1 = new FastqReader(cmdArgs.input)
+ val readFq2 = cmdArgs.input2.map(new FastqReader(_))
+
+ //define a counter to track the number of objects passing through the for loop
+
+ var counter = 0
+
+ try {
+ //Iterate over the fastq file check for the length of both files if not correct, exit the tool and print error message
+
+ var lastRecordR1: Option[FastqRecord] = None
+ var lastRecordR2: Option[FastqRecord] = None
+ for (recordR1 <- readFq1.iterator()) {
+ counter += 1
+ if (readFq2.map(_.hasNext) == Some(false))
+ throw new IllegalStateException("R2 contains less reads then R1")
+
+ //Getting R2 record, None if it's single end
+ val recordR2 = readFq2.map(_.next())
+
+ validFastqRecord(recordR1)
+ duplicateCheck(recordR1, lastRecordR1)
+
+ //Here we check if the readnames of both files are concordant, and if the sequence content are correct DNA/RNA sequences
+ recordR2 match {
+ case Some(recordR2) => // Paired End
+ validFastqRecord(recordR2)
+ duplicateCheck(recordR2, lastRecordR2)
+ checkMate(recordR1, recordR2)
+ case _ => // Single end
+ }
+ if (counter % 1e5 == 0) logger.info(counter + " reads processed")
+ lastRecordR1 = Some(recordR1)
+ lastRecordR2 = recordR2
+ }
+
+ //if R2 is longer then R1 print an error code and exit the tool
+ if (readFq2.map(_.hasNext) == Some(true))
+ throw new IllegalStateException("R2 contains more reads then R1")
+
+ logger.info(s"Possible quality encodings found: ${getPossibleEncodings.mkString(", ")}")
+
+ logger.info(s"Done processing ${counter} fastq records, no errors found")
+ } catch {
+ case e: IllegalStateException =>
+ logger.error(s"Error found at readnumber: $counter, linenumber ${(counter * 4) - 3}")
+ logger.error(e.getMessage)
+ }
+
+ //close both iterators
+ readFq1.close()
+ readFq2.foreach(_.close())
+ }
+
+ private[tools] var minQual: Option[Char] = None
+ private[tools] var maxQual: Option[Char] = None
+
+ /**
+ *
+ * @param record
+ * @throws IllegalStateException
+ */
+ private[tools] def checkQualEncoding(record: FastqRecord): Unit = {
+ val min = record.getBaseQualityString.min
+ val max = record.getBaseQualityString.max
+ if (!minQual.exists(_ <= min)) {
+ minQual = Some(min)
+ getPossibleEncodings
+ }
+ if (!maxQual.exists(_ >= max)) {
+ maxQual = Some(max)
+ getPossibleEncodings
+ }
+ }
+
+ /**
+ *
+ * @return
+ * @throws IllegalStateException
+ */
+ private[tools] def getPossibleEncodings: List[String] = {
+ val buffer: ListBuffer[String] = ListBuffer()
+ (minQual, maxQual) match {
+ case (Some(min), Some(max)) =>
+ if (min >= '!' && max <= 'I') buffer += "Sanger"
+ if (min >= ';' && max <= 'h') buffer += "Solexa"
+ if (min >= '@' && max <= 'h') buffer += "Illumina 1.3+"
+ if (min >= 'C' && max <= 'h') buffer += "Illumina 1.5+"
+ if (min >= '!' && max <= 'J') buffer += "Illumina 1.8+"
+ if (buffer.isEmpty)
+ throw new IllegalStateException(s"No possible quality encoding found. minQual: '$min', maxQual: '$max'")
+ case _ =>
+ }
+ buffer.toList
+ }
+
+ val allowedBases = """([actgnACTGN+]+)""".r
+
+ /**
+ * This function checks for duplicates.
+ * @param current
+ * @param before
+ * @throws IllegalStateException
+ */
+ def duplicateCheck(current: FastqRecord, before: Option[FastqRecord]): Unit = {
+ if (before.exists(_.getReadHeader == current.getReadHeader))
+ throw new IllegalStateException("Duplicate read ID found")
+ }
+
+ /**
+ *
+ * @param record
+ * @throws IllegalStateException
+ */
+ def validFastqRecord(record: FastqRecord): Unit = {
+ checkQualEncoding(record)
+ record.getReadString match {
+ case allowedBases(m) =>
+ case _ => throw new IllegalStateException(s"Non IUPAC symbols identified")
+ }
+ if (record.getReadString.size != record.getBaseQualityString.size)
+ throw new IllegalStateException(s"Sequence length does not match quality length")
+ }
+
+ /**
+ *
+ * @param r1
+ * @param r2
+ * @throws IllegalStateException
+ */
+ def checkMate(r1: FastqRecord, r2: FastqRecord): Unit = {
+ val id1 = r1.getReadHeader.takeWhile(_ != ' ')
+ val id2 = r2.getReadHeader.takeWhile(_ != ' ')
+ if (!(id1 == id2 ||
+ id1.stripSuffix("/1") == id2.stripSuffix("/2") ||
+ id1.stripSuffix(".1") == id2.stripSuffix(".2")))
+ throw new IllegalStateException(s"Sequence headers do not match. R1: '${r1.getReadHeader}', R2: '${r2.getReadHeader}'")
+ }
+}
\ No newline at end of file
diff --git a/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/VcfFilter.scala b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/VcfFilter.scala
index c72222d9fc3278f396c7bdd7b5dff645cf4f2620..d08b05c534896b33324297dde94d386bc2c863c7 100644
--- a/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/VcfFilter.scala
+++ b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/VcfFilter.scala
@@ -103,7 +103,7 @@ object VcfFilter extends ToolCommand {
opt[String]("mustHaveGenotype") unbounded () valueName "<sample:genotype>" action { (x, c) =>
c.copy(mustHaveGenotype = (x.split(":")(0), GenotypeType.valueOf(x.split(":")(1))) :: c.mustHaveGenotype)
} validate { x =>
- if (x.split(":").length == 2 && GenotypeType.values().contains(x.split(":")(1))) success
+ if (x.split(":").length == 2 && GenotypeType.values().map(_.toString).contains(x.split(":")(1))) success
else failure("--mustHaveGenotype should be in this format: sample:genotype")
} text "Must have genotoype <genotype> for this sample. Genotype can be " + GenotypeType.values().mkString(", ")
opt[String]("diffGenotype") unbounded () valueName "<sample:sample>" action { (x, c) =>
diff --git a/public/biopet-tools/src/test/resources/chrQ.refflat b/public/biopet-tools/src/test/resources/chrQ.refflat
new file mode 100644
index 0000000000000000000000000000000000000000..dfcc5110024d4e30ebaf51a229caed2c78bd683f
--- /dev/null
+++ b/public/biopet-tools/src/test/resources/chrQ.refflat
@@ -0,0 +1 @@
+geneA t1 chrQ + 200 500 225 475 3 200,300,400 250,350,500
diff --git a/public/biopet-tools/src/test/resources/empty.bai b/public/biopet-tools/src/test/resources/empty.bai
new file mode 100644
index 0000000000000000000000000000000000000000..e4e22396b4877369154096123eaf25e8bb47503a
Binary files /dev/null and b/public/biopet-tools/src/test/resources/empty.bai differ
diff --git a/public/biopet-tools/src/test/resources/empty.bam b/public/biopet-tools/src/test/resources/empty.bam
new file mode 100644
index 0000000000000000000000000000000000000000..bd4073d80cbf73c689e97d2814f9b1fd00d63895
Binary files /dev/null and b/public/biopet-tools/src/test/resources/empty.bam differ
diff --git a/public/biopet-tools/src/test/resources/paired01c.fq b/public/biopet-tools/src/test/resources/paired01c.fq
new file mode 100644
index 0000000000000000000000000000000000000000..9770dfe1dc3bcfa886ccbaa3749d48732d2d8c58
--- /dev/null
+++ b/public/biopet-tools/src/test/resources/paired01c.fq
@@ -0,0 +1,24 @@
+@r01/2 hello
+T
++
+I
+@r02/2
+A
++
+H
+@r03/2
+C
++
+I
+@r04/2
+G
++
+H
+@r05/2
+T
++
+I
+@r06/2
+T
++
+I
diff --git a/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/BaseCounterTest.scala b/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/BaseCounterTest.scala
new file mode 100644
index 0000000000000000000000000000000000000000..8d6cdd9f1b61cd7dae69c2f53dd7966c83c6b4b3
--- /dev/null
+++ b/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/BaseCounterTest.scala
@@ -0,0 +1,231 @@
+package nl.lumc.sasc.biopet.tools
+
+import java.io.File
+import java.nio.file.Paths
+
+import com.google.common.io.Files
+import htsjdk.samtools.{ SAMReadGroupRecord, SAMSequenceRecord, SAMLineParser, SAMFileHeader }
+import org.scalatest.Matchers
+import org.scalatest.testng.TestNGSuite
+import org.testng.annotations.Test
+import picard.annotation.Gene
+
+import scala.collection.JavaConversions._
+
+/**
+ * Created by pjvan_thof on 1/29/16.
+ */
+class BaseCounterTest extends TestNGSuite with Matchers {
+
+ import BaseCounter._
+ import BaseCounterTest._
+
+ @Test
+ def testCountsClass(): Unit = {
+ val counts = new Counts
+ counts.antiSenseBases shouldBe 0
+ counts.antiSenseReads shouldBe 0
+ counts.senseBases shouldBe 0
+ counts.senseReads shouldBe 0
+ counts.totalBases shouldBe 0
+ counts.totalReads shouldBe 0
+
+ counts.antiSenseBases = 1
+ counts.senseBases = 2
+ counts.totalBases shouldBe 3
+
+ counts.antiSenseReads = 1
+ counts.senseReads = 2
+ counts.totalReads shouldBe 3
+ }
+
+ @Test
+ def testBamRecordBasesOverlapBlocks(): Unit = {
+ val read = BaseCounterTest.lineParser.parseLine("r02\t0\tchrQ\t50\t60\t4M2D4M\t*\t0\t0\tTACGTACGTA\tEEFFGGHHII\tRG:Z:001")
+ bamRecordBasesOverlap(read, 40, 70) shouldBe 8
+ bamRecordBasesOverlap(read, 50, 59) shouldBe 8
+ bamRecordBasesOverlap(read, 50, 55) shouldBe 4
+ bamRecordBasesOverlap(read, 55, 60) shouldBe 4
+ bamRecordBasesOverlap(read, 10, 20) shouldBe 0
+ bamRecordBasesOverlap(read, 40, 49) shouldBe 0
+ bamRecordBasesOverlap(read, 40, 50) shouldBe 1
+ bamRecordBasesOverlap(read, 40, 51) shouldBe 2
+ bamRecordBasesOverlap(read, 58, 70) shouldBe 2
+ bamRecordBasesOverlap(read, 59, 70) shouldBe 1
+ bamRecordBasesOverlap(read, 60, 70) shouldBe 0
+ }
+
+ @Test
+ def testBamRecordBasesOverlap(): Unit = {
+ val read = BaseCounterTest.lineParser.parseLine("r02\t0\tchrQ\t50\t60\t10M\t*\t0\t0\tTACGTACGTA\tEEFFGGHHII\tRG:Z:001")
+ bamRecordBasesOverlap(read, 40, 70) shouldBe 10
+ bamRecordBasesOverlap(read, 50, 59) shouldBe 10
+ bamRecordBasesOverlap(read, 50, 55) shouldBe 6
+ bamRecordBasesOverlap(read, 55, 60) shouldBe 5
+ bamRecordBasesOverlap(read, 10, 20) shouldBe 0
+ bamRecordBasesOverlap(read, 40, 49) shouldBe 0
+ bamRecordBasesOverlap(read, 40, 50) shouldBe 1
+ bamRecordBasesOverlap(read, 40, 51) shouldBe 2
+ bamRecordBasesOverlap(read, 58, 70) shouldBe 2
+ bamRecordBasesOverlap(read, 59, 70) shouldBe 1
+ bamRecordBasesOverlap(read, 60, 70) shouldBe 0
+
+ val counts = new Counts
+ bamRecordBasesOverlap(read, 40, 70, counts, true)
+ counts.senseBases shouldBe 10
+ counts.antiSenseBases shouldBe 0
+ counts.senseReads shouldBe 1
+ counts.antiSenseReads shouldBe 0
+
+ bamRecordBasesOverlap(read, 50, 54, counts, false)
+ counts.senseBases shouldBe 10
+ counts.antiSenseBases shouldBe 5
+ counts.senseReads shouldBe 1
+ counts.antiSenseReads shouldBe 1
+ }
+
+ @Test
+ def testSamRecordStrand: Unit = {
+ val readPlusUnpaired = BaseCounterTest.lineParser.parseLine("r02\t0\tchrQ\t50\t60\t10M\t*\t0\t0\tTACGTACGTA\tEEFFGGHHII\tRG:Z:001")
+ val readMinUnpaired = BaseCounterTest.lineParser.parseLine("r02\t16\tchrQ\t50\t60\t10M\t*\t0\t0\tTACGTACGTA\tEEFFGGHHII\tRG:Z:001")
+ val readPlusPairedR1 = BaseCounterTest.lineParser.parseLine("r02\t73\tchrQ\t50\t60\t10M\t*\t0\t0\tTACGTACGTA\tEEFFGGHHII\tRG:Z:001")
+ val readMinPairedR1 = BaseCounterTest.lineParser.parseLine("r02\t89\tchrQ\t50\t60\t10M\t*\t0\t0\tTACGTACGTA\tEEFFGGHHII\tRG:Z:001")
+ val readPlusPairedR2 = BaseCounterTest.lineParser.parseLine("r02\t137\tchrQ\t50\t60\t10M\t*\t0\t0\tTACGTACGTA\tEEFFGGHHII\tRG:Z:001")
+ val readMinPairedR2 = BaseCounterTest.lineParser.parseLine("r02\t153\tchrQ\t50\t60\t10M\t*\t0\t0\tTACGTACGTA\tEEFFGGHHII\tRG:Z:001")
+
+ samRecordStrand(readPlusUnpaired, true) shouldBe false
+ samRecordStrand(readMinUnpaired, true) shouldBe true
+ samRecordStrand(readPlusPairedR1, true) shouldBe false
+ samRecordStrand(readMinPairedR1, true) shouldBe true
+ samRecordStrand(readPlusPairedR2, true) shouldBe true
+ samRecordStrand(readMinPairedR2, true) shouldBe false
+
+ samRecordStrand(readPlusUnpaired, false) shouldBe true
+ samRecordStrand(readMinUnpaired, false) shouldBe false
+ samRecordStrand(readPlusPairedR1, false) shouldBe true
+ samRecordStrand(readMinPairedR1, false) shouldBe false
+ samRecordStrand(readPlusPairedR2, false) shouldBe false
+ samRecordStrand(readMinPairedR2, false) shouldBe true
+
+ samRecordStrand(readPlusUnpaired, geneA) shouldBe false
+ samRecordStrand(readMinUnpaired, geneA) shouldBe true
+ samRecordStrand(readPlusPairedR1, geneA) shouldBe false
+ samRecordStrand(readMinPairedR1, geneA) shouldBe true
+ samRecordStrand(readPlusPairedR2, geneA) shouldBe true
+ samRecordStrand(readMinPairedR2, geneA) shouldBe false
+
+ samRecordStrand(readPlusUnpaired, geneC) shouldBe true
+ samRecordStrand(readMinUnpaired, geneC) shouldBe false
+ samRecordStrand(readPlusPairedR1, geneC) shouldBe true
+ samRecordStrand(readMinPairedR1, geneC) shouldBe false
+ samRecordStrand(readPlusPairedR2, geneC) shouldBe false
+ samRecordStrand(readMinPairedR2, geneC) shouldBe true
+ }
+
+ @Test
+ def testGeneCount: Unit = {
+ val readPlus = BaseCounterTest.lineParser.parseLine("r02\t0\tchrQ\t101\t60\t10M\t*\t0\t0\tTACGTACGTA\tEEFFGGHHII\tRG:Z:001")
+ val readMin = BaseCounterTest.lineParser.parseLine("r02\t16\tchrQ\t101\t60\t10M\t*\t0\t0\tTACGTACGTA\tEEFFGGHHII\tRG:Z:001")
+ val geneCount = new GeneCount(geneA)
+
+ geneCount.gene shouldBe geneA
+ geneCount.transcripts.size shouldBe 1
+ geneCount.transcripts.head.exonCounts.size shouldBe 4
+ geneCount.transcripts.head.intronCounts.size shouldBe 3
+
+ geneCount.addRecord(readPlus, samRecordStrand(readPlus, geneA))
+ geneCount.exonCounts.map(_.counts.senseBases).sum shouldBe 0
+ geneCount.exonCounts.map(_.counts.antiSenseBases).sum shouldBe 10
+ geneCount.addRecord(readMin, samRecordStrand(readMin, geneA))
+ geneCount.exonCounts.map(_.counts.senseBases).sum shouldBe 10
+ geneCount.exonCounts.map(_.counts.antiSenseBases).sum shouldBe 10
+ }
+
+ @Test
+ def testGroupGenesOnOverlap: Unit = {
+ assert(groupGenesOnOverlap(geneC :: geneD :: Nil)("chrQ").contains(List(geneC)))
+ assert(groupGenesOnOverlap(geneC :: geneD :: Nil)("chrQ").contains(List(geneD)))
+ assert(!groupGenesOnOverlap(geneC :: geneD :: Nil)("chrQ").contains(List(geneD, geneC)))
+
+ assert(!groupGenesOnOverlap(geneC :: geneA :: Nil)("chrQ").contains(List(geneA)))
+ assert(!groupGenesOnOverlap(geneC :: geneA :: Nil)("chrQ").contains(List(geneC)))
+ assert(groupGenesOnOverlap(geneC :: geneA :: Nil)("chrQ").contains(List(geneA, geneC)))
+ }
+
+ @Test
+ def testCreateMetaExonCounts: Unit = {
+ val ab = createMetaExonCounts(geneA :: geneB :: Nil)
+ ab.size shouldBe 9
+ assert(ab.exists(x => x._1 == "geneA" && x._2.start == 101 && x._2.end == 120))
+ assert(ab.exists(x => x._1 == "geneA" && x._2.start == 131 && x._2.end == 140))
+
+ assert(ab.exists(x => x._1 == "geneA,geneB" && x._2.start == 151 && x._2.end == 160))
+ assert(ab.exists(x => x._1 == "geneB" && x._2.start == 161 && x._2.end == 170))
+ assert(ab.exists(x => x._1 == "geneA" && x._2.start == 171 && x._2.end == 180))
+ assert(ab.exists(x => x._1 == "geneA,geneB" && x._2.start == 181 && x._2.end == 190))
+ assert(ab.exists(x => x._1 == "geneA" && x._2.start == 191 && x._2.end == 200))
+
+ assert(ab.exists(x => x._1 == "geneB" && x._2.start == 201 && x._2.end == 210))
+ assert(ab.exists(x => x._1 == "geneB" && x._2.start == 221 && x._2.end == 250))
+ }
+
+ private def resourcePath(p: String): String = {
+ Paths.get(getClass.getResource(p).toURI).toString
+ }
+
+ @Test
+ def testMain: Unit = {
+ val outputDir = Files.createTempDir()
+ outputDir.deleteOnExit()
+ val prefix = "test"
+ val bamFile = new File(resourcePath("/empty.bam"))
+ val refflat = new File(resourcePath("/chrQ.refflat"))
+ main(Array("-o", outputDir.getAbsolutePath, "-p", prefix,
+ "-b", bamFile.getAbsolutePath, "-r", refflat.getAbsolutePath))
+ outputDir.list().size shouldBe 34
+ }
+}
+
+object BaseCounterTest {
+ val lineParser = {
+ val header = new SAMFileHeader
+ header.addSequence(new SAMSequenceRecord("chrQ", 10000))
+ header.addSequence(new SAMSequenceRecord("chrR", 10000))
+ header.addReadGroup(new SAMReadGroupRecord("001"))
+
+ new SAMLineParser(header)
+ }
+
+ val geneA = {
+ val gene = new Gene("chrQ", 101, 200, false, "geneA")
+ gene.addTranscript("A1", 101, 200, 111, 190, 4)
+ for (transcript <- gene) {
+ transcript.name match {
+ case "A1" =>
+ transcript.addExon(101, 120)
+ transcript.addExon(131, 140)
+ transcript.addExon(151, 160)
+ transcript.addExon(171, 200)
+ }
+ }
+ gene
+ }
+
+ val geneB = {
+ val gene = new Gene("chrQ", 151, 250, false, "geneB")
+ gene.addTranscript("A1", 151, 250, 161, 240, 4)
+ for (transcript <- gene) {
+ transcript.name match {
+ case "A1" =>
+ transcript.addExon(151, 170)
+ transcript.addExon(181, 190)
+ transcript.addExon(201, 210)
+ transcript.addExon(221, 250)
+ }
+ }
+ gene
+ }
+
+ val geneC = new Gene("chrQ", 101, 300, true, "geneC")
+ val geneD = new Gene("chrQ", 301, 500, true, "geneD")
+}
\ No newline at end of file
diff --git a/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/MergeTablesTest.scala b/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/MergeTablesTest.scala
index ea9d3a9d2204a924c138351be49b4cd78824a059..06bc5a4a5133ff8cb5d707c78ba639b6e05ba5e7 100644
--- a/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/MergeTablesTest.scala
+++ b/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/MergeTablesTest.scala
@@ -117,13 +117,13 @@ class MergeTablesTest extends TestNGSuite with MockitoSugar with Matchers {
@Test def testPrepInputCustomExtension() = {
// file content doesn't matter
val inFiles = Seq(resourceFile("paired01.sam"), resourceFile("paired02.sam"))
- prepInput(inFiles, ".sam").map(_.name) shouldBe Seq("paired01", "paired02")
+ prepInput(inFiles, ".sam", None).map(_.name) shouldBe Seq("paired01", "paired02")
}
@Test def testPrepInputDuplicate() = {
val inFiles = Seq(new File("README.txt"), new File("README.txt"))
val thrown = intercept[IllegalArgumentException] {
- prepInput(inFiles)
+ prepInput(inFiles, "", None)
}
thrown.getMessage shouldBe "requirement failed: Duplicate samples exist in inputs"
}
diff --git a/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/ValidateFastqTest.scala b/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/ValidateFastqTest.scala
new file mode 100644
index 0000000000000000000000000000000000000000..55d3df72c7c6b385ca3f29fb58709ef45cec4563
--- /dev/null
+++ b/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/ValidateFastqTest.scala
@@ -0,0 +1,123 @@
+package nl.lumc.sasc.biopet.tools
+
+import java.io.{ OutputStream, PrintStream, ByteArrayOutputStream }
+import java.nio.file.Paths
+
+import htsjdk.samtools.fastq.FastqRecord
+import nl.lumc.sasc.biopet.utils.Logging
+import org.apache.log4j.{ FileAppender, Appender }
+import org.scalatest.Matchers
+import org.scalatest.testng.TestNGSuite
+import org.testng.annotations.{ DataProvider, Test }
+
+import scala.collection.JavaConversions._
+
+/**
+ * Created by pjvan_thof on 2/17/16.
+ */
+class ValidateFastqTest extends TestNGSuite with Matchers {
+
+ @Test
+ def testCheckMate: Unit = {
+ ValidateFastq.checkMate(new FastqRecord("read_1", "ATCG", "", "AAAA"), new FastqRecord("read_1", "ATCG", "", "AAAA"))
+
+ intercept[IllegalStateException] {
+ ValidateFastq.checkMate(new FastqRecord("read_1", "ATCG", "", "AAAA"), new FastqRecord("read_2", "ATCG", "", "AAAA"))
+ }
+ }
+
+ @Test
+ def testDuplicateCheck: Unit = {
+ ValidateFastq.duplicateCheck(new FastqRecord("read_1", "ATCG", "", "AAAA"), None)
+ ValidateFastq.duplicateCheck(new FastqRecord("read_1", "ATCG", "", "AAAA"), Some(new FastqRecord("read_2", "ATCG", "", "AAAA")))
+
+ intercept[IllegalStateException] {
+ ValidateFastq.duplicateCheck(new FastqRecord("read_1", "ATCG", "", "AAAA"), Some(new FastqRecord("read_1", "ATCG", "", "AAAA")))
+ }
+ }
+
+ @DataProvider(name = "providerGetPossibleEncodings")
+ def providerGetPossibleEncodings = Array(
+ Array(None, None, Nil),
+ Array(Some('A'), None, Nil),
+ Array(None, Some('A'), Nil),
+ Array(Some('E'), Some('E'), List("Sanger", "Solexa", "Illumina 1.3+", "Illumina 1.5+", "Illumina 1.8+")),
+ Array(Some('+'), Some('+'), List("Sanger", "Illumina 1.8+")),
+ Array(Some('!'), Some('I'), List("Sanger", "Illumina 1.8+")),
+ Array(Some('!'), Some('J'), List("Illumina 1.8+")),
+ Array(Some(';'), Some('h'), List("Solexa")),
+ Array(Some('@'), Some('h'), List("Solexa", "Illumina 1.3+")),
+ Array(Some('C'), Some('h'), List("Solexa", "Illumina 1.3+", "Illumina 1.5+"))
+ )
+
+ @Test(dataProvider = "providerGetPossibleEncodings")
+ def testGetPossibleEncodings(min: Option[Char], max: Option[Char], output: List[String]): Unit = {
+ ValidateFastq.minQual = min
+ ValidateFastq.maxQual = max
+ ValidateFastq.getPossibleEncodings shouldBe output
+ }
+
+ @Test
+ def testGetPossibleEncodingsFail: Unit = {
+ intercept[IllegalStateException] {
+ ValidateFastq.minQual = Some('!')
+ ValidateFastq.maxQual = Some('h')
+ ValidateFastq.getPossibleEncodings
+ }
+ }
+
+ @Test
+ def testCheckQualEncoding: Unit = {
+ ValidateFastq.minQual = None
+ ValidateFastq.maxQual = None
+ ValidateFastq.checkQualEncoding(new FastqRecord("read_1", "ATCG", "", "AAAA"))
+
+ intercept[IllegalStateException] {
+ ValidateFastq.minQual = None
+ ValidateFastq.maxQual = None
+
+ ValidateFastq.checkQualEncoding(new FastqRecord("read_1", "ATCG", "", "A!hA"))
+ }
+
+ intercept[IllegalStateException] {
+ ValidateFastq.minQual = None
+ ValidateFastq.maxQual = None
+
+ ValidateFastq.checkQualEncoding(new FastqRecord("read_1", "ATCG", "", "hhhh"))
+ ValidateFastq.checkQualEncoding(new FastqRecord("read_1", "ATCG", "", "!!!!"))
+ }
+ }
+
+ @Test
+ def testValidFastqRecord: Unit = {
+ ValidateFastq.minQual = None
+ ValidateFastq.maxQual = None
+ ValidateFastq.validFastqRecord(new FastqRecord("read_1", "ATCG", "", "AAAA"))
+
+ intercept[IllegalStateException] {
+ ValidateFastq.validFastqRecord(new FastqRecord("read_1", "ATCG", "", "AAA"))
+ }
+
+ intercept[IllegalStateException] {
+ ValidateFastq.validFastqRecord(new FastqRecord("read_1", "ATYG", "", "AAAA"))
+ }
+ }
+
+ private def resourcePath(p: String): String =
+ Paths.get(getClass.getResource(p).toURI).toString
+
+ @Test
+ def testMain: Unit = {
+ ValidateFastq.minQual = None
+ ValidateFastq.maxQual = None
+ val r1 = resourcePath("/paired01a.fq")
+ val r2 = resourcePath("/paired01b.fq")
+ ValidateFastq.main(Array("-i", r1, "-j", r2))
+
+ //TODO: capture logs
+ ValidateFastq.minQual = None
+ ValidateFastq.maxQual = None
+ val r2fail = resourcePath("/paired01c.fq")
+ ValidateFastq.main(Array("-i", r1, "-j", r2fail))
+ }
+}
diff --git a/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/VcfFilterTest.scala b/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/VcfFilterTest.scala
index 4b3796ee4a3da1fe7bf9635b6d65914b812d640f..afe161575dfb1cfd9d01d360e7a49473aeadfdb4 100644
--- a/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/VcfFilterTest.scala
+++ b/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/VcfFilterTest.scala
@@ -26,7 +26,7 @@ import org.scalatest.testng.TestNGSuite
import org.testng.annotations.Test
import scala.util.Random
-
+import scala.collection.JavaConversions._
/**
* Test class for [[VcfFilter]]
*
@@ -67,6 +67,32 @@ class VcfFilterTest extends TestNGSuite with MockitoSugar with Matchers {
main(arguments)
}
+ @Test def testMustHaveGenotypes() = {
+ /**
+ * This should simply not raise an exception
+ */
+ val tmp = File.createTempFile("VCfFilter", ".vcf.gz")
+ tmp.deleteOnExit()
+ val tmp_path = tmp.getAbsolutePath
+ val arguments: Array[String] = Array("-I", vepped_path, "-o", tmp_path,
+ "--mustHaveGenotype", "Sample_101:HET")
+ main(arguments)
+
+ val size = new VCFFileReader(new File(tmp_path), false).size
+ size shouldBe 1
+
+ val tmp2 = File.createTempFile("VcfFilter", ".vcf.gz")
+ tmp2.deleteOnExit()
+ val tmp2_path = tmp2.getAbsolutePath
+ val arguments2: Array[String] = Array("-I", vepped_path, "-o", tmp2_path,
+ "--mustHaveGenotype", "Sample_101:HOM_VAR")
+ main(arguments2)
+
+ val size2 = new VCFFileReader(new File(tmp2_path), false).size
+ size2 shouldBe 0
+
+ }
+
@Test def testHasGenotype() = {
val reader = new VCFFileReader(vepped, false)
val record = reader.iterator().next()
diff --git a/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/BamUtils.scala b/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/BamUtils.scala
index f13230534af0a61fa29f68daa8d48c81a55e1f23..d0c185cf1a837c816404c2c160bc8f6428e1cc19 100644
--- a/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/BamUtils.scala
+++ b/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/BamUtils.scala
@@ -25,7 +25,8 @@ object BamUtils {
val inputSam = SamReaderFactory.makeDefault.open(file)
val samples = inputSam.getFileHeader.getReadGroups.map(_.getSample).distinct
if (samples.size == 1) samples.head -> file
- else throw new IllegalArgumentException("Bam contains multiple sample IDs: " + file)
+ else if (samples.size > 1) throw new IllegalArgumentException("Bam contains multiple sample IDs: " + file)
+ else throw new IllegalArgumentException("Bam does not contain sample ID or have no readgroups defined: " + file)
}
if (temp.map(_._1).distinct.size != temp.size) throw new IllegalArgumentException("Samples has been found twice")
temp.toMap
diff --git a/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/ConfigUtils.scala b/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/ConfigUtils.scala
index 0679c0d08c441c70e00148594c32054dbb556e80..f0da112c99bea4bb016d13ce8b5b04edc691f430 100644
--- a/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/ConfigUtils.scala
+++ b/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/ConfigUtils.scala
@@ -256,8 +256,9 @@ object ConfigUtils extends Logging {
def any2list(any: Any): List[Any] = {
if (any == null) return null
any match {
- case l: List[_] => l
- case _ => List(any)
+ case l: List[_] => l
+ case l: util.ArrayList[_] => l.toList
+ case _ => List(any)
}
}
diff --git a/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/LazyCheck.scala b/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/LazyCheck.scala
new file mode 100644
index 0000000000000000000000000000000000000000..6eb063d96138ca3c3ef7a559dd625dd5b402d6ab
--- /dev/null
+++ b/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/LazyCheck.scala
@@ -0,0 +1,16 @@
+package nl.lumc.sasc.biopet.utils
+
+/**
+ * Created by pjvan_thof on 1/25/16.
+ */
+class LazyCheck[T](function: => T) {
+ private var _isSet = false
+ def isSet = _isSet
+ lazy val value = {
+ val cache = function
+ _isSet = true
+ cache
+ }
+ def apply() = value
+ def get = value
+}
diff --git a/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/Logging.scala b/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/Logging.scala
index d01755e07300cf09f874bc36f07d640d6567c84e..9d4b9dc2bf84bcda084ce5de9647620e1a130658 100644
--- a/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/Logging.scala
+++ b/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/Logging.scala
@@ -36,7 +36,7 @@ trait Logging {
object Logging {
val logger = Logger.getRootLogger
- private val errors: ListBuffer[Exception] = ListBuffer()
+ private[biopet] val errors: ListBuffer[Exception] = ListBuffer()
def addError(error: String, debug: String = null): Unit = {
val msg = error + (if (debug != null && logger.isDebugEnabled) "; " + debug else "")
diff --git a/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/intervals/BedRecordList.scala b/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/intervals/BedRecordList.scala
index 485b0ae156938784def6937bff29e077cc2f5170..94c7d833d33360b4cf2dd4681b9c8d6ae469047a 100644
--- a/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/intervals/BedRecordList.scala
+++ b/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/intervals/BedRecordList.scala
@@ -60,16 +60,18 @@ case class BedRecordList(val chrRecords: Map[String, List[BedRecord]], val heade
overlaps
.foldLeft(List(record))((result, overlap) => {
(for (r <- result) yield {
- (overlap.start <= r.start, overlap.end >= r.end) match {
- case (true, true) =>
- Nil
- case (true, false) =>
- List(r.copy(start = overlap.end, _originals = List(r)))
- case (false, true) =>
- List(r.copy(end = overlap.start, _originals = List(r)))
- case (false, false) =>
- List(r.copy(end = overlap.start, _originals = List(r)), r.copy(start = overlap.end, _originals = List(r)))
- }
+ if (r.overlapWith(overlap)) {
+ (overlap.start <= r.start, overlap.end >= r.end) match {
+ case (true, true) =>
+ Nil
+ case (true, false) =>
+ List(r.copy(start = overlap.end, _originals = List(r)))
+ case (false, true) =>
+ List(r.copy(end = overlap.start, _originals = List(r)))
+ case (false, false) =>
+ List(r.copy(end = overlap.start, _originals = List(r)), r.copy(start = overlap.end, _originals = List(r)))
+ }
+ } else List(r)
}).flatten
})
}
diff --git a/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/rscript/Rscript.scala b/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/rscript/Rscript.scala
index c71a30a154cf6e0ec4776348cfb94753c7f726c8..d8149c96d29f2a693548d2c8b63a2e0aa5df84f2 100644
--- a/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/rscript/Rscript.scala
+++ b/public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/rscript/Rscript.scala
@@ -23,6 +23,8 @@ import nl.lumc.sasc.biopet.utils.config.Configurable
import scala.sys.process.{ Process, ProcessLogger }
/**
+ * Trait for rscripts, can be used to execute rscripts locally
+ *
* Created by pjvanthof on 13/09/15.
*/
trait Rscript extends Configurable {
@@ -42,14 +44,13 @@ trait Rscript extends Configurable {
script = script.getAbsoluteFile
} else {
val rScript: File = dir match {
- case Some(dir) => new File(dir, script.getName)
- case _ => {
+ case Some(d) => new File(d, script.getName)
+ case _ =>
val file = File.createTempFile(script.getName, ".R")
file.deleteOnExit()
file
- }
}
- if (!rScript.getParentFile.exists) rScript.getParentFile.mkdirs
+ if (!rScript.getAbsoluteFile.getParentFile.exists) rScript.getParentFile.mkdirs
val is = getClass.getResourceAsStream(script.getPath)
val os = new FileOutputStream(rScript)
diff --git a/public/carp/src/main/scala/nl/lumc/sasc/biopet/pipelines/carp/Carp.scala b/public/carp/src/main/scala/nl/lumc/sasc/biopet/pipelines/carp/Carp.scala
index fcc6afa62dd7ff72b046e009fdd931312214a079..17e358d2d86f870f983fe692df9c02475aabf5e4 100644
--- a/public/carp/src/main/scala/nl/lumc/sasc/biopet/pipelines/carp/Carp.scala
+++ b/public/carp/src/main/scala/nl/lumc/sasc/biopet/pipelines/carp/Carp.scala
@@ -18,6 +18,7 @@ package nl.lumc.sasc.biopet.pipelines.carp
import java.io.File
import nl.lumc.sasc.biopet.core._
+import nl.lumc.sasc.biopet.core.report.ReportBuilderExtension
import nl.lumc.sasc.biopet.extensions.macs2.Macs2CallPeak
import nl.lumc.sasc.biopet.extensions.picard.BuildBamIndex
import nl.lumc.sasc.biopet.extensions.samtools.SamtoolsView
@@ -95,7 +96,7 @@ class Carp(val root: Configurable) extends QScript with MultisampleMappingTrait
}
}
- override def reportClass = {
+ override def reportClass: Option[ReportBuilderExtension] = {
val carp = new CarpReport(this)
carp.outputDir = new File(outputDir, "report")
carp.summaryFile = summaryFile
diff --git a/public/carp/src/main/scala/nl/lumc/sasc/biopet/pipelines/carp/CarpReport.scala b/public/carp/src/main/scala/nl/lumc/sasc/biopet/pipelines/carp/CarpReport.scala
index a06cef16f169732aba3ebe31357f907d24ac2eca..756d1e33d32f8008ed5c06fc0f8d2595c15d3b76 100644
--- a/public/carp/src/main/scala/nl/lumc/sasc/biopet/pipelines/carp/CarpReport.scala
+++ b/public/carp/src/main/scala/nl/lumc/sasc/biopet/pipelines/carp/CarpReport.scala
@@ -15,10 +15,9 @@
*/
package nl.lumc.sasc.biopet.pipelines.carp
+import nl.lumc.sasc.biopet.core.report.{ ReportSection, ReportBuilderExtension }
+import nl.lumc.sasc.biopet.pipelines.mapping.MultisampleMappingReportTrait
import nl.lumc.sasc.biopet.utils.config.Configurable
-import nl.lumc.sasc.biopet.core.report.{ ReportBuilderExtension, ReportSection, ReportPage, MultisampleReportBuilder }
-import nl.lumc.sasc.biopet.pipelines.bammetrics.BammetricsReport
-import nl.lumc.sasc.biopet.pipelines.flexiprep.FlexiprepReport
/**
* Class for report for CArp
@@ -29,71 +28,10 @@ class CarpReport(val root: Configurable) extends ReportBuilderExtension {
def builder = CarpReport
}
-object CarpReport extends MultisampleReportBuilder {
-
- /** Root page for the carp report */
- def indexPage = {
- //Source.fromInputStream(getClass.getResourceAsStream("/nl/lumc/sasc/biopet/pipelines/carp/carpFont.ssp")).foreach(print(_))
- ReportPage(
- List("Samples" -> generateSamplesPage(pageArgs)) ++
- Map("Files" -> filesPage,
- "Versions" -> ReportPage(List(), List("Executables" -> ReportSection("/nl/lumc/sasc/biopet/core/report/executables.ssp"
- )), Map())
- ),
- List(
- "Report" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/carp/carpFront.ssp"),
- "Alignment" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp",
- Map("sampleLevel" -> true, "showPlot" -> true, "showTable" -> false)
- ),
- "Insert Size" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/insertSize.ssp",
- Map("sampleLevel" -> true, "showPlot" -> true, "showTable" -> false)),
- "Whole genome coverage" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/wgsHistogram.ssp",
- Map("sampleLevel" -> true, "showPlot" -> true, "showTable" -> false)),
- "QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp",
- Map("showPlot" -> true, "showTable" -> false)),
- "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp",
- Map("showPlot" -> true, "showTable" -> false))
- ),
- pageArgs
- )
- }
-
- /** Files page, can be used general or at sample level */
- def filesPage: ReportPage = ReportPage(List(), List(
- "Input fastq files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepInputfiles.ssp"),
- "After QC fastq files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepOutputfiles.ssp"),
- "Bam files per lib" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/mapping/outputBamfiles.ssp", Map("sampleLevel" -> false)) //,
- //"Preprocessed bam files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/mapping/outputBamfiles.ssp",
- // Map("pipelineName" -> "shiva", "fileTag" -> "preProcessBam"))
- ), Map())
-
- /** Single sample page */
- def samplePage(sampleId: String, args: Map[String, Any]): ReportPage = {
- ReportPage(List(
- "Libraries" -> generateLibraryPage(args),
- "Alignment" -> BammetricsReport.bamMetricsPage(summary, Some(sampleId), None),
- "Files" -> filesPage
- ), List(
- "Alignment" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp",
- if (summary.libraries(sampleId).size > 1) Map("showPlot" -> true) else Map()),
- "Merged" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp", Map("sampleLevel" -> true)),
- "QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp"),
- "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp")
- ), args)
- }
-
- /** Library page */
- def libraryPage(sampleId: String, libId: String, args: Map[String, Any]): ReportPage = {
- ReportPage(List(
- "Alignment" -> BammetricsReport.bamMetricsPage(summary, Some(sampleId), Some(libId)),
- "QC" -> FlexiprepReport.flexiprepPage
- ), List(
- "Alignment" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp"),
- "QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp"),
- "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp")
- ), args)
- }
-
+object CarpReport extends MultisampleMappingReportTrait {
/** Name of the report */
def reportName = "Carp Report"
+ override def frontSection = ReportSection("/nl/lumc/sasc/biopet/pipelines/carp/carpFront.ssp")
+
+ override def pipelineName = "carp"
}
\ No newline at end of file
diff --git a/public/flexiprep/src/main/resources/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp b/public/flexiprep/src/main/resources/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp
index b2f0057b3dc437c496c4a161af515c11f9a3d80e..91c2550725fc7536fe58efc2229544ae42403674 100644
--- a/public/flexiprep/src/main/resources/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp
+++ b/public/flexiprep/src/main/resources/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp
@@ -56,17 +56,22 @@
#end
#if (showPlot)
#{
+ val paired: Boolean = if (sampleId.isDefined && libId.isDefined)
+ summary.getLibraryValue(sampleId.get, libId.get, "flexiprep", "settings", "paired").get.asInstanceOf[Boolean]
+ else summary.getLibraryValues("flexiprep", "settings", "paired").values.exists(_ == Some(true))
FlexiprepReport.baseSummaryPlot(outputDir, "QC_Bases_R1","R1", summary, sampleId = sampleId)
- FlexiprepReport.baseSummaryPlot(outputDir, "QC_Bases_R2","R2", summary, sampleId = sampleId)
+ if (paired) FlexiprepReport.baseSummaryPlot(outputDir, "QC_Bases_R2","R2", summary, sampleId = sampleId)
}#
<div class="panel-body">
<div class="row">
<div class="col-sm-6 col-md-6">
<img src="QC_Bases_R1.png" class="img-responsive" />
</div>
- <div class="col-sm-6 col-md-6">
+ #if (paired)
+ <div class="col-sm-6 col-md-6">
<img src="QC_Bases_R2.png" class="img-responsive" />
- </div>
+ </div>
+ #end
</div>
</div>
@@ -76,8 +81,10 @@
#else
<button type="button" class="btn btn-info" data-toggle="collapse" data-target="#QC_BasesTable">Show table</button>
#end
- <i class="glyphicon glyphicon-file"></i> <a href="QC_Bases_R1.tsv">R1 reads stats</a> -
- <i class="glyphicon glyphicon-file"></i> <a href="QC_Bases_R2.tsv">R2 reads stats</a>
+ <i class="glyphicon glyphicon-file"></i> <a href="QC_Bases_R1.tsv">R1 reads stats</a>
+ #if (paired)
+ - <i class="glyphicon glyphicon-file"></i> <a href="QC_Bases_R2.tsv">R2 reads stats</a>
+ #end
</div>
#end
diff --git a/public/flexiprep/src/main/resources/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp b/public/flexiprep/src/main/resources/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp
index 4a0a60659f5276f7230fef7fabd4cc12f23ae4a4..f9b77db7cd38ab93643f7c97e3a7c1363f051861 100644
--- a/public/flexiprep/src/main/resources/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp
+++ b/public/flexiprep/src/main/resources/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp
@@ -62,17 +62,22 @@
#if (showPlot)
#{
+ val paired: Boolean = if (sampleId.isDefined && libId.isDefined)
+ summary.getLibraryValue(sampleId.get, libId.get, "flexiprep", "settings", "paired").get.asInstanceOf[Boolean]
+ else summary.getLibraryValues("flexiprep", "settings", "paired").values.exists(_ == Some(true))
FlexiprepReport.readSummaryPlot(outputDir, "QC_Reads_R1","R1", summary, sampleId = sampleId)
- FlexiprepReport.readSummaryPlot(outputDir, "QC_Reads_R2","R2", summary, sampleId = sampleId)
+ if (paired) FlexiprepReport.readSummaryPlot(outputDir, "QC_Reads_R2","R2", summary, sampleId = sampleId)
}#
<div class="panel-body">
<div class="row">
<div class="col-sm-6 col-md-6">
<img src="QC_Reads_R1.png" class="img-responsive">
</div>
+ #if (paired)
<div class="col-sm-6 col-md-6">
<img src="QC_Reads_R2.png" class="img-responsive">
</div>
+ #end
</div>
</div>
@@ -82,8 +87,10 @@
#else
<button type="button" class="btn btn-info" data-toggle="collapse" data-target="#QC_ReadsTable">Show table</button>
#end
- <i class="glyphicon glyphicon-file"></i> <a href="QC_Reads_R1.tsv">R1 reads stats</a> -
- <i class="glyphicon glyphicon-file"></i> <a href="QC_Reads_R2.tsv">R2 reads stats</a>
+ <i class="glyphicon glyphicon-file"></i> <a href="QC_Reads_R1.tsv">R1 reads stats</a>
+ #if (paired)
+ - <i class="glyphicon glyphicon-file"></i> <a href="QC_Reads_R2.tsv">R2 reads stats</a>
+ #end
</div>
#end
diff --git a/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/CheckValidateFastq.scala b/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/CheckValidateFastq.scala
new file mode 100644
index 0000000000000000000000000000000000000000..39319507a7b360d734b92b221c1537c08b493aab
--- /dev/null
+++ b/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/CheckValidateFastq.scala
@@ -0,0 +1,49 @@
+/**
+ * Biopet is built on top of GATK Queue for building bioinformatic
+ * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
+ * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
+ * should also be able to execute Biopet tools and pipelines.
+ *
+ * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
+ *
+ * Contact us at: sasc@lumc.nl
+ *
+ * A dual licensing mode is applied. The source code within this project that are
+ * not part of GATK Queue is freely available for non-commercial use under an AGPL
+ * license; For commercial users or users who do not want to follow the AGPL
+ * license, please contact us to obtain a separate license.
+ */
+package nl.lumc.sasc.biopet.pipelines.flexiprep
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.summary.WriteSummary
+import org.broadinstitute.gatk.queue.function.InProcessFunction
+import org.broadinstitute.gatk.utils.commandline.{ Argument, Input }
+
+import scala.io.Source
+
+/**
+ * This class checks md5sums and give an exit code 1 when md5sum is not the same
+ *
+ * Created by pjvanthof on 16/08/15.
+ */
+class CheckValidateFastq extends InProcessFunction {
+ @Input(required = true)
+ var inputLogFile: File = _
+
+ /** Exits whenever the input md5sum is not the same as the output md5sum */
+ def run: Unit = {
+
+ val reader = Source.fromFile(inputLogFile)
+ reader.getLines().foreach { line =>
+ if (line.startsWith("ERROR")) {
+ logger.error("Corrupt fastq file found, aborting pipeline")
+
+ // 130 Simulates a ctr-C
+ Runtime.getRuntime.halt(130)
+ }
+ }
+ reader.close()
+ }
+}
\ No newline at end of file
diff --git a/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Cutadapt.scala b/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Cutadapt.scala
index b34b3772296f9de419f7a249d45daefc513c7259..f974f8c9a43f685390ee0c510ffa0064d07167b5 100644
--- a/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Cutadapt.scala
+++ b/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Cutadapt.scala
@@ -46,16 +46,16 @@ class Cutadapt(root: Configurable, fastqc: Fastqc) extends nl.lumc.sasc.biopet.e
// adapter sequence is clipped but not found by FastQC ~ should not happen since all clipped adapter
// sequences come from FastQC
case _ =>
- throw new IllegalStateException(s"Adapter '$seq' is clipped but not found by FastQC in '$fastq_input'.")
+ throw new IllegalStateException(s"Adapter '$seq' is clipped but not found by FastQC in '$fastqInput'.")
}
// FastQC found no adapters
case otherwise =>
;
- logger.debug(s"No adapters found for summarizing in '$fastq_input'.")
+ logger.debug(s"No adapters found for summarizing in '$fastqInput'.")
None
}
// "adapters" key not found ~ something went wrong in our part
- case _ => throw new RuntimeException(s"Required key 'adapters' not found in stats entry '$fastq_input'.")
+ case _ => throw new RuntimeException(s"Required key 'adapters' not found in stats entry '$fastqInput'.")
}
initStats.updated(adaptersStatsName, adapterCounts)
}
diff --git a/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Flexiprep.scala b/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Flexiprep.scala
index 7c2b9ace137c347e9f78d99543eb56ebf28ef5b4..44d30a0cb350e411cac390e41759806212e2ec6f 100644
--- a/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Flexiprep.scala
+++ b/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Flexiprep.scala
@@ -20,7 +20,7 @@ import nl.lumc.sasc.biopet.core.{ BiopetFifoPipe, PipelineCommand, SampleLibrary
import nl.lumc.sasc.biopet.extensions.{ Zcat, Gzip }
import nl.lumc.sasc.biopet.utils.config.Configurable
import nl.lumc.sasc.biopet.utils.IoUtils._
-import nl.lumc.sasc.biopet.extensions.tools.{ SeqStat, FastqSync }
+import nl.lumc.sasc.biopet.extensions.tools.{ ValidateFastq, SeqStat, FastqSync }
import org.broadinstitute.gatk.queue.QScript
@@ -114,6 +114,17 @@ class Flexiprep(val root: Configurable) extends QScript with SummaryQScript with
addSummarizable(fastqc_R1, "fastqc_R1")
outputFiles += ("fastqc_R1" -> fastqc_R1.output)
+ val validateFastq = new ValidateFastq(this)
+ validateFastq.r1Fastq = input_R1
+ validateFastq.r2Fastq = input_R2
+ validateFastq.jobOutputFile = new File(outputDir, ".validate_fastq.log.out")
+ add(validateFastq)
+
+ val checkValidateFastq = new CheckValidateFastq
+ checkValidateFastq.inputLogFile = validateFastq.jobOutputFile
+ checkValidateFastq.jobOutputFile = new File(outputDir, ".check.validate_fastq.log.out")
+ add(checkValidateFastq)
+
if (paired) {
fastqc_R2 = Fastqc(this, input_R2.get, new File(outputDir, R2_name + ".fastqc/"))
add(fastqc_R2)
@@ -254,6 +265,17 @@ class Flexiprep(val root: Configurable) extends QScript with SummaryQScript with
}
}
+ val validateFastq = new ValidateFastq(this)
+ validateFastq.r1Fastq = fastqR1Qc
+ validateFastq.r2Fastq = fastqR2Qc
+ validateFastq.jobOutputFile = new File(outputDir, ".validate_fastq.qc.log.out")
+ add(validateFastq)
+
+ val checkValidateFastq = new CheckValidateFastq
+ checkValidateFastq.inputLogFile = validateFastq.jobOutputFile
+ checkValidateFastq.jobOutputFile = new File(outputDir, ".check.validate_fastq.qc.log.out")
+ add(checkValidateFastq)
+
outputFiles += ("output_R1_gzip" -> fastqR1Qc)
if (paired) outputFiles += ("output_R2_gzip" -> fastqR2Qc.get)
diff --git a/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/QcCommand.scala b/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/QcCommand.scala
index 22a9a4a526a0a8d0c640b9262baef99063f07288..390d68b58e5335305e836effa745bc36c9c5b8fa 100644
--- a/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/QcCommand.scala
+++ b/public/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/QcCommand.scala
@@ -102,12 +102,12 @@ class QcCommand(val root: Configurable, val fastqc: Fastqc) extends BiopetComman
val foundAdapters = fastqc.foundAdapters.map(_.seq)
if (foundAdapters.nonEmpty) {
val cutadapt = new Cutadapt(root, fastqc)
- cutadapt.fastq_input = seqtk.output
- cutadapt.fastq_output = new File(output.getParentFile, input.getName + ".cutadapt.fq")
- cutadapt.stats_output = new File(flexiprep.outputDir, s"${flexiprep.sampleId.getOrElse("x")}-${flexiprep.libId.getOrElse("x")}.$read.clip.stats")
- if (cutadapt.default_clip_mode == "3") cutadapt.opt_adapter ++= foundAdapters
- else if (cutadapt.default_clip_mode == "5") cutadapt.opt_front ++= foundAdapters
- else if (cutadapt.default_clip_mode == "both") cutadapt.opt_anywhere ++= foundAdapters
+ cutadapt.fastqInput = seqtk.output
+ cutadapt.fastqOutput = new File(output.getParentFile, input.getName + ".cutadapt.fq")
+ cutadapt.statsOutput = new File(flexiprep.outputDir, s"${flexiprep.sampleId.getOrElse("x")}-${flexiprep.libId.getOrElse("x")}.$read.clip.stats")
+ if (cutadapt.defaultClipMode == "3") cutadapt.adapter ++= foundAdapters
+ else if (cutadapt.defaultClipMode == "5") cutadapt.front ++= foundAdapters
+ else if (cutadapt.defaultClipMode == "both") cutadapt.anywhere ++= foundAdapters
addPipeJob(cutadapt)
Some(cutadapt)
} else None
@@ -117,7 +117,7 @@ class QcCommand(val root: Configurable, val fastqc: Fastqc) extends BiopetComman
val sickle = new Sickle(root)
sickle.output_stats = new File(flexiprep.outputDir, s"${flexiprep.sampleId.getOrElse("x")}-${flexiprep.libId.getOrElse("x")}.$read.trim.stats")
sickle.input_R1 = clip match {
- case Some(c) => c.fastq_output
+ case Some(c) => c.fastqOutput
case _ => seqtk.output
}
sickle.output_R1 = new File(output.getParentFile, input.getName + ".sickle.fq")
@@ -127,7 +127,7 @@ class QcCommand(val root: Configurable, val fastqc: Fastqc) extends BiopetComman
val outputFile = (clip, trim) match {
case (_, Some(t)) => t.output_R1
- case (Some(c), _) => c.fastq_output
+ case (Some(c), _) => c.fastqOutput
case _ => seqtk.output
}
diff --git a/public/gears/pom.xml b/public/gears/pom.xml
index c1bf7194cec6f3b71683b36ed2be1bd156b3eb63..07c199380f19a5bc1e295af96ca33ab49d83b4c9 100644
--- a/public/gears/pom.xml
+++ b/public/gears/pom.xml
@@ -38,6 +38,11 @@
<artifactId>BiopetCore</artifactId>
<version>${project.version}</version>
</dependency>
+ <dependency>
+ <groupId>nl.lumc.sasc</groupId>
+ <artifactId>Flexiprep</artifactId>
+ <version>${project.version}</version>
+ </dependency>
<dependency>
<groupId>nl.lumc.sasc</groupId>
<artifactId>BiopetToolsExtensions</artifactId>
diff --git a/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/gearsFront.ssp b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/gearsFront.ssp
index 20ca432859aeee8e0cd2482e190abe8b9586e8b6..67d01100940d62c0bd443ca243ad676f840daf0b 100644
--- a/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/gearsFront.ssp
+++ b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/gearsFront.ssp
@@ -2,8 +2,6 @@
#import(nl.lumc.sasc.biopet.core.report.ReportPage)
<%@ var summary: Summary %>
<%@ var rootPath: String %>
-<%@ var sampleId: Option[String] = None %>
-<%@ var libId: Option[String] = None %>
<table class="table">
<tbody>
@@ -11,8 +9,6 @@
<tr><th>Version</th><td>${summary.getValue("meta", "pipeline_version")}</td></tr>
<tr><th>Last commit hash</th><td>${summary.getValue("meta", "last_commit_hash")}</td></tr>
<tr><th>Output directory</th><td>${summary.getValue("meta", "output_dir")}</td></tr>
- #if(sampleId.isDefined) <tr><th>Sample</th><td>${sampleId}</td></tr> #end
- #if(libId.isDefined) <tr><th>Library</th><td>${libId}</td></tr> #end
</tbody>
</table>
<br/>
diff --git a/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/gearsSingleFront.ssp b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/gearsSingleFront.ssp
new file mode 100644
index 0000000000000000000000000000000000000000..27fa3bc8d8d1706cf5fb2952ad5980964ba2ec47
--- /dev/null
+++ b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/gearsSingleFront.ssp
@@ -0,0 +1,38 @@
+#import(nl.lumc.sasc.biopet.utils.summary.Summary)
+#import(nl.lumc.sasc.biopet.core.report.ReportPage)
+<%@ var summary: Summary %>
+<%@ var rootPath: String %>
+<%@ var sampleId: Option[String] = None %>
+<%@ var libId: Option[String] = None %>
+
+<table class="table">
+<tbody>
+ <tr><th>Pipeline</th><td>Gears</td></tr>
+ <tr><th>Version</th><td>${summary.getValue("meta", "pipeline_version")}</td></tr>
+ <tr><th>Last commit hash</th><td>${summary.getValue("meta", "last_commit_hash")}</td></tr>
+ <tr><th>Output directory</th><td>${summary.getValue("meta", "output_dir")}</td></tr>
+ #if(sampleId.isDefined) <tr><th>Sample</th><td>${sampleId}</td></tr> #end
+ #if(libId.isDefined) <tr><th>Library</th><td>${libId}</td></tr> #end
+</tbody>
+</table>
+<br/>
+<div class="row">
+<div class="col-md-1"></div>
+<div class="col-md-6">
+ <p>\
+ In this web document you can find your <em>Gears</em> pipeline report.
+ Different categories of data can be found in the left-side menu.
+ Statistics per sample and library can be accessed through the top-level menu.
+ Some statistics for target regions can be found in the regions tab.
+ Futhermore, you can view all versions of software tools used by selecting <em>Versions</em> from the top menu.
+ </p>
+
+ <p>
+ <small>Brought to you by <a href="https://sasc.lumc.nl" target="_blank"><abbr
+ title="Sequence Analysis Support Core">SASC</abbr></a> and <a
+ href="https://www.lumc.nl/org/klinische-genetica/" target="_blank"><abbr title="Clinical Genetics LUMC">KG</abbr></a>,
+ LUMC.
+ </small>
+ </p>
+</div>
+</div>
\ No newline at end of file
diff --git a/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/gearsSunburst.ssp b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/gearsSunburst.ssp
index 5aff91fe34c36f2e2e18386a52ad5e3717fedbfd..6c7250493f4ff171ebeb7eb97e8bdcf95d66f734 100644
--- a/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/gearsSunburst.ssp
+++ b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/gearsSunburst.ssp
@@ -54,7 +54,7 @@
<script type="application/ecmascript">
#{
- val rawreport = Map("kraken" -> summary.getValue(sampleId, libId, "gears", "stats", "krakenreport"))
+ val rawreport = Map("kraken" -> summary.getValue(sampleId, libId, "gearskraken", "stats", "krakenreport"))
val jsonReport = ConfigUtils.mapToJson(rawreport)
}#
diff --git a/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/krakenKrona.ssp b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/krakenKrona.ssp
new file mode 100644
index 0000000000000000000000000000000000000000..8ef51a20f1c6332294654343015c0d03acd0d50b
--- /dev/null
+++ b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/krakenKrona.ssp
@@ -0,0 +1,33 @@
+#import(nl.lumc.sasc.biopet.utils.summary.Summary)
+#import(nl.lumc.sasc.biopet.core.report.ReportPage)
+#import(nl.lumc.sasc.biopet.core.report.ReportBuilder)
+#import(nl.lumc.sasc.biopet.pipelines.gears.GearsKraken)
+#import(java.io.File)
+#import(java.io.PrintWriter)
+<%@ var summary: Summary %>
+<%@ var rootPath: String %>
+<%@ var sampleId: Option[String] = None %>
+<%@ var libId: Option[String] = None %>
+<%@ var args: Map[String, Any] %>
+<%@ var outputDir: File %>
+
+<%
+ val summaries = if (sampleId.isEmpty && libId.isEmpty) {
+ summary.getSampleValues("gearskraken", "stats", "krakenreport").map(x => x._1 -> x._2.get.asInstanceOf[Map[String, Any]])
+ } else summary.getValue(sampleId, libId, "gearskraken", "stats", "krakenreport").map(sampleId.get -> _.asInstanceOf[Map[String, Any]]).toList.toMap
+
+ val tempFile = File.createTempFile("krona.", ".xml")
+ tempFile.deleteOnExit()
+ GearsKraken.convertKrakenSummariesToKronaXml(summaries, tempFile)
+
+ val output = ReportBuilder.renderTemplate("/nl/lumc/sasc/biopet/core/report/krona.ssp",
+ args ++ Map("kronaXml" -> tempFile))
+
+
+ val file = new File(outputDir, "kraken_krona.html")
+ val writer = new PrintWriter(file)
+ writer.println(output)
+ writer.close()
+%>
+
+<iframe src="kraken_krona.html" style="width:100%;height:80vh;border:none;"></iframe>
diff --git a/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/qiimeKrona.ssp b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/qiimeKrona.ssp
new file mode 100644
index 0000000000000000000000000000000000000000..39166ca0d29e0d4cf1e8530dd8ca94525f65a659
--- /dev/null
+++ b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/qiimeKrona.ssp
@@ -0,0 +1,24 @@
+#import(nl.lumc.sasc.biopet.core.report.ReportBuilder)
+#import(nl.lumc.sasc.biopet.pipelines.gears.GearsQiimeClosed)
+#import(java.io.File)
+#import(java.io.PrintWriter)
+<%@ var biomFile: File %>
+<%@ var args: Map[String, Any] %>
+<%@ var outputDir: File %>
+
+<%
+ val tempFile = File.createTempFile("krona.", ".xml")
+ tempFile.deleteOnExit()
+ GearsQiimeClosed.qiimeBiomToKrona(biomFile, tempFile)
+
+ val output = ReportBuilder.renderTemplate("/nl/lumc/sasc/biopet/core/report/krona.ssp",
+ args ++ Map("kronaXml" -> tempFile))
+
+
+ val file = new File(outputDir, "kraken_krona.html")
+ val writer = new PrintWriter(file)
+ writer.println(output)
+ writer.close()
+%>
+
+<iframe src="kraken_krona.html" style="width:100%;height:80vh;border:none;"></iframe>
diff --git a/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/report/ext/img/krona/favicon.ico b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/report/ext/img/krona/favicon.ico
new file mode 100644
index 0000000000000000000000000000000000000000..1ff0d0139254691ee19d2cc69236a7c8a463dbbd
Binary files /dev/null and b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/report/ext/img/krona/favicon.ico differ
diff --git a/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/report/ext/img/krona/hidden.png b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/report/ext/img/krona/hidden.png
new file mode 100644
index 0000000000000000000000000000000000000000..0f9ef300d30e29330921d35175f48e718b724396
Binary files /dev/null and b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/report/ext/img/krona/hidden.png differ
diff --git a/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/report/ext/img/krona/loading.gif b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/report/ext/img/krona/loading.gif
new file mode 100644
index 0000000000000000000000000000000000000000..d0bce1542342e912da81a2c260562df172f30d73
Binary files /dev/null and b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/report/ext/img/krona/loading.gif differ
diff --git a/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/report/ext/js/krona-2.0.js b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/report/ext/js/krona-2.0.js
new file mode 100644
index 0000000000000000000000000000000000000000..74025705723f56045b5cbb058d4b597271a8df20
--- /dev/null
+++ b/public/gears/src/main/resources/nl/lumc/sasc/biopet/pipelines/gears/report/ext/js/krona-2.0.js
@@ -0,0 +1,6497 @@
+{//-----------------------------------------------------------------------------
+//
+// PURPOSE
+//
+// Krona is a flexible tool for exploring the relative proportions of
+// hierarchical data, such as metagenomic classifications, using a
+// radial, space-filling display. It is implemented using HTML5 and
+// JavaScript, allowing charts to be explored locally or served over the
+// Internet, requiring only a current version of any major web
+// browser. Krona charts can be created using an Excel template or from
+// common bioinformatic formats using the provided conversion scripts.
+//
+//
+// COPYRIGHT LICENSE
+//
+// Copyright (c) 2011, Battelle National Biodefense Institute (BNBI);
+// all rights reserved. Authored by: Brian Ondov, Nicholas Bergman, and
+// Adam Phillippy
+//
+// This Software was prepared for the Department of Homeland Security
+// (DHS) by the Battelle National Biodefense Institute, LLC (BNBI) as
+// part of contract HSHQDC-07-C-00020 to manage and operate the National
+// Biodefense Analysis and Countermeasures Center (NBACC), a Federally
+// Funded Research and Development Center.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+// * Redistributions of source code must retain the above copyright
+// notice, this list of conditions and the following disclaimer.
+//
+// * Redistributions in binary form must reproduce the above copyright
+// notice, this list of conditions and the following disclaimer in the
+// documentation and/or other materials provided with the distribution.
+//
+// * Neither the name of the Battelle National Biodefense Institute nor
+// the names of its contributors may be used to endorse or promote
+// products derived from this software without specific prior written
+// permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+// HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+//
+//
+// TRADEMARK LICENSE
+//
+// KRONA(TM) is a trademark of the Department of Homeland Security, and use
+// of the trademark is subject to the following conditions:
+//
+// * Distribution of the unchanged, official code/software using the
+// KRONA(TM) mark is hereby permitted by the Department of Homeland
+// Security, provided that the software is distributed without charge
+// and modification.
+//
+// * Distribution of altered source code/software using the KRONA(TM) mark
+// is not permitted unless written permission has been granted by the
+// Department of Homeland Security.
+//
+//
+// FOR MORE INFORMATION VISIT
+//
+// http://krona.sourceforge.net
+//
+//-----------------------------------------------------------------------------
+}
+
+
+var canvas;
+var context;
+var svg; // for snapshot mode
+var collapse = true;
+var collapseCheckBox;
+var collapseLast;
+var compress;
+var compressCheckBox;
+var maxAbsoluteDepthText;
+var maxAbsoluteDepthButtonDecrease;
+var maxAbsoluteDepthButtonIncrease;
+var fontSize = 11;
+var fontSizeText;
+var fontSizeButtonDecrease;
+var fontSizeButtonIncrease;
+var fontSizeLast;
+var radiusButtonDecrease;
+var radiusButtonIncrease;
+var shorten;
+var shortenCheckBox;
+var maxAbsoluteDepth;
+var backButton;
+var upButton;
+var forwardButton;
+var snapshotButton;
+var snapshotMode = false;
+var details;
+var detailsName;
+var search;
+var searchResults;
+var nSearchResults;
+var useHueCheckBox;
+var useHueDiv;
+var datasetDropDown;
+var datasetButtonLast;
+var datasetButtonPrev;
+var datasetButtonNext;
+var keyControl;
+var showKeys = true;
+var linkButton;
+var linkText;
+var frame;
+
+// Node references. Note that the meanings of 'selected' and 'focused' are
+// swapped in the docs.
+//
+var head; // the root of the entire tree
+var selectedNode = 0; // the root of the current view
+var focusNode = 0; // a node chosen for more info (single-click)
+var highlightedNode = 0; // mouse hover node
+var highlightingHidden = false;
+var nodes = new Array();
+var currentNodeID = 0; // to iterate while loading
+
+var nodeHistory = new Array();
+var nodeHistoryPosition = 0;
+
+var dataEnabled = false; // true when supplemental files are present
+
+// store non-Krona GET variables so they can be passed on to links
+//
+var getVariables = new Array();
+
+// selectedNodeLast is separate from the history, since we need to check
+// properties of the last node viewed when browsing through the history
+//
+var selectedNodeLast = 0;
+var zoomOut = false;
+
+// temporary zoom-in while holding the mouse button on a wedge
+//
+var quickLook = false; // true when in quick look state
+var mouseDown = false;
+var mouseDownTime; // to detect mouse button hold
+var quickLookHoldLength = 200;
+
+var imageWidth;
+var imageHeight;
+var centerX;
+var centerY;
+var gRadius;
+var updateViewNeeded = false;
+
+// Determines the angle that the pie chart starts at. 90 degrees makes the
+// center label consistent with the children.
+//
+var rotationOffset = Math.PI / 2;
+
+var buffer;
+var bufferFactor = .1;
+
+// The maps are the small pie charts showing the current slice being viewed.
+//
+var mapBuffer = 10;
+var mapRadius = 0;
+var maxMapRadius = 25;
+var mapWidth = 150;
+var maxLabelOverhang = Math.PI * 4.18;
+
+// Keys are the labeled boxes for slices in the highest level that are too thin
+// to label.
+//
+var maxKeySizeFactor = 2; // will be multiplied by font size
+var keySize;
+var keys;
+var keyBuffer = 10;
+var currentKey;
+var keyMinTextLeft;
+var keyMinAngle;
+
+var minRingWidthFactor = 5; // will be multiplied by font size
+var maxPossibleDepth; // the theoretical max that can be displayed
+var maxDisplayDepth; // the actual depth that will be displayed
+var headerHeight = 0;//document.getElementById('options').clientHeight;
+var historySpacingFactor = 1.6; // will be multiplied by font size
+var historyAlphaDelta = .25;
+
+// appearance
+//
+var lineOpacity = 0.3;
+var saturation = 0.5;
+var lightnessBase = 0.6;
+var lightnessMax = .8;
+var thinLineWidth = .3;
+var highlightLineWidth = 1.5;
+var labelBoxBuffer = 6;
+var labelBoxRounding = 15;
+var labelWidthFudge = 1.05; // The width of unshortened labels are set slightly
+ // longer than the name width so the animation
+ // finishes faster.
+var fontNormal;
+var fontBold;
+var fontFamily = 'sans-serif';
+//var fontFaceBold = 'bold Arial';
+var nodeRadius;
+var angleFactor;
+var tickLength;
+var compressedRadii;
+
+// colors
+//
+var highlightFill = 'rgba(255, 255, 255, .3)';
+var colorUnclassified = 'rgb(220,220,220)';
+
+// label staggering
+//
+var labelOffsets; // will store the current offset at each depth
+//
+// This will store pointers to the last node that had a label in each offset (or "track") of a
+// each depth. These will be used to shorten neighboring labels that would overlap.
+// The [nLabelNodes] index will store the last node with a radial label.
+// labelFirstNodes is the same, but to check for going all the way around and
+// overlapping the first labels.
+//
+var labelLastNodes;
+var labelFirstNodes;
+//
+var nLabelOffsets = 3; // the number of offsets to use
+
+var mouseX = -1;
+var mouseY = -1;
+
+// tweening
+//
+var progress = 0; // for tweening; goes from 0 to 1.
+var progressLast = 0;
+var tweenFactor = 0; // progress converted by a curve for a smoother effect.
+var tweenLength = 850; // in ms
+var tweenCurvature = 13;
+//
+// tweenMax is used to scale the sigmoid function so its range is [0,1] for the
+// domain [0,1]
+//
+var tweenMax = 1 / (1 + Math.exp(-tweenCurvature / 2));
+//
+var tweenStartTime;
+
+// for framerate debug
+//
+var tweenFrames = 0;
+var fpsDisplay = document.getElementById('frameRate');
+
+// Arrays to translate xml attribute names into displayable attribute names
+//
+var attributes = new Array();
+//
+var magnitudeIndex; // the index of attribute arrays used for magnitude
+var membersAssignedIndex;
+var membersSummaryIndex;
+
+// For defining gradients
+//
+var hueDisplayName;
+var hueStopPositions;
+var hueStopHues;
+var hueStopText;
+
+// multiple datasets
+//
+var currentDataset = 0;
+var lastDataset = 0;
+var datasets = 1;
+var datasetNames;
+var datasetSelectSize = 30;
+var datasetAlpha = new Tween(0, 0);
+var datasetWidths = new Array();
+var datasetChanged;
+var datasetSelectWidth = 50;
+
+window.onload = load;
+
+var image;
+var hiddenPattern;
+var loadingImage;
+var logoImage;
+
+function resize()
+{
+ imageWidth = window.innerWidth;
+ imageHeight = window.innerHeight;
+
+ if ( ! snapshotMode )
+ {
+ context.canvas.width = imageWidth;
+ context.canvas.height = imageHeight;
+ }
+
+ if ( datasetDropDown )
+ {
+ var ratio =
+ (datasetDropDown.offsetTop + datasetDropDown.clientHeight) * 2 /
+ imageHeight;
+
+ if ( ratio > 1 )
+ {
+ ratio = 1;
+ }
+
+ ratio = Math.sqrt(ratio);
+
+ datasetSelectWidth =
+ (datasetDropDown.offsetLeft + datasetDropDown.clientWidth) * ratio;
+ }
+ var leftMargin = datasets > 1 ? datasetSelectWidth + 30 : 0;
+ var minDimension = imageWidth - mapWidth - leftMargin > imageHeight ?
+ imageHeight :
+ imageWidth - mapWidth - leftMargin;
+
+ maxMapRadius = minDimension * .03;
+ buffer = minDimension * bufferFactor;
+ margin = minDimension * .015;
+ centerX = (imageWidth - mapWidth - leftMargin) / 2 + leftMargin;
+ centerY = imageHeight / 2;
+ gRadius = minDimension / 2 - buffer;
+ //context.font = '11px sans-serif';
+}
+
+function handleResize()
+{
+ updateViewNeeded = true;
+}
+
+function Attribute()
+{
+}
+
+function Tween(start, end)
+{
+ this.start = start;
+ this.end = end;
+ this.current = this.start;
+
+ this.current = function()
+ {
+ if ( progress == 1 || this.start == this.end )
+ {
+ return this.end;
+ }
+ else
+ {
+ return this.start + tweenFactor * (this.end - this.start);
+ }
+ };
+
+ this.setTarget = function(target)
+ {
+ this.start = this.current();
+ this.end = target;
+ }
+}
+
+function Node()
+{
+ this.id = currentNodeID;
+ currentNodeID++;
+ nodes[this.id] = this;
+
+ this.angleStart = new Tween(Math.PI, 0);
+ this.angleEnd = new Tween(Math.PI, 0);
+ this.radiusInner = new Tween(1, 1);
+ this.labelRadius = new Tween(1, 1);
+ this.labelWidth = new Tween(0, 0);
+ this.scale = new Tween(1, 1); // TEMP
+ this.radiusOuter = new Tween(1, 1);
+
+ this.r = new Tween(255, 255);
+ this.g = new Tween(255, 255);
+ this.b = new Tween(255, 255);
+
+ this.alphaLabel = new Tween(0, 1);
+ this.alphaLine = new Tween(0, 1);
+ this.alphaArc = new Tween(0, 0);
+ this.alphaWedge = new Tween(0, 1);
+ this.alphaOther = new Tween(0, 1);
+ this.alphaPattern = new Tween(0, 0);
+ this.children = Array();
+ this.parent = 0;
+
+ this.attributes = new Array(attributes.length);
+
+ this.addChild = function(child)
+ {
+ this.children.push(child);
+ };
+
+ this.addLabelNode = function(depth, labelOffset)
+ {
+ if ( labelHeadNodes[depth][labelOffset] == 0 )
+ {
+ // this will become the head node for this list
+
+ labelHeadNodes[depth][labelOffset] = this;
+ this.labelPrev = this;
+ }
+
+ var head = labelHeadNodes[depth][labelOffset];
+
+ this.labelNext = head;
+ this.labelPrev = head.labelPrev;
+ head.labelPrev.labelNext = this;
+ head.labelPrev = this;
+ }
+
+ this.canDisplayDepth = function()
+ {
+ // whether this node is at a depth that can be displayed, according
+ // to the max absolute depth
+
+ return this.depth <= maxAbsoluteDepth;
+ }
+
+ this.canDisplayHistory = function()
+ {
+ var radiusInner;
+
+ if ( compress )
+ {
+ radiusInner = compressedRadii[0];
+ }
+ else
+ {
+ radiusInner = nodeRadius;
+ }
+
+ return (
+ -this.labelRadius.end * gRadius +
+ historySpacingFactor * fontSize / 2 <
+ radiusInner * gRadius
+ );
+ }
+
+ this.canDisplayLabelCurrent = function()
+ {
+ return (
+ (this.angleEnd.current() - this.angleStart.current()) *
+ (this.radiusInner.current() * gRadius + gRadius) >=
+ minWidth());
+ }
+
+ this.checkHighlight = function()
+ {
+ if ( this.children.length == 0 && this == focusNode )
+ {
+ //return false;
+ }
+
+ if ( this.hide )
+ {
+ return false;
+ }
+
+ if ( this.radiusInner.end == 1 )
+ {
+ // compressed to the outside; don't check
+
+ return false;
+ }
+
+ var highlighted = false;
+
+ var angleStartCurrent = this.angleStart.current() + rotationOffset;
+ var angleEndCurrent = this.angleEnd.current() + rotationOffset;
+ var radiusInner = this.radiusInner.current() * gRadius;
+
+ for ( var i = 0; i < this.children.length; i++ )
+ {
+ highlighted = this.children[i].checkHighlight();
+
+ if ( highlighted )
+ {
+ return true;
+ }
+ }
+
+ if ( this != selectedNode && ! this.getCollapse() )
+ {
+ context.beginPath();
+ context.arc(0, 0, radiusInner, angleStartCurrent, angleEndCurrent, false);
+ context.arc(0, 0, gRadius, angleEndCurrent, angleStartCurrent, true);
+ context.closePath();
+
+ if ( context.isPointInPath(mouseX - centerX, mouseY - centerY) )
+ {
+ highlighted = true;
+ }
+
+ if
+ (
+ ! highlighted &&
+ (angleEndCurrent - angleStartCurrent) *
+ (radiusInner + gRadius) <
+ minWidth() &&
+ this.getDepth() == selectedNode.getDepth() + 1
+ )
+ {
+ if ( showKeys && this.checkHighlightKey() )
+ {
+ highlighted = true;
+ }
+ }
+ }
+
+ if ( highlighted )
+ {
+ if ( this != highlightedNode )
+ {
+ // document.body.style.cursor='pointer';
+ }
+
+ highlightedNode = this;
+ }
+
+ return highlighted;
+ }
+
+ this.checkHighlightCenter = function()
+ {
+ if ( ! this.canDisplayHistory() )
+ {
+ return;
+ }
+
+ var cx = centerX;
+ var cy = centerY - this.labelRadius.end * gRadius;
+ //var dim = context.measureText(this.name);
+
+ var width = this.nameWidth;
+
+ if ( this.searchResultChildren() )
+ {
+ var results = searchResultString(this.searchResultChildren());
+ var dim = context.measureText(results);
+ width += dim.width;
+ }
+
+ if
+ (
+ mouseX > cx - width / 2 &&
+ mouseX < cx + width / 2 &&
+ mouseY > cy - historySpacingFactor * fontSize / 2 &&
+ mouseY < cy + historySpacingFactor * fontSize / 2
+ )
+ {
+ highlightedNode = this;
+ return;
+ }
+
+ if ( this.getParent() )
+ {
+ this.getParent().checkHighlightCenter();
+ }
+ }
+
+ this.checkHighlightKey = function()
+ {
+ var offset = keyOffset();
+
+ var xMin = imageWidth - keySize - margin - this.keyNameWidth - keyBuffer;
+ var xMax = imageWidth - margin;
+ var yMin = offset;
+ var yMax = offset + keySize;
+
+ currentKey++;
+
+ return (
+ mouseX > xMin &&
+ mouseX < xMax &&
+ mouseY > yMin &&
+ mouseY < yMax);
+ }
+
+ this.checkHighlightMap = function()
+ {
+ if ( this.parent )
+ {
+ this.parent.checkHighlightMap();
+ }
+
+ if ( this.getCollapse() || this == focusNode )
+ {
+ return;
+ }
+
+ var box = this.getMapPosition();
+
+ if
+ (
+ mouseX > box.x - mapRadius &&
+ mouseX < box.x + mapRadius &&
+ mouseY > box.y - mapRadius &&
+ mouseY < box.y + mapRadius
+ )
+ {
+ highlightedNode = this;
+ }
+ }
+
+/* this.collapse = function()
+ {
+ for (var i = 0; i < this.children.length; i++ )
+ {
+ this.children[i] = this.children[i].collapse();
+ }
+
+ if
+ (
+ this.children.length == 1 &&
+ this.children[0].magnitude == this.magnitude
+ )
+ {
+ this.children[0].parent = this.parent;
+ this.children[0].getDepth() = this.parent.getDepth() + 1;
+ return this.children[0];
+ }
+ else
+ {
+ return this;
+ }
+ }
+*/
+ this.draw = function(labelMode, selected, searchHighlighted)
+ {
+ var depth = this.getDepth() - selectedNode.getDepth() + 1;
+// var hidden = false;
+
+ if ( selectedNode == this )
+ {
+ selected = true;
+ }
+
+ var angleStartCurrent = this.angleStart.current() + rotationOffset;
+ var angleEndCurrent = this.angleEnd.current() + rotationOffset;
+ var radiusInner = this.radiusInner.current() * gRadius;
+ var canDisplayLabelCurrent = this.canDisplayLabelCurrent();
+ var hiddenSearchResults = false;
+
+/* if ( ! this.hide )
+ {
+ for ( var i = 0; i < this.children.length; i++ )
+ {
+ if ( this.children[i].hide && this.children[i].searchResults )
+ {
+ hiddenSearchResults = true;
+ }
+ }
+ }
+*/
+ var drawChildren =
+ ( ! this.hide || ! this.hidePrev && progress < 1 ) &&
+ ( ! this.hideAlone || ! this.hideAlonePrev && progress < 1 );
+
+// if ( this.alphaWedge.current() > 0 || this.alphaLabel.current() > 0 )
+ {
+ var lastChildAngleEnd;
+
+ if ( this.hasChildren() )//canDisplayChildren )
+ {
+ lastChildAngleEnd =
+ this.children[this.children.length - 1].angleEnd.current()
+ + rotationOffset;
+ }
+
+ if ( labelMode )
+ {
+ var drawRadial =
+ !(
+ this.parent &&
+ this.parent != selectedNode &&
+ angleEndCurrent == this.parent.angleEnd.current() + rotationOffset
+ );
+
+ if ( angleStartCurrent != angleEndCurrent )
+ {
+ this.drawLines(angleStartCurrent, angleEndCurrent, radiusInner, drawRadial, selected);
+ }
+
+ var alphaOtherCurrent = this.alphaOther.current();
+ var childRadiusInner;
+
+ if ( this == selectedNode || alphaOtherCurrent )
+ {
+ childRadiusInner =
+ this.children[this.children.length - 1].radiusInner.current() * gRadius;
+ }
+
+ if ( this == selectedNode )
+ {
+ this.drawReferenceRings(childRadiusInner);
+ }
+
+ if
+ (
+ selected &&
+ ! searchHighlighted &&
+ this != selectedNode &&
+ (
+ this.isSearchResult ||
+ this.hideAlone && this.searchResultChildren() ||
+ false
+// this.hide &&
+// this.containsSearchResult
+ )
+ )
+ {
+ context.globalAlpha = this.alphaWedge.current();
+
+ drawWedge
+ (
+ angleStartCurrent,
+ angleEndCurrent,
+ radiusInner,
+ gRadius,
+ highlightFill,
+ 0,
+ true
+ );
+
+ if
+ (
+ this.keyed &&
+ ! showKeys &&
+ this.searchResults &&
+ ! searchHighlighted &&
+ this != highlightedNode &&
+ this != focusNode
+ )
+ {
+ var angle = (angleEndCurrent + angleStartCurrent) / 2;
+ this.drawLabel(angle, true, false, true, true);
+ }
+
+ //this.drawHighlight(false);
+ searchHighlighted = true;
+ }
+
+ if
+ (
+ this == selectedNode ||
+// true
+ //(canDisplayLabelCurrent) &&
+ this != highlightedNode &&
+ this != focusNode
+ )
+ {
+ if ( this.radial != this.radialPrev && this.alphaLabel.end == 1 )
+ {
+ context.globalAlpha = tweenFactor;
+ }
+ else
+ {
+ context.globalAlpha = this.alphaLabel.current();
+ }
+
+ this.drawLabel
+ (
+ (angleStartCurrent + angleEndCurrent) / 2,
+ this.hideAlone && this.searchResultChildren() ||
+ (this.isSearchResult || hiddenSearchResults) && selected,
+ this == selectedNode && ! this.radial,
+ selected,
+ this.radial
+ );
+
+ if ( this.radial != this.radialPrev && this.alphaLabel.start == 1 && progress < 1 )
+ {
+ context.globalAlpha = 1 - tweenFactor;
+
+ this.drawLabel
+ (
+ (angleStartCurrent + angleEndCurrent) / 2,
+ (this.isSearchResult || hiddenSearchResults) && selected,
+ this == selectedNodeLast && ! this.radialPrev,
+ selected,
+ this.radialPrev
+ );
+ }
+ }
+
+ if
+ (
+ alphaOtherCurrent &&
+ lastChildAngleEnd != null
+ )
+ {
+ if
+ (
+ (angleEndCurrent - lastChildAngleEnd) *
+ (childRadiusInner + gRadius) >=
+ minWidth()
+ )
+ {
+ //context.font = fontNormal;
+ context.globalAlpha = this.alphaOther.current();
+
+ drawTextPolar
+ (
+ this.getUnclassifiedText(),
+ this.getUnclassifiedPercentage(),
+ (lastChildAngleEnd + angleEndCurrent) / 2,
+ (childRadiusInner + gRadius) / 2,
+ true,
+ false,
+ false,
+ 0,
+ 0
+ );
+ }
+ }
+
+ if ( this == selectedNode && this.keyUnclassified && showKeys )
+ {
+ this.drawKey
+ (
+ (lastChildAngleEnd + angleEndCurrent) / 2,
+ false,
+ false
+ );
+ }
+ }
+ else
+ {
+ var alphaWedgeCurrent = this.alphaWedge.current();
+
+ if ( alphaWedgeCurrent || this.alphaOther.current() )
+ {
+ var currentR = this.r.current();
+ var currentG = this.g.current();
+ var currentB = this.b.current();
+
+ var fill = rgbText(currentR, currentG, currentB);
+
+ var radiusOuter;
+ var lastChildAngle;
+ var truncateWedge =
+ (
+ this.hasChildren() &&
+ ! this.keyed &&
+ (compress || depth < maxDisplayDepth) &&
+ drawChildren
+ );
+
+ if ( truncateWedge )
+ {
+ radiusOuter = this.children[0].radiusInner.current() * gRadius;
+ }
+ else
+ {
+ radiusOuter = gRadius;
+ }
+ /*
+ if ( this.hasChildren() )
+ {
+ radiusOuter = this.children[0].getUncollapsed().radiusInner.current() * gRadius + 1;
+ }
+ else
+ { // TEMP
+ radiusOuter = radiusInner + nodeRadius * gRadius;
+
+ if ( radiusOuter > gRadius )
+ {
+ radiusOuter = gRadius;
+ }
+ }
+ */
+ context.globalAlpha = alphaWedgeCurrent;
+
+ if ( radiusInner != radiusOuter )
+ {
+ drawWedge
+ (
+ angleStartCurrent,
+ angleEndCurrent,
+ radiusInner,
+ radiusOuter,//this.radiusOuter.current() * gRadius,
+ //'rgba(0, 200, 0, .1)',
+ fill,
+ this.alphaPattern.current()
+ );
+
+ if ( truncateWedge )
+ {
+ // fill in the extra space if the sum of our childrens'
+ // magnitudes is less than ours
+
+ if ( lastChildAngleEnd < angleEndCurrent )//&& false) // TEMP
+ {
+ if ( radiusOuter > 1 )
+ {
+ // overlap slightly to hide the seam
+
+ // radiusOuter -= 1;
+ }
+
+ if ( alphaWedgeCurrent < 1 )
+ {
+ context.globalAlpha = this.alphaOther.current();
+ drawWedge
+ (
+ lastChildAngleEnd,
+ angleEndCurrent,
+ radiusOuter,
+ gRadius,
+ colorUnclassified,
+ 0
+ );
+ context.globalAlpha = alphaWedgeCurrent;
+ }
+
+ drawWedge
+ (
+ lastChildAngleEnd,
+ angleEndCurrent,
+ radiusOuter,
+ gRadius,//this.radiusOuter.current() * gRadius,
+ //'rgba(200, 0, 0, .1)',
+ fill,
+ this.alphaPattern.current()
+ );
+ }
+ }
+
+ if ( radiusOuter < gRadius )
+ {
+ // patch up the seam
+ //
+ context.beginPath();
+ context.arc(0, 0, radiusOuter, angleStartCurrent/*lastChildAngleEnd*/, angleEndCurrent, false);
+ context.strokeStyle = fill;
+ context.lineWidth = 1;
+ context.stroke();
+ }
+ }
+
+ if ( this.keyed && selected && showKeys )//&& progress == 1 )
+ {
+ this.drawKey
+ (
+ (angleStartCurrent + angleEndCurrent) / 2,
+ (
+ this == highlightedNode ||
+ this == focusNode ||
+ this.searchResults
+ ),
+ this == highlightedNode || this == focusNode
+ );
+ }
+ }
+ }
+ }
+
+ if ( drawChildren )
+ {
+ // draw children
+ //
+ for ( var i = 0; i < this.children.length; i++ )
+ {
+ if ( this.drawHiddenChildren(i, selected, labelMode, searchHighlighted) )
+ {
+ i = this.children[i].hiddenEnd;
+ }
+ else
+ {
+ this.children[i].draw(labelMode, selected, searchHighlighted);
+ }
+ }
+ }
+ };
+
+ this.drawHiddenChildren = function
+ (
+ firstHiddenChild,
+ selected,
+ labelMode,
+ searchHighlighted
+ )
+ {
+ var firstChild = this.children[firstHiddenChild];
+
+ if ( firstChild.hiddenEnd == null || firstChild.radiusInner.current() == 1 )
+ {
+ return false;
+ }
+
+ for ( var i = firstHiddenChild; i < firstChild.hiddenEnd; i++ )
+ {
+ if ( ! this.children[i].hide || ! this.children[i].hidePrev && progress < 1 )
+ {
+ return false;
+ }
+ }
+
+ var angleStart = firstChild.angleStart.current() + rotationOffset;
+ var lastChild = this.children[firstChild.hiddenEnd];
+ var angleEnd = lastChild.angleEnd.current() + rotationOffset;
+ var radiusInner = gRadius * firstChild.radiusInner.current();
+ var hiddenChildren = firstChild.hiddenEnd - firstHiddenChild + 1;
+
+ if ( labelMode )
+ {
+ var hiddenSearchResults = 0;
+
+ for ( var i = firstHiddenChild; i <= firstChild.hiddenEnd; i++ )
+ {
+ hiddenSearchResults += this.children[i].searchResults;
+
+ if ( this.children[i].magnitude == 0 )
+ {
+ hiddenChildren--;
+ }
+ }
+
+ if
+ (
+ selected &&
+ (angleEnd - angleStart) *
+ (gRadius + gRadius) >=
+ minWidth() ||
+ this == highlightedNode &&
+ hiddenChildren ||
+ hiddenSearchResults
+ )
+ {
+ context.globalAlpha = this.alphaWedge.current();
+
+ this.drawHiddenLabel
+ (
+ angleStart,
+ angleEnd,
+ hiddenChildren,
+ hiddenSearchResults
+ );
+ }
+ }
+
+ var drawWedges = true;
+
+ for ( var i = firstHiddenChild; i <= firstChild.hiddenEnd; i++ )
+ {
+ // all hidden children must be completely hidden to draw together
+
+ if ( this.children[i].alphaPattern.current() != this.children[i].alphaWedge.current() )
+ {
+ drawWedges = false;
+ break;
+ }
+ }
+
+ if ( labelMode )
+ {
+ if ( drawWedges )
+ {
+ var drawRadial = (angleEnd < this.angleEnd.current() + rotationOffset);
+ this.drawLines(angleStart, angleEnd, radiusInner, drawRadial);
+ }
+
+ if ( hiddenSearchResults && ! searchHighlighted )
+ {
+ drawWedge
+ (
+ angleStart,
+ angleEnd,
+ radiusInner,
+ gRadius,//this.radiusOuter.current() * gRadius,
+ highlightFill,
+ 0,
+ true
+ );
+ }
+ }
+ else if ( drawWedges )
+ {
+ context.globalAlpha = this.alphaWedge.current();
+
+ var fill = rgbText
+ (
+ firstChild.r.current(),
+ firstChild.g.current(),
+ firstChild.b.current()
+ );
+
+ drawWedge
+ (
+ angleStart,
+ angleEnd,
+ radiusInner,
+ gRadius,//this.radiusOuter.current() * gRadius,
+ fill,
+ context.globalAlpha,
+ false
+ );
+ }
+
+ return drawWedges;
+ }
+
+ this.drawHiddenLabel = function(angleStart, angleEnd, value, hiddenSearchResults)
+ {
+ var textAngle = (angleStart + angleEnd) / 2;
+ var labelRadius = gRadius + fontSize;//(radiusInner + radius) / 2;
+
+ drawTick(gRadius - fontSize * .75, fontSize * 1.5, textAngle);
+ drawTextPolar
+ (
+ value.toString() + ' more',
+ 0, // inner text
+ textAngle,
+ labelRadius,
+ true, // radial
+ hiddenSearchResults, // bubble
+ this == highlightedNode || this == focusNode, // bold
+ false,
+ hiddenSearchResults
+ );
+ }
+
+ this.drawHighlight = function(bold)
+ {
+ var angleStartCurrent = this.angleStart.current() + rotationOffset;
+ var angleEndCurrent = this.angleEnd.current() + rotationOffset;
+ var radiusInner = this.radiusInner.current() * gRadius;
+
+ //this.setHighlightStyle();
+
+ if ( this == focusNode && this == highlightedNode && this.hasChildren() )
+ {
+// context.fillStyle = "rgba(255, 255, 255, .3)";
+ arrow
+ (
+ angleStartCurrent,
+ angleEndCurrent,
+ radiusInner
+ );
+ }
+ else
+ {
+ drawWedge
+ (
+ angleStartCurrent,
+ angleEndCurrent,
+ radiusInner,
+ gRadius,
+ highlightFill,
+ 0,
+ true
+ );
+ }
+
+ // check if hidden children should be highlighted
+ //
+ for ( var i = 0; i < this.children.length; i++ )
+ {
+ if
+ (
+ this.children[i].getDepth() - selectedNode.getDepth() + 1 <=
+ maxDisplayDepth &&
+ this.children[i].hiddenEnd != null
+ )
+ {
+ var firstChild = this.children[i];
+ var lastChild = this.children[firstChild.hiddenEnd];
+ var hiddenAngleStart = firstChild.angleStart.current() + rotationOffset;
+ var hiddenAngleEnd = lastChild.angleEnd.current() + rotationOffset;
+ var hiddenRadiusInner = gRadius * firstChild.radiusInner.current();
+
+ drawWedge
+ (
+ hiddenAngleStart,
+ hiddenAngleEnd,
+ hiddenRadiusInner,
+ gRadius,
+ 'rgba(255, 255, 255, .3)',
+ 0,
+ true
+ );
+
+ if ( false && ! this.searchResults )
+ {
+ this.drawHiddenLabel
+ (
+ hiddenAngleStart,
+ hiddenAngleEnd,
+ firstChild.hiddenEnd - i + 1
+ );
+ }
+
+ i = firstChild.hiddenEnd;
+ }
+ }
+
+// context.strokeStyle = 'black';
+ context.fillStyle = 'black';
+
+ var highlight = ! ( progress < 1 && zoomOut && this == selectedNodeLast );
+
+ var angle = (angleEndCurrent + angleStartCurrent) / 2;
+
+ if ( ! (this.keyed && showKeys) )
+ {
+ this.drawLabel(angle, true, bold, true, this.radial);
+ }
+ }
+
+ this.drawHighlightCenter = function()
+ {
+ if ( ! this.canDisplayHistory() )
+ {
+ return;
+ }
+
+ context.lineWidth = highlightLineWidth;
+ context.strokeStyle = 'black';
+ context.fillStyle = "rgba(255, 255, 255, .6)";
+
+ context.fillStyle = 'black';
+ this.drawLabel(3 * Math.PI / 2, true, true, false);
+ context.font = fontNormal;
+ }
+
+ this.drawKey = function(angle, highlight, bold)
+ {
+ var offset = keyOffset();
+ var color;
+ var colorText = this.magnitude == 0 ? 'gray' : 'black';
+ var patternAlpha = this.alphaPattern.end;
+ var boxLeft = imageWidth - keySize - margin;
+ var textY = offset + keySize / 2;
+
+ var label;
+ var keyNameWidth;
+
+ if ( this == selectedNode )
+ {
+ color = colorUnclassified;
+ label =
+ this.getUnclassifiedText() +
+ ' ' +
+ this.getUnclassifiedPercentage();
+ keyNameWidth = measureText(label, false);
+ }
+ else
+ {
+ label = this.keyLabel;
+ color = rgbText(this.r.end, this.g.end, this.b.end);
+
+ if ( highlight )
+ {
+ if ( this.searchResultChildren() )
+ {
+ label = label + searchResultString(this.searchResultChildren());
+ }
+
+ keyNameWidth = measureText(label, bold);
+ }
+ else
+ {
+ keyNameWidth = this.keyNameWidth;
+ }
+ }
+
+ var textLeft = boxLeft - keyBuffer - keyNameWidth - fontSize / 2;
+ var labelLeft = textLeft;
+
+ if ( labelLeft > keyMinTextLeft - fontSize / 2 )
+ {
+ keyMinTextLeft -= fontSize / 2;
+
+ if ( keyMinTextLeft < centerX - gRadius + fontSize / 2 )
+ {
+ keyMinTextLeft = centerX - gRadius + fontSize / 2;
+ }
+
+ labelLeft = keyMinTextLeft;
+ }
+
+ var lineX = new Array();
+ var lineY = new Array();
+
+ var bendRadius;
+ var keyAngle = Math.atan((textY - centerY) / (labelLeft - centerX));
+ var arcAngle;
+
+ if ( keyAngle < 0 )
+ {
+ keyAngle += Math.PI;
+ }
+
+ if ( keyMinAngle == 0 || angle < keyMinAngle )
+ {
+ keyMinAngle = angle;
+ }
+
+ if ( angle > Math.PI && keyMinAngle > Math.PI )
+ {
+ // allow lines to come underneath the chart
+
+ angle -= Math.PI * 2;
+ }
+
+ lineX.push(Math.cos(angle) * gRadius);
+ lineY.push(Math.sin(angle) * gRadius);
+
+ if ( angle < keyAngle && textY > centerY + Math.sin(angle) * (gRadius + buffer * (currentKey - 1) / (keys + 1) / 2 + buffer / 2) )
+ {
+ bendRadius = gRadius + buffer - buffer * currentKey / (keys + 1) / 2;
+ }
+ else
+ {
+ bendRadius = gRadius + buffer * currentKey / (keys + 1) / 2 + buffer / 2;
+ }
+
+ var outside =
+ Math.sqrt
+ (
+ Math.pow(labelLeft - centerX, 2) +
+ Math.pow(textY - centerY, 2)
+ ) > bendRadius;
+
+ if ( ! outside )
+ {
+ arcAngle = Math.asin((textY - centerY) / bendRadius);
+
+ keyMinTextLeft = min(keyMinTextLeft, centerX + bendRadius * Math.cos(arcAngle) - fontSize / 2);
+
+ if ( labelLeft < textLeft && textLeft > centerX + bendRadius * Math.cos(arcAngle) )
+ {
+ lineX.push(textLeft - centerX);
+ lineY.push(textY - centerY);
+ }
+ }
+ else
+ {
+ keyMinTextLeft = min(keyMinTextLeft, labelLeft - fontSize / 2);
+
+ if ( angle < keyAngle )
+ {
+ // flip everything over y = x
+ //
+ arcAngle = Math.PI / 2 - keyLineAngle
+ (
+ Math.PI / 2 - angle,
+ Math.PI / 2 - keyAngle,
+ bendRadius,
+ textY - centerY,
+ labelLeft - centerX,
+ lineY,
+ lineX
+ );
+
+ }
+ else
+ {
+ arcAngle = keyLineAngle
+ (
+ angle,
+ keyAngle,
+ bendRadius,
+ labelLeft - centerX,
+ textY - centerY,
+ lineX,
+ lineY
+ );
+ }
+ }
+
+ if ( labelLeft > centerX + bendRadius * Math.cos(arcAngle) ||
+ textY > centerY + bendRadius * Math.sin(arcAngle) + .01)
+// if ( outside || )
+ {
+ lineX.push(labelLeft - centerX);
+ lineY.push(textY - centerY);
+
+ if ( textLeft != labelLeft )
+ {
+ lineX.push(textLeft - centerX);
+ lineY.push(textY - centerY);
+ }
+ }
+
+ context.globalAlpha = this.alphaWedge.current();
+
+ if ( snapshotMode )
+ {
+ var labelSVG;
+
+ if ( this == selectedNode )
+ {
+ labelSVG =
+ this.getUnclassifiedText() +
+ spacer() +
+ this.getUnclassifiedPercentage();
+ }
+ else
+ {
+ labelSVG = this.name + spacer() + this.getPercentage() + '%';
+ }
+
+ svg +=
+ '<rect fill="' + color + '" ' +
+ 'x="' + boxLeft + '" y="' + offset +
+ '" width="' + keySize + '" height="' + keySize + '"/>';
+
+ if ( patternAlpha )
+ {
+ svg +=
+ '<rect fill="url(#hiddenPattern)" style="stroke:none" ' +
+ 'x="' + boxLeft + '" y="' + offset +
+ '" width="' + keySize + '" height="' + keySize + '"/>';
+ }
+
+ svg +=
+ '<path class="line' +
+ (highlight ? ' highlight' : '') +
+ '" d="M ' + (lineX[0] + centerX) + ',' +
+ (lineY[0] + centerY);
+
+ if ( angle != arcAngle )
+ {
+ svg +=
+ ' L ' + (centerX + bendRadius * Math.cos(angle)) + ',' +
+ (centerY + bendRadius * Math.sin(angle)) +
+ ' A ' + bendRadius + ',' + bendRadius + ' 0 ' +
+ '0,' + (angle > arcAngle ? '0' : '1') + ' ' +
+ (centerX + bendRadius * Math.cos(arcAngle)) + ',' +
+ (centerY + bendRadius * Math.sin(arcAngle));
+ }
+
+ for ( var i = 1; i < lineX.length; i++ )
+ {
+ svg +=
+ ' L ' + (centerX + lineX[i]) + ',' +
+ (centerY + lineY[i]);
+ }
+
+ svg += '"/>';
+
+ if ( highlight )
+ {
+ if ( this.searchResultChildren() )
+ {
+ labelSVG = labelSVG + searchResultString(this.searchResultChildren());
+ }
+
+ drawBubbleSVG
+ (
+ boxLeft - keyBuffer - keyNameWidth - fontSize / 2,
+ textY - fontSize,
+ keyNameWidth + fontSize,
+ fontSize * 2,
+ fontSize,
+ 0
+ );
+
+ if ( this.isSearchResult )
+ {
+ drawSearchHighlights
+ (
+ label,
+ boxLeft - keyBuffer - keyNameWidth,
+ textY,
+ 0
+ )
+ }
+ }
+
+ svg += svgText(labelSVG, boxLeft - keyBuffer, textY, 'end', bold, colorText);
+ }
+ else
+ {
+ context.fillStyle = color;
+ context.translate(-centerX, -centerY);
+ context.strokeStyle = 'black';
+ context.globalAlpha = 1;//this.alphaWedge.current();
+
+ context.fillRect(boxLeft, offset, keySize, keySize);
+
+ if ( patternAlpha )
+ {
+ context.globalAlpha = patternAlpha;
+ context.fillStyle = hiddenPattern;
+
+ // make clipping box for Firefox performance
+ context.beginPath();
+ context.moveTo(boxLeft, offset);
+ context.lineTo(boxLeft + keySize, offset);
+ context.lineTo(boxLeft + keySize, offset + keySize);
+ context.lineTo(boxLeft, offset + keySize);
+ context.closePath();
+ context.save();
+ context.clip();
+
+ context.fillRect(boxLeft, offset, keySize, keySize);
+ context.fillRect(boxLeft, offset, keySize, keySize);
+
+ context.restore(); // remove clipping region
+ }
+
+ if ( highlight )
+ {
+ this.setHighlightStyle();
+ context.fillRect(boxLeft, offset, keySize, keySize);
+ }
+ else
+ {
+ context.lineWidth = thinLineWidth;
+ }
+
+ context.strokeRect(boxLeft, offset, keySize, keySize);
+
+ if ( lineX.length )
+ {
+ context.beginPath();
+ context.moveTo(lineX[0] + centerX, lineY[0] + centerY);
+
+ context.arc(centerX, centerY, bendRadius, angle, arcAngle, angle > arcAngle);
+
+ for ( var i = 1; i < lineX.length; i++ )
+ {
+ context.lineTo(lineX[i] + centerX, lineY[i] + centerY);
+ }
+
+ context.globalAlpha = this == selectedNode ?
+ this.children[0].alphaWedge.current() :
+ this.alphaWedge.current();
+ context.lineWidth = highlight ? highlightLineWidth : thinLineWidth;
+ context.stroke();
+ context.globalAlpha = 1;
+ }
+
+ if ( highlight )
+ {
+ drawBubbleCanvas
+ (
+ boxLeft - keyBuffer - keyNameWidth - fontSize / 2,
+ textY - fontSize,
+ keyNameWidth + fontSize,
+ fontSize * 2,
+ fontSize,
+ 0
+ );
+
+ if ( this.isSearchResult )
+ {
+ drawSearchHighlights
+ (
+ label,
+ boxLeft - keyBuffer - keyNameWidth,
+ textY,
+ 0
+ )
+ }
+ }
+
+ drawText(label, boxLeft - keyBuffer, offset + keySize / 2, 0, 'end', bold, colorText);
+
+ context.translate(centerX, centerY);
+ }
+
+ currentKey++;
+ }
+
+ this.drawLabel = function(angle, bubble, bold, selected, radial)
+ {
+ if ( context.globalAlpha == 0 )
+ {
+ return;
+ }
+
+ var innerText;
+ var label;
+ var radius;
+
+ if ( radial )
+ {
+ radius = (this.radiusInner.current() + 1) * gRadius / 2;
+ }
+ else
+ {
+ radius = this.labelRadius.current() * gRadius;
+ }
+
+ if ( radial && (selected || bubble ) )
+ {
+ var percentage = this.getPercentage();
+ innerText = percentage + '%';
+ }
+
+ if
+ (
+ ! radial &&
+ this != selectedNode &&
+ ! bubble &&
+ ( !zoomOut || this != selectedNodeLast)
+ )
+ {
+ label = this.shortenLabel();
+ }
+ else
+ {
+ label = this.name;
+ }
+
+ var flipped = drawTextPolar
+ (
+ label,
+ innerText,
+ angle,
+ radius,
+ radial,
+ bubble,
+ bold,
+// this.isSearchResult && this.shouldAddSearchResultsString() && (!selected || this == selectedNode || highlight),
+ this.isSearchResult && (!selected || this == selectedNode || bubble),
+ (this.hideAlone || !selected || this == selectedNode ) ? this.searchResultChildren() : 0
+ );
+
+ var depth = this.getDepth() - selectedNode.getDepth() + 1;
+
+ if
+ (
+ ! radial &&
+ ! bubble &&
+ this != selectedNode &&
+ this.angleEnd.end != this.angleStart.end &&
+ nLabelOffsets[depth - 2] > 2 &&
+ this.labelWidth.current() > (this.angleEnd.end - this.angleStart.end) * Math.abs(radius) &&
+ ! ( zoomOut && this == selectedNodeLast ) &&
+ this.labelRadius.end > 0
+ )
+ {
+ // name extends beyond wedge; draw tick mark towards the central
+ // radius for easier identification
+
+ var radiusCenter = compress ?
+ (compressedRadii[depth - 1] + compressedRadii[depth - 2]) / 2 :
+ (depth - .5) * nodeRadius;
+
+ if ( this.labelRadius.end > radiusCenter )
+ {
+ if ( flipped )
+ {
+ drawTick(radius - tickLength * 1.4 , tickLength, angle);
+ }
+ else
+ {
+ drawTick(radius - tickLength * 1.7, tickLength, angle);
+ }
+ }
+ else
+ {
+ if ( flipped )
+ {
+ drawTick(radius + tickLength * .7, tickLength, angle);
+ }
+ else
+ {
+ drawTick(radius + tickLength * .4, tickLength, angle);
+ }
+ }
+ }
+ }
+
+ this.drawLines = function(angleStart, angleEnd, radiusInner, drawRadial, selected)
+ {
+ if ( snapshotMode )
+ {
+ if ( this != selectedNode)
+ {
+ if ( angleEnd == angleStart + Math.PI * 2 )
+ {
+ // fudge to prevent overlap, which causes arc ambiguity
+ //
+ angleEnd -= .1 / gRadius;
+ }
+
+ var longArc = angleEnd - angleStart > Math.PI ? 1 : 0;
+
+ var x1 = centerX + radiusInner * Math.cos(angleStart);
+ var y1 = centerY + radiusInner * Math.sin(angleStart);
+
+ var x2 = centerX + gRadius * Math.cos(angleStart);
+ var y2 = centerY + gRadius * Math.sin(angleStart);
+
+ var x3 = centerX + gRadius * Math.cos(angleEnd);
+ var y3 = centerY + gRadius * Math.sin(angleEnd);
+
+ var x4 = centerX + radiusInner * Math.cos(angleEnd);
+ var y4 = centerY + radiusInner * Math.sin(angleEnd);
+
+ if ( this.alphaArc.end )
+ {
+ var dArray =
+ [
+ " M ", x4, ",", y4,
+ " A ", radiusInner, ",", radiusInner, " 0 ", longArc,
+ " 0 ", x1, ",", y1
+ ];
+
+ svg += '<path class="line" d="' + dArray.join('') + '"/>';
+ }
+
+ if ( drawRadial && this.alphaLine.end )
+ {
+ svg += '<line x1="' + x3 + '" y1="' + y3 + '" x2="' + x4 + '" y2="' + y4 + '"/>';
+ }
+ }
+ }
+ else
+ {
+ context.lineWidth = thinLineWidth;
+ context.strokeStyle = 'black';
+ context.beginPath();
+ context.arc(0, 0, radiusInner, angleStart, angleEnd, false);
+ context.globalAlpha = this.alphaArc.current();
+ context.stroke();
+
+ if ( drawRadial )
+ {
+ var x1 = radiusInner * Math.cos(angleEnd);
+ var y1 = radiusInner * Math.sin(angleEnd);
+ var x2 = gRadius * Math.cos(angleEnd);
+ var y2 = gRadius * Math.sin(angleEnd);
+
+ context.beginPath();
+ context.moveTo(x1, y1);
+ context.lineTo(x2, y2);
+
+// if ( this.getCollapse() )//( selected && this != selectedNode )
+ {
+ context.globalAlpha = this.alphaLine.current();
+ }
+
+ context.stroke();
+ }
+ }
+ }
+
+ this.drawMap = function(child)
+ {
+ if ( this.parent )
+ {
+ this.parent.drawMap(child);
+ }
+
+ if ( this.getCollapse() && this != child || this == focusNode )
+ {
+ return;
+ }
+
+ var angleStart =
+ (child.baseMagnitude - this.baseMagnitude) / this.magnitude * Math.PI * 2 +
+ rotationOffset;
+ var angleEnd =
+ (child.baseMagnitude - this.baseMagnitude + child.magnitude) /
+ this.magnitude * Math.PI * 2 +
+ rotationOffset;
+
+ var box = this.getMapPosition();
+
+ context.save();
+ context.fillStyle = 'black';
+ context.textAlign = 'end';
+ context.textBaseline = 'middle';
+
+ var textX = box.x - mapRadius - mapBuffer;
+ var percentage = getPercentage(child.magnitude / this.magnitude);
+
+ var highlight = this == selectedNode || this == highlightedNode;
+
+ if ( highlight )
+ {
+ context.font = fontBold;
+ }
+ else
+ {
+ context.font = fontNormal;
+ }
+
+ context.fillText(percentage + '% of', textX, box.y - mapRadius / 3);
+ context.fillText(this.name, textX, box.y + mapRadius / 3);
+
+ if ( highlight )
+ {
+ context.font = fontNormal;
+ }
+
+ if ( this == highlightedNode && this != selectedNode )
+ {
+ context.fillStyle = 'rgb(245, 245, 245)';
+// context.fillStyle = 'rgb(200, 200, 200)';
+ }
+ else
+ {
+ context.fillStyle = 'rgb(255, 255, 255)';
+ }
+
+ context.beginPath();
+ context.arc(box.x, box.y, mapRadius, 0, Math.PI * 2, true);
+ context.closePath();
+ context.fill();
+
+ if ( this == selectedNode )
+ {
+ context.lineWidth = 1;
+ context.fillStyle = 'rgb(100, 100, 100)';
+ }
+ else
+ {
+ if ( this == highlightedNode )
+ {
+ context.lineWidth = .2;
+ context.fillStyle = 'rgb(190, 190, 190)';
+ }
+ else
+ {
+ context.lineWidth = .2;
+ context.fillStyle = 'rgb(200, 200, 200)';
+ }
+ }
+
+ var maxDepth = this.getMaxDepth();
+
+ if ( ! compress && maxDepth > maxPossibleDepth + this.getDepth() - 1 )
+ {
+ maxDepth = maxPossibleDepth + this.getDepth() - 1;
+ }
+
+ if ( this.getDepth() < selectedNode.getDepth() )
+ {
+ if ( child.getDepth() - 1 >= maxDepth )
+ {
+ maxDepth = child.getDepth();
+ }
+ }
+
+ var radiusInner;
+
+ if ( compress )
+ {
+ radiusInner = 0;
+// Math.atan(child.getDepth() - this.getDepth()) /
+// Math.PI * 2 * .9;
+ }
+ else
+ {
+ radiusInner =
+ (child.getDepth() - this.getDepth()) /
+ (maxDepth - this.getDepth() + 1);
+ }
+
+ context.stroke();
+ context.beginPath();
+
+ if ( radiusInner == 0 )
+ {
+ context.moveTo(box.x, box.y);
+ }
+ else
+ {
+ context.arc(box.x, box.y, mapRadius * radiusInner, angleEnd, angleStart, true);
+ }
+
+ context.arc(box.x, box.y, mapRadius, angleStart, angleEnd, false);
+ context.closePath();
+ context.fill();
+
+ if ( this == highlightedNode && this != selectedNode )
+ {
+ context.lineWidth = 1;
+ context.stroke();
+ }
+
+ context.restore();
+ }
+
+ this.drawReferenceRings = function(childRadiusInner)
+ {
+ if ( snapshotMode )
+ {
+ svg +=
+ '<circle cx="' + centerX + '" cy="' + centerY +
+ '" r="' + childRadiusInner + '"/>';
+ svg +=
+ '<circle cx="' + centerX + '" cy="' + centerY +
+ '" r="' + gRadius + '"/>';
+ }
+ else
+ {
+ context.globalAlpha = 1 - this.alphaLine.current();//this.getUncollapsed().alphaLine.current();
+ context.beginPath();
+ context.arc(0, 0, childRadiusInner, 0, Math.PI * 2, false);
+ context.stroke();
+ context.beginPath();
+ context.arc(0, 0, gRadius, 0, Math.PI * 2, false);
+ context.stroke();
+ }
+ }
+
+ this.getCollapse = function()
+ {
+ return (
+ collapse &&
+ this.collapse &&
+ this.depth != maxAbsoluteDepth
+ );
+ }
+
+ this.getDepth = function()
+ {
+ if ( collapse )
+ {
+ return this.depthCollapsed;
+ }
+ else
+ {
+ return this.depth;
+ }
+ }
+
+ this.getMagnitude = function()
+ {
+ return this.attributes[magnitudeIndex][currentDataset];
+ }
+
+ this.getMapPosition = function()
+ {
+ return {
+ x : (details.offsetLeft + details.clientWidth - mapRadius),
+ y : ((focusNode.getDepth() - this.getDepth()) *
+ (mapBuffer + mapRadius * 2) - mapRadius) +
+ details.clientHeight + details.offsetTop
+ };
+ }
+
+ this.getMaxDepth = function(limit)
+ {
+ var max;
+
+ if ( collapse )
+ {
+ return this.maxDepthCollapsed;
+ }
+ else
+ {
+ if ( this.maxDepth > maxAbsoluteDepth )
+ {
+ return maxAbsoluteDepth;
+ }
+ else
+ {
+ return this.maxDepth;
+ }
+ }
+ }
+
+ this.getData = function(index, summary)
+ {
+ var files = new Array();
+
+ if
+ (
+ this.attributes[index] != null &&
+ this.attributes[index][currentDataset] != null &&
+ this.attributes[index][currentDataset] != ''
+ )
+ {
+ files.push
+ (
+ document.location +
+ '.files/' +
+ this.attributes[index][currentDataset]
+ );
+ }
+
+ if ( summary )
+ {
+ for ( var i = 0; i < this.children.length; i++ )
+ {
+ files = files.concat(this.children[i].getData(index, true));
+ }
+ }
+
+ return files;
+ }
+
+ this.getList = function(index, summary)
+ {
+ var list;
+
+ if
+ (
+ this.attributes[index] != null &&
+ this.attributes[index][currentDataset] != null
+ )
+ {
+ list = this.attributes[index][currentDataset];
+ }
+ else
+ {
+ list = new Array();
+ }
+
+ if ( summary )
+ {
+ for ( var i = 0; i < this.children.length; i++ )
+ {
+ list = list.concat(this.children[i].getList(index, true));
+ }
+ }
+
+ return list;
+ }
+
+ this.getParent = function()
+ {
+ // returns parent, accounting for collapsing or 0 if doesn't exist
+
+ var parent = this.parent;
+
+ while ( parent != 0 && parent.getCollapse() )
+ {
+ parent = parent.parent;
+ }
+
+ return parent;
+ }
+
+ this.getPercentage = function()
+ {
+ return getPercentage(this.magnitude / selectedNode.magnitude);
+ }
+
+ this.getUnclassifiedPercentage = function()
+ {
+ var lastChild = this.children[this.children.length - 1];
+
+ return getPercentage
+ (
+ (
+ this.baseMagnitude +
+ this.magnitude -
+ lastChild.magnitude -
+ lastChild.baseMagnitude
+ ) / this.magnitude
+ ) + '%';
+ }
+
+ this.getUnclassifiedText = function()
+ {
+ return '[unassigned '+ this.name + ']';
+ }
+
+ this.getUncollapsed = function()
+ {
+ // recurse through collapsed children until uncollapsed node is found
+
+ if ( this.getCollapse() )
+ {
+ return this.children[0].getUncollapsed();
+ }
+ else
+ {
+ return this;
+ }
+ }
+
+ this.hasChildren = function()
+ {
+ return this.children.length && this.depth < maxAbsoluteDepth && this.magnitude;
+ }
+
+ this.hasParent = function(parent)
+ {
+ if ( this.parent )
+ {
+ if ( this.parent == parent )
+ {
+ return true;
+ }
+ else
+ {
+ return this.parent.hasParent(parent);
+ }
+ }
+ else
+ {
+ return false;
+ }
+ }
+
+ this.maxVisibleDepth = function(maxDepth)
+ {
+ var childInnerRadius;
+ var depth = this.getDepth() - selectedNode.getDepth() + 1;
+ var currentMaxDepth = depth;
+
+ if ( this.hasChildren() && depth < maxDepth)
+ {
+ var lastChild = this.children[this.children.length - 1];
+
+ if ( this.name == 'Pseudomonadaceae' )
+ {
+ var x = 3;
+ }
+
+ if
+ (
+ lastChild.baseMagnitude + lastChild.magnitude <
+ this.baseMagnitude + this.magnitude
+ )
+ {
+ currentMaxDepth++;
+ }
+
+ if ( compress )
+ {
+ childInnerRadius = compressedRadii[depth - 1];
+ }
+ else
+ {
+ childInnerRadius = (depth) / maxDepth;
+ }
+
+ for ( var i = 0; i < this.children.length; i++ )
+ {
+ if
+ (//true ||
+ this.children[i].magnitude *
+ angleFactor *
+ (childInnerRadius + 1) *
+ gRadius >=
+ minWidth()
+ )
+ {
+ var childMaxDepth = this.children[i].maxVisibleDepth(maxDepth);
+
+ if ( childMaxDepth > currentMaxDepth )
+ {
+ currentMaxDepth = childMaxDepth;
+ }
+ }
+ }
+ }
+
+ return currentMaxDepth;
+ }
+
+ this.resetLabelWidth = function()
+ {
+ var nameWidthOld = this.nameWidth;
+
+ if ( ! this.radial )//&& fontSize != fontSizeLast )
+ {
+ var dim = context.measureText(this.name);
+ this.nameWidth = dim.width;
+ }
+
+ if ( fontSize != fontSizeLast && this.labelWidth.end == nameWidthOld * labelWidthFudge )
+ {
+ // font size changed; adjust start of tween to match
+
+ this.labelWidth.start = this.nameWidth * labelWidthFudge;
+ }
+ else
+ {
+ this.labelWidth.start = this.labelWidth.current();
+ }
+
+ this.labelWidth.end = this.nameWidth * labelWidthFudge;
+ }
+
+ this.restrictLabelWidth = function(width)
+ {
+ if ( width < this.labelWidth.end )
+ {
+ this.labelWidth.end = width;
+ }
+ }
+
+ this.search = function()
+ {
+ this.isSearchResult = false;
+ this.searchResults = 0;
+
+ if
+ (
+ ! this.getCollapse() &&
+ search.value != '' &&
+ this.name.toLowerCase().indexOf(search.value.toLowerCase()) != -1
+ )
+ {
+ this.isSearchResult = true;
+ this.searchResults = 1;
+ nSearchResults++;
+ }
+
+ for ( var i = 0; i < this.children.length; i++ )
+ {
+ this.searchResults += this.children[i].search();
+ }
+
+ return this.searchResults;
+ }
+
+ this.searchResultChildren = function()
+ {
+ if ( this.isSearchResult )
+ {
+ return this.searchResults - 1;
+ }
+ else
+ {
+ return this.searchResults;
+ }
+ }
+
+ this.setDepth = function(depth, depthCollapsed)
+ {
+ this.depth = depth;
+ this.depthCollapsed = depthCollapsed;
+
+ if
+ (
+ this.children.length == 1 &&
+// this.magnitude > 0 &&
+ this.children[0].magnitude == this.magnitude &&
+ ( head.children.length > 1 || this.children[0].children.length )
+ )
+ {
+ this.collapse = true;
+ }
+ else
+ {
+ this.collapse = false;
+ depthCollapsed++;
+ }
+
+ for ( var i = 0; i < this.children.length; i++ )
+ {
+ this.children[i].setDepth(depth + 1, depthCollapsed);
+ }
+ }
+
+ this.setHighlightStyle = function()
+ {
+ context.lineWidth = highlightLineWidth;
+
+ if ( this.hasChildren() || this != focusNode || this != highlightedNode )
+ {
+ context.strokeStyle = 'black';
+ context.fillStyle = "rgba(255, 255, 255, .3)";
+ }
+ else
+ {
+ context.strokeStyle = 'rgb(90,90,90)';
+ context.fillStyle = "rgba(155, 155, 155, .3)";
+ }
+ }
+
+ this.setLabelWidth = function(node)
+ {
+ if ( ! shorten || this.radial )
+ {
+ return; // don't need to set width
+ }
+
+ if ( node.hide )
+ {
+ alert('wtf');
+ return;
+ }
+
+ var angle = (this.angleStart.end + this.angleEnd.end) / 2;
+ var a; // angle difference
+
+ if ( node == selectedNode )
+ {
+ a = Math.abs(angle - node.angleOther);
+ }
+ else
+ {
+ a = Math.abs(angle - (node.angleStart.end + node.angleEnd.end) / 2);
+ }
+
+ if ( a == 0 )
+ {
+ return;
+ }
+
+ if ( a > Math.PI )
+ {
+ a = 2 * Math.PI - a;
+ }
+
+ if ( node.radial || node == selectedNode )
+ {
+ var nodeLabelRadius;
+
+ if ( node == selectedNode )
+ {
+ // radial 'other' label
+
+ nodeLabelRadius = (node.children[0].radiusInner.end + 1) / 2;
+ }
+ else
+ {
+ nodeLabelRadius = (node.radiusInner.end + 1) / 2;
+ }
+
+ if ( a < Math.PI / 2 )
+ {
+ var r = this.labelRadius.end * gRadius + .5 * fontSize
+ var hypotenuse = r / Math.cos(a);
+ var opposite = r * Math.tan(a);
+ var fontRadius = .8 * fontSize;
+
+ if
+ (
+ nodeLabelRadius * gRadius < hypotenuse &&
+ this.labelWidth.end / 2 + fontRadius > opposite
+ )
+ {
+ this.labelWidth.end = 2 * (opposite - fontRadius);
+ }
+ }
+ }
+ else if
+ (
+ this.labelRadius.end == node.labelRadius.end &&
+ a < Math.PI / 4
+ )
+ {
+ // same radius with small angle; use circumferential approximation
+
+ var dist = a * this.labelRadius.end * gRadius - fontSize * (1 - a * 4 / Math.PI) * 1.3;
+
+ if ( this.labelWidth.end < dist )
+ {
+ node.restrictLabelWidth((dist - this.labelWidth.end / 2) * 2);
+ }
+ else if ( node.labelWidth.end < dist )
+ {
+ this.restrictLabelWidth((dist - node.labelWidth.end / 2) * 2);
+ }
+ else
+ {
+ // both labels reach halfway point; restrict both
+
+ this.labelWidth.end = dist;
+ node.labelWidth.end = dist
+ }
+ }
+ else
+ {
+ var r1 = this.labelRadius.end * gRadius;
+ var r2 = node.labelRadius.end * gRadius;
+
+ // first adjust the radii to account for the height of the font by shifting them
+ // toward each other
+ //
+ var fontFudge = .35 * fontSize;
+ //
+ if ( this.labelRadius.end < node.labelRadius.end )
+ {
+ r1 += fontFudge;
+ r2 -= fontFudge;
+ }
+ else if ( this.labelRadius.end > node.labelRadius.end )
+ {
+ r1 -= fontFudge;
+ r2 += fontFudge;
+ }
+ else
+ {
+ r1 -= fontFudge;
+ r2 -= fontFudge;
+ }
+
+ var r1s = r1 * r1;
+ var r2s = r2 * r2;
+
+ // distance between the centers of the two labels
+ //
+ var dist = Math.sqrt(r1s + r2s - 2 * r1 * r2 * Math.cos(a));
+
+ // angle at our label center between our radius and the line to the other label center
+ //
+ var b = Math.acos((r1s + dist * dist - r2s) / (2 * r1 * dist));
+
+ // distance from our label center to the intersection of the two tangents
+ //
+ var l1 = Math.sin(a + b - Math.PI / 2) * dist / Math.sin(Math.PI - a);
+
+ // distance from other label center the the intersection of the two tangents
+ //
+ var l2 = Math.sin(Math.PI / 2 - b) * dist / Math.sin(Math.PI - a);
+
+ l1 = Math.abs(l1) - .4 * fontSize;
+ l2 = Math.abs(l2) - .4 * fontSize;
+/*
+ // amount to shorten the distances because of the height of the font
+ //
+ var l3 = 0;
+ var fontRadius = fontSize * .55;
+ //
+ if ( l1 < 0 || l2 < 0 )
+ {
+ var l4 = fontRadius / Math.tan(a);
+ l1 = Math.abs(l1);
+ l2 = Math.abs(l2);
+
+ l1 -= l4;
+ l2 -= l4;
+ }
+ else
+ {
+ var c = Math.PI - a;
+
+ l3 = fontRadius * Math.tan(c / 2);
+ }
+*/
+ if ( this.labelWidth.end / 2 > l1 && node.labelWidth.end / 2 > l2 )
+ {
+ // shorten the farthest one from the intersection
+
+ if ( l1 > l2 )
+ {
+ this.restrictLabelWidth(2 * (l1));// - l3 - fontRadius));
+ }
+ else
+ {
+ node.restrictLabelWidth(2 * (l2));// - l3 - fontRadius));
+ }
+ }/*
+ else if ( this.labelWidth.end / 2 > l1 + l3 && node.labelWidth.end / 2 > l2 - l3 )
+ {
+ node.restrictLabelWidth(2 * (l2 - l3));
+ }
+ else if ( this.labelWidth.end / 2 > l1 - l3 && node.labelWidth.end / 2 > l2 + l3 )
+ {
+ this.restrictLabelWidth(2 * (l1 - l3));
+ }*/
+ }
+ }
+
+ this.setMagnitudes = function(baseMagnitude)
+ {
+ this.magnitude = this.getMagnitude();
+ this.baseMagnitude = baseMagnitude;
+
+ for ( var i = 0; i < this.children.length; i++ )
+ {
+ this.children[i].setMagnitudes(baseMagnitude);
+ baseMagnitude += this.children[i].magnitude;
+ }
+
+ this.maxChildMagnitude = baseMagnitude;
+ }
+
+ this.setMaxDepths = function()
+ {
+ this.maxDepth = this.depth;
+ this.maxDepthCollapsed = this.depthCollapsed;
+
+ for ( i in this.children )
+ {
+ var child = this.children[i];
+
+ child.setMaxDepths();
+
+ if ( child.maxDepth > this.maxDepth )
+ {
+ this.maxDepth = child.maxDepth;
+ }
+
+ if
+ (
+ child.maxDepthCollapsed > this.maxDepthCollapsed &&
+ (child.depth <= maxAbsoluteDepth || maxAbsoluteDepth == 0)
+ )
+ {
+ this.maxDepthCollapsed = child.maxDepthCollapsed;
+ }
+ }
+ }
+
+ this.setTargetLabelRadius = function()
+ {
+ var depth = this.getDepth() - selectedNode.getDepth() + 1;
+ var index = depth - 2;
+ var labelOffset = labelOffsets[index];
+
+ if ( this.radial )
+ {
+ //this.labelRadius.setTarget((this.radiusInner.end + 1) / 2);
+ var max =
+ depth == maxDisplayDepth ?
+ 1 :
+ compressedRadii[index + 1];
+
+ this.labelRadius.setTarget((compressedRadii[index] + max) / 2);
+ }
+ else
+ {
+ var radiusCenter;
+ var width;
+
+ if ( compress )
+ {
+ if ( nLabelOffsets[index] > 1 )
+ {
+ this.labelRadius.setTarget
+ (
+ lerp
+ (
+ labelOffset + .75,
+ 0,
+ nLabelOffsets[index] + .5,
+ compressedRadii[index],
+ compressedRadii[index + 1]
+ )
+ );
+ }
+ else
+ {
+ this.labelRadius.setTarget((compressedRadii[index] + compressedRadii[index + 1]) / 2);
+ }
+ }
+ else
+ {
+ radiusCenter =
+ nodeRadius * (depth - 1) +
+ nodeRadius / 2;
+ width = nodeRadius;
+
+ this.labelRadius.setTarget
+ (
+ radiusCenter + width * ((labelOffset + 1) / (nLabelOffsets[index] + 1) - .5)
+ );
+ }
+ }
+
+ if ( ! this.hide && ! this.keyed && nLabelOffsets[index] )
+ {
+ // check last and first labels in each track for overlap
+
+ for ( var i = 0; i < maxDisplayDepth - 1; i++ )
+ {
+ for ( var j = 0; j <= nLabelOffsets[i]; j++ )
+ {
+ var last = labelLastNodes[i][j];
+ var first = labelFirstNodes[i][j];
+
+ if ( last )
+ {
+ if ( j == nLabelOffsets[i] )
+ {
+ // last is radial
+ this.setLabelWidth(last);
+ }
+ else
+ {
+ last.setLabelWidth(this);
+ }
+ }
+
+ if ( first )
+ {
+ if ( j == nLabelOffsets[i] )
+ {
+ this.setLabelWidth(first);
+ }
+ else
+ {
+ first.setLabelWidth(this);
+ }
+ }
+ }
+ }
+
+ if ( selectedNode.canDisplayLabelOther )
+ {
+ this.setLabelWidth(selectedNode); // in case there is an 'other' label
+ }
+
+ if ( this.radial )
+ {
+ // use the last 'track' of this depth for radial
+
+ labelLastNodes[index][nLabelOffsets[index]] = this;
+
+ if ( labelFirstNodes[index][nLabelOffsets[index]] == 0 )
+ {
+ labelFirstNodes[index][nLabelOffsets[index]] = this;
+ }
+ }
+ else
+ {
+ labelLastNodes[index][labelOffset] = this;
+
+ // update offset
+
+ labelOffsets[index] += 1;
+
+ if ( labelOffsets[index] > nLabelOffsets[index] )
+ {
+ labelOffsets[index] -= nLabelOffsets[index];
+
+ if ( !(nLabelOffsets[index] & 1) )
+ {
+ labelOffsets[index]--;
+ }
+ }
+ else if ( labelOffsets[index] == nLabelOffsets[index] )
+ {
+ labelOffsets[index] -= nLabelOffsets[index];
+
+ if ( false && !(nLabelOffsets[index] & 1) )
+ {
+ labelOffsets[index]++;
+ }
+ }
+
+ if ( labelFirstNodes[index][labelOffset] == 0 )
+ {
+ labelFirstNodes[index][labelOffset] = this;
+ }
+ }
+ }
+ else if ( this.hide )
+ {
+ this.labelWidth.end = 0;
+ }
+ }
+
+ this.setTargets = function()
+ {
+ if ( this == selectedNode )
+ {
+ this.setTargetsSelected
+ (
+ 0,
+ 1,
+ lightnessBase,
+ false,
+ false
+ );
+ return;
+ }
+
+ var depthRelative = this.getDepth() - selectedNode.getDepth();
+
+ var parentOfSelected = selectedNode.hasParent(this);
+/* (
+// ! this.getCollapse() &&
+ this.baseMagnitude <= selectedNode.baseMagnitude &&
+ this.baseMagnitude + this.magnitude >=
+ selectedNode.baseMagnitude + selectedNode.magnitude
+ );
+*/
+ if ( parentOfSelected )
+ {
+ this.resetLabelWidth();
+ }
+ else
+ {
+ //context.font = fontNormal;
+ var dim = context.measureText(this.name);
+ this.nameWidth = dim.width;
+ //this.labelWidth.setTarget(this.labelWidth.end);
+ this.labelWidth.setTarget(0);
+ }
+
+ // set angles
+ //
+ if ( this.baseMagnitude <= selectedNode.baseMagnitude )
+ {
+ this.angleStart.setTarget(0);
+ }
+ else
+ {
+ this.angleStart.setTarget(Math.PI * 2);
+ }
+ //
+ if
+ (
+ parentOfSelected ||
+ this.baseMagnitude + this.magnitude >=
+ selectedNode.baseMagnitude + selectedNode.magnitude
+ )
+ {
+ this.angleEnd.setTarget(Math.PI * 2);
+ }
+ else
+ {
+ this.angleEnd.setTarget(0);
+ }
+
+ // children
+ //
+ for ( var i = 0; i < this.children.length; i++ )
+ {
+ this.children[i].setTargets();
+ }
+
+ if ( this.getDepth() <= selectedNode.getDepth() )
+ {
+ // collapse in
+
+ this.radiusInner.setTarget(0);
+
+ if ( parentOfSelected )
+ {
+ this.labelRadius.setTarget
+ (
+ (depthRelative) *
+ historySpacingFactor * fontSize / gRadius
+ );
+ //this.scale.setTarget(1 - (selectedNode.getDepth() - this.getDepth()) / 18); // TEMP
+ }
+ else
+ {
+ this.labelRadius.setTarget(0);
+ //this.scale.setTarget(1); // TEMP
+ }
+ }
+ else if ( depthRelative + 1 > maxDisplayDepth )
+ {
+ // collapse out
+
+ this.radiusInner.setTarget(1);
+ this.labelRadius.setTarget(1);
+ //this.scale.setTarget(1); // TEMP
+ }
+ else
+ {
+ // don't collapse
+
+ if ( compress )
+ {
+ this.radiusInner.setTarget(compressedRadii[depthRelative - 1]);
+ }
+ else
+ {
+ this.radiusInner.setTarget(nodeRadius * (depthRelative));
+ }
+
+ //this.scale.setTarget(1); // TEMP
+
+ if ( this == selectedNode )
+ {
+ this.labelRadius.setTarget(0);
+ }
+ else
+ {
+ if ( compress )
+ {
+ this.labelRadius.setTarget
+ (
+ (compressedRadii[depthRelative - 1] + compressedRadii[depthRelative]) / 2
+ );
+ }
+ else
+ {
+ this.labelRadius.setTarget(nodeRadius * (depthRelative) + nodeRadius / 2);
+ }
+ }
+ }
+
+// this.r.start = this.r.end;
+// this.g.start = this.g.end;
+// this.b.start = this.b.end;
+
+ this.r.setTarget(255);
+ this.g.setTarget(255);
+ this.b.setTarget(255);
+
+ this.alphaLine.setTarget(0);
+ this.alphaArc.setTarget(0);
+ this.alphaWedge.setTarget(0);
+ this.alphaPattern.setTarget(0);
+ this.alphaOther.setTarget(0);
+
+ if ( parentOfSelected && ! this.getCollapse() )
+ {
+ var alpha =
+ (
+ 1 -
+ (selectedNode.getDepth() - this.getDepth()) /
+ (Math.floor((compress ? compressedRadii[0] : nodeRadius) * gRadius / (historySpacingFactor * fontSize) - .5) + 1)
+ );
+
+ if ( alpha < 0 )
+ {
+ alpha = 0;
+ }
+
+ this.alphaLabel.setTarget(alpha);
+ this.radial = false;
+ }
+ else
+ {
+ this.alphaLabel.setTarget(0);
+ }
+
+ this.hideAlonePrev = this.hideAlone;
+ this.hidePrev = this.hide;
+
+ if ( parentOfSelected )
+ {
+ this.hideAlone = false;
+ this.hide = false;
+ }
+
+ if ( this.getParent() == selectedNode.getParent() )
+ {
+ this.hiddenEnd = null;
+ }
+
+ this.radialPrev = this.radial;
+ }
+
+ this.setTargetsSelected = function(hueMin, hueMax, lightness, hide, nextSiblingHidden)
+ {
+ var collapse = this.getCollapse();
+ var depth = this.getDepth() - selectedNode.getDepth() + 1;
+ var canDisplayChildLabels = false;
+ var lastChild;
+
+ if ( this.hasChildren() )//&& ! hide )
+ {
+ lastChild = this.children[this.children.length - 1];
+ this.hideAlone = true;
+ }
+ else
+ {
+ this.hideAlone = false;
+ }
+
+ // set child wedges
+ //
+ for ( var i = 0; i < this.children.length; i++ )
+ {
+ this.children[i].setTargetWedge();
+
+ if
+ (
+ ! this.children[i].hide &&
+ ( collapse || depth < maxDisplayDepth ) &&
+ this.depth < maxAbsoluteDepth
+ )
+ {
+ canDisplayChildLabels = true;
+ this.hideAlone = false;
+ }
+ }
+
+ if ( this == selectedNode || lastChild && lastChild.angleEnd.end < this.angleEnd.end - .01)
+ {
+ this.hideAlone = false;
+ }
+
+ if ( this.hideAlonePrev == undefined )
+ {
+ this.hideAlonePrev = this.hideAlone;
+ }
+
+ if ( this == selectedNode )
+ {
+ var otherArc =
+ angleFactor *
+ (
+ this.baseMagnitude + this.magnitude -
+ lastChild.baseMagnitude - lastChild.magnitude
+ );
+ this.canDisplayLabelOther =
+ otherArc *
+ (this.children[0].radiusInner.end + 1) * gRadius >=
+ minWidth();
+
+ this.keyUnclassified = false;
+
+ if ( this.canDisplayLabelOther )
+ {
+ this.angleOther = Math.PI * 2 - otherArc / 2;
+ }
+ else if ( otherArc > 0.0000000001 )
+ {
+ this.keyUnclassified = true;
+ keys++;
+ }
+
+ this.angleStart.setTarget(0);
+ this.angleEnd.setTarget(Math.PI * 2);
+ this.radiusInner.setTarget(0);
+ this.hidePrev = this.hide;
+ this.hide = false;
+ this.hideAlonePrev = this.hideAlone;
+ this.hideAlone = false;
+ this.keyed = false;
+ }
+
+ if ( hueMax - hueMin > 1 / 12 )
+ {
+ hueMax = hueMin + 1 / 12;
+ }
+
+ // set lightness
+ //
+ if ( ! ( hide || this.hideAlone ) )
+ {
+ if ( useHue() )
+ {
+ lightness = (lightnessBase + lightnessMax) / 2;
+ }
+ else
+ {
+ lightness = lightnessBase + (depth - 1) * lightnessFactor;
+
+ if ( lightness > lightnessMax )
+ {
+ lightness = lightnessMax;
+ }
+ }
+ }
+
+ if ( hide )
+ {
+ this.hide = true;
+ }
+
+ if ( this.hidePrev == undefined )
+ {
+ this.hidePrev = this.hide;
+ }
+
+ var hiddenStart = -1;
+ var hiddenHueNumer = 0;
+ var hiddenHueDenom = 0;
+ var i = 0;
+
+ if ( ! this.hide )
+ {
+ this.hiddenEnd = null;
+ }
+
+ while ( true )
+ {
+ if ( ! this.hideAlone && ! hide && ( i == this.children.length || ! this.children[i].hide ) )
+ {
+ // reached a non-hidden child or the end; set targets for
+ // previous group of hidden children (if any) using their
+ // average hue
+
+ if ( hiddenStart != -1 )
+ {
+ var hiddenHue = hiddenHueDenom ? hiddenHueNumer / hiddenHueDenom : hueMin;
+
+ for ( var j = hiddenStart; j < i; j++ )
+ {
+ this.children[j].setTargetsSelected
+ (
+ hiddenHue,
+ null,
+ lightness,
+ false,
+ j < i - 1
+ );
+
+ this.children[j].hiddenEnd = null;
+ }
+
+ this.children[hiddenStart].hiddenEnd = i - 1;
+ }
+ }
+
+ if ( i == this.children.length )
+ {
+ break;
+ }
+
+ var child = this.children[i];
+ var childHueMin;
+ var childHueMax;
+
+ if ( this.magnitude > 0 && ! this.hide && ! this.hideAlone )
+ {
+ if ( useHue() )
+ {
+ childHueMin = child.hues[currentDataset];
+ }
+ else if ( this == selectedNode )
+ {
+ var min = 0.0;
+ var max = 1.0;
+
+ if ( this.children.length > 6 )
+ {
+ childHueMin = lerp((1 - Math.pow(1 - i / this.children.length, 1.4)) * .95, 0, 1, min, max);
+ childHueMax = lerp((1 - Math.pow(1 - (i + .55) / this.children.length, 1.4)) * .95, 0, 1, min, max);
+ }
+ else
+ {
+ childHueMin = lerp(i / this.children.length, 0, 1, min, max);
+ childHueMax = lerp((i + .55) / this.children.length, 0, 1, min, max);
+ }
+ }
+ else
+ {
+ childHueMin = lerp
+ (
+ child.baseMagnitude,
+ this.baseMagnitude,
+ this.baseMagnitude + this.magnitude,
+ hueMin,
+ hueMax
+ );
+ childHueMax = lerp
+ (
+ child.baseMagnitude + child.magnitude * .99,
+ this.baseMagnitude,
+ this.baseMagnitude + this.magnitude,
+ hueMin,
+ hueMax
+ );
+ }
+ }
+ else
+ {
+ childHueMin = hueMin;
+ childHueMax = hueMax;
+ }
+
+ if ( ! this.hideAlone && ! hide && ! this.hide && child.hide )
+ {
+ if ( hiddenStart == -1 )
+ {
+ hiddenStart = i;
+ }
+
+ if ( useHue() )
+ {
+ hiddenHueNumer += childHueMin * child.magnitude;
+ hiddenHueDenom += child.magnitude;
+ }
+ else
+ {
+ hiddenHueNumer += childHueMin;
+ hiddenHueDenom++;
+ }
+ }
+ else
+ {
+ hiddenStart = -1;
+
+ this.children[i].setTargetsSelected
+ (
+ childHueMin,
+ childHueMax,
+ lightness,
+ hide || this.keyed || this.hideAlone || this.hide && ! collapse,
+ false
+ );
+ }
+
+ i++;
+ }
+
+ if ( this.hue && this.magnitude )
+ {
+ this.hue.setTarget(this.hues[currentDataset]);
+
+ if ( this.attributes[magnitudeIndex][lastDataset] == 0 )
+ {
+ this.hue.start = this.hue.end;
+ }
+ }
+
+ this.radialPrev = this.radial;
+
+ if ( this == selectedNode )
+ {
+ this.resetLabelWidth();
+ this.labelWidth.setTarget(this.nameWidth * labelWidthFudge);
+ this.alphaWedge.setTarget(0);
+ this.alphaLabel.setTarget(1);
+ this.alphaOther.setTarget(1);
+ this.alphaArc.setTarget(0);
+ this.alphaLine.setTarget(0);
+ this.alphaPattern.setTarget(0);
+ this.r.setTarget(255);
+ this.g.setTarget(255);
+ this.b.setTarget(255);
+ this.radial = false;
+ this.labelRadius.setTarget(0);
+ }
+ else
+ {
+ var rgb = hslToRgb
+ (
+ hueMin,
+ saturation,
+ lightness
+ );
+
+ this.r.setTarget(rgb.r);
+ this.g.setTarget(rgb.g);
+ this.b.setTarget(rgb.b);
+ this.alphaOther.setTarget(0);
+
+ this.alphaWedge.setTarget(1);
+
+ if ( this.hide || this.hideAlone )
+ {
+ this.alphaPattern.setTarget(1);
+ }
+ else
+ {
+ this.alphaPattern.setTarget(0);
+ }
+
+ // set radial
+ //
+ if ( ! ( hide || this.hide ) )//&& ! this.keyed )
+ {
+ if ( this.hideAlone )
+ {
+ this.radial = true;
+ }
+ else if ( false && canDisplayChildLabels )
+ {
+ this.radial = false;
+ }
+ else
+ {
+ this.radial = true;
+
+ if ( this.hasChildren() && depth < maxDisplayDepth )
+ {
+ var lastChild = this.children[this.children.length - 1];
+
+ if
+ (
+ lastChild.angleEnd.end == this.angleEnd.end ||
+ (
+ (this.angleStart.end + this.angleEnd.end) / 2 -
+ lastChild.angleEnd.end
+ ) * (this.radiusInner.end + 1) * gRadius * 2 <
+ minWidth()
+ )
+ {
+ this.radial = false;
+ }
+ }
+ }
+ }
+
+ // set alphaLabel
+ //
+ if
+ (
+ collapse ||
+ hide ||
+ this.hide ||
+ this.keyed ||
+ depth > maxDisplayDepth ||
+ ! this.canDisplayDepth()
+ )
+ {
+ this.alphaLabel.setTarget(0);
+ }
+ else
+ {
+ if
+ (
+ (this.radial || nLabelOffsets[depth - 2])
+ )
+ {
+ this.alphaLabel.setTarget(1);
+ }
+ else
+ {
+ this.alphaLabel.setTarget(0);
+
+ if ( this.radialPrev )
+ {
+ this.alphaLabel.start = 0;
+ }
+ }
+ }
+
+ // set alphaArc
+ //
+ if
+ (
+ collapse ||
+ hide ||
+ depth > maxDisplayDepth ||
+ ! this.canDisplayDepth()
+ )
+ {
+ this.alphaArc.setTarget(0);
+ }
+ else
+ {
+ this.alphaArc.setTarget(1);
+ }
+
+ // set alphaLine
+ //
+ if
+ (
+ hide ||
+ this.hide && nextSiblingHidden ||
+ depth > maxDisplayDepth ||
+ ! this.canDisplayDepth()
+ )
+ {
+ this.alphaLine.setTarget(0);
+ }
+ else
+ {
+ this.alphaLine.setTarget(1);
+ }
+
+ //if ( ! this.radial )
+ {
+ this.resetLabelWidth();
+ }
+
+ // set labelRadius target
+ //
+ if ( collapse )
+ {
+ this.labelRadius.setTarget(this.radiusInner.end);
+ }
+ else
+ {
+ if ( depth > maxDisplayDepth || ! this.canDisplayDepth() )
+ {
+ this.labelRadius.setTarget(1);
+ }
+ else
+ {
+ this.setTargetLabelRadius();
+ }
+ }
+ }
+ }
+
+ this.setTargetWedge = function()
+ {
+ var depth = this.getDepth() - selectedNode.getDepth() + 1;
+
+ // set angles
+ //
+ var baseMagnitudeRelative = this.baseMagnitude - selectedNode.baseMagnitude;
+ //
+ this.angleStart.setTarget(baseMagnitudeRelative * angleFactor);
+ this.angleEnd.setTarget((baseMagnitudeRelative + this.magnitude) * angleFactor);
+
+ // set radiusInner
+ //
+ if ( depth > maxDisplayDepth || ! this.canDisplayDepth() )
+ {
+ this.radiusInner.setTarget(1);
+ }
+ else
+ {
+ if ( compress )
+ {
+ this.radiusInner.setTarget(compressedRadii[depth - 2]);
+ }
+ else
+ {
+ this.radiusInner.setTarget(nodeRadius * (depth - 1));
+ }
+ }
+
+ if ( this.hide != undefined )
+ {
+ this.hidePrev = this.hide;
+ }
+
+ if ( this.hideAlone != undefined )
+ {
+ this.hideAlonePrev = this.hideAlone;
+ }
+
+ // set hide
+ //
+ if
+ (
+ (this.angleEnd.end - this.angleStart.end) *
+ (this.radiusInner.end * gRadius + gRadius) <
+ minWidth()
+ )
+ {
+ if ( depth == 2 && ! this.getCollapse() && this.depth <= maxAbsoluteDepth )
+ {
+ this.keyed = true;
+ keys++;
+ this.hide = false;
+
+ var percentage = this.getPercentage();
+ this.keyLabel = this.name + ' ' + percentage + '%';
+ var dim = context.measureText(this.keyLabel);
+ this.keyNameWidth = dim.width;
+ }
+ else
+ {
+ this.keyed = false;
+ this.hide = depth > 2;
+ }
+ }
+ else
+ {
+ this.keyed = false;
+ this.hide = false;
+ }
+ }
+
+ this.shortenLabel = function()
+ {
+ var label = this.name;
+
+ var labelWidth = this.nameWidth;
+ var maxWidth = this.labelWidth.current();
+ var minEndLength = 0;
+
+ if ( labelWidth > maxWidth && label.length > minEndLength * 2 )
+ {
+ var endLength =
+ Math.floor((label.length - 1) * maxWidth / labelWidth / 2);
+
+ if ( endLength < minEndLength )
+ {
+ endLength = minEndLength;
+ }
+
+ return (
+ label.substring(0, endLength) +
+ '...' +
+ label.substring(label.length - endLength));
+ }
+ else
+ {
+ return label;
+ }
+ }
+
+/* this.shouldAddSearchResultsString = function()
+ {
+ if ( this.isSearchResult )
+ {
+ return this.searchResults > 1;
+ }
+ else
+ {
+ return this.searchResults > 0;
+ }
+ }
+*/
+ this.sort = function()
+ {
+ this.children.sort(function(a, b){return b.getMagnitude() - a.getMagnitude()});
+
+ for (var i = 0; i < this.children.length; i++)
+ {
+ this.children[i].sort();
+ }
+ }
+}
+
+var options;
+
+function addOptionElement(position, innerHTML, title)
+{
+ var div = document.createElement("div");
+// div.style.position = 'absolute';
+// div.style.top = position + 'px';
+ div.innerHTML = innerHTML;
+// div.style.display = 'block';
+ div.style.padding = '2px';
+
+ if ( title )
+ {
+ div.title = title;
+ }
+
+ options.appendChild(div);
+ var height = 0;//div.clientHeight;
+ return position + height;
+}
+
+function addOptionElements(hueName, hueDefault)
+{
+ options = document.createElement('div');
+ options.style.position = 'absolute';
+ options.style.top = '0px';
+ options.addEventListener('mousedown', function(e) {mouseClick(e)}, false);
+// options.onmouseup = function(e) {mouseUp(e)}
+ document.body.appendChild(options);
+
+ document.body.style.font = '11px sans-serif';
+ var position = 5;
+
+ details = document.createElement('div');
+ details.style.position = 'absolute';
+ details.style.top = '1%';
+ details.style.right = '2%';
+ details.style.textAlign = 'right';
+ document.body.insertBefore(details, canvas);
+// <div id="details" style="position:absolute;top:1%;right:2%;text-align:right;">
+
+ details.innerHTML = '\
+<span id="detailsName" style="font-weight:bold"></span> \
+<input type="button" id="detailsExpand" onclick="expand(focusNode);"\
+value="↔" title="Expand this wedge to become the new focus of the chart"/><br/>\
+<div id="detailsInfo" style="float:right"></div>';
+
+ keyControl = document.createElement('input');
+ keyControl.type = 'button';
+ keyControl.value = showKeys ? 'x' : '…';
+ keyControl.style.position = '';
+ keyControl.style.position = 'fixed';
+ keyControl.style.visibility = 'hidden';
+
+ document.body.insertBefore(keyControl, canvas);
+
+ var logoElement = document.getElementById('logo');
+
+ if ( logoElement )
+ {
+ logoImage = logoElement.src;
+ }
+ else
+ {
+ logoImage = 'http://krona.sourceforge.net/img/logo.png';
+ }
+
+// document.getElementById('options').style.fontSize = '9pt';
+ position = addOptionElement
+ (
+ position,
+'<a style="margin:2px" target="_blank" href="http://krona.sourceforge.net"><div style="display:inline-block;vertical-align:middle;background-color:#EEEEEE;border:1px solid gray;padding:2px;font-size:18px"><img style="vertical-align:middle;" src="' + logoImage + '"/><span style="vertical-align:middle;color:#555555">Krona</span></div></a><input type="button" id="back" value="←" title="Go back (Shortcut: ←)"/>\
+<input type="button" id="forward" value="→" title="Go forward (Shortcut: →)"/> \
+ Search: <input type="text" id="search"/>\
+<input id="searchClear" type="button" value="x" onclick="clearSearch()"/> \
+<span id="searchResults"></span>'
+ );
+
+ if ( datasets > 1 )
+ {
+ var size = datasets < datasetSelectSize ? datasets : datasetSelectSize;
+
+ var select =
+ '<table style="border-collapse:collapse;padding:0px"><tr><td style="padding:0px">' +
+ '<select id="datasets" style="min-width:100px" size="' + size + '" onchange="onDatasetChange()">';
+
+ for ( var i = 0; i < datasetNames.length; i++ )
+ {
+ select += '<option>' + datasetNames[i] + '</option>';
+ }
+
+ select +=
+ '</select></td><td style="vertical-align:top;padding:1px;">' +
+ '<input style="display:block" title="Previous dataset (Shortcut: ↑)" id="prevDataset" type="button" value="↑" onclick="prevDataset()" disabled="true"/>' +
+ '<input title="Next dataset (Shortcut: ↓)" id="nextDataset" type="button" value="↓" onclick="nextDataset()"/><br/></td>' +
+ '<td style="padding-top:1px;vertical-align:top"><input title="Switch to the last dataset that was viewed (Shortcut: TAB)" id="lastDataset" type="button" style="font:11px Times new roman" value="last" onclick="selectLastDataset()"/></td></tr></table>';
+
+ position = addOptionElement(position + 5, select);
+
+ datasetDropDown = document.getElementById('datasets');
+ datasetButtonLast = document.getElementById('lastDataset');
+ datasetButtonPrev = document.getElementById('prevDataset');
+ datasetButtonNext = document.getElementById('nextDataset');
+
+ position += datasetDropDown.clientHeight;
+ }
+
+ position = addOptionElement
+ (
+ position + 5,
+'<input type="button" id="maxAbsoluteDepthDecrease" value="-"/>\
+<span id="maxAbsoluteDepth"></span>\
+ <input type="button" id="maxAbsoluteDepthIncrease" value="+"/> Max depth',
+'Maximum depth to display, counted from the top level \
+and including collapsed wedges.'
+ );
+
+ position = addOptionElement
+ (
+ position,
+'<input type="button" id="fontSizeDecrease" value="-"/>\
+<span id="fontSize"></span>\
+ <input type="button" id="fontSizeIncrease" value="+"/> Font size'
+ );
+
+ position = addOptionElement
+ (
+ position,
+'<input type="button" id="radiusDecrease" value="-"/>\
+<input type="button" id="radiusIncrease" value="+"/> Chart size'
+ );
+
+ if ( hueName )
+ {
+ hueDisplayName = attributes[attributeIndex(hueName)].displayName;
+
+ position = addOptionElement
+ (
+ position + 5,
+ '<input type="checkbox" id="useHue" style="float:left" ' +
+ '/><div>Color by<br/>' + hueDisplayName +
+ '</div>'
+ );
+
+ useHueCheckBox = document.getElementById('useHue');
+ useHueCheckBox.checked = hueDefault;
+ useHueCheckBox.onclick = handleResize;
+ useHueCheckBox.onmousedown = suppressEvent;
+ }
+ /*
+ position = addOptionElement
+ (
+ position + 5,
+ ' <input type="checkbox" id="shorten" checked="checked" />Shorten labels</div>',
+ 'Prevent labels from overlapping by shortening them'
+ );
+
+ position = addOptionElement
+ (
+ position,
+ ' <input type="checkbox" id="compress" checked="checked" />Compress',
+ 'Compress wedges if needed to show the entire depth'
+ );
+ */
+ position = addOptionElement
+ (
+ position,
+ '<input type="checkbox" id="collapse" checked="checked" />Collapse',
+ 'Collapse wedges that are redundant (entirely composed of another wedge)'
+ );
+
+ position = addOptionElement
+ (
+ position + 5,
+ '<input type="button" id="snapshot" value="Snapshot"/>',
+'Render the current view as SVG (Scalable Vector Graphics), a publication-\
+quality format that can be printed and saved (see Help for browser compatibility)'
+ );
+
+ position = addOptionElement
+ (
+ position + 5,
+'<input type="button" id="linkButton" value="Link"/>\
+<input type="text" size="30" id="linkText"/>',
+'Show a link to this view that can be copied for bookmarking or sharing'
+ );
+
+ position = addOptionElement
+ (
+ position + 5,
+'<input type="button" id="help" value="?"\
+onclick="window.open(\'https://sourceforge.net/p/krona/wiki/Browsing%20Krona%20charts/\', \'help\')"/>',
+'Help'
+ );
+}
+
+function arrow(angleStart, angleEnd, radiusInner)
+{
+ if ( context.globalAlpha == 0 )
+ {
+ return;
+ }
+
+ var angleCenter = (angleStart + angleEnd) / 2;
+ var radiusArrowInner = radiusInner - gRadius / 10;//nodeRadius * gRadius;
+ var radiusArrowOuter = gRadius * 1.1;//(1 + nodeRadius);
+ var radiusArrowCenter = (radiusArrowInner + radiusArrowOuter) / 2;
+ var pointLength = (radiusArrowOuter - radiusArrowInner) / 5;
+
+ context.fillStyle = highlightFill;
+ context.lineWidth = highlightLineWidth;
+
+ // First, mask out the first half of the arrow. This will prevent the tips
+ // from superimposing if the arrow goes most of the way around the circle.
+ // Masking is done by setting the clipping region to the inverse of the
+ // half-arrow, which is defined by cutting the half-arrow out of a large
+ // rectangle
+ //
+ context.beginPath();
+ context.arc(0, 0, radiusInner, angleCenter, angleEnd, false);
+ context.lineTo
+ (
+ radiusArrowInner * Math.cos(angleEnd),
+ radiusArrowInner * Math.sin(angleEnd)
+ );
+ context.lineTo
+ (
+ radiusArrowCenter * Math.cos(angleEnd) - pointLength * Math.sin(angleEnd),
+ radiusArrowCenter * Math.sin(angleEnd) + pointLength * Math.cos(angleEnd)
+ );
+ context.lineTo
+ (
+ radiusArrowOuter * Math.cos(angleEnd),
+ radiusArrowOuter * Math.sin(angleEnd)
+ );
+ context.arc(0, 0, gRadius, angleEnd, angleCenter, true);
+ context.closePath();
+ context.moveTo(-imageWidth, -imageHeight);
+ context.lineTo(imageWidth, -imageHeight);
+ context.lineTo(imageWidth, imageHeight);
+ context.lineTo(-imageWidth, imageHeight);
+ context.closePath();
+ context.save();
+ context.clip();
+
+ // Next, draw the other half-arrow with the first half masked out
+ //
+ context.beginPath();
+ context.arc(0, 0, radiusInner, angleCenter, angleStart, true);
+ context.lineTo
+ (
+ radiusArrowInner * Math.cos(angleStart),
+ radiusArrowInner * Math.sin(angleStart)
+ );
+ context.lineTo
+ (
+ radiusArrowCenter * Math.cos(angleStart) + pointLength * Math.sin(angleStart),
+ radiusArrowCenter * Math.sin(angleStart) - pointLength * Math.cos(angleStart)
+ );
+ context.lineTo
+ (
+ radiusArrowOuter * Math.cos(angleStart),
+ radiusArrowOuter * Math.sin(angleStart)
+ );
+ context.arc(0, 0, gRadius, angleStart, angleCenter, false);
+ context.fill();
+ context.stroke();
+
+ // Finally, remove the clipping region and draw the first half-arrow. This
+ // half is extended slightly to fill the seam.
+ //
+ context.restore();
+ context.beginPath();
+ context.arc(0, 0, radiusInner, angleCenter - 2 / (2 * Math.PI * radiusInner), angleEnd, false);
+ context.lineTo
+ (
+ radiusArrowInner * Math.cos(angleEnd),
+ radiusArrowInner * Math.sin(angleEnd)
+ );
+ context.lineTo
+ (
+ radiusArrowCenter * Math.cos(angleEnd) - pointLength * Math.sin(angleEnd),
+ radiusArrowCenter * Math.sin(angleEnd) + pointLength * Math.cos(angleEnd)
+ );
+ context.lineTo
+ (
+ radiusArrowOuter * Math.cos(angleEnd),
+ radiusArrowOuter * Math.sin(angleEnd)
+ );
+ context.arc(0, 0, gRadius, angleEnd, angleCenter - 2 / (2 * Math.PI * gRadius), true);
+ context.fill();
+ context.stroke();
+}
+
+function attributeIndex(aname)
+{
+ for ( var i = 0 ; i < attributes.length; i++ )
+ {
+ if ( aname == attributes[i].name )
+ {
+ return i;
+ }
+ }
+
+ return null;
+}
+
+function checkHighlight()
+{
+ var lastHighlightedNode = highlightedNode;
+ var lastHighlightingHidden = highlightingHidden;
+
+ highlightedNode = selectedNode;
+ resetKeyOffset();
+
+ if ( progress == 1 )
+ {
+ selectedNode.checkHighlight();
+ if ( selectedNode.getParent() )
+ {
+ selectedNode.getParent().checkHighlightCenter();
+ }
+
+ focusNode.checkHighlightMap();
+ }
+
+ if ( highlightedNode != selectedNode )
+ {
+ if ( highlightedNode == focusNode )
+ {
+// canvas.style.display='none';
+// window.resizeBy(1,0);
+// canvas.style.cursor='ew-resize';
+// window.resizeBy(-1,0);
+// canvas.style.display='inline';
+ }
+ else
+ {
+// canvas.style.cursor='pointer';
+ }
+ }
+ else
+ {
+// canvas.style.cursor='auto';
+ }
+
+ if
+ (
+ (
+ true ||
+ highlightedNode != lastHighlightedNode ||
+ highlightingHidden != highlightingHiddenLast
+ ) &&
+ progress == 1
+ )
+ {
+ draw(); // TODO: handle in update()
+ }
+}
+
+function checkSelectedCollapse()
+{
+ var newNode = selectedNode;
+
+ while ( newNode.getCollapse() )
+ {
+ newNode = newNode.children[0];
+ }
+
+ if ( newNode.children.length == 0 )
+ {
+ newNode = newNode.getParent();
+ }
+
+ if ( newNode != selectedNode )
+ {
+ selectNode(newNode);
+ }
+}
+
+function clearSearch()
+{
+ if ( search.value != '' )
+ {
+ search.value = '';
+ onSearchChange();
+ }
+}
+
+function createSVG()
+{
+ svgNS = "http://www.w3.org/2000/svg";
+ var SVG = {};
+ SVG.xlinkns = "http://www.w3.org/1999/xlink";
+
+ var newSVG = document.createElementNS(svgNS, "svg:svg");
+
+ newSVG.setAttribute("id", "canvas");
+ // How big is the canvas in pixels
+ newSVG.setAttribute("width", '100%');
+ newSVG.setAttribute("height", '100%');
+ // Set the coordinates used by drawings in the canvas
+// newSVG.setAttribute("viewBox", "0 0 " + imageWidth + " " + imageHeight);
+ // Define the XLink namespace that SVG uses
+ newSVG.setAttributeNS
+ (
+ "http://www.w3.org/2000/xmlns/",
+ "xmlns:xlink",
+ SVG.xlinkns
+ );
+
+ return newSVG;
+}
+
+function degrees(radians)
+{
+ return radians * 180 / Math.PI;
+}
+
+function draw()
+{
+ tweenFrames++;
+ //resize();
+// context.fillRect(0, 0, imageWidth, imageHeight);
+ context.clearRect(0, 0, imageWidth, imageHeight);
+
+ context.font = fontNormal;
+ context.textBaseline = 'middle';
+
+ //context.strokeStyle = 'rgba(0, 0, 0, 0.3)';
+ context.translate(centerX, centerY);
+
+ resetKeyOffset();
+
+ head.draw(false, false); // draw pie slices
+ head.draw(true, false); // draw labels
+
+ var pathRoot = selectedNode;
+
+ if ( focusNode != 0 && focusNode != selectedNode )
+ {
+ context.globalAlpha = 1;
+ focusNode.drawHighlight(true);
+ pathRoot = focusNode;
+ }
+
+ if
+ (
+ highlightedNode &&
+ highlightedNode.getDepth() >= selectedNode.getDepth() &&
+ highlightedNode != focusNode
+ )
+ {
+ if
+ (
+ progress == 1 &&
+ highlightedNode != selectedNode &&
+ (
+ highlightedNode != focusNode ||
+ focusNode.children.length > 0
+ )
+ )
+ {
+ context.globalAlpha = 1;
+ highlightedNode.drawHighlight(true);
+ }
+
+ //pathRoot = highlightedNode;
+ }
+ else if
+ (
+ progress == 1 &&
+ highlightedNode.getDepth() < selectedNode.getDepth()
+ )
+ {
+ context.globalAlpha = 1;
+ highlightedNode.drawHighlightCenter();
+ }
+
+ if ( quickLook && false) // TEMP
+ {
+ context.globalAlpha = 1 - progress / 2;
+ selectedNode.drawHighlight(true);
+ }
+ else if ( progress < 1 )//&& zoomOut() )
+ {
+ if ( !zoomOut)//() )
+ {
+ context.globalAlpha = selectedNode.alphaLine.current();
+ selectedNode.drawHighlight(true);
+ }
+ else if ( selectedNodeLast )
+ {
+ context.globalAlpha = 1 - 4 * Math.pow(progress - .5, 2);
+ selectedNodeLast.drawHighlight(false);
+ }
+ }
+
+ drawDatasetName();
+
+ //drawHistory();
+
+ context.translate(-centerX, -centerY);
+ context.globalAlpha = 1;
+
+ mapRadius =
+ (imageHeight / 2 - details.clientHeight - details.offsetTop) /
+ (pathRoot.getDepth() - 1) * 3 / 4 / 2;
+
+ if ( mapRadius > maxMapRadius )
+ {
+ mapRadius = maxMapRadius;
+ }
+
+ mapBuffer = mapRadius / 2;
+
+ //context.font = fontNormal;
+ pathRoot.drawMap(pathRoot);
+
+ if ( hueDisplayName && useHue() )
+ {
+ drawLegend();
+ }
+}
+
+function drawBubble(angle, radius, width, radial, flip)
+{
+ var height = fontSize * 2;
+ var x;
+ var y;
+
+ width = width + fontSize;
+
+ if ( radial )
+ {
+ y = -fontSize;
+
+ if ( flip )
+ {
+ x = radius - width + fontSize / 2;
+ }
+ else
+ {
+ x = radius - fontSize / 2;
+ }
+ }
+ else
+ {
+ x = -width / 2;
+ y = -radius - fontSize;
+ }
+
+ if ( snapshotMode )
+ {
+ drawBubbleSVG(x + centerX, y + centerY, width, height, fontSize, angle);
+ }
+ else
+ {
+ drawBubbleCanvas(x, y, width, height, fontSize, angle);
+ }
+}
+
+function drawBubbleCanvas(x, y, width, height, radius, rotation)
+{
+ context.strokeStyle = 'black';
+ context.lineWidth = highlightLineWidth;
+ context.fillStyle = 'rgba(255, 255, 255, .75)';
+ context.rotate(rotation);
+ roundedRectangle(x, y, width, fontSize * 2, fontSize);
+ context.fill();
+ context.stroke();
+ context.rotate(-rotation);
+}
+
+function drawBubbleSVG(x, y, width, height, radius, rotation)
+{
+ svg +=
+ '<rect x="' + x + '" y="' + y +
+ '" width="' + width +
+ '" height="' + height +
+ '" rx="' + radius +
+ '" ry="' + radius +
+ '" fill="rgba(255, 255, 255, .75)' +
+ '" class="highlight" ' +
+ 'transform="rotate(' +
+ degrees(rotation) + ',' + centerX + ',' + centerY +
+ ')"/>';
+}
+
+function drawDatasetName()
+{
+ var alpha = datasetAlpha.current();
+
+ if ( alpha > 0 )
+ {
+ var radius = gRadius * compressedRadii[0] / -2;
+
+ if ( alpha > 1 )
+ {
+ alpha = 1;
+ }
+
+ context.globalAlpha = alpha;
+
+ drawBubble(0, -radius, datasetWidths[currentDataset], false, false);
+ drawText(datasetNames[currentDataset], 0, radius, 0, 'center', true);
+ }
+}
+
+function drawHistory()
+{
+ var alpha = 1;
+ context.textAlign = 'center';
+
+ for ( var i = 0; i < nodeHistoryPosition && alpha > 0; i++ )
+ {
+
+ context.globalAlpha = alpha - historyAlphaDelta * tweenFactor;
+ context.fillText
+ (
+ nodeHistory[nodeHistoryPosition - i - 1].name,
+ 0,
+ (i + tweenFactor) * historySpacingFactor * fontSize - 1
+ );
+
+ if ( alpha > 0 )
+ {
+ alpha -= historyAlphaDelta;
+ }
+ }
+
+ context.globalAlpha = 1;
+}
+
+function drawLegend()
+{
+ var left = imageWidth * .01;
+ var width = imageHeight * .0265;
+ var height = imageHeight * .15;
+ var top = imageHeight - fontSize * 3.5 - height;
+ var textLeft = left + width + fontSize / 2;
+
+ context.fillStyle = 'black';
+ context.textAlign = 'start';
+ context.font = fontNormal;
+// context.fillText(valueStartText, textLeft, top + height);
+// context.fillText(valueEndText, textLeft, top);
+ context.fillText(hueDisplayName, left, imageHeight - fontSize * 1.5);
+
+ var gradient = context.createLinearGradient(0, top + height, 0, top);
+
+ for ( var i = 0; i < hueStopPositions.length; i++ )
+ {
+ gradient.addColorStop(hueStopPositions[i], hueStopHsl[i]);
+
+ var textY = top + (1 - hueStopPositions[i]) * height;
+
+ if
+ (
+ i == 0 ||
+ i == hueStopPositions.length - 1 ||
+ textY > top + fontSize && textY < top + height - fontSize
+ )
+ {
+ context.fillText(hueStopText[i], textLeft, textY);
+ }
+ }
+
+ context.fillStyle = gradient;
+ context.fillRect(left, top, width, height);
+ context.lineWidth = thinLineWidth;
+ context.strokeRect(left, top, width, height);
+}
+
+function drawLegendSVG()
+{
+ var left = imageWidth * .01;
+ var width = imageHeight * .0265;
+ var height = imageHeight * .15;
+ var top = imageHeight - fontSize * 3.5 - height;
+ var textLeft = left + width + fontSize / 2;
+
+ var text = '';
+
+ text += svgText(hueDisplayName, left, imageHeight - fontSize * 1.5);
+
+ var svgtest = '<linearGradient id="gradient" x1="0%" y1="100%" x2="0%" y2="0%">';
+
+ for ( var i = 0; i < hueStopPositions.length; i++ )
+ {
+ svgtest +=
+ '<stop offset="' + round(hueStopPositions[i] * 100) +
+ '%" style="stop-color:' + hueStopHsl[i] + '"/>';
+
+ var textY = top + (1 - hueStopPositions[i]) * height;
+
+ if
+ (
+ i == 0 ||
+ i == hueStopPositions.length - 1 ||
+ textY > top + fontSize && textY < top + height - fontSize
+ )
+ {
+ text += svgText(hueStopText[i], textLeft, textY);
+ }
+ }
+
+ svgtest += '</linearGradient>';
+ //alert(svgtest);
+ svg += svgtest;
+ svg +=
+ '<rect style="fill:url(#gradient)" x="' + left + '" y="' + top +
+ '" width="' + width + '" height="' + height + '"/>';
+
+ svg += text;
+}
+
+function drawSearchHighlights(label, bubbleX, bubbleY, rotation, center)
+{
+ var index = -1;
+ var labelLength = label.length;
+
+ bubbleX -= fontSize / 4;
+
+ do
+ {
+ index = label.toLowerCase().indexOf(search.value.toLowerCase(), index + 1);
+
+ if ( index != -1 && index < labelLength )
+ {
+ var dim = context.measureText(label.substr(0, index));
+ var x = bubbleX + dim.width;
+
+ dim = context.measureText(label.substr(index, search.value.length));
+
+ var y = bubbleY - fontSize * 3 / 4;
+ var width = dim.width + fontSize / 2;
+ var height = fontSize * 3 / 2;
+ var radius = fontSize / 2;
+
+ if ( snapshotMode )
+ {
+ if ( center )
+ {
+ x += centerX;
+ y += centerY;
+ }
+
+ svg +=
+ '<rect x="' + x + '" y="' + y +
+ '" width="' + width +
+ '" height="' + height +
+ '" rx="' + radius +
+ '" ry="' + radius +
+ '" class="searchHighlight' +
+ '" transform="rotate(' +
+ degrees(rotation) + ',' + centerX + ',' + centerY +
+ ')"/>';
+ }
+ else
+ {
+ context.fillStyle = 'rgb(255, 255, 100)';
+ context.rotate(rotation);
+ roundedRectangle(x, y, width, height, radius);
+ context.fill();
+ context.rotate(-rotation);
+ }
+ }
+ }
+ while ( index != -1 && index < labelLength );
+}
+
+function drawText(text, x, y, angle, anchor, bold, color)
+{
+ if ( color == undefined )
+ {
+ color = 'black';
+ }
+
+ if ( snapshotMode )
+ {
+ svg +=
+ '<text x="' + (centerX + x) + '" y="' + (centerY + y) +
+ '" text-anchor="' + anchor + '" style="font-color:' + color + ';font-weight:' + (bold ? 'bold' : 'normal') +
+ '" transform="rotate(' + degrees(angle) + ',' + centerX + ',' + centerY + ')">' +
+ text + '</text>';
+ }
+ else
+ {
+ context.fillStyle = color;
+ context.textAlign = anchor;
+ context.font = bold ? fontBold : fontNormal;
+ context.rotate(angle);
+ context.fillText(text, x, y);
+ context.rotate(-angle);
+ }
+}
+
+function drawTextPolar
+(
+ text,
+ innerText,
+ angle,
+ radius,
+ radial,
+ bubble,
+ bold,
+ searchResult,
+ searchResults
+)
+{
+ var anchor;
+ var textX;
+ var textY;
+ var spacer;
+ var totalText = text;
+ var flip;
+
+ if ( snapshotMode )
+ {
+ spacer = '   ';
+ }
+ else
+ {
+ spacer = ' ';
+ }
+
+ if ( radial )
+ {
+ flip = angle < 3 * Math.PI / 2;
+
+ if ( flip )
+ {
+ angle -= Math.PI;
+ radius = -radius;
+ anchor = 'end';
+
+ if ( innerText )
+ {
+ totalText = text + spacer + innerText;
+ }
+ }
+ else
+ {
+ anchor = 'start';
+
+ if ( innerText )
+ {
+ totalText = innerText + spacer + text;
+ }
+ }
+
+ textX = radius;
+ textY = 0;
+ }
+ else
+ {
+ flip = angle < Math.PI || angle > 2 * Math.PI;
+ var label;
+
+ anchor = snapshotMode ? 'middle' : 'center';
+
+ if ( flip )
+ {
+ angle -= Math.PI;
+ radius = -radius;
+ }
+
+ angle += Math.PI / 2;
+ textX = 0;
+ textY = -radius;
+ }
+
+ if ( bubble )
+ {
+ var textActual = totalText;
+
+ if ( innerText && snapshotMode )
+ {
+ if ( flip )
+ {
+ textActual = text + ' ' + innerText;
+ }
+ else
+ {
+ textActual = innerText + ' ' + text;
+ }
+ }
+
+ if ( searchResults )
+ {
+ textActual = textActual + searchResultString(searchResults);
+ }
+
+ var textWidth = measureText(textActual, bold);
+
+ var x = textX;
+
+ if ( anchor == 'end' )
+ {
+ x -= textWidth;
+ }
+ else if ( anchor != 'start' )
+ {
+ // centered
+ x -= textWidth / 2;
+ }
+
+ drawBubble(angle, radius, textWidth, radial, flip);
+
+ if ( searchResult )
+ {
+ drawSearchHighlights
+ (
+ textActual,
+ x,
+ textY,
+ angle,
+ true
+ )
+ }
+ }
+
+ if ( searchResults )
+ {
+ totalText = totalText + searchResultString(searchResults);
+ }
+
+ drawText(totalText, textX, textY, angle, anchor, bold);
+
+ return flip;
+}
+
+function drawTick(start, length, angle)
+{
+ if ( snapshotMode )
+ {
+ svg +=
+ '<line x1="' + (centerX + start) +
+ '" y1="' + centerY +
+ '" x2="' + (centerX + start + length) +
+ '" y2="' + centerY +
+ '" class="tick" transform="rotate(' +
+ degrees(angle) + ',' + centerX + ',' + centerY +
+ ')"/>';
+ }
+ else
+ {
+ context.rotate(angle);
+ context.beginPath();
+ context.moveTo(start, 0);
+ context.lineTo(start + length, 0);
+ context.lineWidth = thinLineWidth * 2;
+ context.stroke();
+ context.rotate(-angle);
+ }
+}
+
+function drawWedge
+(
+ angleStart,
+ angleEnd,
+ radiusInner,
+ radiusOuter,
+ color,
+ patternAlpha,
+ highlight
+)
+{
+ if ( context.globalAlpha == 0 )
+ {
+ return;
+ }
+
+ if ( snapshotMode )
+ {
+ if ( angleEnd == angleStart + Math.PI * 2 )
+ {
+ // fudge to prevent overlap, which causes arc ambiguity
+ //
+ angleEnd -= .1 / gRadius;
+ }
+
+ var longArc = angleEnd - angleStart > Math.PI ? 1 : 0;
+
+ var x1 = centerX + radiusInner * Math.cos(angleStart);
+ var y1 = centerY + radiusInner * Math.sin(angleStart);
+
+ var x2 = centerX + gRadius * Math.cos(angleStart);
+ var y2 = centerY + gRadius * Math.sin(angleStart);
+
+ var x3 = centerX + gRadius * Math.cos(angleEnd);
+ var y3 = centerY + gRadius * Math.sin(angleEnd);
+
+ var x4 = centerX + radiusInner * Math.cos(angleEnd);
+ var y4 = centerY + radiusInner * Math.sin(angleEnd);
+
+ var dArray =
+ [
+ " M ", x1, ",", y1,
+ " L ", x2, ",", y2,
+ " A ", gRadius, ",", gRadius, " 0 ", longArc, ",1 ", x3, ",", y3,
+ " L ", x4, ",", y4,
+ " A ", radiusInner, ",", radiusInner, " 0 ", longArc, " 0 ", x1, ",", y1,
+ " Z "
+ ];
+
+ svg +=
+ '<path class="'+ (highlight ? 'highlight' : 'wedge') + '" fill="' + color +
+ '" d="' + dArray.join('') + '"/>';
+
+ if ( patternAlpha > 0 )
+ {
+ svg +=
+ '<path class="wedge" fill="url(#hiddenPattern)" d="' +
+ dArray.join('') + '"/>';
+ }
+ }
+ else
+ {
+ // fudge to prevent seams during animation
+ //
+ angleEnd += 1 / gRadius;
+
+ context.fillStyle = color;
+ context.beginPath();
+ context.arc(0, 0, radiusInner, angleStart, angleEnd, false);
+ context.arc(0, 0, radiusOuter, angleEnd, angleStart, true);
+ context.closePath();
+ context.fill();
+
+ if ( patternAlpha > 0 )
+ {
+ context.save();
+ context.clip();
+ context.globalAlpha = patternAlpha;
+ context.fillStyle = hiddenPattern;
+ context.fill();
+ context.restore();
+ }
+
+ if ( highlight )
+ {
+ context.lineWidth = highlight ? highlightLineWidth : thinLineWidth;
+ context.strokeStyle = 'black';
+ context.stroke();
+ }
+ }
+}
+
+function expand(node)
+{
+ selectNode(node);
+ updateView();
+}
+
+function focusLost()
+{
+ mouseX = -1;
+ mouseY = -1;
+ checkHighlight();
+ document.body.style.cursor = 'auto';
+}
+
+function fontSizeDecrease()
+{
+ if ( fontSize > 1 )
+ {
+ fontSize--;
+ updateViewNeeded = true;
+ }
+}
+
+function fontSizeIncrease()
+{
+ fontSize++;
+ updateViewNeeded = true;
+}
+
+function getGetString(name, value, bool)
+{
+ return name + '=' + (bool ? value ? 'true' : 'false' : value);
+}
+
+function hideLink()
+{
+ hide(linkText);
+ show(linkButton);
+}
+
+function show(object)
+{
+ object.style.display = 'inline';
+}
+
+function hide(object)
+{
+ object.style.display = 'none';
+}
+
+function showLink()
+{
+ var urlHalves = String(document.location).split('?');
+ var newGetVariables = new Array();
+
+ newGetVariables.push
+ (
+ getGetString('dataset', currentDataset, false),
+ getGetString('node', selectedNode.id, false),
+ getGetString('collapse', collapse, true),
+ getGetString('color', useHue(), true),
+ getGetString('depth', maxAbsoluteDepth - 1, false),
+ getGetString('font', fontSize, false),
+ getGetString('key', showKeys, true)
+ );
+
+ hide(linkButton);
+ show(linkText);
+ linkText.value = urlHalves[0] + '?' + getVariables.concat(newGetVariables).join('&');
+ //linkText.disabled = false;
+ linkText.focus();
+ linkText.select();
+ //linkText.disabled = true;
+// document.location = urlHalves[0] + '?' + getVariables.join('&');
+}
+
+function getFirstChild(element)
+{
+ element = element.firstChild;
+
+ if ( element && element.nodeType != 1 )
+ {
+ element = getNextSibling(element);
+ }
+
+ return element;
+}
+
+function getNextSibling(element)
+{
+ do
+ {
+ element = element.nextSibling;
+ }
+ while ( element && element.nodeType != 1 );
+
+ return element;
+}
+
+function getPercentage(fraction)
+{
+ return round(fraction * 100);
+}
+
+function hslText(hue)
+{
+ if ( 1 || snapshotMode )
+ {
+ // Safari doesn't seem to allow hsl() in SVG
+
+ var rgb = hslToRgb(hue, saturation, (lightnessBase + lightnessMax) / 2);
+
+ return rgbText(rgb.r, rgb.g, rgb.b);
+ }
+ else
+ {
+ var hslArray =
+ [
+ 'hsl(',
+ Math.floor(hue * 360),
+ ',',
+ Math.floor(saturation * 100),
+ '%,',
+ Math.floor((lightnessBase + lightnessMax) * 50),
+ '%)'
+ ];
+
+ return hslArray.join('');
+ }
+}
+
+function hslToRgb(h, s, l)
+{
+ var m1, m2;
+ var r, g, b;
+
+ if (s == 0)
+ {
+ r = g = b = Math.floor((l * 255));
+ }
+ else
+ {
+ if (l <= 0.5)
+ {
+ m2 = l * (s + 1);
+ }
+ else
+ {
+ m2 = l + s - l * s;
+ }
+
+ m1 = l * 2 - m2;
+
+ r = Math.floor(hueToRgb(m1, m2, h + 1 / 3));
+ g = Math.floor(hueToRgb(m1, m2, h));
+ b = Math.floor(hueToRgb(m1, m2, h - 1/3));
+ }
+
+ return {r: r, g: g, b: b};
+}
+
+function hueToRgb(m1, m2, hue)
+{
+ var v;
+
+ while (hue < 0)
+ {
+ hue += 1;
+ }
+
+ while (hue > 1)
+ {
+ hue -= 1;
+ }
+
+ if (6 * hue < 1)
+ v = m1 + (m2 - m1) * hue * 6;
+ else if (2 * hue < 1)
+ v = m2;
+ else if (3 * hue < 2)
+ v = m1 + (m2 - m1) * (2/3 - hue) * 6;
+ else
+ v = m1;
+
+ return 255 * v;
+}
+
+function interpolateHue(hueStart, hueEnd, valueStart, valueEnd)
+{
+ // since the gradient will be RGB based, we need to add stops to hit all the
+ // colors in the hue spectrum
+
+ hueStopPositions = new Array();
+ hueStopHsl = new Array();
+ hueStopText = new Array();
+
+ hueStopPositions.push(0);
+ hueStopHsl.push(hslText(hueStart));
+ hueStopText.push(round(valueStart));
+
+ for
+ (
+ var i = (hueStart > hueEnd ? 5 / 6 : 1 / 6);
+ (hueStart > hueEnd ? i > 0 : i < 1);
+ i += (hueStart > hueEnd ? -1 : 1) / 6
+ )
+ {
+ if
+ (
+ hueStart > hueEnd ?
+ i > hueEnd && i < hueStart :
+ i > hueStart && i < hueEnd
+ )
+ {
+ hueStopPositions.push(lerp(i, hueStart, hueEnd, 0, 1));
+ hueStopHsl.push(hslText(i));
+ hueStopText.push(round(lerp
+ (
+ i,
+ hueStart,
+ hueEnd,
+ valueStart,
+ valueEnd
+ )));
+ }
+ }
+
+ hueStopPositions.push(1);
+ hueStopHsl.push(hslText(hueEnd));
+ hueStopText.push(round(valueEnd));
+}
+
+function keyLineAngle(angle, keyAngle, bendRadius, keyX, keyY, pointsX, pointsY)
+{
+ if ( angle < Math.PI / 2 && keyY < bendRadius * Math.sin(angle)
+ || angle > Math.PI / 2 && keyY < bendRadius)
+ {
+ return Math.asin(keyY / bendRadius);
+ }
+ else
+ {
+ // find the angle of the normal to a tangent line that goes to
+ // the label
+
+ var textDist = Math.sqrt
+ (
+ Math.pow(keyX, 2) +
+ Math.pow(keyY, 2)
+ );
+
+ var tanAngle = Math.acos(bendRadius / textDist) + keyAngle;
+
+ if ( angle < tanAngle || angle < Math.PI / 2 )//|| labelLeft < centerX )
+ {
+ // angle doesn't reach far enough for tangent; collapse and
+ // connect directly to label
+
+ if ( keyY / Math.tan(angle) > 0 )
+ {
+ pointsX.push(keyY / Math.tan(angle));
+ pointsY.push(keyY);
+ }
+ else
+ {
+ pointsX.push(bendRadius * Math.cos(angle));
+ pointsY.push(bendRadius * Math.sin(angle));
+ }
+
+ return angle;
+ }
+ else
+ {
+ return tanAngle;
+ }
+ }
+}
+
+function keyOffset()
+{
+ return imageHeight - (keys - currentKey + 1) * (keySize + keyBuffer) + keyBuffer - margin;
+}
+
+function lerp(value, fromStart, fromEnd, toStart, toEnd)
+{
+ return (value - fromStart) *
+ (toEnd - toStart) /
+ (fromEnd - fromStart) +
+ toStart;
+}
+
+function createCanvas()
+{
+ canvas = document.createElement('canvas');
+ document.body.appendChild(canvas);
+ context = canvas.getContext('2d');
+}
+
+function load()
+{
+ document.body.style.overflow = "hidden";
+ document.body.style.margin = 0;
+
+ createCanvas();
+
+ if ( context == undefined )
+ {
+ document.body.innerHTML = '\
+<br/>This browser does not support HTML5 (see \
+<a href="http://sourceforge.net/p/krona/wiki/Browser%20support/">Browser support</a>).\
+ ';
+ return;
+ }
+
+ if ( typeof context.fillText != 'function' )
+ {
+ document.body.innerHTML = '\
+<br/>This browser does not support HTML5 canvas text (see \
+<a href="http://sourceforge.net/p/krona/wiki/Browser%20support/">Browser support</a>).\
+ ';
+ return;
+ }
+
+ resize();
+
+ var kronaElement = document.getElementsByTagName('krona')[0];
+
+ var magnitudeName;
+ var hueName;
+ var hueDefault;
+ var hueStart;
+ var hueEnd;
+ var valueStart;
+ var valueEnd;
+
+ if ( kronaElement.getAttribute('collapse') != undefined )
+ {
+ collapse = kronaElement.getAttribute('collapse') == 'true';
+ }
+
+ if ( kronaElement.getAttribute('key') != undefined )
+ {
+ showKeys = kronaElement.getAttribute('key') == 'true';
+ }
+
+ for
+ (
+ var element = getFirstChild(kronaElement);
+ element;
+ element = getNextSibling(element)
+ )
+ {
+ switch ( element.tagName.toLowerCase() )
+ {
+ case 'attributes':
+ magnitudeName = element.getAttribute('magnitude');
+ //
+ for
+ (
+ var attributeElement = getFirstChild(element);
+ attributeElement;
+ attributeElement = getNextSibling(attributeElement)
+ )
+ {
+ var tag = attributeElement.tagName.toLowerCase();
+
+ if ( tag == 'attribute' )
+ {
+ var attribute = new Attribute();
+ attribute.name = attributeElement.firstChild.nodeValue.toLowerCase();
+ attribute.displayName = attributeElement.getAttribute('display');
+
+ if ( attributeElement.getAttribute('hrefBase') )
+ {
+ attribute.hrefBase = attributeElement.getAttribute('hrefBase');
+ }
+
+ if ( attributeElement.getAttribute('target') )
+ {
+ attribute.target = attributeElement.getAttribute('target');
+ }
+
+ if ( attribute.name == magnitudeName )
+ {
+ magnitudeIndex = attributes.length;
+ }
+
+ if ( attributeElement.getAttribute('listAll') )
+ {
+ attribute.listAll = attributeElement.getAttribute('listAll').toLowerCase();
+ }
+ else if ( attributeElement.getAttribute('listNode') )
+ {
+ attribute.listNode = attributeElement.getAttribute('listNode').toLowerCase();
+ }
+ else if ( attributeElement.getAttribute('dataAll') )
+ {
+ attribute.dataAll = attributeElement.getAttribute('dataAll').toLowerCase();
+ }
+ else if ( attributeElement.getAttribute('dataNode') )
+ {
+ attribute.dataNode = attributeElement.getAttribute('dataNode').toLowerCase();
+ }
+
+ if ( attributeElement.getAttribute('postUrl') )
+ {
+ attribute.postUrl = attributeElement.getAttribute('postUrl');
+ }
+
+ if ( attributeElement.getAttribute('postVar') )
+ {
+ attribute.postVar = attributeElement.getAttribute('postVar');
+ }
+
+ if ( attributeElement.getAttribute('mono') )
+ {
+ attribute.mono = true;
+ }
+
+ attributes.push(attribute);
+ }
+ else if ( tag == 'list' )
+ {
+ var attribute = new Attribute();
+
+ attribute.name = attributeElement.firstChild.nodeValue;
+ attribute.list = true;
+ attributes.push(attribute);
+ }
+ else if ( tag == 'data' )
+ {
+ var attribute = new Attribute();
+
+ attribute.name = attributeElement.firstChild.nodeValue;
+ attribute.data = true;
+ attributes.push(attribute);
+
+ var enableScript = document.createElement('script');
+ var date = new Date();
+ enableScript.src =
+ attributeElement.getAttribute('enable') + '?' +
+ date.getTime();
+ document.body.appendChild(enableScript);
+ }
+ }
+ break;
+
+ case 'color':
+ hueName = element.getAttribute('attribute');
+ hueStart = Number(element.getAttribute('hueStart')) / 360;
+ hueEnd = Number(element.getAttribute('hueEnd')) / 360;
+ valueStart = Number(element.getAttribute('valueStart'));
+ valueEnd = Number(element.getAttribute('valueEnd'));
+ //
+ interpolateHue(hueStart, hueEnd, valueStart, valueEnd);
+ //
+ if ( element.getAttribute('default') == 'true' )
+ {
+ hueDefault = true;
+ }
+ break;
+
+ case 'datasets':
+ datasetNames = new Array();
+ //
+ for ( j = getFirstChild(element); j; j = getNextSibling(j) )
+ {
+ datasetNames.push(j.firstChild.nodeValue);
+ }
+ datasets = datasetNames.length;
+ break;
+
+ case 'node':
+ head = loadTreeDOM
+ (
+ element,
+ magnitudeName,
+ hueName,
+ hueStart,
+ hueEnd,
+ valueStart,
+ valueEnd
+ );
+ break;
+ }
+ }
+
+ // get GET options
+ //
+ var urlHalves = String(document.location).split('?');
+ var datasetDefault = 0;
+ var maxDepthDefault;
+ var nodeDefault = 0;
+ //
+ if ( urlHalves[1] )
+ {
+ var vars = urlHalves[1].split('&');
+
+ for ( i = 0; i < vars.length; i++ )
+ {
+ var pair = vars[i].split('=');
+
+ switch ( pair[0] )
+ {
+ case 'collapse':
+ collapse = pair[1] == 'true';
+ break;
+
+ case 'color':
+ hueDefault = pair[1] == 'true';
+ break;
+
+ case 'dataset':
+ datasetDefault = Number(pair[1]);
+ break;
+
+ case 'depth':
+ maxDepthDefault = Number(pair[1]) + 1;
+ break;
+
+ case 'key':
+ showKeys = pair[1] == 'true';
+ break;
+
+ case 'font':
+ fontSize = Number(pair[1]);
+ break;
+
+ case 'node':
+ nodeDefault = Number(pair[1]);
+ break;
+
+ default:
+ getVariables.push(pair[0] + '=' + pair[1]);
+ break;
+ }
+ }
+ }
+
+ addOptionElements(hueName, hueDefault);
+ setCallBacks();
+
+ head.sort();
+ maxAbsoluteDepth = 0;
+ selectDataset(datasetDefault);
+
+ if ( maxDepthDefault && maxDepthDefault < head.maxDepth )
+ {
+ maxAbsoluteDepth = maxDepthDefault;
+ }
+ else
+ {
+ maxAbsoluteDepth = head.maxDepth;
+ }
+
+ selectNode(nodes[nodeDefault]);
+
+ setInterval(update, 20);
+
+ window.onresize = handleResize;
+ updateMaxAbsoluteDepth();
+ updateViewNeeded = true;
+}
+
+function loadTreeDOM
+(
+ domNode,
+ magnitudeName,
+ hueName,
+ hueStart,
+ hueEnd,
+ valueStart,
+ valueEnd
+)
+{
+ var newNode = new Node();
+
+ newNode.name = domNode.getAttribute('name');
+
+ if ( domNode.getAttribute('href') )
+ {
+ newNode.href = domNode.getAttribute('href');
+ }
+
+ if ( hueName )
+ {
+ newNode.hues = new Array();
+ }
+
+ for ( var i = getFirstChild(domNode); i; i = getNextSibling(i) )
+ {
+ switch ( i.tagName.toLowerCase() )
+ {
+ case 'node':
+ var newChild = loadTreeDOM
+ (
+ i,
+ magnitudeName,
+ hueName,
+ hueStart,
+ hueEnd,
+ valueStart,
+ valueEnd
+ );
+ newChild.parent = newNode;
+ newNode.children.push(newChild);
+ break;
+
+ default:
+ var attributeName = i.tagName.toLowerCase();
+ var index = attributeIndex(attributeName);
+ //
+ newNode.attributes[index] = new Array();
+ //
+ for ( var j = getFirstChild(i); j; j = getNextSibling(j) )
+ {
+ if ( attributes[index] == undefined )
+ {
+ var x = 5;
+ }
+ if ( attributes[index].list )
+ {
+ newNode.attributes[index].push(new Array());
+
+ for ( var k = getFirstChild(j); k; k = getNextSibling(k) )
+ {
+ newNode.attributes[index][newNode.attributes[index].length - 1].push(k.firstChild.nodeValue);
+ }
+ }
+ else
+ {
+ var value = j.firstChild ? j.firstChild.nodeValue : '';
+
+ if ( j.getAttribute('href') )
+ {
+ var target;
+
+ if ( attributes[index].target )
+ {
+ target = ' target="' + attributes[index].target + '"';
+ }
+
+ value = '<a href="' + attributes[index].hrefBase + j.getAttribute('href') + '"' + target + '>' + value + '</a>';
+ }
+
+ newNode.attributes[index].push(value);
+ }
+ }
+ //
+ if ( attributeName == magnitudeName || attributeName == hueName )
+ {
+ for ( j = 0; j < datasets; j++ )
+ {
+ var value = newNode.attributes[index][j] == undefined ? 0 : Number(newNode.attributes[index][j]);
+
+ newNode.attributes[index][j] = value;
+
+ if ( attributeName == hueName )
+ {
+ var hue = lerp
+ (
+ value,
+ valueStart,
+ valueEnd,
+ hueStart,
+ hueEnd
+ );
+
+ if ( hue < hueStart == hueStart < hueEnd )
+ {
+ hue = hueStart;
+ }
+ else if ( hue > hueEnd == hueStart < hueEnd )
+ {
+ hue = hueEnd;
+ }
+
+ newNode.hues[j] = hue;
+ }
+ }
+
+ if ( attributeName == hueName )
+ {
+ newNode.hue = new Tween(newNode.hues[0], newNode.hues[0]);
+ }
+ }
+ break;
+ }
+ }
+
+ return newNode;
+}
+
+function maxAbsoluteDepthDecrease()
+{
+ if ( maxAbsoluteDepth > 2 )
+ {
+ maxAbsoluteDepth--;
+ head.setMaxDepths();
+ handleResize();
+ }
+}
+
+function maxAbsoluteDepthIncrease()
+{
+ if ( maxAbsoluteDepth < head.maxDepth )
+ {
+ maxAbsoluteDepth++;
+ head.setMaxDepths();
+ handleResize();
+ }
+}
+
+function measureText(text, bold)
+{
+ context.font = bold ? fontBold : fontNormal;
+ var dim = context.measureText(text);
+ return dim.width;
+}
+
+function min(a, b)
+{
+ return a < b ? a : b;
+}
+
+function minWidth()
+{
+ // Min wedge width (at center) for displaying a node (or for displaying a
+ // label if it's at the highest level being viewed, multiplied by 2 to make
+ // further calculations simpler
+
+ return (fontSize * 2.3);
+}
+
+function mouseMove(e)
+{
+ mouseX = e.pageX;
+ mouseY = e.pageY - headerHeight;
+
+ if ( head && ! quickLook )
+ {
+ checkHighlight();
+ }
+}
+
+function mouseClick(e)
+{
+ if ( highlightedNode == focusNode && focusNode != selectedNode || selectedNode.hasParent(highlightedNode) )
+ {
+ if ( highlightedNode.hasChildren() )
+ {
+ expand(highlightedNode);
+ }
+ }
+ else if ( progress == 1 )//( highlightedNode != selectedNode )
+ {
+ setFocus(highlightedNode);
+// document.body.style.cursor='ew-resize';
+ draw();
+ checkHighlight();
+ var date = new Date();
+ mouseDownTime = date.getTime();
+ mouseDown = true;
+ }
+}
+
+function mouseUp(e)
+{
+ if ( quickLook )
+ {
+ navigateBack();
+ quickLook = false;
+ }
+
+ mouseDown = false;
+}
+
+function navigateBack()
+{
+ if ( nodeHistoryPosition > 0 )
+ {
+ nodeHistory[nodeHistoryPosition] = selectedNode;
+ nodeHistoryPosition--;
+
+ if ( nodeHistory[nodeHistoryPosition].collapse )
+ {
+ collapseCheckBox.checked = collapse = false;
+ }
+
+ setSelectedNode(nodeHistory[nodeHistoryPosition]);
+ updateDatasetButtons();
+ updateView();
+ }
+}
+
+function navigateUp()
+{
+ if ( selectedNode.getParent() )
+ {
+ selectNode(selectedNode.getParent());
+ updateView();
+ }
+}
+
+function navigateForward()
+{
+ if ( nodeHistoryPosition < nodeHistory.length - 1 )
+ {
+ nodeHistoryPosition++;
+ var newNode = nodeHistory[nodeHistoryPosition];
+
+ if ( newNode.collapse )
+ {
+ collapseCheckBox.checked = collapse = false;
+ }
+
+ if ( nodeHistoryPosition == nodeHistory.length - 1 )
+ {
+ // this will ensure the forward button is disabled
+
+ nodeHistory.length = nodeHistoryPosition;
+ }
+
+ setSelectedNode(newNode);
+ updateDatasetButtons();
+ updateView();
+ }
+}
+
+function nextDataset()
+{
+ var newDataset = currentDataset;
+
+ do
+ {
+ if ( newDataset == datasets - 1 )
+ {
+ newDataset = 0;
+ }
+ else
+ {
+ newDataset++;
+ }
+ }
+ while ( datasetDropDown.options[newDataset].disabled )
+
+ selectDataset(newDataset);
+}
+
+function onDatasetChange()
+{
+ selectDataset(datasetDropDown.selectedIndex);
+}
+
+function onKeyDown(event)
+{
+ if
+ (
+ event.keyCode == 37 &&
+ document.activeElement.id != 'search' &&
+ document.activeElement.id != 'linkText'
+ )
+ {
+ navigateBack();
+ event.preventDefault();
+ }
+ else if
+ (
+ event.keyCode == 39 &&
+ document.activeElement.id != 'search' &&
+ document.activeElement.id != 'linkText'
+ )
+ {
+ navigateForward();
+ event.preventDefault();
+ }
+ else if ( event.keyCode == 38 && datasets > 1 )
+ {
+ prevDataset();
+
+ //if ( document.activeElement.id == 'datasets' )
+ {
+ event.preventDefault();
+ }
+ }
+ else if ( event.keyCode == 40 && datasets > 1 )
+ {
+ nextDataset();
+
+ //if ( document.activeElement.id == 'datasets' )
+ {
+ event.preventDefault();
+ }
+ }
+ else if ( event.keyCode == 9 && datasets > 1 )
+ {
+ selectLastDataset();
+ event.preventDefault();
+ }
+ else if ( event.keyCode == 83 )
+ {
+ progress += .2;
+ }
+ else if ( event.keyCode == 66 )
+ {
+ progress -= .2;
+ }
+ else if ( event.keyCode == 70 )
+ {
+ progress = 1;
+ }
+}
+
+function onKeyPress(event)
+{
+ if ( event.keyCode == 38 && datasets > 1 )
+ {
+// prevDataset();
+
+ //if ( document.activeElement.id == 'datasets' )
+ {
+ event.preventDefault();
+ }
+ }
+ else if ( event.keyCode == 40 && datasets > 1 )
+ {
+// nextDataset();
+
+ //if ( document.activeElement.id == 'datasets' )
+ {
+ event.preventDefault();
+ }
+ }
+}
+
+function onKeyUp(event)
+{
+ if ( event.keyCode == 27 && document.activeElement.id == 'search' )
+ {
+ search.value = '';
+ onSearchChange();
+ }
+ else if ( event.keyCode == 38 && datasets > 1 )
+ {
+// prevDataset();
+
+ //if ( document.activeElement.id == 'datasets' )
+ {
+ event.preventDefault();
+ }
+ }
+ else if ( event.keyCode == 40 && datasets > 1 )
+ {
+// nextDataset();
+
+ //if ( document.activeElement.id == 'datasets' )
+ {
+ event.preventDefault();
+ }
+ }
+}
+
+function onSearchChange()
+{
+ nSearchResults = 0;
+ head.search();
+
+ if ( search.value == '' )
+ {
+ searchResults.innerHTML = '';
+ }
+ else
+ {
+ searchResults.innerHTML = nSearchResults + ' results';
+ }
+
+ setFocus(selectedNode);
+ draw();
+}
+
+function post(url, variable, value, postWindow)
+{
+ var form = document.createElement('form');
+ var input = document.createElement('input');
+ var inputDataset = document.createElement('input');
+
+ form.appendChild(input);
+ form.appendChild(inputDataset);
+
+ form.method = "POST";
+ form.action = url;
+
+ if ( postWindow == undefined )
+ {
+ form.target = '_blank';
+ postWindow = window;
+ }
+
+ input.type = 'hidden';
+ input.name = variable;
+ input.value = value;
+
+ inputDataset.type = 'hidden';
+ inputDataset.name = 'dataset';
+ inputDataset.value = currentDataset;
+
+ postWindow.document.body.appendChild(form);
+ form.submit();
+}
+
+function prevDataset()
+{
+ var newDataset = currentDataset;
+
+ do
+ {
+ if ( newDataset == 0 )
+ {
+ newDataset = datasets - 1;
+ }
+ else
+ {
+ newDataset--;
+ }
+ }
+ while ( datasetDropDown.options[newDataset].disabled );
+
+ selectDataset(newDataset);
+}
+
+function radiusDecrease()
+{
+ if ( bufferFactor < .309 )
+ {
+ bufferFactor += .03;
+ updateViewNeeded = true;
+ }
+}
+
+function radiusIncrease()
+{
+ if ( bufferFactor > .041 )
+ {
+ bufferFactor -= .03;
+ updateViewNeeded = true;
+ }
+}
+
+function resetKeyOffset()
+{
+ currentKey = 1;
+ keyMinTextLeft = centerX + gRadius + buffer - buffer / (keys + 1) / 2 + fontSize / 2;
+ keyMinAngle = 0;
+}
+
+function rgbText(r, g, b)
+{
+ var rgbArray =
+ [
+ "rgb(",
+ Math.floor(r),
+ ",",
+ Math.floor(g),
+ ",",
+ Math.floor(b),
+ ")"
+ ];
+
+ return rgbArray.join('');
+}
+
+function round(number)
+{
+ if ( number >= 1 || number <= -1 )
+ {
+ return number.toFixed(0);
+ }
+ else
+ {
+ return number.toPrecision(1);
+ }
+}
+
+function roundedRectangle(x, y, width, height, radius)
+{
+ if ( radius * 2 > width )
+ {
+ radius = width / 2;
+ }
+
+ if ( radius * 2 > height )
+ {
+ radius = height / 2;
+ }
+
+ context.beginPath();
+ context.arc(x + radius, y + radius, radius, Math.PI, Math.PI * 3 / 2, false);
+ context.lineTo(x + width - radius, y);
+ context.arc(x + width - radius, y + radius, radius, Math.PI * 3 / 2, Math.PI * 2, false);
+ context.lineTo(x + width, y + height - radius);
+ context.arc(x + width - radius, y + height - radius, radius, 0, Math.PI / 2, false);
+ context.lineTo(x + radius, y + height);
+ context.arc(x + radius, y + height - radius, radius, Math.PI / 2, Math.PI, false);
+ context.lineTo(x, y + radius);
+}
+
+function passClick(e)
+{
+ mouseClick(e);
+}
+
+function searchResultString(results)
+{
+ var searchResults = this.searchResults;
+
+ if ( this.isSearchResult )
+ {
+ // don't count ourselves
+ searchResults--;
+ }
+
+ return ' - ' + results + (results > 1 ? ' results' : ' result');
+}
+
+function setCallBacks()
+{
+ canvas.onselectstart = function(){return false;} // prevent unwanted highlighting
+ options.onselectstart = function(){return false;} // prevent unwanted highlighting
+ document.onmousemove = mouseMove;
+ window.onblur = focusLost;
+ window.onmouseout = focusLost;
+ document.onkeyup = onKeyUp;
+ document.onkeydown = onKeyDown;
+ canvas.onmousedown = mouseClick;
+ document.onmouseup = mouseUp;
+ keyControl.onclick = toggleKeys;
+ collapseCheckBox = document.getElementById('collapse');
+ collapseCheckBox.checked = collapse;
+ collapseCheckBox.onclick = handleResize;
+ collapseCheckBox.onmousedown = suppressEvent;
+ maxAbsoluteDepthText = document.getElementById('maxAbsoluteDepth');
+ maxAbsoluteDepthButtonDecrease = document.getElementById('maxAbsoluteDepthDecrease');
+ maxAbsoluteDepthButtonIncrease = document.getElementById('maxAbsoluteDepthIncrease');
+ maxAbsoluteDepthButtonDecrease.onclick = maxAbsoluteDepthDecrease;
+ maxAbsoluteDepthButtonIncrease.onclick = maxAbsoluteDepthIncrease;
+ maxAbsoluteDepthButtonDecrease.onmousedown = suppressEvent;
+ maxAbsoluteDepthButtonIncrease.onmousedown = suppressEvent;
+ fontSizeText = document.getElementById('fontSize');
+ fontSizeButtonDecrease = document.getElementById('fontSizeDecrease');
+ fontSizeButtonIncrease = document.getElementById('fontSizeIncrease');
+ fontSizeButtonDecrease.onclick = fontSizeDecrease;
+ fontSizeButtonIncrease.onclick = fontSizeIncrease;
+ fontSizeButtonDecrease.onmousedown = suppressEvent;
+ fontSizeButtonIncrease.onmousedown = suppressEvent;
+ radiusButtonDecrease = document.getElementById('radiusDecrease');
+ radiusButtonIncrease = document.getElementById('radiusIncrease');
+ radiusButtonDecrease.onclick = radiusDecrease;
+ radiusButtonIncrease.onclick = radiusIncrease;
+ radiusButtonDecrease.onmousedown = suppressEvent;
+ radiusButtonIncrease.onmousedown = suppressEvent;
+ maxAbsoluteDepth = 0;
+ backButton = document.getElementById('back');
+ backButton.onclick = navigateBack;
+ backButton.onmousedown = suppressEvent;
+ forwardButton = document.getElementById('forward');
+ forwardButton.onclick = navigateForward;
+ forwardButton.onmousedown = suppressEvent;
+ snapshotButton = document.getElementById('snapshot');
+ snapshotButton.onclick = snapshot;
+ snapshotButton.onmousedown = suppressEvent;
+ detailsName = document.getElementById('detailsName');
+ detailsExpand = document.getElementById('detailsExpand');
+ detailsInfo = document.getElementById('detailsInfo');
+ search = document.getElementById('search');
+ search.onkeyup = onSearchChange;
+ search.onmousedown = suppressEvent;
+ searchResults = document.getElementById('searchResults');
+ useHueDiv = document.getElementById('useHueDiv');
+ linkButton = document.getElementById('linkButton');
+ linkButton.onclick = showLink;
+ linkButton.onmousedown = suppressEvent;
+ linkText = document.getElementById('linkText');
+ linkText.onblur = hideLink;
+ linkText.onmousedown = suppressEvent;
+ hide(linkText);
+ var helpButton = document.getElementById('help');
+ helpButton.onmousedown = suppressEvent;
+ var searchClear = document.getElementById('searchClear');
+ searchClear.onmousedown = suppressEvent;
+ if ( datasets > 1 )
+ {
+ datasetDropDown.onmousedown = suppressEvent;
+ var prevDatasetButton = document.getElementById('prevDataset');
+ prevDatasetButton.onmousedown = suppressEvent;
+ var nextDatasetButton = document.getElementById('nextDataset');
+ nextDatasetButton.onmousedown = suppressEvent;
+ var lastDatasetButton = document.getElementById('lastDataset');
+ lastDatasetButton.onmousedown = suppressEvent;
+ }
+
+ image = document.getElementById('hiddenImage');
+
+ if ( image.complete )
+ {
+ hiddenPattern = context.createPattern(image, 'repeat');
+ }
+ else
+ {
+ image.onload = function()
+ {
+ hiddenPattern = context.createPattern(image, 'repeat');
+ }
+ }
+
+ var loadingImageElement = document.getElementById('loadingImage');
+
+ if ( loadingImageElement )
+ {
+ loadingImage = loadingImageElement.src;
+ }
+}
+
+function selectDataset(newDataset)
+{
+ lastDataset = currentDataset;
+ currentDataset = newDataset
+ if ( datasets > 1 )
+ {
+ datasetDropDown.selectedIndex = currentDataset;
+ updateDatasetButtons();
+ datasetAlpha.start = 1.5;
+ datasetChanged = true;
+ }
+ head.setMagnitudes(0);
+ head.setDepth(1, 1);
+ head.setMaxDepths();
+ handleResize();
+}
+
+function selectLastDataset()
+{
+ selectDataset(lastDataset);
+ handleResize();
+}
+
+function selectNode(newNode)
+{
+ if ( selectedNode != newNode )
+ {
+ // truncate history at current location to create a new branch
+ //
+ nodeHistory.length = nodeHistoryPosition;
+
+ if ( selectedNode != 0 )
+ {
+ nodeHistory.push(selectedNode);
+ nodeHistoryPosition++;
+ }
+
+ setSelectedNode(newNode);
+ //updateView();
+ }
+
+ updateDatasetButtons();
+}
+
+function setFocus(node)
+{
+ if ( node == focusNode )
+ {
+// return;
+ }
+
+ focusNode = node;
+
+ if ( node.href )
+ {
+ detailsName.innerHTML =
+ '<a target="_blank" href="' + node.href + '">' + node.name + '</a>';
+ }
+ else
+ {
+ detailsName.innerHTML = node.name;
+ }
+
+ var table = '<table>';
+
+ table += '<tr><td></td></tr>';
+
+ for ( var i = 0; i < node.attributes.length; i++ )
+ {
+ if ( attributes[i].displayName && node.attributes[i] != undefined )
+ {
+ var index = node.attributes[i].length == 1 && attributes[i].mono ? 0 : currentDataset;
+
+ if ( typeof node.attributes[i][currentDataset] == 'number' || node.attributes[i][index] != undefined && node.attributes[i][currentDataset] != '' )
+ {
+ var value = node.attributes[i][index];
+
+ if ( attributes[i].listNode != undefined )
+ {
+ value =
+ '<a href="" onclick="showList(' +
+ attributeIndex(attributes[i].listNode) + ',' + i +
+ ',false);return false;" title="Show list">' +
+ value + '</a>';
+ }
+ else if ( attributes[i].listAll != undefined )
+ {
+ value =
+ '<a href="" onclick="showList(' +
+ attributeIndex(attributes[i].listAll) + ',' + i +
+ ',true);return false;" title="Show list">' +
+ value + '</a>';
+ }
+ else if ( attributes[i].dataNode != undefined && dataEnabled )
+ {
+ value =
+ '<a href="" onclick="showData(' +
+ attributeIndex(attributes[i].dataNode) + ',' + i +
+ ',false);return false;" title="Show data">' +
+ value + '</a>';
+ }
+ else if ( attributes[i].dataAll != undefined && dataEnabled )
+ {
+ value =
+ '<a href="" onclick="showData(' +
+ attributeIndex(attributes[i].dataAll) + ',' + i +
+ ',true);return false;" title="Show data">' +
+ value + '</a>';
+ }
+
+ table +=
+ '<tr><td><strong>' + attributes[i].displayName + ':</strong></td><td>' +
+ value + '</td></tr>';
+ }
+ }
+ }
+
+ table += '</table>';
+ detailsInfo.innerHTML = table;
+
+ detailsExpand.disabled = !focusNode.hasChildren() || focusNode == selectedNode;
+}
+
+function setSelectedNode(newNode)
+{
+ if ( selectedNode && selectedNode.hasParent(newNode) )
+ {
+ zoomOut = true;
+ }
+ else
+ {
+ zoomOut = false;
+ }
+
+ selectedNodeLast = selectedNode;
+ selectedNode = newNode;
+
+ //if ( focusNode != selectedNode )
+ {
+ setFocus(selectedNode);
+ }
+}
+
+function waitForData(dataWindow, target, title, time, postUrl, postVar)
+{
+ if ( nodeData.length == target )
+ {
+ if ( postUrl != undefined )
+ {
+ for ( var i = 0; i < nodeData.length; i++ )
+ {
+ nodeData[i] = nodeData[i].replace(/\n/g, ',');
+ }
+
+ var postString = nodeData.join('');
+ postString = postString.slice(0, -1);
+
+ dataWindow.document.body.removeChild(dataWindow.document.getElementById('loading'));
+ document.body.removeChild(document.getElementById('data'));
+
+ post(postUrl, postVar, postString, dataWindow);
+ }
+ else
+ {
+ //dataWindow.document.body.removeChild(dataWindow.document.getElementById('loading'));
+ //document.body.removeChild(document.getElementById('data'));
+
+ dataWindow.document.open();
+ dataWindow.document.write('<pre>' + nodeData.join('') + '</pre>');
+ dataWindow.document.close();
+ }
+
+ dataWindow.document.title = title; // replace after document.write()
+ }
+ else
+ {
+ var date = new Date();
+
+ if ( date.getTime() - time > 10000 )
+ {
+ dataWindow.document.body.removeChild(dataWindow.document.getElementById('loading'));
+ document.body.removeChild(document.getElementById('data'));
+ dataWindow.document.body.innerHTML =
+ 'Timed out loading supplemental files for:<br/>' + document.location;
+ }
+ else
+ {
+ setTimeout(function() {waitForData(dataWindow, target, title, time, postUrl, postVar);}, 100);
+ }
+ }
+}
+
+function data(newData)
+{
+ nodeData.push(newData);
+}
+
+function enableData()
+{
+ dataEnabled = true;
+}
+
+function showData(indexData, indexAttribute, summary)
+{
+ var dataWindow = window.open('', '_blank');
+ var title = 'Krona - ' + attributes[indexAttribute].displayName + ' - ' + focusNode.name;
+ dataWindow.document.title = title;
+
+ nodeData = new Array();
+
+ if ( dataWindow && dataWindow.document && dataWindow.document.body != null )
+ {
+ //var loadImage = document.createElement('img');
+ //loadImage.src = "file://localhost/Users/ondovb/Krona/KronaTools/img/loading.gif";
+ //loadImage.id = "loading";
+ //loadImage.alt = "Loading...";
+ //dataWindow.document.body.appendChild(loadImage);
+ dataWindow.document.body.innerHTML =
+ '<img id="loading" src="' + loadingImage + '" alt="Loading..."></img>';
+ }
+
+ var scripts = document.createElement('div');
+ scripts.id = 'data';
+ document.body.appendChild(scripts);
+
+ var files = focusNode.getData(indexData, summary);
+
+ var date = new Date();
+ var time = date.getTime();
+
+ for ( var i = 0; i < files.length; i++ )
+ {
+ var script = document.createElement('script');
+ script.src = files[i] + '?' + time;
+ scripts.appendChild(script);
+ }
+
+ waitForData(dataWindow, files.length, title, time, attributes[indexAttribute].postUrl, attributes[indexAttribute].postVar);
+
+ return false;
+}
+
+function showList(indexList, indexAttribute, summary)
+{
+ var list = focusNode.getList(indexList, summary);
+
+ if ( attributes[indexAttribute].postUrl != undefined )
+ {
+ post(attributes[indexAttribute].postUrl, attributes[indexAttribute].postVar, list.join(','));
+ }
+ else
+ {
+ var dataWindow = window.open('', '_blank');
+
+ if ( true || navigator.appName == 'Microsoft Internet Explorer' ) // :(
+ {
+ dataWindow.document.open();
+ dataWindow.document.write('<pre>' + list.join('\n') + '</pre>');
+ dataWindow.document.close();
+ }
+ else
+ {
+ var pre = document.createElement('pre');
+ dataWindow.document.body.appendChild(pre);
+ pre.innerHTML = list;
+ }
+
+ dataWindow.document.title = 'Krona - ' + attributes[indexAttribute].displayName + ' - ' + focusNode.name;
+ }
+}
+
+function snapshot()
+{
+ svg = svgHeader();
+
+ resetKeyOffset();
+
+ snapshotMode = true;
+
+ selectedNode.draw(false, true);
+ selectedNode.draw(true, true);
+
+ if ( focusNode != 0 && focusNode != selectedNode )
+ {
+ context.globalAlpha = 1;
+ focusNode.drawHighlight(true);
+ }
+
+ if ( hueDisplayName && useHue() )
+ {
+ drawLegendSVG();
+ }
+
+ snapshotMode = false;
+
+ svg += svgFooter();
+
+ snapshotWindow = window.open
+ (
+ 'data:image/svg+xml;charset=utf-8,' + encodeURIComponent(svg),
+ '_blank'
+ );
+/* var data = window.open('data:text/plain;charset=utf-8,hello', '_blank');
+ var data = window.open('', '_blank');
+ data.document.open('text/plain');
+ data.document.write('hello');
+ data.document.close();
+ var button = document.createElement('input');
+ button.type = 'button';
+ button.value = 'save';
+ button.onclick = save;
+ data.document.body.appendChild(button);
+// snapshotWindow.document.write(svg);
+// snapshotWindow.document.close();
+*/
+}
+
+function save()
+{
+ alert(document.body.innerHTML);
+}
+
+function spacer()
+{
+ if ( snapshotMode )
+ {
+ return '   ';
+ }
+ else
+ {
+ return ' ';
+ }
+}
+
+function suppressEvent(e)
+{
+ e.cancelBubble = true;
+ if (e.stopPropagation) e.stopPropagation();
+}
+
+function svgFooter()
+{
+ return '</svg>';
+}
+
+function svgHeader()
+{
+ var patternWidth = fontSize * .6;//radius / 50;
+
+ return '\
+<?xml version="1.0" standalone="no"?>\
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" \
+ "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\
+<svg width="' + imageWidth + '" height="' + imageHeight + '" version="1.1"\
+ xmlns="http://www.w3.org/2000/svg">\
+<title>Krona (snapshot) - ' +
+(datasets > 1 ? datasetNames[currentDataset] + ' - ' : '') + selectedNode.name +
+'</title>\
+<defs>\
+ <style type="text/css">\
+ text {font-size: ' + fontSize + 'px; font-family: ' + fontFamily + '; dominant-baseline:central}\
+ path {stroke-width:' + thinLineWidth * fontSize / 12 + ';}\
+ path.wedge {stroke:none}\
+ path.line {fill:none;stroke:black;}\
+ line {stroke:black;stroke-width:' + thinLineWidth * fontSize / 12 + ';}\
+ line.tick {stroke-width:' + thinLineWidth * fontSize / 6 + ';}\
+ line.pattern {stroke-width:' + thinLineWidth * fontSize / 18 + ';}\
+ circle {fill:none;stroke:black;stroke-width:' + thinLineWidth * fontSize / 12 + ';}\
+ rect {stroke:black;stroke-width:' + thinLineWidth * fontSize / 12 + ';}\
+ .highlight {stroke:black;stroke-width:'+ highlightLineWidth * fontSize / 12 + ';}\
+ .searchHighlight {fill:rgb(255, 255, 100);stroke:none;}\
+ </style>\
+<pattern id="hiddenPattern" patternUnits="userSpaceOnUse" \
+x="0" y="0" width="' + patternWidth + '" height="' + patternWidth + '">\
+<line class="pattern" x1="0" y1="0" x2="' + patternWidth / 2 + '" y2="' + patternWidth / 2 + '"/>\
+<line class="pattern" x1="' + patternWidth / 2 + '" y1="' + patternWidth +
+'" x2="' + patternWidth + '" y2="' + patternWidth / 2 + '"/>\
+</pattern>\
+</defs>\
+';
+}
+
+function svgText(text, x, y, anchor, bold, color)
+{
+ if ( typeof(anchor) == 'undefined' )
+ {
+ anchor = 'start';
+ }
+
+ if ( color == undefined )
+ {
+ color = 'black';
+ }
+
+ return '<text x="' + x + '" y="' + y +
+ '" style="font-color:' + color + ';font-weight:' + (bold ? 'bold' : 'normal') +
+ '" text-anchor="' + anchor + '">' + text + '</text>';
+}
+
+function toggleKeys()
+{
+ if ( showKeys )
+ {
+ keyControl.value = '…';
+ showKeys = false;
+ }
+ else
+ {
+ keyControl.value = 'x';
+ showKeys = true;
+ }
+
+ updateKeyControl();
+
+ if ( progress == 1 )
+ {
+ draw();
+ }
+}
+
+function update()
+{
+ if ( ! head )
+ {
+ return;
+ }
+
+ if ( mouseDown && focusNode != selectedNode )
+ {
+ var date = new Date();
+
+ if ( date.getTime() - mouseDownTime > quickLookHoldLength )
+ {
+ if ( focusNode.hasChildren() )
+ {
+ expand(focusNode);
+ quickLook = true;
+ }
+ }
+ }
+
+ if ( updateViewNeeded )
+ {
+ resize();
+ mouseX = -1;
+ mouseY = -1;
+
+ collapse = collapseCheckBox.checked;
+ compress = true;//compressCheckBox.checked;
+ shorten = true;//shortenCheckBox.checked;
+
+ checkSelectedCollapse();
+ updateMaxAbsoluteDepth();
+
+ if ( focusNode.getCollapse() || focusNode.depth > maxAbsoluteDepth )
+ {
+ setFocus(selectedNode);
+ }
+ else
+ {
+ setFocus(focusNode);
+ }
+
+ updateView();
+
+ updateViewNeeded = false;
+ }
+
+ var date = new Date();
+ progress = (date.getTime() - tweenStartTime) / tweenLength;
+// progress += .01;
+
+ if ( progress >= 1 )
+ {
+ progress = 1;
+ }
+
+ if ( progress != progressLast )
+ {
+ tweenFactor =// progress;
+ (1 / (1 + Math.exp(-tweenCurvature * (progress - .5))) - .5) /
+ (tweenMax - .5) / 2 + .5;
+
+ if ( progress == 1 )
+ {
+ snapshotButton.disabled = false;
+ zoomOut = false;
+
+ //updateKeyControl();
+
+ if ( ! quickLook )
+ {
+ //checkHighlight();
+ }
+
+
+ if ( fpsDisplay )
+ {
+ fpsDisplay.innerHTML = 'fps: ' + Math.round(tweenFrames * 1000 / tweenLength);
+ }
+ }
+
+ draw();
+ }
+
+ progressLast = progress;
+}
+
+function updateDatasetButtons()
+{
+ if ( datasets == 1 )
+ {
+ return;
+ }
+
+ var node = selectedNode ? selectedNode : head;
+
+ datasetButtonLast.disabled =
+ node.attributes[magnitudeIndex][lastDataset] == 0;
+
+ datasetButtonPrev.disabled = true;
+ datasetButtonNext.disabled = true;
+
+ for ( var i = 0; i < datasets; i++ )
+ {
+ var disable = node.attributes[magnitudeIndex][i] == 0;
+
+ datasetDropDown.options[i].disabled = disable;
+
+ if ( ! disable )
+ {
+ if ( i != currentDataset )
+ {
+ datasetButtonPrev.disabled = false;
+ datasetButtonNext.disabled = false;
+ }
+ }
+ }
+}
+
+function updateDatasetWidths()
+{
+ if ( datasets > 1 )
+ {
+ for ( var i = 0; i < datasets; i++ )
+ {
+ context.font = fontBold;
+ var dim = context.measureText(datasetNames[i]);
+ datasetWidths[i] = dim.width;
+ }
+ }
+}
+
+function updateKeyControl()
+{
+ if ( keys == 0 )//|| progress != 1 )
+ {
+ keyControl.style.visibility = 'hidden';
+ }
+ else
+ {
+ keyControl.style.visibility = 'visible';
+ keyControl.style.right = margin + 'px';
+
+ if ( showKeys )
+ {
+ keyControl.style.top =
+ imageHeight -
+ (
+ keys * (keySize + keyBuffer) -
+ keyBuffer +
+ margin +
+ keyControl.clientHeight * 1.5
+ ) + 'px';
+ }
+ else
+ {
+ keyControl.style.top =
+ (imageHeight - margin - keyControl.clientHeight) + 'px';
+ }
+ }
+}
+
+function updateView()
+{
+ if ( selectedNode.depth > maxAbsoluteDepth - 1 )
+ {
+ maxAbsoluteDepth = selectedNode.depth + 1;
+ }
+
+ highlightedNode = selectedNode;
+
+ angleFactor = 2 * Math.PI / (selectedNode.magnitude);
+
+ maxPossibleDepth = Math.floor(gRadius / (fontSize * minRingWidthFactor));
+
+ if ( maxPossibleDepth < 4 )
+ {
+ maxPossibleDepth = 4;
+ }
+
+ var minRadiusInner = fontSize * 8 / gRadius;
+ var minRadiusFirst = fontSize * 6 / gRadius;
+ var minRadiusOuter = fontSize * 5 / gRadius;
+
+ if ( .25 < minRadiusInner )
+ {
+ minRadiusInner = .25;
+ }
+
+ if ( .15 < minRadiusFirst )
+ {
+ minRadiusFirst = .15;
+ }
+
+ if ( .15 < minRadiusOuter )
+ {
+ minRadiusOuter = .15;
+ }
+
+ // visibility of nodes depends on the depth they are displayed at,
+ // so we need to set the max depth assuming they can all be displayed
+ // and iterate it down based on the deepest child node we can display
+ //
+ var maxDepth;
+ var newMaxDepth = selectedNode.getMaxDepth() - selectedNode.getDepth() + 1;
+ //
+ do
+ {
+ maxDepth = newMaxDepth;
+
+ if ( ! compress && maxDepth > maxPossibleDepth )
+ {
+ maxDepth = maxPossibleDepth;
+ }
+
+ if ( compress )
+ {
+ compressedRadii = new Array(maxDepth);
+
+ compressedRadii[0] = minRadiusInner;
+
+ var offset = 0;
+
+ while
+ (
+ lerp
+ (
+ Math.atan(offset + 2),
+ Math.atan(offset + 1),
+ Math.atan(maxDepth + offset - 1),
+ minRadiusInner,
+ 1 - minRadiusOuter
+ ) - minRadiusInner > minRadiusFirst &&
+ offset < 10
+ )
+ {
+ offset++;
+ }
+
+ offset--;
+
+ for ( var i = 1; i < maxDepth; i++ )
+ {
+ compressedRadii[i] = lerp
+ (
+ Math.atan(i + offset),
+ Math.atan(offset),
+ Math.atan(maxDepth + offset - 1),
+ minRadiusInner,
+ 1 - minRadiusOuter
+ )
+ }
+ }
+ else
+ {
+ nodeRadius = 1 / maxDepth;
+ }
+
+ newMaxDepth = selectedNode.maxVisibleDepth(maxDepth);
+
+ if ( compress )
+ {
+ if ( newMaxDepth <= maxPossibleDepth )
+ {
+// compress
+ }
+ }
+ else
+ {
+ if ( newMaxDepth > maxPossibleDepth )
+ {
+ newMaxDepth = maxPossibleDepth;
+ }
+ }
+ }
+ while ( newMaxDepth < maxDepth );
+
+ maxDisplayDepth = maxDepth;
+
+ lightnessFactor = (lightnessMax - lightnessBase) / (maxDepth > 8 ? 8 : maxDepth);
+ keys = 0;
+
+ nLabelOffsets = new Array(maxDisplayDepth - 1);
+ labelOffsets = new Array(maxDisplayDepth - 1);
+ labelLastNodes = new Array(maxDisplayDepth - 1);
+ labelFirstNodes = new Array(maxDisplayDepth - 1);
+
+ for ( var i = 0; i < maxDisplayDepth - 1; i++ )
+ {
+ if ( compress )
+ {
+ if ( i == maxDisplayDepth - 1 )
+ {
+ nLabelOffsets[i] = 0;
+ }
+ else
+ {
+ var width =
+ (compressedRadii[i + 1] - compressedRadii[i]) *
+ gRadius;
+
+ nLabelOffsets[i] = Math.floor(width / fontSize / 1.2);
+
+ if ( nLabelOffsets[i] > 2 )
+ {
+ nLabelOffsets[i] = min
+ (
+ Math.floor(width / fontSize / 1.75),
+ 5
+ );
+ }
+ }
+ }
+ else
+ {
+ nLabelOffsets[i] = Math.max
+ (
+ Math.floor(Math.sqrt((nodeRadius * gRadius / fontSize)) * 1.5),
+ 3
+ );
+ }
+
+ labelOffsets[i] = Math.floor((nLabelOffsets[i] - 1) / 2);
+ labelLastNodes[i] = new Array(nLabelOffsets[i] + 1);
+ labelFirstNodes[i] = new Array(nLabelOffsets[i] + 1);
+
+ for ( var j = 0; j <= nLabelOffsets[i]; j++ )
+ {
+ // these arrays will allow nodes with neighboring labels to link to
+ // each other to determine max label length
+
+ labelLastNodes[i][j] = 0;
+ labelFirstNodes[i][j] = 0;
+ }
+ }
+
+ fontSizeText.innerHTML = fontSize;
+ fontNormal = fontSize + 'px ' + fontFamily;
+ context.font = fontNormal;
+ fontBold = 'bold ' + fontSize + 'px ' + fontFamily;
+ tickLength = fontSize * .7;
+
+ head.setTargets(0);
+
+ keySize = ((imageHeight - margin * 3) * 1 / 2) / keys * 3 / 4;
+
+ if ( keySize > fontSize * maxKeySizeFactor )
+ {
+ keySize = fontSize * maxKeySizeFactor;
+ }
+
+ keyBuffer = keySize / 3;
+
+ fontSizeLast = fontSize;
+
+ if ( datasetChanged )
+ {
+ datasetChanged = false;
+ }
+ else
+ {
+ datasetAlpha.start = 0;
+ }
+
+ var date = new Date();
+ tweenStartTime = date.getTime();
+ progress = 0;
+ tweenFrames = 0;
+
+ updateKeyControl();
+ updateDatasetWidths();
+
+ document.title = 'Krona - ' + selectedNode.name;
+ updateNavigationButtons();
+ snapshotButton.disabled = true;
+
+ maxAbsoluteDepthText.innerHTML = maxAbsoluteDepth - 1;
+
+ maxAbsoluteDepthButtonDecrease.disabled = (maxAbsoluteDepth == 2);
+ maxAbsoluteDepthButtonIncrease.disabled = (maxAbsoluteDepth == head.maxDepth);
+
+ if ( collapse != collapseLast && search.value != '' )
+ {
+ onSearchChange();
+ collapseLast = collapse;
+ }
+}
+
+function updateMaxAbsoluteDepth()
+{
+ while ( selectedNode.depth > maxAbsoluteDepth - 1 )
+ {
+ selectedNode = selectedNode.getParent();
+ }
+}
+
+function updateNavigationButtons()
+{
+ backButton.disabled = (nodeHistoryPosition == 0);
+// upButton.disabled = (selectedNode.getParent() == 0);
+ forwardButton.disabled = (nodeHistoryPosition == nodeHistory.length);
+}
+
+function useHue()
+{
+ return useHueCheckBox && useHueCheckBox.checked;
+}
+/*
+function zoomOut()
+{
+ return (
+ selectedNodeLast != 0 &&
+ selectedNodeLast.getDepth() < selectedNode.getDepth());
+}
+*/
\ No newline at end of file
diff --git a/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/CombineReads.scala b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/CombineReads.scala
new file mode 100644
index 0000000000000000000000000000000000000000..af2f46af6b0a88e7e09804f4d35ac723cf0a1481
--- /dev/null
+++ b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/CombineReads.scala
@@ -0,0 +1,84 @@
+package nl.lumc.sasc.biopet.pipelines.gears
+
+import nl.lumc.sasc.biopet.core.SampleLibraryTag
+import nl.lumc.sasc.biopet.core.summary.SummaryQScript
+import nl.lumc.sasc.biopet.extensions.{ Cutadapt, Flash }
+import nl.lumc.sasc.biopet.pipelines.flexiprep.Fastqc
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by pjvanthof on 29/12/15.
+ */
+class CombineReads(val root: Configurable) extends QScript with SummaryQScript with SampleLibraryTag {
+ @Input(doc = "R1 reads in FastQ format", shortName = "R1", required = false)
+ var fastqR1: File = _
+
+ @Input(doc = "R2 reads in FastQ format", shortName = "R2", required = false)
+ var fastqR2: File = _
+
+ override def fixedValues = Map("flash" -> Map("compress" -> true))
+
+ /** Init for pipeline */
+ def init(): Unit = {
+ }
+
+ private lazy val flash = new Flash(this)
+
+ private lazy val forwardPrimers: List[String] = config("forward_primers", default = Nil)
+ private lazy val reversePrimers: List[String] = config("reverse_primers", default = Nil)
+
+ def combinedFastq: File = if ((forwardPrimers ::: reversePrimers).nonEmpty)
+ swapExt(outputDir, flash.combinedFastq, ".fastq.gz", ".clip.fastq.gz")
+ else flash.combinedFastq
+
+ def notCombinedR1Fastq: File = if ((forwardPrimers ::: reversePrimers).nonEmpty)
+ swapExt(outputDir, flash.notCombinedR1, ".fastq.gz", ".clip.fastq.gz")
+ else flash.notCombinedR1
+
+ def notCombinedR2Fastq: File = if ((forwardPrimers ::: reversePrimers).nonEmpty)
+ swapExt(outputDir, flash.notCombinedR2, ".fastq.gz", ".clip.fastq.gz")
+ else flash.notCombinedR2
+
+ /** Pipeline itself */
+ def biopetScript(): Unit = {
+ flash.outputDirectory = new File(outputDir, "flash")
+ flash.fastqR1 = fastqR1
+ flash.fastqR2 = fastqR2
+ flash.isIntermediate = (forwardPrimers ::: reversePrimers).nonEmpty
+ add(flash)
+
+ if ((forwardPrimers ::: reversePrimers).nonEmpty) {
+ val cutadapt = new Cutadapt(this)
+ cutadapt.fastqInput = flash.combinedFastq
+ cutadapt.fastqOutput = this.combinedFastq
+ cutadapt.statsOutput = swapExt(outputDir, cutadapt.fastqOutput, ".fastq.gz", ".stats")
+ (forwardPrimers ::: reversePrimers).foreach(cutadapt.anywhere += _)
+ add(cutadapt)
+ addSummarizable(cutadapt, "cutadapt")
+ }
+
+ val combinedFastqc = Fastqc(this, this.combinedFastq, new File(outputDir, "combined_fastqc"))
+ add(combinedFastqc)
+ addSummarizable(combinedFastqc, "fastqc_combined")
+
+ val notCombinedR1Fastqc = Fastqc(this, this.combinedFastq, new File(outputDir, "not_combined_R1_fastqc"))
+ add(notCombinedR1Fastqc)
+ addSummarizable(notCombinedR1Fastqc, "fastqc_not_combined_R1")
+
+ val notCombinedR2Fastqc = Fastqc(this, this.combinedFastq, new File(outputDir, "not_combined_R2_fastqc"))
+ add(notCombinedR2Fastqc)
+ addSummarizable(notCombinedR2Fastqc, "fastqc_not_combined_R2")
+
+ addSummaryJobs()
+ }
+
+ /** Must return a map with used settings for this pipeline */
+ def summarySettings: Map[String, Any] = Map()
+
+ /** File to put in the summary for thie pipeline */
+ def summaryFiles: Map[String, File] = Map()
+
+ /** Name of summary output file */
+ def summaryFile: File = new File(outputDir, "combine_reads.summary.json")
+}
diff --git a/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/ExtractUnmappedReads.scala b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/ExtractUnmappedReads.scala
new file mode 100644
index 0000000000000000000000000000000000000000..6d043c8f7ca3e588ff5d81fbf48eeee4611a8955
--- /dev/null
+++ b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/ExtractUnmappedReads.scala
@@ -0,0 +1,51 @@
+package nl.lumc.sasc.biopet.pipelines.gears
+
+import nl.lumc.sasc.biopet.core.BiopetQScript
+import nl.lumc.sasc.biopet.extensions.picard.SamToFastq
+import nl.lumc.sasc.biopet.extensions.samtools.SamtoolsView
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by pjvanthof on 04/12/15.
+ */
+class ExtractUnmappedReads(val root: Configurable) extends QScript with BiopetQScript {
+
+ var bamFile: File = _
+
+ var outputName: String = _
+
+ override def defaults = Map(
+ "samtofastq" -> Map(
+ "validationstringency" -> "LENIENT"
+ )
+ )
+
+ def init(): Unit = {
+ require(bamFile != null)
+ if (outputName == null) outputName = bamFile.getName.stripSuffix(".bam")
+ }
+
+ def fastqUnmappedR1 = new File(outputDir, s"$outputName.unmapped.R1.fq.gz")
+ def fastqUnmappedR2 = new File(outputDir, s"$outputName.unmapped.R2.fq.gz")
+ def fastqUnmappedSingletons = new File(outputDir, s"$outputName.unmapped.singletons.fq.gz")
+
+ def biopetScript(): Unit = {
+ val samtoolsViewSelectUnmapped = new SamtoolsView(this)
+ samtoolsViewSelectUnmapped.input = bamFile
+ samtoolsViewSelectUnmapped.b = true
+ samtoolsViewSelectUnmapped.output = swapExt(outputDir, bamFile, ".bam", "unmapped.bam")
+ samtoolsViewSelectUnmapped.f = List("12")
+ samtoolsViewSelectUnmapped.isIntermediate = true
+ add(samtoolsViewSelectUnmapped)
+
+ // start bam to fastq (only on unaligned reads) also extract the matesam
+ val samToFastq = new SamToFastq(this)
+ samToFastq.input = samtoolsViewSelectUnmapped.output
+ samToFastq.fastqR1 = fastqUnmappedR1
+ samToFastq.fastqR2 = fastqUnmappedR2
+ samToFastq.fastqUnpaired = fastqUnmappedSingletons
+ samToFastq.isIntermediate = true
+ add(samToFastq)
+ }
+}
diff --git a/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/Gears.scala b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/Gears.scala
index 780f983d593544ddd5d5ffc017a65195cb0691e5..37c6f110acab86db6ffb243037e7b5a1d7c22aed 100644
--- a/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/Gears.scala
+++ b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/Gears.scala
@@ -1,158 +1,167 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
package nl.lumc.sasc.biopet.pipelines.gears
-import nl.lumc.sasc.biopet.core.summary.SummaryQScript
import nl.lumc.sasc.biopet.core.BiopetQScript.InputFile
-import nl.lumc.sasc.biopet.core.{ PipelineCommand, SampleLibraryTag }
-import nl.lumc.sasc.biopet.extensions.kraken.{ Kraken, KrakenReport }
-import nl.lumc.sasc.biopet.extensions.picard.SamToFastq
-import nl.lumc.sasc.biopet.extensions.samtools.SamtoolsView
-import nl.lumc.sasc.biopet.extensions.tools.KrakenReportToJson
+import nl.lumc.sasc.biopet.core.{ PipelineCommand, MultiSampleQScript }
+import nl.lumc.sasc.biopet.extensions.tools.MergeOtuMaps
+import nl.lumc.sasc.biopet.extensions.{ Gzip, Zcat, Ln }
+import nl.lumc.sasc.biopet.extensions.qiime.MergeOtuTables
+import nl.lumc.sasc.biopet.pipelines.flexiprep.Flexiprep
import nl.lumc.sasc.biopet.utils.config.Configurable
import org.broadinstitute.gatk.queue.QScript
/**
- * Created by wyleung
+ * Created by pjvanthof on 03/12/15.
*/
-class Gears(val root: Configurable) extends QScript with SummaryQScript with SampleLibraryTag {
+class Gears(val root: Configurable) extends QScript with MultiSampleQScript { qscript =>
def this() = this(null)
- @Input(doc = "R1 reads in FastQ format", shortName = "R1", required = false)
- var fastqR1: Option[File] = None
-
- @Input(doc = "R2 reads in FastQ format", shortName = "R2", required = false)
- var fastqR2: Option[File] = None
-
- @Input(doc = "All unmapped reads will be extracted from this bam for analysis", shortName = "bam", required = false)
- var bamFile: Option[File] = None
+ override def reportClass = {
+ val gearsReport = new GearsReport(this)
+ gearsReport.outputDir = new File(outputDir, "report")
+ gearsReport.summaryFile = summaryFile
+ Some(gearsReport)
+ }
- @Argument(required = false)
- var outputName: String = _
+ override def fixedValues = Map("gearssingle" -> Map("skip_flexiprep" -> true))
- /** Executed before running the script */
+ /** Init for pipeline */
def init(): Unit = {
- require(fastqR1.isDefined || bamFile.isDefined, "Please specify fastq-file(s) or bam file")
- require(fastqR1.isDefined != bamFile.isDefined, "Provide either a bam file or la R1 file")
-
- if (outputName == null) {
- if (fastqR1.isDefined) outputName = fastqR1.map(_.getName
- .stripSuffix(".gz")
- .stripSuffix(".fastq")
- .stripSuffix(".fq"))
- .getOrElse("noName")
- else outputName = bamFile.map(_.getName.stripSuffix(".bam")).getOrElse("noName")
- }
+ }
- if (fastqR1.isDefined) {
- fastqR1.foreach(inputFiles :+= InputFile(_))
- fastqR2.foreach(inputFiles :+= InputFile(_))
- } else {
- inputFiles :+= InputFile(bamFile.get)
- }
+ /** Name of summary output file */
+ def summaryFile: File = new File(outputDir, "gears.summary.json")
+
+ /** Pipeline itself */
+ def biopetScript(): Unit = {
+ addSamplesJobs()
+ addSummaryJobs()
}
- override def reportClass = {
- val gears = new GearsReport(this)
- gears.outputDir = new File(outputDir, "report")
- gears.summaryFile = summaryFile
- sampleId.foreach(gears.args += "sampleId" -> _)
- libId.foreach(gears.args += "libId" -> _)
- Some(gears)
+ def qiimeClosedDir: Option[File] = {
+ if (samples.values.flatMap(_.gs.qiimeClosed).nonEmpty) {
+ Some(new File(outputDir, "qiime_closed_reference"))
+ } else None
+
}
- override def defaults = Map(
- "samtofastq" -> Map(
- "validationstringency" -> "LENIENT"
- )
- )
- /** Method to add jobs */
- def biopetScript(): Unit = {
- val fastqFiles: List[File] = bamFile.map { bamfile =>
-
- val samtoolsViewSelectUnmapped = new SamtoolsView(this)
- samtoolsViewSelectUnmapped.input = bamfile
- samtoolsViewSelectUnmapped.b = true
- samtoolsViewSelectUnmapped.output = new File(outputDir, s"$outputName.unmapped.bam")
- samtoolsViewSelectUnmapped.f = List("12")
- samtoolsViewSelectUnmapped.isIntermediate = true
- add(samtoolsViewSelectUnmapped)
-
- // start bam to fastq (only on unaligned reads) also extract the matesam
- val samToFastq = new SamToFastq(this)
- samToFastq.input = samtoolsViewSelectUnmapped.output
- samToFastq.fastqR1 = new File(outputDir, s"$outputName.unmapped.R1.fq.gz")
- samToFastq.fastqR2 = new File(outputDir, s"$outputName.unmapped.R2.fq.gz")
- samToFastq.fastqUnpaired = new File(outputDir, s"$outputName.unmapped.singleton.fq.gz")
- samToFastq.isIntermediate = true
- add(samToFastq)
-
- List(samToFastq.fastqR1, samToFastq.fastqR2)
- }.getOrElse(List(fastqR1, fastqR2).flatten)
-
- // start kraken
- val krakenAnalysis = new Kraken(this)
- krakenAnalysis.input = fastqFiles
- krakenAnalysis.output = new File(outputDir, s"$outputName.krkn.raw")
-
- krakenAnalysis.paired = fastqFiles.length == 2
-
- krakenAnalysis.classified_out = Some(new File(outputDir, s"$outputName.krkn.classified.fastq"))
- krakenAnalysis.unclassified_out = Some(new File(outputDir, s"$outputName.krkn.unclassified.fastq"))
- add(krakenAnalysis)
-
- outputFiles += ("kraken_output_raw" -> krakenAnalysis.output)
- outputFiles += ("kraken_classified_out" -> krakenAnalysis.classified_out.getOrElse(""))
- outputFiles += ("kraken_unclassified_out" -> krakenAnalysis.unclassified_out.getOrElse(""))
-
- // create kraken summary file
- val krakenReport = new KrakenReport(this)
- krakenReport.input = krakenAnalysis.output
- krakenReport.show_zeros = true
- krakenReport.output = new File(outputDir, s"$outputName.krkn.full")
- add(krakenReport)
-
- outputFiles += ("kraken_report_input" -> krakenReport.input)
- outputFiles += ("kraken_report_output" -> krakenReport.output)
-
- val krakenReportJSON = new KrakenReportToJson(this)
- krakenReportJSON.inputReport = krakenReport.output
- krakenReportJSON.output = new File(outputDir, s"$outputName.krkn.json")
- krakenReportJSON.skipNames = config("skipNames", default = false)
- add(krakenReportJSON)
- addSummarizable(krakenReportJSON, "krakenreport")
-
- outputFiles += ("kraken_report_json_input" -> krakenReportJSON.inputReport)
- outputFiles += ("kraken_report_json_output" -> krakenReportJSON.output)
+ def qiimeClosedOtuTable: Option[File] = qiimeClosedDir.map(new File(_, "otu_table.biom"))
+ def qiimeClosedOtuMap: Option[File] = qiimeClosedDir.map(new File(_, "otu_map.txt"))
+
+ /**
+ * Method where the multisample jobs should be added, this will be executed only when running the -sample argument is not given.
+ */
+ def addMultiSampleJobs(): Unit = {
+ val gss = samples.values.flatMap(_.gs.qiimeClosed).toList
+ val closedOtuTables = gss.map(_.otuTable)
+ val closedOtuMaps = gss.map(_.otuMap)
+ require(closedOtuTables.size == closedOtuMaps.size)
+ if (closedOtuTables.nonEmpty) {
+ if (closedOtuTables.size > 1) {
+ val mergeTables = new MergeOtuTables(qscript)
+ mergeTables.input = closedOtuTables
+ mergeTables.outputFile = qiimeClosedOtuTable.get
+ add(mergeTables)
+
+ val mergeMaps = new MergeOtuMaps(qscript)
+ mergeMaps.input = closedOtuMaps
+ mergeMaps.output = qiimeClosedOtuMap.get
+ add(mergeMaps)
+
+ } else {
+ add(Ln(qscript, closedOtuMaps.head, qiimeClosedOtuMap.get))
+ add(Ln(qscript, closedOtuTables.head, qiimeClosedOtuTable.get))
+ }
+
+ //TODO: Plots
- addSummaryJobs()
+ }
}
- /** Location of summary file */
- def summaryFile = new File(outputDir, sampleId.getOrElse("sampleName_unknown") + ".gears.summary.json")
+ /**
+ * Factory method for Sample class
+ * @param id SampleId
+ * @return Sample class
+ */
+ def makeSample(id: String): Sample = new Sample(id)
+
+ class Sample(sampleId: String) extends AbstractSample(sampleId) {
+ /**
+ * Factory method for Library class
+ * @param id SampleId
+ * @return Sample class
+ */
+ def makeLibrary(id: String): Library = new Library(id)
+
+ class Library(libId: String) extends AbstractLibrary(libId) {
+
+ lazy val flexiprep = new Flexiprep(qscript)
+ flexiprep.sampleId = Some(sampleId)
+ flexiprep.libId = Some(libId)
+ flexiprep.input_R1 = config("R1")
+ flexiprep.input_R2 = config("R2")
+ flexiprep.outputDir = new File(libDir, "flexiprep")
+
+ lazy val gs = new GearsSingle(qscript)
+ gs.sampleId = Some(sampleId)
+ gs.libId = Some(libId)
+ gs.outputDir = libDir
+
+ /** Function that add library jobs */
+ protected def addJobs(): Unit = {
+ inputFiles :+= InputFile(flexiprep.input_R1, config("R1_md5"))
+ flexiprep.input_R2.foreach(inputFiles :+= InputFile(_, config("R2_md5")))
+ add(flexiprep)
+
+ gs.fastqR1 = Some(flexiprep.fastqR1Qc)
+ gs.fastqR2 = flexiprep.fastqR2Qc
+ add(gs)
+ }
+
+ /** Must return files to store into summary */
+ def summaryFiles: Map[String, File] = Map()
+
+ /** Must returns stats to store into summary */
+ def summaryStats = Map()
+ }
+
+ lazy val gs = new GearsSingle(qscript)
+ gs.sampleId = Some(sampleId)
+ gs.outputDir = sampleDir
+
+ /** Function to add sample jobs */
+ protected def addJobs(): Unit = {
+ addPerLibJobs()
+
+ val flexipreps = libraries.values.map(_.flexiprep).toList
+
+ val mergeR1: File = new File(sampleDir, s"$sampleId.R1.fq.gz")
+ add(Zcat(qscript, flexipreps.map(_.fastqR1Qc)) | new Gzip(qscript) > mergeR1)
+
+ val mergeR2 = if (flexipreps.exists(_.paired)) Some(new File(sampleDir, s"$sampleId.R2.fq.gz")) else None
+ mergeR2.foreach { file =>
+ add(Zcat(qscript, flexipreps.flatMap(_.fastqR2Qc)) | new Gzip(qscript) > file)
+ }
+
+ gs.fastqR1 = Some(mergeR1)
+ gs.fastqR2 = mergeR2
+ add(gs)
+ }
+
+ /** Must return files to store into summary */
+ def summaryFiles: Map[String, File] = Map()
+
+ /** Must returns stats to store into summary */
+ def summaryStats: Any = Map()
+ }
- /** Pipeline settings shown in the summary file */
- def summarySettings: Map[String, Any] = Map.empty
+ /** Must return a map with used settings for this pipeline */
+ def summarySettings: Map[String, Any] = Map()
- /** Statistics shown in the summary file */
- def summaryFiles: Map[String, File] = Map.empty ++
- (if (bamFile.isDefined) Map("input_bam" -> bamFile.get) else Map()) ++
- (if (fastqR1.isDefined) Map("input_R1" -> fastqR1.get) else Map()) ++
- outputFiles
+ /** File to put in the summary for thie pipeline */
+ def summaryFiles: Map[String, File] = (
+ qiimeClosedOtuTable.map("qiime_closed_otu_table" -> _) ++
+ qiimeClosedOtuMap.map("qiime_closed_otu_map" -> _)
+ ).toMap
}
-/** This object give a default main method to the pipelines */
object Gears extends PipelineCommand
\ No newline at end of file
diff --git a/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsKraken.scala b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsKraken.scala
new file mode 100644
index 0000000000000000000000000000000000000000..d1eda017425529f4732e166836500abda153958c
--- /dev/null
+++ b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsKraken.scala
@@ -0,0 +1,157 @@
+package nl.lumc.sasc.biopet.pipelines.gears
+
+import java.io.{ File, PrintWriter }
+
+import nl.lumc.sasc.biopet.core.SampleLibraryTag
+import nl.lumc.sasc.biopet.core.summary.SummaryQScript
+import nl.lumc.sasc.biopet.extensions.kraken.{ KrakenReport, Kraken }
+import nl.lumc.sasc.biopet.extensions.tools.KrakenReportToJson
+import nl.lumc.sasc.biopet.utils.ConfigUtils
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+import scala.collection.mutable
+import scala.xml.{ PrettyPrinter, Node }
+
+/**
+ * Created by pjvanthof on 04/12/15.
+ */
+class GearsKraken(val root: Configurable) extends QScript with SummaryQScript with SampleLibraryTag {
+
+ var fastqR1: File = _
+
+ var fastqR2: Option[File] = None
+
+ var outputName: String = _
+
+ def init(): Unit = {
+ require(fastqR1 != null)
+ if (outputName == null) outputName = fastqR1.getName
+ .stripSuffix(".gz")
+ .stripSuffix(".fq")
+ .stripSuffix(".fastq")
+ }
+
+ def biopetScript(): Unit = {
+ // start kraken
+ val krakenAnalysis = new Kraken(this)
+ krakenAnalysis.input = fastqR1 :: fastqR2.toList
+ krakenAnalysis.output = new File(outputDir, s"$outputName.krkn.raw")
+
+ krakenAnalysis.paired = fastqR2.isDefined
+
+ krakenAnalysis.classified_out = Some(new File(outputDir, s"$outputName.krkn.classified.fastq"))
+ krakenAnalysis.unclassified_out = Some(new File(outputDir, s"$outputName.krkn.unclassified.fastq"))
+ add(krakenAnalysis)
+
+ outputFiles += ("kraken_output_raw" -> krakenAnalysis.output)
+ outputFiles += ("kraken_classified_out" -> krakenAnalysis.classified_out.getOrElse(""))
+ outputFiles += ("kraken_unclassified_out" -> krakenAnalysis.unclassified_out.getOrElse(""))
+
+ // create kraken summary file
+ val krakenReport = new KrakenReport(this)
+ krakenReport.input = krakenAnalysis.output
+ krakenReport.show_zeros = true
+ krakenReport.output = new File(outputDir, s"$outputName.krkn.full")
+ add(krakenReport)
+
+ outputFiles += ("kraken_report_input" -> krakenReport.input)
+ outputFiles += ("kraken_report_output" -> krakenReport.output)
+
+ val krakenReportJSON = new KrakenReportToJson(this)
+ krakenReportJSON.inputReport = krakenReport.output
+ krakenReportJSON.output = new File(outputDir, s"$outputName.krkn.json")
+ krakenReportJSON.skipNames = config("skipNames", default = false)
+ add(krakenReportJSON)
+ addSummarizable(krakenReportJSON, "krakenreport")
+
+ outputFiles += ("kraken_report_json_input" -> krakenReportJSON.inputReport)
+ outputFiles += ("kraken_report_json_output" -> krakenReportJSON.output)
+
+ addSummaryJobs()
+ }
+
+ /** Location of summary file */
+ def summaryFile = new File(outputDir, sampleId.getOrElse("sampleName_unknown") + ".kraken.summary.json")
+
+ /** Pipeline settings shown in the summary file */
+ def summarySettings: Map[String, Any] = Map.empty
+
+ /** Statistics shown in the summary file */
+ def summaryFiles: Map[String, File] = outputFiles + ("input_R1" -> fastqR1) ++ (fastqR2 match {
+ case Some(file) => Map("input_R1" -> file)
+ case _ => Map()
+ })
+}
+
+object GearsKraken {
+
+ def convertKrakenJsonToKronaXml(files: Map[String, File], outputFile: File): Unit = {
+ val summaries = files.map { case (k, v) => k -> ConfigUtils.fileToConfigMap(v) }
+ convertKrakenSummariesToKronaXml(summaries, outputFile)
+ }
+
+ def convertKrakenSummariesToKronaXml(summaries: Map[String, Map[String, Any]], outputFile: File): Unit = {
+
+ val samples = summaries.keys.toList.sorted
+
+ val taxs: mutable.Map[String, Any] = mutable.Map()
+
+ def addTax(map: Map[String, Any], path: List[String] = Nil): Unit = {
+ val name = map("name").toString
+ val x = path.foldLeft(taxs)((a, b) => if (a.contains(b)) a(b).asInstanceOf[mutable.Map[String, Any]] else {
+ a += b -> mutable.Map[String, Any]()
+ a(b).asInstanceOf[mutable.Map[String, Any]]
+ })
+
+ if (!x.contains(name)) x += name -> mutable.Map[String, Any]()
+
+ map("children").asInstanceOf[List[Any]].foreach(x => addTax(x.asInstanceOf[Map[String, Any]], path ::: name :: Nil))
+ }
+
+ summaries.foreach { x => addTax(x._2("classified").asInstanceOf[Map[String, Any]]) }
+
+ def getValue(sample: String, path: List[String], key: String) = {
+ path.foldLeft(summaries(sample)("classified").asInstanceOf[Map[String, Any]]) { (b, a) =>
+ b.getOrElse("children", List[Map[String, Any]]())
+ .asInstanceOf[List[Map[String, Any]]]
+ .find(_.getOrElse("name", "") == a).getOrElse(Map[String, Any]())
+ }.get(key)
+ }
+
+ def createNodes(map: mutable.Map[String, Any], path: List[String] = Nil): Seq[Node] = {
+ map.map {
+ case (k, v) =>
+ val node = <node name={ k }></node>
+ val sizes = samples.map { sample =>
+ if (k == "root") {
+ val unclassified = summaries(sample)("unclassified").asInstanceOf[Map[String, Any]]("size").asInstanceOf[Long]
+ <val>
+ { getValue(sample, (path ::: k :: Nil).tail, "size").getOrElse(0).toString.toLong + unclassified }
+ </val>
+ } else {
+ <val>
+ { getValue(sample, (path ::: k :: Nil).tail, "size").getOrElse(0) }
+ </val>
+ }
+ }
+ val size = <size>{ sizes }</size>
+ node.copy(child = size ++ createNodes(v.asInstanceOf[mutable.Map[String, Any]], path ::: k :: Nil))
+ }.toSeq
+ }
+
+ val xml = <krona>
+ <attributes magnitude="size">
+ <attribute display="size">size</attribute>
+ </attributes>
+ <datasets>
+ { samples.map { sample => <dataset>{ sample }</dataset> } }
+ </datasets>
+ </krona>
+
+ val writer = new PrintWriter(outputFile)
+ val prettyXml = new PrettyPrinter(80, 2)
+ writer.println(prettyXml.format(xml.copy(child = xml.child ++ createNodes(taxs))))
+ writer.close()
+ }
+}
\ No newline at end of file
diff --git a/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsQiimeClosed.scala b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsQiimeClosed.scala
new file mode 100644
index 0000000000000000000000000000000000000000..7fa102d1111b64967c2b5a71088729feed06c804
--- /dev/null
+++ b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsQiimeClosed.scala
@@ -0,0 +1,135 @@
+package nl.lumc.sasc.biopet.pipelines.gears
+
+import java.io.{ File, PrintWriter }
+
+import nl.lumc.sasc.biopet.core.summary.SummaryQScript
+import nl.lumc.sasc.biopet.core.SampleLibraryTag
+import nl.lumc.sasc.biopet.extensions.Flash
+import nl.lumc.sasc.biopet.extensions.qiime._
+import nl.lumc.sasc.biopet.utils.ConfigUtils
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+import scala.collection.mutable
+import scala.collection.mutable.ListBuffer
+import scala.xml.{ PrettyPrinter, Elem }
+
+/**
+ * Created by pjvan_thof on 12/4/15.
+ */
+class GearsQiimeClosed(val root: Configurable) extends QScript with SummaryQScript with SampleLibraryTag {
+
+ var fastqInput: File = _
+
+ override def defaults = Map(
+ "splitlibrariesfastq" -> Map(
+ "barcode_type" -> "not-barcoded"
+ )
+ )
+
+ def init() = {
+ require(fastqInput != null)
+ }
+
+ private var _otuMap: File = _
+ def otuMap = _otuMap
+
+ private var _otuTable: File = _
+ def otuTable = _otuTable
+
+ def biopetScript() = {
+
+ val splitLib = new SplitLibrariesFastq(this)
+ splitLib.input :+= fastqInput
+ splitLib.outputDir = new File(outputDir, "split_libraries_fastq")
+ sampleId.foreach(splitLib.sample_ids :+= _)
+ add(splitLib)
+
+ val closedReference = new PickClosedReferenceOtus(this)
+ closedReference.inputFasta = splitLib.outputSeqs
+ closedReference.outputDir = new File(outputDir, "pick_closed_reference_otus")
+ add(closedReference)
+ _otuMap = closedReference.otuMap
+ _otuTable = closedReference.otuTable
+
+ addSummaryJobs()
+ }
+
+ /** Must return a map with used settings for this pipeline */
+ def summarySettings: Map[String, Any] = Map()
+
+ /** File to put in the summary for thie pipeline */
+ def summaryFiles: Map[String, File] = Map("otu_table" -> otuTable, "otu_map" -> otuMap)
+
+ /** Name of summary output file */
+ def summaryFile: File = new File(outputDir, "summary.closed_reference.json")
+}
+
+object GearsQiimeClosed {
+ def qiimeBiomToKrona(inputFile: File, outputFile: File): Unit = {
+ val biom = ConfigUtils.fileToConfigMap(inputFile)
+
+ val samples = biom("columns").asInstanceOf[List[Map[String, Any]]].toArray.map(_("id"))
+
+ val sortedSamples = samples.toList.map(_.toString).sorted
+
+ case class TaxNode(name: String, level: String) {
+ val childs: ListBuffer[TaxNode] = ListBuffer()
+
+ val counts: mutable.Map[String, Long] = mutable.Map()
+ def totalCount(sample: String): Long = counts.getOrElse(sample, 0L) + childs.map(_.totalCount(sample)).sum
+
+ def node: Elem = {
+ val sizes = sortedSamples.map { sample => <val>{ totalCount(sample) }</val> }
+ val size = <size>{ sizes }</size>
+
+ val node = <node name={ name }>{ size }</node>
+
+ node.copy(child = node.child ++ childs.map(_.node))
+ }
+ }
+
+ val root = TaxNode("root", "-")
+
+ val taxs = biom("rows").asInstanceOf[List[Map[String, Any]]].toArray.map { row =>
+ val taxonomy = row("metadata").asInstanceOf[Map[String, Any]]("taxonomy")
+ .asInstanceOf[List[String]].filter(!_.endsWith("__"))
+ taxonomy.foldLeft(root) { (a, b) =>
+ val n = b.split("__", 2)
+ val level = n(0)
+ val name = n(1)
+ val bla = a.childs.find(_ == TaxNode(name, level))
+ bla match {
+ case Some(node) => node
+ case _ =>
+ val node = TaxNode(name, level)
+ a.childs += node
+ node
+ }
+ }
+ }
+
+ biom("data").asInstanceOf[List[List[Any]]].map { data =>
+ val row = data(0).asInstanceOf[Long]
+ val column = data(1).asInstanceOf[Long]
+ val value = data(2).asInstanceOf[Long]
+ val sample = samples(column.toInt).toString
+ taxs(row.toInt).counts += sample -> (value + taxs(row.toInt).counts.getOrElse(sample, 0L))
+ value
+ }.sum
+
+ val xml = <krona>
+ <attributes magnitude="size">
+ <attribute display="size">size</attribute>
+ </attributes>
+ <datasets>
+ { sortedSamples.map { sample => <dataset>{ sample }</dataset> } }
+ </datasets>
+ </krona>
+
+ val writer = new PrintWriter(outputFile)
+ val prettyXml = new PrettyPrinter(80, 2)
+ writer.println(prettyXml.format(xml.copy(child = xml.child :+ root.node)))
+ writer.close()
+ }
+}
diff --git a/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsQiimeRtax.scala b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsQiimeRtax.scala
new file mode 100644
index 0000000000000000000000000000000000000000..f50a38a8652c4f14f26a62eb3f4a55f6a0cce9f9
--- /dev/null
+++ b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsQiimeRtax.scala
@@ -0,0 +1,82 @@
+package nl.lumc.sasc.biopet.pipelines.gears
+
+import nl.lumc.sasc.biopet.core.{ SampleLibraryTag, BiopetQScript }
+import nl.lumc.sasc.biopet.extensions.qiime.{ SplitLibrariesFastq, AssignTaxonomy, PickRepSet, PickOtus }
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by pjvan_thof on 12/4/15.
+ */
+class GearsQiimeRtax(val root: Configurable) extends QScript with BiopetQScript with SampleLibraryTag {
+
+ var fastqR1: File = _
+
+ var fastqR2: Option[File] = None
+
+ override def fixedValues = Map(
+ "assigntaxonomy" -> Map(
+ "assignment_method" -> "rtax"
+ )
+ )
+
+ override def defaults = Map(
+ "pickotus" -> Map(
+ "otu_picking_method" -> "uclust_ref",
+ "suppress_new_clusters" -> true,
+ "enable_rev_strand_match" -> true
+ ),
+ "splitlibrariesfastq" -> Map(
+ "barcode_type" -> "not-barcoded"
+ ),
+ "assigntaxonomy" -> Map(
+ "amplicon_id_regex" -> """(\S+)\s+(\S+?)""",
+ "header_id_regex" -> """S+s+(S+?)""",
+ "read_id_regex" -> """S+s+(S+)"""
+ )
+ )
+
+ def init() = {
+ require(fastqR1 != null)
+ }
+
+ def biopetScript() = {
+
+ val slfR1 = new SplitLibrariesFastq(this)
+ slfR1.input :+= fastqR1
+ slfR1.outputDir = new File(outputDir, "split_libraries_fastq_R1")
+ sampleId.foreach(slfR1.sample_ids :+= _)
+ add(slfR1)
+
+ lazy val slfR2 = fastqR2.map { file =>
+ val j = new SplitLibrariesFastq(this)
+ j.input :+= file
+ j.outputDir = new File(outputDir, "split_libraries_fastq_R2")
+ sampleId.foreach(j.sample_ids :+= _)
+ add(j)
+ j
+ }
+
+ val pickOtus = new PickOtus(this)
+ pickOtus.inputFasta = slfR1.outputSeqs
+ pickOtus.outputDir = new File(outputDir, "pick_otus")
+ add(pickOtus)
+
+ val pickRepSet = new PickRepSet(this)
+ val repSetOutputDir = new File(outputDir, "pick_rep_set")
+ pickRepSet.inputFile = pickOtus.otusTxt
+ pickRepSet.fastaInput = Some(slfR1.outputSeqs)
+ pickRepSet.outputFasta = Some(new File(repSetOutputDir, slfR1.outputSeqs.getName))
+ pickRepSet.logFile = Some(new File(repSetOutputDir, slfR1.outputSeqs.getName
+ .stripSuffix(".fasta").stripSuffix(".fa").stripSuffix(".fna") + ".log"))
+ add(pickRepSet)
+
+ val assignTaxonomy = new AssignTaxonomy(this)
+ assignTaxonomy.outputDir = new File(outputDir, "assign_taxonomy")
+ assignTaxonomy.jobOutputFile = new File(assignTaxonomy.outputDir, ".assign_taxonomy.out")
+ assignTaxonomy.inputFasta = pickRepSet.outputFasta.get
+ assignTaxonomy.read_1_seqs_fp = Some(slfR1.outputSeqs)
+ assignTaxonomy.read_2_seqs_fp = slfR2.map(_.outputSeqs)
+ add(assignTaxonomy)
+ }
+}
diff --git a/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsReport.scala b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsReport.scala
index f0ad762064f8d4a16b2750c4a3d749ab06b8b581..aa819f08c3ddd78d96853e88c4f660417f89ae8f 100644
--- a/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsReport.scala
+++ b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsReport.scala
@@ -1,50 +1,95 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
package nl.lumc.sasc.biopet.pipelines.gears
-import nl.lumc.sasc.biopet.core.report._
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.report.{ ReportSection, ReportPage, MultisampleReportBuilder, ReportBuilderExtension }
+import nl.lumc.sasc.biopet.pipelines.flexiprep.FlexiprepReport
import nl.lumc.sasc.biopet.utils.config.Configurable
+/**
+ * Report for Gears
+ *
+ * Created by pjvan_thof on 12/10/15.
+ */
class GearsReport(val root: Configurable) extends ReportBuilderExtension {
def builder = GearsReport
}
-object GearsReport extends ReportBuilder {
+object GearsReport extends MultisampleReportBuilder {
- // TODO: Add dustbin analysis (aggregated)
- // TODO: Add alignment stats per sample for the dustbin analysis
+ def reportName = "Gears Report"
- override def extFiles = super.extFiles ++ List("js/gears.js")
+ override def extFiles = super.extFiles ++ List("js/gears.js", "js/krona-2.0.js", "img/krona/loading.gif", "img/krona/hidden.png", "img/krona/favicon.ico")
.map(x => ExtFile("/nl/lumc/sasc/biopet/pipelines/gears/report/ext/" + x, x))
def indexPage = {
+ val krakenExecuted = summary.getSampleValues("gearskraken", "stats", "krakenreport").values.forall(_.isDefined)
+ val qiimeClosesOtuTable = summary.getValue("gears", "files", "pipeline", "qiime_closed_otu_table", "path")
+ .map(x => new File(x.toString))
+
ReportPage(
+ (if (krakenExecuted) List("Kraken analysis" -> ReportPage(List(), List(
+ "Krona plot" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gears/krakenKrona.ssp"
+ )), Map()))
+ else Nil) ::: (if (qiimeClosesOtuTable.isDefined) List("Qiime closed reference analysis" -> ReportPage(List(), List(
+ "Krona plot" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gears/qiimeKrona.ssp"
+ )), Map("biomFile" -> qiimeClosesOtuTable.get)))
+ else Nil) ::: List("Samples" -> generateSamplesPage(pageArgs)) ++
+ Map(
+ "Versions" -> ReportPage(List(), List(
+ "Executables" -> ReportSection("/nl/lumc/sasc/biopet/core/report/executables.ssp")
+ ), Map())
+ ),
List(
- "Versions" -> ReportPage(List(), List((
- "Executables" -> ReportSection("/nl/lumc/sasc/biopet/core/report/executables.ssp"
- ))), Map())
- ),
- List(
- "Gears intro" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gears/gearsFront.ssp"),
- "Sunburst analysis" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gears/gearsSunburst.ssp")
- ),
+ "Report" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gears/gearsFront.ssp")) ++
+ List(
+ "QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp",
+ Map("showPlot" -> true, "showTable" -> false)),
+ "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp",
+ Map("showPlot" -> true, "showTable" -> false))
+ ),
pageArgs
)
}
- def reportName = "Gears :: Metagenomics Report"
+ /** Single sample page */
+ def samplePage(sampleId: String, args: Map[String, Any]): ReportPage = {
+ val krakenExecuted = summary.getValue(Some(sampleId), None, "gearskraken", "stats", "krakenreport").isDefined
+ val qiimeClosesOtuTable = summary.getValue(Some(sampleId), None, "gearsqiimeclosed", "files", "pipeline", "otu_table", "path")
+ .map(x => new File(x.toString))
-}
+ ReportPage((if (krakenExecuted) List("Kraken" -> ReportPage(List(), List(
+ "Kraken analysis" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gears/krakenKrona.ssp"
+ )), Map()))
+ else Nil) ::: (if (qiimeClosesOtuTable.isDefined) List("Qiime closed reference analysis" -> ReportPage(List(), List(
+ "Krona plot" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gears/qiimeKrona.ssp"
+ )), Map("biomFile" -> qiimeClosesOtuTable.get)))
+ else Nil) ::: List(
+ "Libraries" -> generateLibraryPage(args)
+ ), List("QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp"),
+ "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp")
+ ), args)
+ }
+
+ /** Library page */
+ def libraryPage(sampleId: String, libId: String, args: Map[String, Any]): ReportPage = {
+ val flexiprepExecuted = summary.getLibraryValue(sampleId, libId, "flexiprep").isDefined
+ val krakenExecuted = summary.getValue(Some(sampleId), Some(libId), "gearskraken", "stats", "krakenreport").isDefined
+ val qiimeClosesOtuTable = summary.getValue(Some(sampleId), Some(libId), "gearsqiimeclosed", "files", "pipeline", "otu_table", "path")
+ .map(x => new File(x.toString))
+
+ ReportPage(
+ (if (flexiprepExecuted) List("QC" -> FlexiprepReport.flexiprepPage) else Nil
+ ) ::: (if (krakenExecuted) List("Kraken" -> ReportPage(List(), List(
+ "Kraken analysis" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gears/krakenKrona.ssp"
+ )), Map()))
+ else Nil) ::: (if (qiimeClosesOtuTable.isDefined) List("Qiime closed reference analysis" -> ReportPage(List(), List(
+ "Krona plot" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gears/qiimeKrona.ssp"
+ )), Map("biomFile" -> qiimeClosesOtuTable.get)))
+ else Nil), List(
+ "QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp"),
+ "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp")
+ ), args)
+ }
+
+}
\ No newline at end of file
diff --git a/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSeqCount.scala b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSeqCount.scala
new file mode 100644
index 0000000000000000000000000000000000000000..70b850ce1ae85d8f9dcf70cab4484e126b6eb589
--- /dev/null
+++ b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSeqCount.scala
@@ -0,0 +1,29 @@
+package nl.lumc.sasc.biopet.pipelines.gears
+
+import nl.lumc.sasc.biopet.core.{ BiopetQScript, SampleLibraryTag }
+import nl.lumc.sasc.biopet.core.summary.SummaryQScript
+import nl.lumc.sasc.biopet.extensions.tools.SageCountFastq
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by pjvan_thof on 12/29/15.
+ */
+class GearsSeqCount(val root: Configurable) extends QScript with BiopetQScript with SampleLibraryTag {
+
+ var fastqInput: File = _
+
+ def countFile = swapExt(outputDir, fastqInput, ".fastq.gz", ".counts.txt")
+
+ /** Init for pipeline */
+ def init(): Unit = {
+ }
+
+ /** Pipeline itself */
+ def biopetScript(): Unit = {
+ val seqCount = new SageCountFastq(this)
+ seqCount.input = fastqInput
+ seqCount.output = countFile
+ add(seqCount)
+ }
+}
diff --git a/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSingle.scala b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSingle.scala
new file mode 100644
index 0000000000000000000000000000000000000000..2be7fe4bf97783cd27a9dc3da7dac63d528b7271
--- /dev/null
+++ b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSingle.scala
@@ -0,0 +1,166 @@
+/**
+ * Biopet is built on top of GATK Queue for building bioinformatic
+ * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
+ * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
+ * should also be able to execute Biopet tools and pipelines.
+ *
+ * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
+ *
+ * Contact us at: sasc@lumc.nl
+ *
+ * A dual licensing mode is applied. The source code within this project that are
+ * not part of GATK Queue is freely available for non-commercial use under an AGPL
+ * license; For commercial users or users who do not want to follow the AGPL
+ * license, please contact us to obtain a separate license.
+ */
+package nl.lumc.sasc.biopet.pipelines.gears
+
+import nl.lumc.sasc.biopet.core.summary.SummaryQScript
+import nl.lumc.sasc.biopet.core.BiopetQScript.InputFile
+import nl.lumc.sasc.biopet.core.{ PipelineCommand, SampleLibraryTag }
+import nl.lumc.sasc.biopet.pipelines.flexiprep.Flexiprep
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by wyleung
+ */
+class GearsSingle(val root: Configurable) extends QScript with SummaryQScript with SampleLibraryTag {
+ def this() = this(null)
+
+ @Input(doc = "R1 reads in FastQ format", shortName = "R1", required = false)
+ var fastqR1: Option[File] = None
+
+ @Input(doc = "R2 reads in FastQ format", shortName = "R2", required = false)
+ var fastqR2: Option[File] = None
+
+ @Input(doc = "All unmapped reads will be extracted from this bam for analysis", shortName = "bam", required = false)
+ var bamFile: Option[File] = None
+
+ @Argument(required = false)
+ var outputName: String = _
+
+ lazy val krakenScript = if (config("gears_use_kraken", default = true)) Some(new GearsKraken(this)) else None
+ lazy val qiimeRatx = if (config("gears_use_qiime_rtax", default = false)) Some(new GearsQiimeRtax(this)) else None
+ lazy val qiimeClosed = if (config("gears_use_qiime_closed", default = false)) Some(new GearsQiimeClosed(this)) else None
+ lazy val seqCount = if (config("gears_use_seq_count", default = false)) Some(new GearsSeqCount(this)) else None
+
+ /** Executed before running the script */
+ def init(): Unit = {
+ require(fastqR1.isDefined || bamFile.isDefined, "Please specify fastq-file(s) or bam file")
+ require(fastqR1.isDefined != bamFile.isDefined, "Provide either a bam file or a R1/R2 file")
+
+ if (outputName == null) {
+ if (fastqR1.isDefined) outputName = fastqR1.map(_.getName
+ .stripSuffix(".gz")
+ .stripSuffix(".fastq")
+ .stripSuffix(".fq"))
+ .getOrElse("noName")
+ else outputName = bamFile.map(_.getName.stripSuffix(".bam")).getOrElse("noName")
+ }
+
+ if (fastqR1.isDefined) {
+ fastqR1.foreach(inputFiles :+= InputFile(_))
+ fastqR2.foreach(inputFiles :+= InputFile(_))
+ } else inputFiles :+= InputFile(bamFile.get)
+ }
+
+ override def reportClass = {
+ val gears = new GearsSingleReport(this)
+ gears.outputDir = new File(outputDir, "report")
+ gears.summaryFile = summaryFile
+ sampleId.foreach(gears.args += "sampleId" -> _)
+ libId.foreach(gears.args += "libId" -> _)
+ Some(gears)
+ }
+
+ protected var skipFlexiprep: Boolean = config("skip_flexiprep", default = false)
+
+ protected def executeFlexiprep(r1: File, r2: Option[File]): (File, Option[File]) = {
+ if (!skipFlexiprep) {
+ val flexiprep = new Flexiprep(this)
+ flexiprep.input_R1 = r1
+ flexiprep.input_R2 = r2
+ flexiprep.outputDir = new File(outputDir, "flexiprep")
+ add(flexiprep)
+ (flexiprep.fastqR1Qc, flexiprep.fastqR2Qc)
+ } else (r1, r2)
+ }
+
+ /** Method to add jobs */
+ def biopetScript(): Unit = {
+ val (r1, r2): (File, Option[File]) = (fastqR1, fastqR2, bamFile) match {
+ case (Some(r1), _, _) => executeFlexiprep(r1, fastqR2)
+ case (_, _, Some(bam)) =>
+ val extract = new ExtractUnmappedReads(this)
+ extract.outputDir = outputDir
+ extract.bamFile = bam
+ extract.outputName = outputName
+ add(extract)
+ executeFlexiprep(extract.fastqUnmappedR1, Some(extract.fastqUnmappedR2))
+ case _ => throw new IllegalArgumentException("Missing input files")
+ }
+
+ lazy val combinedFastq = {
+ r2 match {
+ case Some(r2) =>
+ val combineReads = new CombineReads(this)
+ combineReads.outputDir = new File(outputDir, "combine_reads")
+ combineReads.fastqR1 = r1
+ combineReads.fastqR2 = r2
+ add(combineReads)
+ combineReads.combinedFastq
+ case _ => r1
+ }
+ }
+
+ krakenScript foreach { kraken =>
+ kraken.outputDir = new File(outputDir, "kraken")
+ kraken.fastqR1 = r1
+ kraken.fastqR2 = r2
+ kraken.outputName = outputName
+ add(kraken)
+ }
+
+ qiimeRatx foreach { qiimeRatx =>
+ qiimeRatx.outputDir = new File(outputDir, "qiime_rtax")
+ qiimeRatx.fastqR1 = r1
+ qiimeRatx.fastqR2 = r2
+ add(qiimeRatx)
+ }
+
+ qiimeClosed foreach { qiimeClosed =>
+ qiimeClosed.outputDir = new File(outputDir, "qiime_closed")
+ qiimeClosed.fastqInput = combinedFastq
+ add(qiimeClosed)
+ }
+
+ seqCount.foreach { seqCount =>
+ seqCount.fastqInput = combinedFastq
+ seqCount.outputDir = new File(outputDir, "seq_count")
+ add(seqCount)
+ }
+
+ addSummaryJobs()
+ }
+
+ /** Location of summary file */
+ def summaryFile = new File(outputDir, sampleId.getOrElse("sampleName_unknown") + ".gears.summary.json")
+
+ /** Pipeline settings shown in the summary file */
+ def summarySettings: Map[String, Any] = Map(
+ "skip_flexiprep" -> skipFlexiprep,
+ "gears_use_kraken" -> krakenScript.isDefined,
+ "gear_use_qiime_rtax" -> qiimeRatx.isDefined,
+ "gear_use_qiime_closed" -> qiimeClosed.isDefined
+ )
+
+ /** Statistics shown in the summary file */
+ def summaryFiles: Map[String, File] = Map.empty ++
+ (if (bamFile.isDefined) Map("input_bam" -> bamFile.get) else Map()) ++
+ (if (fastqR1.isDefined) Map("input_R1" -> fastqR1.get) else Map()) ++
+ outputFiles
+}
+
+/** This object give a default main method to the pipelines */
+object GearsSingle extends PipelineCommand
\ No newline at end of file
diff --git a/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSingleReport.scala b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSingleReport.scala
new file mode 100644
index 0000000000000000000000000000000000000000..2532afb51c1ea2b03a2f6c7280047cd8336d3db1
--- /dev/null
+++ b/public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSingleReport.scala
@@ -0,0 +1,50 @@
+/**
+ * Biopet is built on top of GATK Queue for building bioinformatic
+ * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
+ * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
+ * should also be able to execute Biopet tools and pipelines.
+ *
+ * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
+ *
+ * Contact us at: sasc@lumc.nl
+ *
+ * A dual licensing mode is applied. The source code within this project that are
+ * not part of GATK Queue is freely available for non-commercial use under an AGPL
+ * license; For commercial users or users who do not want to follow the AGPL
+ * license, please contact us to obtain a separate license.
+ */
+package nl.lumc.sasc.biopet.pipelines.gears
+
+import nl.lumc.sasc.biopet.core.report._
+import nl.lumc.sasc.biopet.utils.config.Configurable
+
+class GearsSingleReport(val root: Configurable) extends ReportBuilderExtension {
+ def builder = GearsSingleReport
+}
+
+object GearsSingleReport extends ReportBuilder {
+
+ // TODO: Add dustbin analysis (aggregated)
+ // TODO: Add alignment stats per sample for the dustbin analysis
+
+ override def extFiles = super.extFiles ++ List("js/gears.js", "js/krona-2.0.js", "img/krona/loading.gif", "img/krona/hidden.png", "img/krona/favicon.ico")
+ .map(x => ExtFile("/nl/lumc/sasc/biopet/pipelines/gears/report/ext/" + x, x))
+
+ def indexPage = {
+ ReportPage(
+ List(
+ "Versions" -> ReportPage(List(), List((
+ "Executables" -> ReportSection("/nl/lumc/sasc/biopet/core/report/executables.ssp"
+ ))), Map())
+ ),
+ List(
+ "Gears intro" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gears/gearsSingleFront.ssp"),
+ "Kraken analysis" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gears/krakenKrona.ssp")
+ ),
+ pageArgs
+ )
+ }
+
+ def reportName = "Gears :: Metagenomics Report"
+
+}
diff --git a/public/gears/src/test/resources/hpv_simu_R1.krkn.json b/public/gears/src/test/resources/hpv_simu_R1.krkn.json
new file mode 100644
index 0000000000000000000000000000000000000000..f8f31c0aee86d0bfa52fc9d83e1e6a8f74221487
--- /dev/null
+++ b/public/gears/src/test/resources/hpv_simu_R1.krkn.json
@@ -0,0 +1,135 @@
+{
+ "unclassified" : {
+ "children" : [
+
+ ],
+ "name" : "unclassified",
+ "count" : 732,
+ "taxid" : 0,
+ "size" : 732,
+ "cladelevel" : 0,
+ "taxonrank" : "U"
+ },
+ "classified" : {
+ "children" : [
+ {
+ "children" : [
+ {
+ "children" : [
+ {
+ "children" : [
+ {
+ "children" : [
+ {
+ "children" : [
+ {
+ "children" : [
+ {
+ "children" : [
+ {
+ "children" : [
+
+ ],
+ "name" : "Human herpesvirus 4 type 2",
+ "count" : 6,
+ "taxid" : 12509,
+ "size" : 6,
+ "cladelevel" : 8,
+ "taxonrank" : "-"
+ }
+ ],
+ "name" : "Human herpesvirus 4",
+ "count" : 3902,
+ "taxid" : 10376,
+ "size" : 3908,
+ "cladelevel" : 7,
+ "taxonrank" : "S"
+ }
+ ],
+ "name" : "Lymphocryptovirus",
+ "count" : 0,
+ "taxid" : 10375,
+ "size" : 3908,
+ "cladelevel" : 6,
+ "taxonrank" : "G"
+ }
+ ],
+ "name" : "Gammaherpesvirinae",
+ "count" : 0,
+ "taxid" : 10374,
+ "size" : 3908,
+ "cladelevel" : 5,
+ "taxonrank" : "-"
+ },
+ {
+ "children" : [
+ {
+ "children" : [
+ {
+ "children" : [
+
+ ],
+ "name" : "Human herpesvirus 5",
+ "count" : 5360,
+ "taxid" : 10359,
+ "size" : 5360,
+ "cladelevel" : 7,
+ "taxonrank" : "S"
+ }
+ ],
+ "name" : "Cytomegalovirus",
+ "count" : 0,
+ "taxid" : 10358,
+ "size" : 5360,
+ "cladelevel" : 6,
+ "taxonrank" : "G"
+ }
+ ],
+ "name" : "Betaherpesvirinae",
+ "count" : 0,
+ "taxid" : 10357,
+ "size" : 5360,
+ "cladelevel" : 5,
+ "taxonrank" : "-"
+ }
+ ],
+ "name" : "Herpesviridae",
+ "count" : 0,
+ "taxid" : 10292,
+ "size" : 9268,
+ "cladelevel" : 4,
+ "taxonrank" : "F"
+ }
+ ],
+ "name" : "Herpesvirales",
+ "count" : 0,
+ "taxid" : 548681,
+ "size" : 9268,
+ "cladelevel" : 3,
+ "taxonrank" : "O"
+ }
+ ],
+ "name" : "dsDNA viruses, no RNA stage",
+ "count" : 0,
+ "taxid" : 35237,
+ "size" : 9268,
+ "cladelevel" : 2,
+ "taxonrank" : "-"
+ }
+ ],
+ "name" : "Viruses",
+ "count" : 0,
+ "taxid" : 10239,
+ "size" : 9268,
+ "cladelevel" : 1,
+ "taxonrank" : "D"
+ }
+ ],
+ "name" : "root",
+ "count" : 0,
+ "taxid" : 1,
+ "size" : 9268,
+ "cladelevel" : 0,
+ "taxonrank" : "-"
+ }
+}
diff --git a/public/gears/src/test/resources/otu_table.biom b/public/gears/src/test/resources/otu_table.biom
new file mode 100644
index 0000000000000000000000000000000000000000..827ae5370dfed1c26a7b09b792edf188d3198cca
--- /dev/null
+++ b/public/gears/src/test/resources/otu_table.biom
@@ -0,0 +1 @@
+{"id": "None","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","generated_by": "QIIME 1.9.1","date": "2016-02-05T12:16:01.988182","matrix_element_type": "float","shape": [1175, 2],"type": "OTU table","matrix_type": "sparse","data": [[0,0,136.0],[1,0,6.0],[2,0,2.0],[3,0,2.0],[4,0,2.0],[5,0,37.0],[6,0,2.0],[7,0,1.0],[8,0,6.0],[9,0,59.0],[10,0,4.0],[11,0,1059.0],[11,1,1.0],[12,0,2.0],[13,0,42.0],[13,1,3.0],[14,0,10.0],[15,0,17.0],[16,0,1.0],[17,0,2.0],[18,0,1.0],[19,0,2.0],[20,0,3.0],[21,0,1.0],[22,0,1.0],[23,0,4.0],[24,0,1.0],[25,0,1.0],[26,0,3.0],[27,0,2.0],[28,0,3.0],[29,0,1.0],[30,0,40.0],[30,1,64.0],[31,0,3.0],[32,0,7.0],[33,0,10.0],[34,0,112.0],[35,0,14.0],[36,0,4.0],[37,0,3.0],[38,0,233.0],[39,0,10.0],[40,0,2.0],[41,0,1.0],[42,0,1.0],[43,0,161.0],[44,0,1.0],[45,0,1.0],[46,0,1.0],[47,0,4.0],[48,0,130.0],[49,0,1.0],[50,0,1.0],[51,0,9.0],[52,0,1.0],[53,0,14.0],[54,0,3.0],[55,0,1.0],[56,0,1.0],[57,0,229.0],[58,0,13.0],[59,0,68.0],[59,1,33.0],[60,0,2.0],[61,0,1.0],[62,0,132.0],[63,0,10.0],[63,1,1.0],[64,0,1.0],[64,1,1.0],[65,0,2.0],[66,0,11.0],[67,0,1.0],[68,0,4.0],[69,0,3.0],[70,0,1.0],[71,0,15.0],[72,0,1.0],[73,0,8.0],[74,0,1.0],[75,0,44.0],[76,0,6.0],[77,0,1.0],[78,0,59.0],[79,0,2.0],[80,0,5.0],[81,0,174.0],[82,0,1.0],[83,0,375.0],[84,0,3.0],[85,0,9.0],[86,0,1.0],[87,0,185.0],[88,0,1.0],[89,0,34.0],[90,0,1.0],[91,0,7.0],[92,0,3053.0],[93,0,2.0],[94,0,4.0],[95,0,1.0],[96,0,5.0],[97,0,12.0],[98,0,85.0],[99,0,8.0],[100,0,3.0],[101,0,1.0],[102,0,5.0],[103,0,12.0],[104,0,1.0],[105,0,18.0],[106,0,4.0],[107,0,115.0],[108,0,21.0],[109,0,2.0],[110,0,1.0],[111,0,2008.0],[112,0,2.0],[113,0,1.0],[114,0,1.0],[115,0,1.0],[116,0,3.0],[117,0,44.0],[118,0,3.0],[119,0,2.0],[120,0,6.0],[121,0,2.0],[122,0,208.0],[123,0,26.0],[124,0,3.0],[125,0,11.0],[126,0,40.0],[127,0,2.0],[128,0,2.0],[129,0,1.0],[130,0,1.0],[131,0,887.0],[132,0,473.0],[133,0,5.0],[134,0,1.0],[135,0,4.0],[136,0,1.0],[137,0,2.0],[138,0,7.0],[139,0,2.0],[140,0,1.0],[141,0,13.0],[142,0,6.0],[143,0,1.0],[144,0,2.0],[145,0,4.0],[146,0,3.0],[147,0,6.0],[148,0,1.0],[149,0,1.0],[150,0,66.0],[151,0,1729.0],[152,0,1.0],[153,0,1.0],[154,0,3.0],[155,0,1.0],[156,0,1.0],[157,0,1.0],[158,0,3.0],[159,0,9.0],[160,0,1.0],[161,0,12.0],[162,0,4.0],[163,0,12.0],[164,0,11.0],[165,0,25.0],[166,0,5.0],[167,0,1.0],[168,0,2.0],[169,0,1.0],[170,0,2.0],[171,0,26.0],[172,0,1.0],[173,0,3.0],[174,0,34.0],[175,0,1.0],[176,0,8.0],[177,0,35.0],[178,0,2.0],[179,0,7.0],[180,0,1.0],[181,0,4.0],[182,0,13.0],[183,0,91.0],[184,0,3.0],[185,0,1.0],[186,0,9.0],[187,0,9.0],[188,0,5.0],[189,0,21.0],[190,0,1.0],[191,0,1.0],[192,0,63.0],[193,0,1.0],[194,0,3.0],[195,0,3.0],[196,0,2.0],[197,0,6.0],[198,0,48.0],[198,1,43.0],[199,0,18.0],[200,0,4.0],[201,0,1.0],[202,0,6.0],[203,0,6.0],[204,0,1.0],[205,0,6.0],[206,0,22.0],[207,0,606.0],[208,0,6.0],[209,0,589.0],[210,0,1.0],[211,0,4.0],[212,0,3.0],[213,0,1.0],[214,0,2.0],[215,0,9.0],[216,0,1.0],[217,0,3.0],[218,0,1.0],[219,0,37.0],[220,0,1.0],[221,0,1.0],[222,0,5.0],[223,0,8.0],[224,0,6.0],[225,0,1.0],[226,0,1.0],[227,0,1.0],[228,0,1.0],[229,0,1.0],[230,0,1.0],[231,0,139.0],[232,0,2.0],[233,0,2.0],[234,0,2.0],[235,0,13.0],[236,0,1.0],[237,0,1.0],[238,0,8.0],[239,0,69.0],[240,0,3.0],[241,0,5.0],[242,0,306.0],[243,0,2.0],[244,0,2.0],[245,0,159.0],[245,1,1.0],[246,0,1.0],[247,0,4.0],[248,0,12.0],[248,1,1.0],[249,0,3.0],[250,0,7.0],[251,0,1.0],[252,0,2.0],[253,0,137.0],[254,0,1.0],[255,0,1.0],[256,0,1.0],[257,0,1.0],[258,0,1.0],[259,0,1.0],[260,0,25.0],[261,0,1.0],[262,0,22.0],[263,0,19.0],[264,0,2.0],[265,0,5.0],[266,0,1.0],[267,0,2.0],[268,0,1.0],[269,0,2.0],[270,0,2.0],[271,0,1.0],[272,0,2.0],[273,0,5.0],[274,0,1.0],[275,0,3.0],[276,0,376.0],[277,0,12.0],[278,0,1.0],[279,0,3.0],[280,0,1.0],[281,0,2.0],[282,0,1.0],[283,0,26.0],[284,0,1.0],[285,0,8.0],[286,0,1.0],[287,0,124.0],[288,0,2.0],[289,0,1.0],[290,0,137.0],[291,0,2.0],[292,0,2.0],[293,0,488.0],[294,0,1.0],[295,0,1.0],[296,0,1.0],[297,0,36.0],[298,0,3.0],[299,0,1.0],[300,0,6.0],[301,0,2.0],[302,0,3.0],[303,0,17.0],[304,0,56.0],[305,0,2.0],[306,0,1.0],[307,0,1.0],[308,0,1.0],[309,0,3.0],[309,1,2.0],[310,0,2.0],[311,0,1.0],[312,0,1.0],[313,0,1.0],[314,0,1.0],[315,0,1.0],[316,0,6.0],[317,0,5.0],[318,0,5.0],[319,0,3878.0],[320,0,35.0],[321,0,645.0],[322,0,2.0],[323,0,1.0],[324,0,5.0],[325,0,4.0],[326,0,7.0],[327,0,23.0],[328,0,6.0],[329,0,1.0],[330,0,3.0],[331,0,1.0],[332,0,7.0],[333,0,4.0],[334,0,5.0],[335,0,1.0],[336,0,1.0],[337,0,2.0],[338,0,19.0],[339,0,18.0],[340,0,2.0],[341,0,5.0],[342,0,10.0],[343,0,2.0],[344,0,1201.0],[345,0,2.0],[346,0,1.0],[347,0,2515.0],[348,0,12.0],[349,0,155.0],[350,0,7.0],[351,0,10.0],[352,0,3.0],[353,0,8.0],[353,1,1.0],[354,0,7.0],[355,0,2.0],[356,0,1.0],[357,0,3.0],[358,0,1.0],[359,0,1.0],[360,0,4.0],[361,0,71.0],[362,0,1.0],[363,0,1.0],[364,0,2.0],[365,0,1.0],[366,0,3.0],[367,0,7.0],[368,0,3.0],[369,0,1.0],[370,0,1.0],[371,0,3.0],[372,0,1.0],[373,0,3.0],[374,0,5.0],[375,0,1.0],[376,0,1.0],[377,0,1.0],[378,0,1.0],[379,0,163.0],[380,0,9.0],[381,0,2.0],[382,0,10.0],[383,0,3.0],[384,0,4.0],[385,0,2.0],[386,0,2.0],[387,0,1.0],[388,0,1083.0],[389,0,73.0],[390,0,2.0],[391,0,1.0],[392,0,2.0],[393,0,1.0],[394,0,1.0],[395,0,2.0],[396,0,1.0],[397,0,91.0],[398,0,1.0],[399,0,14.0],[400,0,21.0],[401,0,2.0],[402,0,1.0],[403,0,1.0],[404,0,2.0],[405,0,13.0],[406,0,1.0],[407,0,1.0],[408,0,1.0],[409,0,425.0],[410,0,4.0],[411,0,4525.0],[412,0,1.0],[413,0,1.0],[414,0,5.0],[415,0,5.0],[416,0,2.0],[417,0,81.0],[418,0,275.0],[419,0,3.0],[420,0,5.0],[421,0,1.0],[422,0,2.0],[423,0,59.0],[424,0,54.0],[425,0,1572.0],[425,1,2.0],[426,0,132.0],[427,0,1.0],[428,0,1.0],[429,0,13.0],[430,0,1.0],[431,0,1.0],[432,0,333.0],[433,0,446.0],[434,0,4.0],[435,0,3.0],[436,0,9.0],[437,0,1.0],[438,0,13.0],[439,0,149.0],[440,0,13.0],[441,0,17.0],[442,0,139.0],[443,0,4.0],[444,0,4.0],[445,0,5.0],[446,0,672.0],[446,1,1.0],[447,0,1.0],[448,0,1.0],[449,0,1.0],[450,0,5.0],[451,0,1.0],[452,0,9.0],[453,0,1.0],[454,0,1.0],[455,0,3.0],[456,0,88.0],[457,0,3.0],[458,0,1.0],[459,0,39.0],[460,0,24.0],[461,0,6.0],[462,0,3.0],[463,0,5.0],[464,0,60.0],[465,0,2.0],[466,0,1.0],[467,0,2.0],[468,0,1.0],[469,0,1085.0],[470,0,4.0],[471,0,5.0],[472,0,1.0],[473,0,1.0],[474,0,124.0],[475,0,1.0],[476,0,8.0],[477,0,10.0],[478,0,26.0],[479,0,3243.0],[480,0,1.0],[481,0,4.0],[482,0,18.0],[483,0,1.0],[484,0,1.0],[485,0,1.0],[486,0,7.0],[487,0,81.0],[488,0,329.0],[489,0,4.0],[490,0,2558.0],[491,0,74.0],[492,0,2.0],[493,0,5.0],[494,0,1.0],[495,0,19.0],[496,0,3.0],[497,0,1021.0],[497,1,1.0],[498,0,178.0],[499,0,2.0],[499,1,9.0],[500,0,5.0],[501,0,1.0],[502,0,1.0],[503,0,8.0],[504,0,1.0],[505,0,9.0],[506,0,158.0],[507,0,2.0],[508,0,1.0],[509,0,1.0],[510,0,1.0],[511,0,1.0],[512,0,37.0],[513,0,13.0],[514,0,7.0],[515,0,10.0],[516,0,1.0],[517,0,11.0],[518,0,2.0],[519,0,4872.0],[519,1,3.0],[520,0,1.0],[521,0,2.0],[522,0,1.0],[523,0,8.0],[524,0,1.0],[525,0,5.0],[526,0,1.0],[527,0,25.0],[528,0,3.0],[529,0,27.0],[530,0,2.0],[531,0,2.0],[532,0,1.0],[533,0,114.0],[534,0,8.0],[535,0,3.0],[536,0,1.0],[537,0,1.0],[538,0,1.0],[539,0,2.0],[540,0,4.0],[541,0,1.0],[542,0,13.0],[543,0,3.0],[544,0,3.0],[545,0,48.0],[546,0,6.0],[547,0,3.0],[548,0,4.0],[549,0,1.0],[550,0,2.0],[551,0,3.0],[552,0,2.0],[553,0,5.0],[554,0,58.0],[555,0,2.0],[556,0,1.0],[557,0,2.0],[558,0,1.0],[559,0,14.0],[560,0,4.0],[561,0,2.0],[562,0,3.0],[563,0,6.0],[564,0,2.0],[565,0,1.0],[566,0,1.0],[567,0,1.0],[568,0,9.0],[569,0,10.0],[570,1,1.0],[571,1,1.0],[572,1,3.0],[573,1,1.0],[574,1,13.0],[575,1,206.0],[576,1,2.0],[577,1,1.0],[578,1,21.0],[579,1,20.0],[580,1,2.0],[581,1,1.0],[582,1,185.0],[583,1,1.0],[584,1,4.0],[585,1,1.0],[586,1,1.0],[587,1,4.0],[588,1,76.0],[589,1,4.0],[590,1,2.0],[591,1,5.0],[592,1,1.0],[593,1,1.0],[594,1,1.0],[595,1,2.0],[596,1,1.0],[597,1,3.0],[598,1,2.0],[599,1,5.0],[600,1,7.0],[601,1,30.0],[602,1,4.0],[603,1,1.0],[604,1,2.0],[605,1,3.0],[606,1,1.0],[607,1,3.0],[608,1,1.0],[609,1,1.0],[610,1,3.0],[611,1,1.0],[612,1,1.0],[613,1,6.0],[614,1,1.0],[615,1,1.0],[616,1,1.0],[617,1,25.0],[618,1,1.0],[619,1,1.0],[620,1,3.0],[621,1,6.0],[622,1,1.0],[623,1,3.0],[624,1,2919.0],[625,1,1.0],[626,1,1.0],[627,1,17.0],[628,1,19.0],[629,1,1.0],[630,1,1.0],[631,1,2.0],[632,1,1.0],[633,1,1.0],[634,1,1.0],[635,1,1.0],[636,1,6.0],[637,1,1.0],[638,1,1.0],[639,1,4.0],[640,1,1.0],[641,1,1.0],[642,1,3170.0],[643,1,1.0],[644,1,1.0],[645,1,1.0],[646,1,2.0],[647,1,1.0],[648,1,213.0],[649,1,2.0],[650,1,3.0],[651,1,1.0],[652,1,1.0],[653,1,2.0],[654,1,2.0],[655,1,1.0],[656,1,1.0],[657,1,4.0],[658,1,1.0],[659,1,4.0],[660,1,1.0],[661,1,2.0],[662,1,1.0],[663,1,2.0],[664,1,2.0],[665,1,6.0],[666,1,1.0],[667,1,1.0],[668,1,1.0],[669,1,1.0],[670,1,18.0],[671,1,3.0],[672,1,76.0],[673,1,25.0],[674,1,1.0],[675,1,1.0],[676,1,8.0],[677,1,1.0],[678,1,1.0],[679,1,1.0],[680,1,10.0],[681,1,3.0],[682,1,4.0],[683,1,7.0],[684,1,8.0],[685,1,1.0],[686,1,2.0],[687,1,6.0],[688,1,1.0],[689,1,3.0],[690,1,2.0],[691,1,1.0],[692,1,3.0],[693,1,30.0],[694,1,1.0],[695,1,1.0],[696,1,1.0],[697,1,2.0],[698,1,209.0],[699,1,1.0],[700,1,84.0],[701,1,1.0],[702,1,1.0],[703,1,19.0],[704,1,1.0],[705,1,7.0],[706,1,1.0],[707,1,1.0],[708,1,1.0],[709,1,2.0],[710,1,1.0],[711,1,6.0],[712,1,1910.0],[713,1,2.0],[714,1,4.0],[715,1,1.0],[716,1,1.0],[717,1,3.0],[718,1,1.0],[719,1,1.0],[720,1,1.0],[721,1,5.0],[722,1,1.0],[723,1,1.0],[724,1,1.0],[725,1,11.0],[726,1,353.0],[727,1,12.0],[728,1,1.0],[729,1,1.0],[730,1,6.0],[731,1,33.0],[732,1,959.0],[733,1,4.0],[734,1,4.0],[735,1,1.0],[736,1,1.0],[737,1,21.0],[738,1,1.0],[739,1,1.0],[740,1,1.0],[741,1,1.0],[742,1,1.0],[743,1,7.0],[744,1,25.0],[745,1,3.0],[746,1,1.0],[747,1,2.0],[748,1,1.0],[749,1,12.0],[750,1,7.0],[751,1,5.0],[752,1,1.0],[753,1,145.0],[754,1,1.0],[755,1,1.0],[756,1,1.0],[757,1,8.0],[758,1,2.0],[759,1,1.0],[760,1,19.0],[761,1,37.0],[762,1,1.0],[763,1,1.0],[764,1,1.0],[765,1,3.0],[766,1,1.0],[767,1,1805.0],[768,1,63.0],[769,1,1.0],[770,1,1490.0],[771,1,2.0],[772,1,322.0],[773,1,3.0],[774,1,2.0],[775,1,1.0],[776,1,5.0],[777,1,1.0],[778,1,1.0],[779,1,2.0],[780,1,18.0],[781,1,1.0],[782,1,2.0],[783,1,7.0],[784,1,6.0],[785,1,1.0],[786,1,166.0],[787,1,1.0],[788,1,9.0],[789,1,1.0],[790,1,3.0],[791,1,1.0],[792,1,1.0],[793,1,1.0],[794,1,10.0],[795,1,3.0],[796,1,1.0],[797,1,8.0],[798,1,9.0],[799,1,17.0],[800,1,1.0],[801,1,1.0],[802,1,1.0],[803,1,21.0],[804,1,2.0],[805,1,1146.0],[806,1,1.0],[807,1,298.0],[808,1,2.0],[809,1,1.0],[810,1,1.0],[811,1,1.0],[812,1,15.0],[813,1,2.0],[814,1,2.0],[815,1,6.0],[816,1,2.0],[817,1,11.0],[818,1,1.0],[819,1,6.0],[820,1,1.0],[821,1,13.0],[822,1,11.0],[823,1,1.0],[824,1,1.0],[825,1,16.0],[826,1,1.0],[827,1,1.0],[828,1,41.0],[829,1,1.0],[830,1,2.0],[831,1,1.0],[832,1,5.0],[833,1,4.0],[834,1,1.0],[835,1,5.0],[836,1,2.0],[837,1,1.0],[838,1,4.0],[839,1,7.0],[840,1,1.0],[841,1,1.0],[842,1,324.0],[843,1,3.0],[844,1,5.0],[845,1,2.0],[846,1,1.0],[847,1,3.0],[848,1,1.0],[849,1,3.0],[850,1,5.0],[851,1,3.0],[852,1,916.0],[853,1,1.0],[854,1,1.0],[855,1,5.0],[856,1,1.0],[857,1,1.0],[858,1,124.0],[859,1,4.0],[860,1,2.0],[861,1,21.0],[862,1,13.0],[863,1,3.0],[864,1,2.0],[865,1,2.0],[866,1,5.0],[867,1,7.0],[868,1,115.0],[869,1,58.0],[870,1,1.0],[871,1,1.0],[872,1,1.0],[873,1,1737.0],[874,1,9.0],[875,1,1.0],[876,1,1.0],[877,1,4.0],[878,1,1.0],[879,1,40.0],[880,1,1.0],[881,1,2.0],[882,1,1.0],[883,1,6.0],[884,1,4.0],[885,1,1.0],[886,1,3.0],[887,1,1.0],[888,1,76.0],[889,1,3.0],[890,1,3.0],[891,1,5.0],[892,1,2.0],[893,1,2.0],[894,1,12.0],[895,1,38.0],[896,1,1.0],[897,1,47.0],[898,1,1.0],[899,1,1.0],[900,1,1.0],[901,1,22.0],[902,1,1.0],[903,1,6.0],[904,1,11.0],[905,1,1.0],[906,1,14.0],[907,1,1.0],[908,1,1.0],[909,1,200.0],[910,1,3.0],[911,1,1.0],[912,1,4.0],[913,1,1329.0],[914,1,2.0],[915,1,39.0],[916,1,3.0],[917,1,1.0],[918,1,2.0],[919,1,1.0],[920,1,1.0],[921,1,2.0],[922,1,1.0],[923,1,60.0],[924,1,2.0],[925,1,1.0],[926,1,1.0],[927,1,2.0],[928,1,1.0],[929,1,41.0],[930,1,1.0],[931,1,10.0],[932,1,2.0],[933,1,1.0],[934,1,1.0],[935,1,2.0],[936,1,3.0],[937,1,1.0],[938,1,3.0],[939,1,1.0],[940,1,1.0],[941,1,1.0],[942,1,691.0],[943,1,2.0],[944,1,3.0],[945,1,1.0],[946,1,5.0],[947,1,1.0],[948,1,1.0],[949,1,1.0],[950,1,1.0],[951,1,1.0],[952,1,1.0],[953,1,218.0],[954,1,5.0],[955,1,2.0],[956,1,1.0],[957,1,2.0],[958,1,1.0],[959,1,2.0],[960,1,3.0],[961,1,359.0],[962,1,2.0],[963,1,58.0],[964,1,13.0],[965,1,2.0],[966,1,1.0],[967,1,10.0],[968,1,1.0],[969,1,58.0],[970,1,3.0],[971,1,1.0],[972,1,1.0],[973,1,1.0],[974,1,2.0],[975,1,231.0],[976,1,2.0],[977,1,1.0],[978,1,3.0],[979,1,15.0],[980,1,2.0],[981,1,2.0],[982,1,20.0],[983,1,1.0],[984,1,1.0],[985,1,1.0],[986,1,1.0],[987,1,2.0],[988,1,2.0],[989,1,1.0],[990,1,3.0],[991,1,1.0],[992,1,10.0],[993,1,55.0],[994,1,1.0],[995,1,3.0],[996,1,3.0],[997,1,1.0],[998,1,1.0],[999,1,21.0],[1000,1,44.0],[1001,1,1.0],[1002,1,3.0],[1003,1,2.0],[1004,1,6.0],[1005,1,13.0],[1006,1,2.0],[1007,1,1.0],[1008,1,1.0],[1009,1,13.0],[1010,1,1.0],[1011,1,1.0],[1012,1,1.0],[1013,1,1.0],[1014,1,3.0],[1015,1,3.0],[1016,1,1.0],[1017,1,1.0],[1018,1,4.0],[1019,1,1.0],[1020,1,12.0],[1021,1,1.0],[1022,1,1.0],[1023,1,13.0],[1024,1,13.0],[1025,1,1.0],[1026,1,3.0],[1027,1,1.0],[1028,1,1.0],[1029,1,2.0],[1030,1,2.0],[1031,1,1.0],[1032,1,3.0],[1033,1,1.0],[1034,1,6.0],[1035,1,1.0],[1036,1,1.0],[1037,1,2.0],[1038,1,4.0],[1039,1,3.0],[1040,1,4.0],[1041,1,4.0],[1042,1,5.0],[1043,1,2.0],[1044,1,1.0],[1045,1,2.0],[1046,1,1.0],[1047,1,1.0],[1048,1,1.0],[1049,1,1.0],[1050,1,8.0],[1051,1,3.0],[1052,1,1.0],[1053,1,1.0],[1054,1,1.0],[1055,1,1.0],[1056,1,1.0],[1057,1,1.0],[1058,1,5.0],[1059,1,2.0],[1060,1,1.0],[1061,1,4.0],[1062,1,1.0],[1063,1,1.0],[1064,1,1.0],[1065,1,11.0],[1066,1,6.0],[1067,1,3.0],[1068,1,1.0],[1069,1,1.0],[1070,1,1.0],[1071,1,4.0],[1072,1,1.0],[1073,1,4.0],[1074,1,3.0],[1075,1,1.0],[1076,1,11.0],[1077,1,49.0],[1078,1,1.0],[1079,1,2.0],[1080,1,9.0],[1081,1,1.0],[1082,1,1.0],[1083,1,92.0],[1084,1,1.0],[1085,1,1.0],[1086,1,27.0],[1087,1,2.0],[1088,1,1.0],[1089,1,1.0],[1090,1,2.0],[1091,1,35.0],[1092,1,8.0],[1093,1,1.0],[1094,1,3.0],[1095,1,1.0],[1096,1,17.0],[1097,1,9.0],[1098,1,54.0],[1099,1,1.0],[1100,1,2.0],[1101,1,2.0],[1102,1,1.0],[1103,1,2.0],[1104,1,2.0],[1105,1,40.0],[1106,1,16.0],[1107,1,1.0],[1108,1,1.0],[1109,1,4.0],[1110,1,654.0],[1111,1,8.0],[1112,1,1.0],[1113,1,1.0],[1114,1,2.0],[1115,1,76.0],[1116,1,78.0],[1117,1,1.0],[1118,1,1.0],[1119,1,1.0],[1120,1,1.0],[1121,1,1.0],[1122,1,11.0],[1123,1,1.0],[1124,1,2.0],[1125,1,34.0],[1126,1,1.0],[1127,1,1076.0],[1128,1,28.0],[1129,1,3.0],[1130,1,9.0],[1131,1,1.0],[1132,1,39.0],[1133,1,11.0],[1134,1,1.0],[1135,1,1.0],[1136,1,17.0],[1137,1,2.0],[1138,1,23.0],[1139,1,15.0],[1140,1,2.0],[1141,1,1.0],[1142,1,16.0],[1143,1,1.0],[1144,1,1.0],[1145,1,2.0],[1146,1,1.0],[1147,1,2.0],[1148,1,4.0],[1149,1,1.0],[1150,1,1.0],[1151,1,9.0],[1152,1,2.0],[1153,1,1.0],[1154,1,1.0],[1155,1,1.0],[1156,1,9.0],[1157,1,1.0],[1158,1,3.0],[1159,1,1.0],[1160,1,1.0],[1161,1,1.0],[1162,1,5.0],[1163,1,13.0],[1164,1,3.0],[1165,1,2.0],[1166,1,1.0],[1167,1,1.0],[1168,1,1.0],[1169,1,4.0],[1170,1,324.0],[1171,1,3.0],[1172,1,3.0],[1173,1,1.0],[1174,1,2.0]],"rows": [{"id": "2480553", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "1092725", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Micrococcaceae", "g__Rothia", "s__dentocariosa"]}},{"id": "1021368", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4375688", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Epsilonproteobacteria", "o__Campylobacterales", "f__Campylobacteraceae", "g__Campylobacter", "s__"]}},{"id": "499109", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4307790", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Selenomonas", "s__"]}},{"id": "4399781", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "569210", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "4325275", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4325272", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4454356", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "1086274", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__", "s__"]}},{"id": "799024", "metadata": {"taxonomy": ["k__Bacteria", "p__TM7", "c__TM7-3", "o__", "f__", "g__", "s__"]}},{"id": "866280", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Micrococcaceae", "g__Rothia", "s__mucilaginosa"]}},{"id": "1061772", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Planococcaceae", "g__", "s__"]}},{"id": "241454", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "4346977", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4313722", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "4298880", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "522025", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4308793", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "4464348", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "87442", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__Flavobacteriaceae", "g__Capnocytophaga", "s__ochracea"]}},{"id": "4302049", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "983098", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__Flavobacteriaceae", "g__Capnocytophaga", "s__"]}},{"id": "993647", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Carnobacteriaceae", "g__Granulicatella", "s__"]}},{"id": "4383918", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "4308098", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "3166216", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "884751", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "1111582", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Enterococcaceae", "g__Enterococcus", "s__"]}},{"id": "337212", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "83011", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__", "s__"]}},{"id": "4373910", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__oralis"]}},{"id": "250288", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Peptostreptococcaceae", "g__", "s__"]}},{"id": "1083194", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4409545", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "569584", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "1085832", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "2163609", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Coriobacteriia", "o__Coriobacteriales", "f__Coriobacteriaceae", "g__Atopobium", "s__"]}},{"id": "59574", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "358343", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "2199223", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__nigrescens"]}},{"id": "517548", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__"]}},{"id": "139520", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Aggregatibacter", "s__"]}},{"id": "573034", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__endodontalis"]}},{"id": "4438988", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4428998", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "585419", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__"]}},{"id": "4427609", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__melaninogenica"]}},{"id": "4431355", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__", "s__"]}},{"id": "499019", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "4355718", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__hyovaginalis"]}},{"id": "1108638", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "859700", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "530224", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__Flavobacteriaceae", "g__Capnocytophaga", "s__"]}},{"id": "2406759", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "92131", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "642525", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Selenomonas", "s__"]}},{"id": "545299", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "154939", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Butyrivibrio", "s__"]}},{"id": "74330", "metadata": {"taxonomy": ["k__Bacteria", "p__Spirochaetes", "c__Spirochaetes", "o__Spirochaetales", "f__Spirochaetaceae", "g__Treponema", "s__socranskii"]}},{"id": "1866742", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Parvimonas", "s__"]}},{"id": "526682", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "4298305", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "4310829", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "586458", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "905088", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__Gemellaceae", "g__", "s__"]}},{"id": "591221", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Xanthomonadales", "f__Xanthomonadaceae", "g__Xanthomonas", "s__axonopodis"]}},{"id": "3581175", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__", "s__"]}},{"id": "4482428", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "989579", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "1754506", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Cardiobacteriales", "f__Cardiobacteriaceae", "g__Cardiobacterium", "s__"]}},{"id": "4290143", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "684494", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Enterococcaceae", "g__Enterococcus", "s__"]}},{"id": "1065569", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__Gemellaceae", "g__", "s__"]}},{"id": "4305935", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Paludibacter", "s__"]}},{"id": "4320312", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "1080820", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "4334770", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "4400869", "metadata": {"taxonomy": ["k__Bacteria", "p__SR1", "c__", "o__", "f__", "g__", "s__"]}},{"id": "960871", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "521268", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__melaninogenica"]}},{"id": "898309", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__nanceiensis"]}},{"id": "1007430", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "207340", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Mogibacteriaceae]", "g__", "s__"]}},{"id": "4331006", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "4306852", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__melaninogenica"]}},{"id": "3678349", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "536866", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "148259", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "257278", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "1060621", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__cinerea"]}},{"id": "524725", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Coriobacteriia", "o__Coriobacteriales", "f__Coriobacteriaceae", "g__Atopobium", "s__"]}},{"id": "535901", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Dialister", "s__"]}},{"id": "4306166", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "4374645", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__subflava"]}},{"id": "897109", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Aggregatibacter", "s__"]}},{"id": "3866487", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Oribacterium", "s__"]}},{"id": "4320756", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "584730", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Cardiobacteriales", "f__Cardiobacteriaceae", "g__", "s__"]}},{"id": "837177", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Burkholderiaceae", "g__Burkholderia", "s__"]}},{"id": "4378846", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "344593", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__subflava"]}},{"id": "4366522", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "851935", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "878129", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "851938", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Erysipelotrichi", "o__Erysipelotrichales", "f__Erysipelotrichaceae", "g__Bulleidia", "s__moorei"]}},{"id": "4340137", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "4307078", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "261558", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Bacillaceae", "g__Thalassobacillus", "s__"]}},{"id": "1042479", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__melaninogenica"]}},{"id": "645055", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "4315605", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "4405932", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "922239", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__", "g__", "s__"]}},{"id": "4296080", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "516198", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "271159", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Carnobacteriaceae", "g__Granulicatella", "s__"]}},{"id": "4391625", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__parvula"]}},{"id": "2228", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "4299445", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Kingella", "s__"]}},{"id": "2222", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__pallens"]}},{"id": "4296242", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Megasphaera", "s__"]}},{"id": "4314454", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "527630", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Clostridiaceae", "g__", "s__"]}},{"id": "903426", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Micrococcaceae", "g__Rothia", "s__mucilaginosa"]}},{"id": "558276", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Gallibacterium", "s__"]}},{"id": "780788", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Xanthomonadales", "f__Xanthomonadaceae", "g__", "s__"]}},{"id": "4395175", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Conchiformibius", "s__"]}},{"id": "4326857", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "1090059", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Carnobacteriaceae", "g__Granulicatella", "s__"]}},{"id": "904345", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__", "s__"]}},{"id": "4433676", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__[Weeksellaceae]", "g__", "s__"]}},{"id": "240049", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "4309323", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "4384936", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__Gemellaceae", "g__Gemella", "s__"]}},{"id": "4331219", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "4345640", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "875735", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "103151", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "31235", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "4295763", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "4079463", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "1980933", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__parvula"]}},{"id": "1005952", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "2466322", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Peptostreptococcaceae", "g__", "s__"]}},{"id": "2208658", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4447398", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4295238", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__[Paraprevotellaceae]", "g__[Prevotella]", "s__"]}},{"id": "569912", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "970138", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "181971", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__N09", "s__"]}},{"id": "4395884", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Parvimonas", "s__"]}},{"id": "92263", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Selenomonas", "s__"]}},{"id": "4406302", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Catonella", "s__"]}},{"id": "4359222", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "4428060", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__melaninogenica"]}},{"id": "15366", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "654696", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "886640", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__[Paraprevotellaceae]", "g__[Prevotella]", "s__"]}},{"id": "2614328", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "609533", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "4307309", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "1049387", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Xanthomonadales", "f__Xanthomonadaceae", "g__Pseudoxanthomonas", "s__mexicana"]}},{"id": "32546", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Epsilonproteobacteria", "o__Campylobacterales", "f__Campylobacteraceae", "g__Campylobacter", "s__"]}},{"id": "4314749", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "4307303", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "4326635", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__cinerea"]}},{"id": "1712416", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__Gemellaceae", "g__Gemella", "s__"]}},{"id": "4306157", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "1008348", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__[Paraprevotellaceae]", "g__[Prevotella]", "s__"]}},{"id": "2676430", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "528357", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "934651", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "4430639", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "590735", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "122517", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Catonella", "s__"]}},{"id": "54330", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "557100", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__Flavobacteriaceae", "g__Capnocytophaga", "s__"]}},{"id": "125235", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Kingella", "s__"]}},{"id": "4483174", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "585653", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Epsilonproteobacteria", "o__Campylobacterales", "f__Campylobacteraceae", "g__Campylobacter", "s__"]}},{"id": "4329788", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "226450", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Eikenella", "s__"]}},{"id": "76751", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "4365611", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "4379223", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "2647328", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Actinobacillus", "s__"]}},{"id": "925707", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__Gemellaceae", "g__", "s__"]}},{"id": "3388775", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "414943", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__"]}},{"id": "1033687", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "4335016", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "2901970", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "1036557", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__subflava"]}},{"id": "871442", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "59566", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "444857", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "941096", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4310208", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "561636", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "88035", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "1096706", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "983600", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4365756", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "181155", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__", "s__"]}},{"id": "1066621", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__melaninogenica"]}},{"id": "4466616", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "1073276", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4320547", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "1092300", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "567960", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "1616059", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Epsilonproteobacteria", "o__Campylobacterales", "f__Campylobacteraceae", "g__Campylobacter", "s__"]}},{"id": "513500", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4440404", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__cinerea"]}},{"id": "997010", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "1935279", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "41911", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "92512", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Butyrivibrio", "s__"]}},{"id": "563369", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pseudomonadales", "f__Moraxellaceae", "g__Acinetobacter", "s__"]}},{"id": "249748", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Bacillaceae", "g__Bacillus", "s__"]}},{"id": "922397", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "888300", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "561537", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__"]}},{"id": "4408085", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__"]}},{"id": "717565", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Comamonadaceae", "g__", "s__"]}},{"id": "534922", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__", "s__"]}},{"id": "4321547", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "4396235", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__subflava"]}},{"id": "801579", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Planococcaceae", "g__Lysinibacillus", "s__boronitolerans"]}},{"id": "1084417", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Burkholderiaceae", "g__Lautropia", "s__"]}},{"id": "1051669", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4307464", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Comamonadaceae", "g__", "s__"]}},{"id": "344318", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__copri"]}},{"id": "722854", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "928424", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "545772", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "1921813", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Burkholderiaceae", "g__Lautropia", "s__"]}},{"id": "4451251", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Coriobacteriia", "o__Coriobacteriales", "f__Coriobacteriaceae", "g__Atopobium", "s__"]}},{"id": "861375", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "2469654", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__[Paraprevotellaceae]", "g__[Prevotella]", "s__"]}},{"id": "935742", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__melaninogenica"]}},{"id": "4430300", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "1084906", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "12574", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "4299137", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "4299136", "metadata": {"taxonomy": ["k__Bacteria", "p__TM7", "c__TM7-3", "o__CW040", "f__F16", "g__", "s__"]}},{"id": "246785", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "139056", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Aggregatibacter", "s__"]}},{"id": "298862", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "1076557", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "986708", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "999477", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__nanceiensis"]}},{"id": "4390646", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "523025", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4401260", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4336070", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "14159", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Mogibacteriaceae]", "g__", "s__"]}},{"id": "14157", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Mogibacteriaceae]", "g__", "s__"]}},{"id": "915452", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__"]}},{"id": "4465561", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__melaninogenica"]}},{"id": "4323390", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "1023075", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__"]}},{"id": "516966", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4322712", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "724120", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4412991", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__", "s__"]}},{"id": "851923", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "3569942", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "557978", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "566233", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "73324", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "86428", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "921522", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__influenzae"]}},{"id": "593803", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "93000", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__[Paraprevotellaceae]", "g__[Prevotella]", "s__"]}},{"id": "4344228", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "1000269", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "280567", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "4321396", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "502919", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Selenomonas", "s__"]}},{"id": "4417053", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__", "s__"]}},{"id": "531206", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Mogibacteriaceae]", "g__Mogibacterium", "s__"]}},{"id": "4334976", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__"]}},{"id": "308956", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__endodontalis"]}},{"id": "562825", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__", "s__"]}},{"id": "942534", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__", "s__"]}},{"id": "4455887", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "888466", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "4403854", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "4305201", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__Flavobacteriaceae", "g__Capnocytophaga", "s__ochracea"]}},{"id": "970302", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "905211", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Micrococcaceae", "g__Rothia", "s__"]}},{"id": "888944", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "2410938", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4310396", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__[Paraprevotellaceae]", "g__[Prevotella]", "s__"]}},{"id": "4310395", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Oribacterium", "s__"]}},{"id": "4404224", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__copri"]}},{"id": "1122364", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__", "s__"]}},{"id": "4404220", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "2959075", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "815207", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Butyrivibrio", "s__"]}},{"id": "1027587", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Carnobacteriaceae", "g__Granulicatella", "s__"]}},{"id": "239506", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "1013657", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__cinerea"]}},{"id": "197273", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "1620065", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Bacillaceae", "g__Bacillus", "s__"]}},{"id": "4296987", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Selenomonas", "s__noxia"]}},{"id": "403701", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Dialister", "s__"]}},{"id": "714461", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "15059", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Aerococcaceae", "g__Granulicatella", "s__balaenopterae"]}},{"id": "537362", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "506496", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4297420", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "4312342", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__subflava"]}},{"id": "887706", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4301566", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "3221156", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "355750", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "71649", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "931121", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "2991800", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__infantis"]}},{"id": "1025385", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__Gemellaceae", "g__Gemella", "s__"]}},{"id": "524676", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Oribacterium", "s__"]}},{"id": "7764", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Cardiobacteriales", "f__Cardiobacteriaceae", "g__Cardiobacterium", "s__"]}},{"id": "168817", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__Flavobacteriaceae", "g__Capnocytophaga", "s__ochracea"]}},{"id": "1084952", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__", "s__"]}},{"id": "894969", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "92329", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Parvimonas", "s__"]}},{"id": "4306836", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4372058", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "525942", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__melaninogenica"]}},{"id": "92636", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__Flavobacteriaceae", "g__Capnocytophaga", "s__"]}},{"id": "714766", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Moryella", "s__"]}},{"id": "1124305", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4351077", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "1007926", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "515747", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "4297838", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Micrococcaceae", "g__Rothia", "s__aeria"]}},{"id": "548694", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Xanthomonadales", "f__Xanthomonadaceae", "g__", "s__"]}},{"id": "2714267", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__[Paraprevotellaceae]", "g__[Prevotella]", "s__tannerae"]}},{"id": "4422456", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "4390825", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__", "s__"]}},{"id": "342427", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "4460404", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__melaninogenica"]}},{"id": "341460", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__"]}},{"id": "579608", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4458959", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__"]}},{"id": "221648", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "11296", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "2627856", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "1067006", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Kingella", "s__"]}},{"id": "510422", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "4330071", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "109413", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Actinobacillus", "s__"]}},{"id": "641832", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "4331858", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "521851", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Carnobacteriaceae", "g__Granulicatella", "s__"]}},{"id": "4427030", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "724271", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Planococcaceae", "g__Lysinibacillus", "s__boronitolerans"]}},{"id": "4335578", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Mogibacteriaceae]", "g__", "s__"]}},{"id": "4318869", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "2901960", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Acidaminobacteraceae]", "g__", "s__"]}},{"id": "2195", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__nigrescens"]}},{"id": "2901965", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4321400", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4437024", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "114621", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Epsilonproteobacteria", "o__Campylobacterales", "f__Campylobacteraceae", "g__Campylobacter", "s__"]}},{"id": "705241", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__pallens"]}},{"id": "965500", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "851961", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "585435", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Carnobacteriaceae", "g__Carnobacterium", "s__"]}},{"id": "3723096", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4347099", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "887694", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Burkholderiaceae", "g__Lautropia", "s__"]}},{"id": "388019", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "1916970", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "584347", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "530206", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "4411138", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Micrococcaceae", "g__Rothia", "s__mucilaginosa"]}},{"id": "1042850", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "787663", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Mogibacteriaceae]", "g__Mogibacterium", "s__"]}},{"id": "3472245", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__", "s__"]}},{"id": "579128", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Planococcaceae", "g__Solibacillus", "s__"]}},{"id": "4295743", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "4344933", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__", "s__"]}},{"id": "2662130", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__parvula"]}},{"id": "927328", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__", "s__"]}},{"id": "4298633", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__[Weeksellaceae]", "g__", "s__"]}},{"id": "1026498", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Eikenella", "s__"]}},{"id": "4388707", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__Flavobacteriaceae", "g__Capnocytophaga", "s__ochracea"]}},{"id": "4420474", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "4332636", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Selenomonas", "s__"]}},{"id": "3089522", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "470724", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__cinerea"]}},{"id": "4309301", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "926526", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Micrococcaceae", "g__Rothia", "s__mucilaginosa"]}},{"id": "921101", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "963216", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Aggregatibacter", "s__"]}},{"id": "4306055", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "529233", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4402709", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "3040812", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__parvula"]}},{"id": "73471", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "4443201", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Tannerella", "s__"]}},{"id": "1062944", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__[Paraprevotellaceae]", "g__[Prevotella]", "s__"]}},{"id": "851932", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Kingella", "s__denitrificans"]}},{"id": "4443207", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "300432", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Epsilonproteobacteria", "o__Campylobacterales", "f__Campylobacteraceae", "g__Campylobacter", "s__"]}},{"id": "708925", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Gallibacterium", "s__"]}},{"id": "938948", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "523036", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__Gemellaceae", "g__", "s__"]}},{"id": "72536", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "1078248", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Bacillaceae", "g__Bacillus", "s__"]}},{"id": "4465803", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "711275", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__infantis"]}},{"id": "511378", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__"]}},{"id": "851822", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "4328364", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "430191", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Epsilonproteobacteria", "o__Campylobacterales", "f__Campylobacteraceae", "g__Campylobacter", "s__rectus"]}},{"id": "114821", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__parvula"]}},{"id": "736957", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "269907", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__[Paraprevotellaceae]", "g__[Prevotella]", "s__"]}},{"id": "4298899", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__subflava"]}},{"id": "1082539", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4307391", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__melaninogenica"]}},{"id": "1010329", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__Flavobacteriaceae", "g__Capnocytophaga", "s__"]}},{"id": "4394099", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Rhodocyclales", "f__Rhodocyclaceae", "g__Propionivibrio", "s__"]}},{"id": "109414", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Aggregatibacter", "s__"]}},{"id": "4320699", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "4456236", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "1017181", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Micrococcaceae", "g__Rothia", "s__mucilaginosa"]}},{"id": "4298291", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__melaninogenica"]}},{"id": "9562", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__", "s__"]}},{"id": "4340653", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__subflava"]}},{"id": "4318671", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "4318672", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "4424239", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "1074210", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__Gemellaceae", "g__", "s__"]}},{"id": "4297119", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "530164", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "4430826", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "4300778", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "2914680", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "4317631", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "787709", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "4440191", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "4365687", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "864640", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Carnobacteriaceae", "g__Granulicatella", "s__"]}},{"id": "4397579", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "4432042", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4477696", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "2930734", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Carnobacteriaceae", "g__Granulicatella", "s__"]}},{"id": "4346614", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4416763", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "905769", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "4432435", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "4304901", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "1059729", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Carnobacteriaceae", "g__Granulicatella", "s__"]}},{"id": "967427", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4428042", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "484320", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__", "s__"]}},{"id": "898207", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Carnobacteriaceae", "g__Granulicatella", "s__"]}},{"id": "92535", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "1097868", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Cardiobacteriales", "f__Cardiobacteriaceae", "g__Cardiobacterium", "s__"]}},{"id": "2394", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__Flavobacteriaceae", "g__Capnocytophaga", "s__ochracea"]}},{"id": "610111", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "4368771", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Selenomonas", "s__"]}},{"id": "749837", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Oribacterium", "s__"]}},{"id": "4417749", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__Flavobacteriaceae", "g__Capnocytophaga", "s__"]}},{"id": "4310192", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "799211", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__[Paraprevotellaceae]", "g__[Prevotella]", "s__"]}},{"id": "4296512", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__Flavobacteriaceae", "g__Capnocytophaga", "s__"]}},{"id": "4296513", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__", "s__"]}},{"id": "4402254", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "146094", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "851704", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Parvimonas", "s__"]}},{"id": "1931", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "1078207", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "864465", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4320462", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__cinerea"]}},{"id": "2654263", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "882765", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__Gemellaceae", "g__", "s__"]}},{"id": "4295455", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__"]}},{"id": "4336077", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__"]}},{"id": "4406621", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Tannerella", "s__"]}},{"id": "971907", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Actinobacillus", "s__parahaemolyticus"]}},{"id": "923098", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "68416", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "518743", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__parvula"]}},{"id": "1139769", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "865782", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "4448731", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "1696853", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Carnobacteriaceae", "g__Granulicatella", "s__"]}},{"id": "92231", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Aggregatibacter", "s__segnis"]}},{"id": "4297332", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "968954", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "1101669", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__Gemellaceae", "g__Gemella", "s__"]}},{"id": "217734", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__anginosus"]}},{"id": "222032", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__subflava"]}},{"id": "3506872", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__dispar"]}},{"id": "4318872", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__"]}},{"id": "251967", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "54794", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4326647", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "324532", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "370964", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Aggregatibacter", "s__pneumotropica"]}},{"id": "813617", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pseudomonadales", "f__Pseudomonadaceae", "g__Pseudomonas", "s__"]}},{"id": "549823", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "594001", "metadata": {"taxonomy": ["k__Bacteria", "p__Tenericutes", "c__Mollicutes", "o__Mycoplasmatales", "f__Mycoplasmataceae", "g__Mycoplasma", "s__"]}},{"id": "3449122", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "1088134", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4402735", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__", "s__"]}},{"id": "1085410", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "1004910", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "584516", "metadata": {"taxonomy": ["k__Bacteria", "p__TM7", "c__TM7-3", "o__", "f__", "g__", "s__"]}},{"id": "1068572", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__durum"]}},{"id": "4447993", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Flavobacteriia", "o__Flavobacteriales", "f__Flavobacteriaceae", "g__Capnocytophaga", "s__ochracea"]}},{"id": "968675", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "820843", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Mogibacteriaceae]", "g__Mogibacterium", "s__"]}},{"id": "4301737", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "4375080", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "4365567", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__cinerea"]}},{"id": "335565", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "1065974", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Enterococcaceae", "g__Vagococcus", "s__"]}},{"id": "1029036", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "2825358", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "567427", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "941024", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "931950", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4442170", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "4294773", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "1068499", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "862115", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Aggregatibacter", "s__"]}},{"id": "516611", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "15570", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "611914", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "103768", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "661259", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "591583", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4310500", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "338605", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Neisseria", "s__"]}},{"id": "879972", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4322998", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Fusobacteriaceae", "g__Fusobacterium", "s__"]}},{"id": "42091", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Peptococcaceae", "g__Peptococcus", "s__"]}},{"id": "4315069", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "108729", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Actinobacillus", "s__"]}},{"id": "3889756", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Veillonella", "s__parvula"]}},{"id": "1671681", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "627071", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4324467", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "4366889", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4395661", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "70628", "metadata": {"taxonomy": ["k__Bacteria", "p__Fusobacteria", "c__Fusobacteriia", "o__Fusobacteriales", "f__Leptotrichiaceae", "g__Leptotrichia", "s__"]}},{"id": "70580", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Actinobacillus", "s__porcinus"]}},{"id": "564704", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Leuconostocaceae", "g__Weissella", "s__"]}},{"id": "4315538", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Burkholderiaceae", "g__Lautropia", "s__"]}},{"id": "527840", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Planococcaceae", "g__Rummeliibacillus", "s__"]}},{"id": "4321397", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "4303114", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "555654", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__", "s__"]}},{"id": "3825935", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__", "s__"]}},{"id": "865469", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Haemophilus", "s__parainfluenzae"]}},{"id": "4403576", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__", "s__"]}},{"id": "38227", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__[Paraprevotellaceae]", "g__[Prevotella]", "s__"]}},{"id": "4315833", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Neisseriales", "f__Neisseriaceae", "g__Eikenella", "s__"]}},{"id": "9510", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pasteurellales", "f__Pasteurellaceae", "g__Actinobacillus", "s__delphinicola"]}},{"id": "1022944", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "4321136", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__"]}},{"id": "4386761", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "2366384", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Clostridiaceae", "g__", "s__"]}},{"id": "979761", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "145619", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "134726", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "925326", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Peptoniphilus", "s__"]}},{"id": "137056", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Planococcaceae", "g__", "s__"]}},{"id": "410908", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "531539", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "561171", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "193591", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "984326", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Finegoldia", "s__"]}},{"id": "366237", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "4353745", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "363692", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "196271", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "180442", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "1081058", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "583656", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "1888677", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Streptococcus", "s__anginosus"]}},{"id": "360329", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "1944498", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "174589", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "301149", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "329313", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "152001", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__aureus"]}},{"id": "4357712", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "366716", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "4343580", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "456393", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "369429", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "368950", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "194512", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "581782", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "4329112", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__fragilis"]}},{"id": "553111", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__lubricantis"]}},{"id": "846710", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Comamonadaceae", "g__", "s__"]}},{"id": "4454531", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "637901", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Comamonadaceae", "g__Delftia", "s__"]}},{"id": "182117", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "2331530", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "190610", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "184175", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "2949328", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "4442390", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__fragilis"]}},{"id": "876714", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pseudomonadales", "f__Pseudomonadaceae", "g__Pseudomonas", "s__"]}},{"id": "3989856", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "505565", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "198830", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "187144", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "797229", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "304641", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "310071", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "271214", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "947112", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "295085", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "2675920", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "189920", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "581079", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__Oscillospira", "s__"]}},{"id": "692756", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "187582", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__", "s__"]}},{"id": "184729", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "361619", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "197426", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Dorea", "s__"]}},{"id": "186352", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "177224", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "299576", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__variabile"]}},{"id": "358461", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Alphaproteobacteria", "o__Rhodobacterales", "f__Rhodobacteraceae", "g__Paracoccus", "s__"]}},{"id": "4312969", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__epidermidis"]}},{"id": "191043", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "611039", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "812921", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Alphaproteobacteria", "o__Rhodobacterales", "f__Rhodobacteraceae", "g__Paracoccus", "s__marcusii"]}},{"id": "134265", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "1103964", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__pettenkoferi"]}},{"id": "1075307", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "165489", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "510295", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__", "s__"]}},{"id": "196951", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__Ruminococcus", "s__"]}},{"id": "984831", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "562376", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "290468", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Dorea", "s__"]}},{"id": "658370", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "158047", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "820202", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "3141094", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "968363", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "191633", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "326116", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "338987", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Coprococcus", "s__"]}},{"id": "189782", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "3224662", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Epulopiscium", "s__"]}},{"id": "3940440", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "928538", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "308057", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "246494", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "367092", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "370287", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__Faecalibacterium", "s__prausnitzii"]}},{"id": "4401110", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "1039477", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__epidermidis"]}},{"id": "1602805", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "344746", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Dialister", "s__"]}},{"id": "566976", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "1111191", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "363389", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Clostridiaceae", "g__Clostridium", "s__"]}},{"id": "519673", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__", "g__", "s__"]}},{"id": "181589", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__equorum"]}},{"id": "3472078", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "520081", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "1749079", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "1918384", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__fragilis"]}},{"id": "495001", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Mogibacteriaceae]", "g__Mogibacterium", "s__"]}},{"id": "323231", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "182116", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "1019823", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Peptoniphilus", "s__"]}},{"id": "133065", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "4369878", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "345362", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "449856", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "3409154", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "576785", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Comamonadaceae", "g__", "s__"]}},{"id": "4435690", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "300952", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Coprococcus", "s__"]}},{"id": "4380886", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "197072", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__uniformis"]}},{"id": "365628", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Phascolarctobacterium", "s__"]}},{"id": "583974", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "191919", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "566243", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "1098434", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Peptoniphilus", "s__"]}},{"id": "192684", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "369227", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "568952", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "552849", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Cellulomonadaceae", "g__Cellulomonas", "s__xylanilytica"]}},{"id": "368318", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "199034", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Clostridiaceae", "g__Clostridium", "s__"]}},{"id": "337010", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "4407301", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "276484", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "1025949", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Alphaproteobacteria", "o__Rhizobiales", "f__", "g__", "s__"]}},{"id": "348304", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "984924", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "1063810", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__aureus"]}},{"id": "586093", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "3256931", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "323526", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Clostridiaceae", "g__", "s__"]}},{"id": "1107335", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pseudomonadales", "f__Moraxellaceae", "g__Acinetobacter", "s__"]}},{"id": "4030375", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "231787", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "1906635", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__caccae"]}},{"id": "1067519", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Bacillaceae", "g__Bacillus", "s__"]}},{"id": "178994", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "344525", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__eggerthii"]}},{"id": "178991", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "511476", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "1012358", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "315429", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "360015", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "196553", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__Oscillospira", "s__"]}},{"id": "128223", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "180999", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "804621", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Mobiluncus", "s__"]}},{"id": "534507", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "1097208", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__aureus"]}},{"id": "2137001", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "907241", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "342397", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "2693224", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Alphaproteobacteria", "o__Sphingomonadales", "f__Sphingomonadaceae", "g__Sphingomonas", "s__"]}},{"id": "266777", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Peptoniphilus", "s__"]}},{"id": "1843701", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Planococcaceae", "g__Viridibacillus", "s__"]}},{"id": "2874602", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "357334", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "592866", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__"]}},{"id": "552026", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "197367", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "361702", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__Ruminococcus", "s__"]}},{"id": "360553", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "716006", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__Lactococcus", "s__"]}},{"id": "28218", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "189384", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "352034", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "198184", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__Ruminococcus", "s__"]}},{"id": "536902", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "2237211", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "363731", "metadata": {"taxonomy": ["k__Bacteria", "p__Verrucomicrobia", "c__Verrucomicrobiae", "o__Verrucomicrobiales", "f__Verrucomicrobiaceae", "g__Akkermansia", "s__muciniphila"]}},{"id": "4352875", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__Oscillospira", "s__"]}},{"id": "295075", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "210965", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "289709", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "197924", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__uniformis"]}},{"id": "495096", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "341953", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "861807", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "198788", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "190815", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "3867172", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "570350", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Alphaproteobacteria", "o__Sphingomonadales", "f__Sphingomonadaceae", "g__Sphingobium", "s__"]}},{"id": "259772", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Coprococcus", "s__"]}},{"id": "589277", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "503236", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "188887", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "580629", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "4354477", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "535375", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__ovatus"]}},{"id": "357582", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "3376513", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "3794053", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Dorea", "s__"]}},{"id": "808245", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "365891", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "360995", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__", "s__"]}},{"id": "2683271", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "1002005", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Micrococcaceae", "g__", "s__"]}},{"id": "173654", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "187702", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "1871858", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__[Saprospirae]", "o__[Saprospirales]", "f__Chitinophagaceae", "g__Sediminibacterium", "s__"]}},{"id": "132873", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "942245", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "463361", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "365118", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Coprococcus", "s__"]}},{"id": "583448", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "369822", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "195115", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "587045", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "465079", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Planococcaceae", "g__", "s__"]}},{"id": "1029165", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "316515", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Streptococcaceae", "g__", "s__"]}},{"id": "313593", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Roseburia", "s__"]}},{"id": "360158", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "4404731", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "840795", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "184753", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "753638", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Dialister", "s__"]}},{"id": "572970", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "4008675", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "517797", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Dorea", "s__"]}},{"id": "514453", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "505587", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Finegoldia", "s__"]}},{"id": "307661", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "581003", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "192093", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "4393172", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__fragilis"]}},{"id": "1508541", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "195807", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "356760", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Erysipelotrichi", "o__Erysipelotrichales", "f__Erysipelotrichaceae", "g__", "s__"]}},{"id": "4360128", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "313764", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "1624382", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "4174963", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "564806", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "190965", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "1040889", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "199228", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Coprococcus", "s__"]}},{"id": "522984", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__variabile"]}},{"id": "205904", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "374568", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "362308", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "979315", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__", "g__", "s__"]}},{"id": "196946", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "174008", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "359872", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Deltaproteobacteria", "o__Desulfovibrionales", "f__Desulfovibrionaceae", "g__Bilophila", "s__"]}},{"id": "4380656", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "1100471", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Peptoniphilus", "s__"]}},{"id": "174952", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "4447432", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "838594", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Bacillaceae", "g__Bacillus", "s__"]}},{"id": "811257", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Alphaproteobacteria", "o__Caulobacterales", "f__Caulobacteraceae", "g__Caulobacter", "s__"]}},{"id": "551822", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Clostridiaceae", "g__", "s__"]}},{"id": "593376", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "188648", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "1024188", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Alphaproteobacteria", "o__Sphingomonadales", "f__Sphingomonadaceae", "g__Sphingomonas", "s__wittichii"]}},{"id": "188316", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__Oscillospira", "s__"]}},{"id": "4278525", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "583089", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "1084865", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "224105", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Clostridiaceae", "g__Clostridium", "s__"]}},{"id": "759751", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "194095", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "333341", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "187196", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "145401", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "4361727", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "542096", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "654307", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Peptoniphilus", "s__"]}},{"id": "1060029", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "1906483", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "3272632", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "180341", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Dorea", "s__"]}},{"id": "2430693", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__fragilis"]}},{"id": "179623", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "258375", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Dialister", "s__"]}},{"id": "495394", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "494971", "metadata": {"taxonomy": ["k__Bacteria", "p__Synergistetes", "c__Synergistia", "o__Synergistales", "f__Dethiosulfovibrionaceae", "g__Pyramidobacter", "s__"]}},{"id": "734945", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Alphaproteobacteria", "o__Sphingomonadales", "f__Sphingomonadaceae", "g__Sphingomonas", "s__"]}},{"id": "312140", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "577170", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "1839271", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Epulopiscium", "s__"]}},{"id": "591671", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "509416", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "975306", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "4453773", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Deltaproteobacteria", "o__Desulfovibrionales", "f__Desulfovibrionaceae", "g__Desulfovibrio", "s__"]}},{"id": "363264", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "503197", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "195157", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "192234", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "584571", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "365634", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Roseburia", "s__"]}},{"id": "132892", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "988314", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pseudomonadales", "f__Moraxellaceae", "g__Acinetobacter", "s__johnsonii"]}},{"id": "1069592", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Carnobacteriaceae", "g__Granulicatella", "s__"]}},{"id": "198530", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__uniformis"]}},{"id": "1097113", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "3396094", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "1020410", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "193509", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Dorea", "s__"]}},{"id": "465989", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "201772", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "364203", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Deltaproteobacteria", "o__Desulfovibrionales", "f__Desulfovibrionaceae", "g__Desulfovibrio", "s__"]}},{"id": "358834", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Coprococcus", "s__"]}},{"id": "573061", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Deltaproteobacteria", "o__Desulfovibrionales", "f__Desulfovibrionaceae", "g__Desulfovibrio", "s__"]}},{"id": "300829", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Clostridiaceae", "g__Clostridium", "s__"]}},{"id": "588197", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "4441343", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "4357811", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "4130483", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__epidermidis"]}},{"id": "496787", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "542066", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__", "g__", "s__"]}},{"id": "585480", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Anaerostipes", "s__"]}},{"id": "196986", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "1053898", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Peptoniphilus", "s__"]}},{"id": "841907", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Deltaproteobacteria", "o__Desulfovibrionales", "f__Desulfovibrionaceae", "g__Bilophila", "s__"]}},{"id": "180615", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "334185", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__", "g__", "s__"]}},{"id": "362342", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__Ruminococcus", "s__"]}},{"id": "194909", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "3426658", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "545862", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "3252211", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__epidermidis"]}},{"id": "495270", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "4379449", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Erysipelotrichi", "o__Erysipelotrichales", "f__Erysipelotrichaceae", "g__Clostridium", "s__saccharogumia"]}},{"id": "3061119", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "583746", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Dialister", "s__"]}},{"id": "1713225", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "103606", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "34139", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "741701", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "996970", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "804526", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Coprococcus", "s__"]}},{"id": "377874", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Planococcaceae", "g__", "s__"]}},{"id": "740317", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Alphaproteobacteria", "o__Rhizobiales", "f__Bradyrhizobiaceae", "g__", "s__"]}},{"id": "13493", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "141145", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "2134452", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "190441", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "3887769", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "708680", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "345637", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "626495", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "888055", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "9710", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "543942", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pseudomonadales", "f__Moraxellaceae", "g__Acinetobacter", "s__"]}},{"id": "503372", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "3671383", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "893041", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Coriobacteriia", "o__Coriobacteriales", "f__Coriobacteriaceae", "g__", "s__"]}},{"id": "4448331", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "4438116", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "336133", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "383971", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "4424408", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "183662", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "320395", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "1047041", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "299851", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "3410999", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "851668", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "192015", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "288521", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "337765", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "495451", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "576914", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "4366843", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "146557", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Dialister", "s__"]}},{"id": "524318", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "14287", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "317199", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "535601", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "4405100", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "69384", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "2731539", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__fragilis"]}},{"id": "4375000", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "183296", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "304108", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "538223", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "589071", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__uniformis"]}},{"id": "269949", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "175062", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "813945", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pseudomonadales", "f__Pseudomonadaceae", "g__", "s__"]}},{"id": "524457", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Arcanobacterium", "s__"]}},{"id": "4321285", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "211706", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "175703", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "470382", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "1144153", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "17444", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Enterococcaceae", "g__Enterococcus", "s__"]}},{"id": "811644", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "367176", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__Oscillospira", "s__"]}},{"id": "441265", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "370183", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "361170", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Deltaproteobacteria", "o__Desulfovibrionales", "f__Desulfovibrionaceae", "g__Bilophila", "s__"]}},{"id": "1101451", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Micrococcaceae", "g__Micrococcus", "s__"]}},{"id": "556240", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Coprococcus", "s__"]}},{"id": "28246", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "4392183", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "131921", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "365484", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "349036", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "572882", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Planococcaceae", "g__", "s__"]}},{"id": "313144", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "388506", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "190706", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "193233", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "196219", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Parabacteroides", "s__"]}},{"id": "309720", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__", "s__"]}},{"id": "176297", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "1051082", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "495396", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "968342", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "712047", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Clostridiaceae", "g__Clostridium", "s__perfringens"]}},{"id": "1023405", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "221454", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__Ruminococcus", "s__"]}},{"id": "943989", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Salinicoccus", "s__"]}},{"id": "929230", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "345172", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "199716", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "329597", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "818602", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pseudomonadales", "f__Pseudomonadaceae", "g__Pseudomonas", "s__"]}},{"id": "1090458", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "571178", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__", "s__"]}},{"id": "529873", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "4473763", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__fragilis"]}},{"id": "175535", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "198449", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "4256470", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__ovatus"]}},{"id": "4406925", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "198874", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "4324964", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "177150", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "556835", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Veillonellaceae", "g__Phascolarctobacterium", "s__"]}},{"id": "181171", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "191276", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "1061641", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "351659", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "696563", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__producta"]}},{"id": "1061566", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "1008689", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "268507", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Peptoniphilus", "s__"]}},{"id": "198928", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__"]}},{"id": "844589", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__S24-7", "g__", "s__"]}},{"id": "870118", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__aureus"]}},{"id": "944063", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__epidermidis"]}},{"id": "3474081", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__fragilis"]}},{"id": "527751", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "137845", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Bacillaceae", "g__Bacillus", "s__"]}},{"id": "1105814", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Alphaproteobacteria", "o__Rhizobiales", "f__Bradyrhizobiaceae", "g__Bradyrhizobium", "s__"]}},{"id": "713335", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Alphaproteobacteria", "o__Rhizobiales", "f__Xanthobacteraceae", "g__Labrys", "s__"]}},{"id": "192839", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "3890155", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "722376", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "439908", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "1129060", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "523542", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Dorea", "s__"]}},{"id": "2920309", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "544480", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "956625", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Varibaculum", "s__"]}},{"id": "888575", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__", "g__", "s__"]}},{"id": "2599028", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "197003", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Coprococcus", "s__"]}},{"id": "357471", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "195465", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "4332466", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Cytophagia", "o__Cytophagales", "f__Cytophagaceae", "g__Spirosoma", "s__"]}},{"id": "193769", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "312217", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "666917", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Xanthomonadales", "f__Xanthomonadaceae", "g__", "s__"]}},{"id": "404338", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "955102", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Actinomyces", "s__"]}},{"id": "205615", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "328098", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__", "s__"]}},{"id": "4315290", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "503315", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Finegoldia", "s__"]}},{"id": "183495", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "1024093", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Finegoldia", "s__"]}},{"id": "191113", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "362853", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "301578", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "960695", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__aureus"]}},{"id": "90624", "metadata": {"taxonomy": ["k__Bacteria", "p__Cyanobacteria", "c__4C0d-2", "o__MLE1-12", "f__", "g__", "s__"]}},{"id": "195215", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "514272", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Coprococcus", "s__"]}},{"id": "1814180", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "113265", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__variabile"]}},{"id": "183603", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__fragilis"]}},{"id": "558603", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Deltaproteobacteria", "o__Desulfovibrionales", "f__Desulfovibrionaceae", "g__Desulfovibrio", "s__"]}},{"id": "576007", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__", "g__", "s__"]}},{"id": "176704", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "357168", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "326662", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "588216", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "253380", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Dorea", "s__"]}},{"id": "2084904", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Staphylococcaceae", "g__Staphylococcus", "s__"]}},{"id": "246717", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Epsilonproteobacteria", "o__Campylobacterales", "f__Campylobacteraceae", "g__Campylobacter", "s__"]}},{"id": "960682", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pseudomonadales", "f__Moraxellaceae", "g__Acinetobacter", "s__"]}},{"id": "4356641", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "562038", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "4481719", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "1062748", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Mycobacteriaceae", "g__Mycobacterium", "s__"]}},{"id": "363400", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "194925", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "206826", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Brevibacteriaceae", "g__Brevibacterium", "s__"]}},{"id": "352304", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "4354229", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "181239", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "567715", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "554163", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "807795", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "760967", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "198251", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "960131", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Bacillales", "f__Planococcaceae", "g__", "s__"]}},{"id": "528421", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "359689", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "546876", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "1040713", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "192142", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Actinomycetaceae", "g__Arcanobacterium", "s__"]}},{"id": "350277", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__uniformis"]}},{"id": "304948", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "196139", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__", "s__"]}},{"id": "339013", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "503174", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "1076587", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Dorea", "s__formicigenerans"]}},{"id": "437105", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Oxalobacteraceae", "g__Ralstonia", "s__"]}},{"id": "767863", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Enterococcaceae", "g__", "s__"]}},{"id": "833731", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__Klebsiella", "s__oxytoca"]}},{"id": "255367", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "583117", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "1066814", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Prevotellaceae", "g__Prevotella", "s__"]}},{"id": "966331", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Dermacoccaceae", "g__Dermacoccus", "s__"]}},{"id": "829745", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Comamonadaceae", "g__", "s__"]}},{"id": "384716", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Gemellales", "f__", "g__", "s__"]}},{"id": "1111115", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__[Paraprevotellaceae]", "g__Paraprevotella", "s__"]}},{"id": "368462", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "182176", "metadata": {"taxonomy": ["k__Bacteria", "p__Verrucomicrobia", "c__Verrucomicrobiae", "o__Verrucomicrobiales", "f__Verrucomicrobiaceae", "g__Akkermansia", "s__muciniphila"]}},{"id": "75585", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__", "g__", "s__"]}},{"id": "4378683", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "225569", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pseudomonadales", "f__Pseudomonadaceae", "g__Pseudomonas", "s__"]}},{"id": "1091060", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Alphaproteobacteria", "o__Sphingomonadales", "f__Sphingomonadaceae", "g__Sphingomonas", "s__"]}},{"id": "396697", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Clostridiaceae", "g__Clostridium", "s__perfringens"]}},{"id": "129761", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__", "s__"]}},{"id": "2656868", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "368261", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "874462", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "1111294", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "355424", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "301184", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "3149595", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Clostridiaceae", "g__", "s__"]}},{"id": "445575", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "1078587", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "495084", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Anaerococcus", "s__"]}},{"id": "495086", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Porphyromonas", "s__"]}},{"id": "585914", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Porphyromonadaceae", "g__Parabacteroides", "s__distasonis"]}},{"id": "560336", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "514086", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__obeum"]}},{"id": "539820", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Ruminococcaceae", "g__Oscillospira", "s__"]}},{"id": "188127", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "171559", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "525458", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__", "g__", "s__"]}},{"id": "513445", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "963344", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pseudomonadales", "f__Moraxellaceae", "g__Enhydrobacter", "s__"]}},{"id": "1007599", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "195774", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "297334", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "386273", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Epsilonproteobacteria", "o__Campylobacterales", "f__Campylobacteraceae", "g__Campylobacter", "s__ureolyticus"]}},{"id": "1096610", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Finegoldia", "s__"]}},{"id": "288784", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "1108656", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "13463", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "280799", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Comamonadaceae", "g__Tepidimonas", "s__"]}},{"id": "1030519", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Nocardioidaceae", "g__", "s__"]}},{"id": "298716", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "186592", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Coprococcus", "s__"]}},{"id": "182854", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "3252949", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__[Ruminococcus]", "s__gnavus"]}},{"id": "4365143", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}},{"id": "299267", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "3251419", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__", "s__"]}},{"id": "190309", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "354850", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "270094", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "633252", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Pseudomonadales", "f__Pseudomonadaceae", "g__Pseudomonas", "s__"]}},{"id": "112329", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__bovis"]}},{"id": "187841", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "176450", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__Lachnospiraceae", "g__Blautia", "s__"]}},{"id": "1106674", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Betaproteobacteria", "o__Burkholderiales", "f__Comamonadaceae", "g__", "s__"]}},{"id": "549991", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Bacilli", "o__Lactobacillales", "f__Lactobacillaceae", "g__Lactobacillus", "s__"]}},{"id": "351231", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__fragilis"]}},{"id": "609964", "metadata": {"taxonomy": ["k__Bacteria", "p__Firmicutes", "c__Clostridia", "o__Clostridiales", "f__[Tissierellaceae]", "g__Peptoniphilus", "s__"]}},{"id": "4417325", "metadata": {"taxonomy": ["k__Bacteria", "p__Bacteroidetes", "c__Bacteroidia", "o__Bacteroidales", "f__Bacteroidaceae", "g__Bacteroides", "s__"]}},{"id": "820346", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__", "s__"]}},{"id": "858026", "metadata": {"taxonomy": ["k__Bacteria", "p__Actinobacteria", "c__Actinobacteria", "o__Actinomycetales", "f__Corynebacteriaceae", "g__Corynebacterium", "s__"]}}],"columns": [{"id": "Mgm4459735", "metadata": null},{"id": "Mgm4457768", "metadata": null}]}
\ No newline at end of file
diff --git a/public/gears/src/test/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsKrakenTest.scala b/public/gears/src/test/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsKrakenTest.scala
new file mode 100644
index 0000000000000000000000000000000000000000..5f209cf0bb1ba9a3c8c4091e98ed842015fc6d00
--- /dev/null
+++ b/public/gears/src/test/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsKrakenTest.scala
@@ -0,0 +1,25 @@
+package nl.lumc.sasc.biopet.pipelines.gears
+
+import java.io.File
+import java.nio.file.Paths
+
+import org.scalatest.Matchers
+import org.scalatest.testng.TestNGSuite
+import org.testng.annotations.Test
+
+/**
+ * Created by pjvan_thof on 2/5/16.
+ */
+class GearsKrakenTest extends TestNGSuite with Matchers {
+ private def resourcePath(p: String): String = {
+ Paths.get(getClass.getResource(p).toURI).toString
+ }
+
+ @Test
+ def testConvertKrakenJsonToKronaXml: Unit = {
+ val krakenJsonFile = new File(resourcePath("/hpv_simu_R1.krkn.json"))
+ val outputFile = File.createTempFile("krona.", ".xml")
+ outputFile.deleteOnExit()
+ GearsKraken.convertKrakenJsonToKronaXml(Map("test" -> krakenJsonFile), outputFile)
+ }
+}
diff --git a/public/gears/src/test/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsQiimeClosedTest.scala b/public/gears/src/test/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsQiimeClosedTest.scala
new file mode 100644
index 0000000000000000000000000000000000000000..58fdd3aaafc2e3d6e798c458f39d2ea8f0601b67
--- /dev/null
+++ b/public/gears/src/test/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsQiimeClosedTest.scala
@@ -0,0 +1,25 @@
+package nl.lumc.sasc.biopet.pipelines.gears
+
+import java.io.File
+import java.nio.file.Paths
+
+import org.scalatest.Matchers
+import org.scalatest.testng.TestNGSuite
+import org.testng.annotations.Test
+
+/**
+ * Created by pjvan_thof on 2/5/16.
+ */
+class GearsQiimeClosedTest extends TestNGSuite with Matchers {
+ private def resourcePath(p: String): String = {
+ Paths.get(getClass.getResource(p).toURI).toString
+ }
+
+ @Test
+ def testQiimeBiomToKrona: Unit = {
+ val qiimeBiomFile = new File(resourcePath("/otu_table.biom"))
+ val outputFile = File.createTempFile("krona.", ".xml")
+ outputFile.deleteOnExit()
+ GearsQiimeClosed.qiimeBiomToKrona(qiimeBiomFile, outputFile)
+ }
+}
diff --git a/public/gears/src/test/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSingleTest.scala b/public/gears/src/test/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSingleTest.scala
new file mode 100644
index 0000000000000000000000000000000000000000..49e2eb4ec48baca659afe4559a9943507bf16aab
--- /dev/null
+++ b/public/gears/src/test/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSingleTest.scala
@@ -0,0 +1,154 @@
+/**
+ * Biopet is built on top of GATK Queue for building bioinformatic
+ * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
+ * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
+ * should also be able to execute Biopet tools and pipelines.
+ *
+ * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
+ *
+ * Contact us at: sasc@lumc.nl
+ *
+ * A dual licensing mode is applied. The source code within this project that are
+ * not part of GATK Queue is freely available for non-commercial use under an AGPL
+ * license; For commercial users or users who do not want to follow the AGPL
+ * license, please contact us to obtain a separate license.
+ */
+package nl.lumc.sasc.biopet.pipelines.gears
+
+import java.io.File
+
+import com.google.common.io.Files
+import nl.lumc.sasc.biopet.extensions.kraken.{ Kraken, KrakenReport }
+import nl.lumc.sasc.biopet.extensions.picard.SamToFastq
+import nl.lumc.sasc.biopet.extensions.samtools.SamtoolsView
+import nl.lumc.sasc.biopet.extensions.tools.KrakenReportToJson
+import nl.lumc.sasc.biopet.utils.ConfigUtils
+import nl.lumc.sasc.biopet.utils.config.Config
+import org.apache.commons.io.FileUtils
+import org.broadinstitute.gatk.queue.QSettings
+import org.scalatest.Matchers
+import org.scalatest.testng.TestNGSuite
+import org.testng.annotations._
+
+/**
+ * Test class for [[GearsSingle]]
+ *
+ * Created by wyleung on 10/22/15.
+ */
+
+class GearsSingleTest extends TestNGSuite with Matchers {
+ def initPipeline(map: Map[String, Any]): GearsSingle = {
+ new GearsSingle {
+ override def configName = "gearssingle"
+
+ override def globalConfig = new Config(map)
+
+ qSettings = new QSettings
+ qSettings.runName = "test"
+ }
+ }
+
+ @DataProvider(name = "gearsOptions")
+ def gearsOptions = {
+ val bool = Array(true, false)
+
+ for (
+ fromBam <- bool;
+ pair <- bool;
+ hasOutputName <- bool;
+ kraken <- bool;
+ qiimeClosed <- bool;
+ qiimeRtax <- bool;
+ seqCount <- bool
+ ) yield Array("", fromBam, pair, hasOutputName, kraken, qiimeClosed, qiimeRtax, seqCount)
+ }
+
+ @Test(dataProvider = "gearsOptions")
+ def testGears(dummy: String,
+ fromBam: Boolean,
+ paired: Boolean,
+ hasOutputName: Boolean,
+ kraken: Boolean,
+ qiimeClosed: Boolean,
+ qiimeRtax: Boolean,
+ seqCount: Boolean) = {
+ val map = ConfigUtils.mergeMaps(Map(
+ "gears_use_kraken" -> kraken,
+ "gears_use_qiime_rtax" -> qiimeRtax,
+ "gears_use_qiime_closed" -> qiimeClosed,
+ "gears_use_seq_count" -> seqCount,
+ "output_dir" -> GearsSingleTest.outputDir
+ ), Map(GearsSingleTest.executables.toSeq: _*))
+
+ val gears: GearsSingle = initPipeline(map)
+
+ if (fromBam) {
+ gears.bamFile = Some(GearsSingleTest.bam)
+ } else {
+ gears.fastqR1 = Some(GearsSingleTest.r1)
+ gears.fastqR2 = if (paired) Some(GearsSingleTest.r2) else None
+ }
+ if (hasOutputName)
+ gears.outputName = "test"
+
+ gears.script()
+
+ if (hasOutputName) {
+ gears.outputName shouldBe "test"
+ } else {
+ // in the following cases the filename should have been determined by the filename
+ gears.outputName shouldBe (if (fromBam) "bamfile" else "R1")
+ }
+
+ gears.krakenScript.isDefined shouldBe kraken
+ gears.qiimeClosed.isDefined shouldBe qiimeClosed
+ gears.qiimeRatx.isDefined shouldBe qiimeRtax
+ gears.seqCount.isDefined shouldBe seqCount
+
+ // SamToFastq should have started if it was started from bam
+ gears.functions.count(_.isInstanceOf[SamtoolsView]) shouldBe (if (fromBam) 1 else 0)
+ gears.functions.count(_.isInstanceOf[SamToFastq]) shouldBe (if (fromBam) 1 else 0)
+
+ gears.functions.count(_.isInstanceOf[Kraken]) shouldBe (if (kraken) 1 else 0)
+ gears.functions.count(_.isInstanceOf[KrakenReport]) shouldBe (if (kraken) 1 else 0)
+ gears.functions.count(_.isInstanceOf[KrakenReportToJson]) shouldBe (if (kraken) 1 else 0)
+ }
+
+ // remove temporary run directory all tests in the class have been run
+ @AfterClass def removeTempOutputDir() = {
+ FileUtils.deleteDirectory(GearsSingleTest.outputDir)
+ }
+}
+
+object GearsSingleTest {
+ val outputDir = Files.createTempDir()
+ new File(outputDir, "input").mkdirs()
+
+ val r1 = new File(outputDir, "input" + File.separator + "R1.fq")
+ Files.touch(r1)
+ r1.deleteOnExit()
+ val r2 = new File(outputDir, "input" + File.separator + "R2.fq")
+ Files.touch(r2)
+ r2.deleteOnExit()
+ val bam = new File(outputDir, "input" + File.separator + "bamfile.bam")
+ Files.touch(bam)
+ bam.deleteOnExit()
+
+ val executables = Map(
+ "kraken" -> Map("exe" -> "test", "db" -> "test"),
+ "krakenreport" -> Map("exe" -> "test", "db" -> "test"),
+ "sambamba" -> Map("exe" -> "test"),
+ "samtools" -> Map("exe" -> "test"),
+ "md5sum" -> Map("exe" -> "test"),
+ "assigntaxonomy" -> Map("exe" -> "test"),
+ "pickclosedreferenceotus" -> Map("exe" -> "test"),
+ "pickotus" -> Map("exe" -> "test"),
+ "pickrepset" -> Map("exe" -> "test"),
+ "splitlibrariesfastq" -> Map("exe" -> "test"),
+ "flash" -> Map("exe" -> "test"),
+ "fastqc" -> Map("exe" -> "test"),
+ "seqtk" -> Map("exe" -> "test"),
+ "sickle" -> Map("exe" -> "test"),
+ "cutadapt" -> Map("exe" -> "test")
+ )
+}
diff --git a/public/gears/src/test/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsTest.scala b/public/gears/src/test/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsTest.scala
index fb8148194dc4afa26699e4051d47c8953271bf0c..de0be0ba546a47e1f4f9f819a8fb0e3baa610dde 100644
--- a/public/gears/src/test/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsTest.scala
+++ b/public/gears/src/test/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsTest.scala
@@ -1,42 +1,20 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
package nl.lumc.sasc.biopet.pipelines.gears
import java.io.File
import com.google.common.io.Files
-import nl.lumc.sasc.biopet.extensions.kraken.{ Kraken, KrakenReport }
-import nl.lumc.sasc.biopet.extensions.picard.SamToFastq
-import nl.lumc.sasc.biopet.extensions.samtools.SamtoolsView
-import nl.lumc.sasc.biopet.extensions.tools.KrakenReportToJson
import nl.lumc.sasc.biopet.utils.ConfigUtils
import nl.lumc.sasc.biopet.utils.config.Config
import org.apache.commons.io.FileUtils
import org.broadinstitute.gatk.queue.QSettings
import org.scalatest.Matchers
import org.scalatest.testng.TestNGSuite
-import org.testng.annotations._
+import org.testng.annotations.{ DataProvider, Test, AfterClass }
/**
- * Test class for [[Gears]]
- *
- * Created by wyleung on 10/22/15.
+ * Created by pjvanthof on 04/02/16.
*/
-
-class GearsPipelineTest(val testset: String) extends TestNGSuite with Matchers {
+class GearsTest extends TestNGSuite with Matchers {
def initPipeline(map: Map[String, Any]): Gears = {
new Gears {
override def configName = "gears"
@@ -49,65 +27,39 @@ class GearsPipelineTest(val testset: String) extends TestNGSuite with Matchers {
}
@DataProvider(name = "gearsOptions")
- def gearsOptions = {
- val startFromBam = Array(true, false)
- val paired = Array(true, false)
- val hasOutputNames = Array(true, false)
- val hasFileExtensions = Array(true, false)
+ def shivaOptions = {
+ val bool = Array(true, false)
for (
- fromBam <- startFromBam;
- pair <- paired;
- hasOutputName <- hasOutputNames;
- hasFileExtension <- hasFileExtensions
- ) yield Array(testset, fromBam, pair, hasOutputName, hasFileExtension)
+ s1 <- bool; s2 <- bool; qiimeClosed <- bool
+ ) yield Array("", s1, s2, qiimeClosed)
}
@Test(dataProvider = "gearsOptions")
- def testGears(testset: String, fromBam: Boolean, paired: Boolean,
- hasOutputName: Boolean, hasFileExtension: Boolean) = {
- val map = ConfigUtils.mergeMaps(Map(
- "output_dir" -> GearsTest.outputDir
- ), Map(GearsTest.executables.toSeq: _*))
-
- val gears: Gears = initPipeline(map)
-
- if (fromBam) {
- gears.bamFile = if (hasFileExtension) Some(GearsTest.bam) else Some(GearsTest.bam_noext)
- } else {
- gears.fastqR1 = if (hasFileExtension) Some(GearsTest.r1) else Some(GearsTest.r1_noext)
- gears.fastqR2 = if (paired) if (hasFileExtension) Some(GearsTest.r2) else Some(GearsTest.r2_noext) else None
+ def testGears(dummy: String, sample1: Boolean, sample2: Boolean, qiimeCLosed: Boolean): Unit = {
+ val map = {
+ var m: Map[String, Any] = GearsTest.config
+ if (sample1) m = ConfigUtils.mergeMaps(GearsTest.sample1, m)
+ if (sample2) m = ConfigUtils.mergeMaps(GearsTest.sample2, m)
+ ConfigUtils.mergeMaps(Map("gear_use_qiime_closed" -> qiimeCLosed), m)
}
- if (hasOutputName)
- gears.outputName = "test"
- gears.script()
-
- if (hasOutputName) {
- gears.outputName shouldBe "test"
- } else {
- // in the following cases the filename should have been determined by the filename
- if (hasFileExtension) {
- gears.outputName shouldBe (if (fromBam) "bamfile" else "R1")
- } else {
- // no real use-case for this one, have this is for sanity check
- gears.outputName shouldBe (if (fromBam) "bamfile" else "R1")
+ if (!sample1 && !sample2) { // When no samples
+ intercept[IllegalArgumentException] {
+ initPipeline(map).script()
}
- }
-
- // SamToFastq should have started if it was started from bam
- gears.functions.count(_.isInstanceOf[SamtoolsView]) shouldBe (if (fromBam) 1 else 0)
- gears.functions.count(_.isInstanceOf[SamToFastq]) shouldBe (if (fromBam) 1 else 0)
+ } else {
+ val pipeline = initPipeline(map)
+ pipeline.script()
- gears.functions.count(_.isInstanceOf[Kraken]) shouldBe 1
- gears.functions.count(_.isInstanceOf[KrakenReport]) shouldBe 1
- gears.functions.count(_.isInstanceOf[KrakenReportToJson]) shouldBe 1
+ }
}
// remove temporary run directory all tests in the class have been run
@AfterClass def removeTempOutputDir() = {
FileUtils.deleteDirectory(GearsTest.outputDir)
}
+
}
object GearsTest {
@@ -121,18 +73,45 @@ object GearsTest {
val bam = new File(outputDir, "input" + File.separator + "bamfile.bam")
Files.touch(bam)
- val r1_noext = new File(outputDir, "input" + File.separator + "R1")
- Files.touch(r1_noext)
- val r2_noext = new File(outputDir, "input" + File.separator + "R2")
- Files.touch(r2_noext)
- val bam_noext = new File(outputDir, "input" + File.separator + "bamfile")
- Files.touch(bam_noext)
-
- val executables = Map(
+ val config = Map(
+ "output_dir" -> outputDir,
"kraken" -> Map("exe" -> "test", "db" -> "test"),
"krakenreport" -> Map("exe" -> "test", "db" -> "test"),
"sambamba" -> Map("exe" -> "test"),
+ "mergeotutables" -> Map("exe" -> "test"),
"samtools" -> Map("exe" -> "test"),
- "md5sum" -> Map("exe" -> "test")
+ "md5sum" -> Map("exe" -> "test"),
+ "assigntaxonomy" -> Map("exe" -> "test"),
+ "pickclosedreferenceotus" -> Map("exe" -> "test"),
+ "pickotus" -> Map("exe" -> "test"),
+ "pickrepset" -> Map("exe" -> "test"),
+ "splitlibrariesfastq" -> Map("exe" -> "test"),
+ "flash" -> Map("exe" -> "test"),
+ "fastqc" -> Map("exe" -> "test"),
+ "seqtk" -> Map("exe" -> "test"),
+ "sickle" -> Map("exe" -> "test"),
+ "cutadapt" -> Map("exe" -> "test")
)
+
+ val sample1 = Map(
+ "samples" -> Map("sample1" -> Map("libraries" -> Map(
+ "lib1" -> Map(
+ "R1" -> r1.getAbsolutePath,
+ "R2" -> r2.getAbsolutePath
+ )
+ )
+ )))
+
+ val sample2 = Map(
+ "samples" -> Map("sample3" -> Map("libraries" -> Map(
+ "lib1" -> Map(
+ "R1" -> r1.getAbsolutePath,
+ "R2" -> r2.getAbsolutePath
+ ),
+ "lib2" -> Map(
+ "R1" -> r1.getAbsolutePath,
+ "R2" -> r2.getAbsolutePath
+ )
+ )
+ )))
}
diff --git a/public/gentrap/pom.xml b/public/gentrap/pom.xml
index 42b558833ce1d09ce16933fc1ed1a3fd4e63e852..2a43fbddea3f257e9955ccf74a9c62360e15c2d1 100644
--- a/public/gentrap/pom.xml
+++ b/public/gentrap/pom.xml
@@ -33,6 +33,11 @@
<name>Gentrap</name>
<dependencies>
+ <dependency>
+ <groupId>nl.lumc.sasc</groupId>
+ <artifactId>Shiva</artifactId>
+ <version>${project.version}</version>
+ </dependency>
<dependency>
<groupId>nl.lumc.sasc</groupId>
<artifactId>Mapping</artifactId>
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/aggr_base_count.R b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/aggr_base_count.R
deleted file mode 100755
index df4e0bd02efe530164e34ebf3cfac4982362065a..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/aggr_base_count.R
+++ /dev/null
@@ -1,237 +0,0 @@
-#!/usr/bin/env Rscript
-
-# aggr_base_count.R
-#
-# Given a count file, write tab-delimited file(s) aggregating the counts
-# at gene and/or exon level.
-#
-# (c) 2013 by Wibowo Arindrarto [LUMC - SASC]
-# Adapted from Peter-Bram 't Hoen's script: 'merge_table_script_shark_PH3.r'
-
-# General function to install package if it does not exist
-# Otherwise, it only loads the package
-usePackage <- function(p) {
- r <- getOption("repos")
- r["CRAN"] <- "http://cran.us.r-project.org"
- options(repos = r)
- rm(r)
- if (!is.element(p, installed.packages()[,1]))
- install.packages(p, dep = TRUE)
- require(p, character.only = TRUE)
-}
-
-usePackage("getopt")
-
-## FLAGS ##
-LEVELS <- c('gene', 'exon')
-OUT.DIR <- getwd()
-DEBUG <- FALSE
-if (DEBUG) {
- message("## DEBUG MODE ##")
-}
-
-
-## FUNCTIONS ##
-CheckCountFiles <- function(count.files, DEBUG=FALSE) {
- # Given a vector of sample names, checks whether the .count files exist.
- #
- # Count files are the input files used to analyze the RNA-Seq expression
- # levels. They must conform to the following file name:
- # '{sample_name}/{sample_name}.count'
- #
- # Args:
- # - paths: string vector of file paths
- for (cfile in count.files) {
-
- if (!file.exists(cfile)) {
- stop(paste("Path '", cfile, "' does not exist. Exiting.", sep=""))
- }
-
- if (DEBUG) {
- message("Path '", cfile, "' exists.", sep="")
- }
- }
-}
-
-CountBaseExons <- function(count.files, count.names,
- col.header=c("gene", "chr", "start", "stop")) {
- # Given a list of count files, return a data frame containing their values.
- #
- # The count files must be a tab-separate file containing the following
- # columns in the same order:
- # 1. chromosome
- # 2. start position
- # 3. stop position
- # 4. total nucleotide counts
- # 5. nucleotide counts per exon
- # 6. gene name
- #
- # The returned data frame has the following columns:
- #
- # 1. gene name
- # 2. chromosome
- # 3. start position
- # 4. stop position
- # 5... total nucleotide counts for each sample
- #
- # This function assumes that for all count files, the values of the first
- # three columns are the same for each row.
- #
- # Args:
- # - count.files: string vector of count file paths
- # - col.headers: string vector of default data frame output headers
-
- # given a count file path, extract its fourth column
- GetNucCount <- function(x) {
- read.table(x, as.is=TRUE)[4]
- }
-
- # initial data frame is from the first file
- exon.counts <- read.table(count.files[1], as.is=TRUE)
- exon.counts <- exon.counts[, c(6, 1:3, 4)]
- colnames(exon.counts)[1:5] <- append(col.header, count.names[1])
-
- if (length(count.files) > 1) {
- # why doesn't R provide a nice way to slice remaining items??
- remaining.files <- count.files[2: length(count.files)]
- remaining.names <- count.names[2: length(count.names)]
- # append all nucleotide counts from remaining files to exon.counts
- exon.counts <- cbind(exon.counts, lapply(remaining.files, GetNucCount))
- # and rename these columns accordingly
- end.idx <- 5 + length(remaining.files)
- colnames(exon.counts)[6:end.idx] <- remaining.names
- }
-
- return(exon.counts)
-}
-
-CountExons <- function(exon.df) {
- # Given a data frame containing exon counts, return a data frame consisting of
- # compacted exon counts.
- #
- # In a compacted exon count data frame, each exon has its own unique name
- # consisting of its gene source and its start-stop coordinates.
- #
- # Args:
- # - exon.df: data frame of complete exon counts
-
-
- # create new data frame of the exon counts, concatenating gene name, and the
- # exon start-stop coordinates
- exon.dis.counts <- cbind(paste(paste(exon.df$gene, exon.df$start,
- sep=":"), exon.df$stop, sep="-"),
- exon.df[5: length(exon.df)])
- colnames(exon.dis.counts)[1] <- "exon"
- counts.in.samples <- as.matrix(exon.dis.counts[2:ncol(exon.dis.counts)])
- exon.counts <- aggregate(counts.in.samples ~ exon, data=exon.dis.counts, FUN=sum,
- na.rm=TRUE)
- colnames(exon.counts)[2:ncol(exon.counts)] <- colnames(counts.in.samples)
-
- return (exon.counts)
-}
-
-CountGenes <- function(exon.df) {
- # Given a data frame containing exon counts, return a data frame of gene
- # counts.
- #
- # See CountBaseExons for the input data frame format.
- #
- # Args:
- # - exon.df: data frame of complete exon counts
-
- # basically an aggregate of exon counts with the same gene name
- counts.in.samples <- as.matrix(exon.df[5:ncol(exon.df)])
- gene.counts <- aggregate(counts.in.samples ~ gene, data=exon.df, FUN=sum,
- na.rm=TRUE)
- # first column is gene
- colnames(gene.counts)[2:ncol(gene.counts)] <- colnames(counts.in.samples)
-
- return(gene.counts)
-}
-
-
-# load package for arg parsing
-library('getopt')
-
-# create spec for arg parsing
-spec <- matrix(c(
- # colon-separated paths to each count files
- 'count-file', 'I', 1, 'character',
- # colon-separated paths of each count file label; order must be the same
- # as the count files
- 'count-name', 'N', 1, 'character',
- # output file for gene level counts
- 'gene-count', 'G', 1, 'character',
- # output file for exon level counts
- 'exon-count', 'E', 1, 'character',
- # help
- 'help', 'H', 0, 'logical'
-), byrow=TRUE, ncol=4)
-opt <- getopt(spec)
-
-# print help if requested
-if (!is.null(opt[['help']])) {
- cat(getopt(spec, usage=TRUE))
- q(status=1)
-}
-
-# we need gene-count and/or exon-count flag
-if (is.null(opt[['gene-count']]) & is.null(opt[['exon-count']])) {
- message("Error: Either '--gene-count' and/or '--exon-count' must have a value.")
- q(status=1)
-}
-
-# set fallback values for optional args
-if (!is.null(opt[['output-dir']])) {
- OUT.DIR <- normalizePath(opt[['output-dir']])
- # create directory if it doesn't exist
- dir.create(OUT.DIR, showWarnings=FALSE)
-}
-
-# parse the input file paths and check their presence
-if (!is.null(opt[['count-file']])) {
- count.files <- opt[['count-file']]
- count.files <- unlist(strsplit(gsub(' ', '', count.files), ':'))
- CheckCountFiles(count.files, DEBUG)
-} else {
- stop("Required input count file path(s) not present. Exiting.")
-}
-
-# parse the input count labels and check if its length is the same as the input
-# files
-if (!is.null(opt[['count-name']])) {
- count.names <- opt[['count-name']]
- count.names <- unlist(strsplit(gsub(' ', '', count.names), ':'))
- if (length(count.names) != length(count.files)) {
- stop("Mismatched count file paths and labels. Exiting.")
- }
-} else {
- stop("Required input count file label(s) not present. Exiting.")
-}
-
-# set output file name for gene counts
-if (!is.null(opt[['gene-count']])) {
- gene.out <- opt[['gene-count']]
-} else {
- gene.out <- NULL
-}
-
-# set output file name for exon counts
-if (!is.null(opt[['exon-count']])) {
- exon.out <- opt[['exon-count']]
-} else {
- exon.out <- NULL
-}
-
-# count base exons (complete with coordinates)
-base.exon.counts <- CountBaseExons(count.files, count.names)
-
-# and write output files, depending on the flags
-if (!is.null(gene.out)) {
- gene.counts <- CountGenes(base.exon.counts)
- write.table(gene.counts, file = gene.out, sep = "\t", quote = FALSE, row.names = FALSE)
-}
-if (!is.null(exon.out)) {
- exon.counts <- CountExons(base.exon.counts)
- write.table(exon.counts, file = exon.out, sep = "\t", quote = FALSE, row.names = FALSE)
-}
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/bam_rna.py b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/bam_rna.py
deleted file mode 100755
index d2c14cff2588f01c7a9e3ba87ab5558244cb856e..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/bam_rna.py
+++ /dev/null
@@ -1,391 +0,0 @@
-#!/usr/bin/env python2.7
-#
-# Biopet is built on top of GATK Queue for building bioinformatic
-# pipelines. It is mainly intended to support LUMC SHARK cluster which is running
-# SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
-# should also be able to execute Biopet tools and pipelines.
-#
-# Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
-#
-# Contact us at: sasc@lumc.nl
-#
-# A dual licensing mode is applied. The source code within this project that are
-# not part of GATK Queue is freely available for non-commercial use under an AGPL
-# license; For commercial users or users who do not want to follow the AGPL
-# license, please contact us to obtain a separate license.
-#
-
-
-# bam_rna.py
-#
-# Generate read pair and alignment statistics for a BAM file.
-#
-# Part of the Gentrap pipeline
-#
-# (c) 2013 Wibowo Arindrarto [SASC - LUMC]
-
-import argparse
-import json
-import locale
-import os
-from collections import OrderedDict
-from functools import partial
-
-import pysam
-
-# set locale to group digits
-locale.setlocale(locale.LC_ALL, '')
-# formatters for output
-int_fmt = partial(locale.format, grouping=True, percent='%i')
-float_fmt = partial(locale.format, grouping=True, percent='%.2f')
-
-# -F 0x4
-func_nmap = lambda rec: not rec.flag & 0x4
-# -f 0xC
-func_nunmap = lambda rec: (rec.flag & 0x4) and (rec.flag & 0x8)
-# -F 0xC
-func_nmap_pair = lambda rec: not rec.flag & 0xC
-# -f 0x2
-func_nmap_pair_ok = lambda rec: rec.flag & 0x2
-# mapped to different chromosomes / reference sequences
-func_nmap_diffchr = lambda rec: rec.rnext != rec.tid
-# -F 0x4 -f 0x8
-func_nmap_sgltn = lambda rec: (not rec.flag & 0x4) and (rec.flag & 0x8)
-# check if spliced
-func_splice = lambda rec: 'N' in rec.cigarstring
-# check if pass QC
-# not bool since we always need to run each read through it
-func_qc = lambda rec: 1 if rec.flag & 0x200 else 0
-
-FLAGS = OrderedDict((
- ('total', 'Total'),
- ('unmapped', 'Unmapped'),
- ('mapped', 'Mapped'),
- ('mappedPair', 'Mapped pairs'),
- ('mappedPairProper', 'Properly mapped pairs'),
- ('mappedDiffChr', 'Different chromosomes'),
- ('mappedDiffChrQ', 'Different chromosomes, MAPQ >=5'),
- ('singleton', 'Singletons'),
- ('totalSplice', 'Split reads, total'),
- ('splicePairProper', 'Split reads, properly mapped'),
- ('spliceSingleton', 'Split reads, singletons'),
-))
-
-class BarnStat(object):
-
- """Class representing a collection of BAM statistics for RNA-seq data."""
-
- def __init__(self, bamfile, read_pair_suffix_len=0, id_sorted=False,
- validate=False):
- assert os.path.exists(bamfile), "BAM file %r not found." % bamfile
- self.validate = validate
- self.bamfile = bamfile
-
- self.flags = FLAGS.keys()
- # length of read pair suffix (e.g. '/2' has len == 2)
- self.suflen = read_pair_suffix_len
- if not id_sorted:
- self._count_unsorted()
- else:
- self._count_sorted()
-
- self._format_counts()
-
- def _adjust_counts(self, alns, reads):
- """Adjusts the alignment and read counts."""
- # we need to adjust the unmapped counts for alignments as each
- # alignments consists of two reads (one read pair) which may be mapped
- # multiple times as singletons and/or whole read pairs.
- # so unmapped alns is always == unmapped read pairs + singleton *reads*
- # counts (proxy for the set of unmapped singletons)
- if 'unmapped' in alns:
- alns['unmapped'] += reads['singleton']
- else:
- # tophat, splits unmapped reads into its own BAM file
- alns['unmapped'] = 0
-
- return alns, reads
-
- def _count_sorted(self):
- """Counts read and alignment statistics for ID-sorted BAM file."""
- flags = self.flags
- reads, alns, alns_qc = {}, {}, {}
- read_flags = dict.fromkeys(flags, False)
- cur_qname = None
-
- # init counts
- for flag in flags:
- reads[flag], alns[flag], alns_qc[flag] = 0, 0, 0
-
- # iterate over each record
- # index for suffix removal, if suffix exist (> 0)
- if self.suflen:
- sufslice = slice(-self.suflen)
- else:
- sufslice = slice(None)
- for rec in pysam.Samfile(self.bamfile, 'rb'):
- # different qname mean we've finished parsing each unique read
- # so reset the flags and add them to the counters appropriately
- if cur_qname != rec.qname[sufslice]:
- for flag in flags:
- reads[flag] += int(read_flags[flag])
- # reset the qname tracker
- cur_qname = rec.qname[sufslice]
- # and the read flag tracker
- read_flags = dict.fromkeys(flags, False)
- # total, total splice
- alns['total'] += 1
- alns_qc['total'] += func_qc(rec)
- read_flags['total'] = True
- if func_splice(rec):
- alns['totalSplice'] += 1
- alns_qc['totalSplice'] += func_qc(rec)
- read_flags['totalSplice'] = True
- # unmapped
- if func_nunmap(rec):
- alns['unmapped'] += 1
- alns_qc['unmapped'] += func_qc(rec)
- read_flags['unmapped'] = True
- else:
- # mapped
- if func_nmap(rec):
- alns['mapped'] += 1
- alns_qc['mapped'] += func_qc(rec)
- read_flags['mapped'] = True
- # mapped pairs
- if func_nmap_pair(rec):
- alns['mappedPair'] += 1
- alns_qc['mappedPair'] += func_qc(rec)
- read_flags['mappedPair'] = True
- # proper pairs, proper pairs splice
- if func_nmap_pair_ok(rec):
- alns['mappedPairProper'] += 1
- alns_qc['mappedPairProper'] += func_qc(rec)
- read_flags['mappedPairProper'] = True
- if func_splice(rec):
- alns['splicePairProper'] += 1
- alns_qc['splicePairProper'] += func_qc(rec)
- read_flags['splicePairProper'] = True
- # mapped to different chromosomes
- elif func_nmap_diffchr(rec):
- alns['mappedDiffChr'] += 1
- alns_qc['mappedDiffChr'] += func_qc(rec)
- read_flags['mappedDiffChr'] = True
- if rec.mapq >= 5:
- alns['mappedDiffChrQ'] += 1
- alns_qc['mappedDiffChrQ'] += func_qc(rec)
- read_flags['mappedDiffChrQ'] = True
- # singletons, singletons splice
- elif func_nmap_sgltn(rec):
- alns['singleton'] += 1
- alns_qc['singleton'] += func_qc(rec)
- read_flags['singleton'] = True
- if func_splice(rec):
- alns['spliceSingleton'] += 1
- alns_qc['spliceSingleton'] += func_qc(rec)
- read_flags['spliceSingleton'] = True
-
- # for the last read, since we don't pass the qname check again
- for flag in flags:
- reads[flag] += int(read_flags[flag])
-
- self.aln_counts, self.read_counts = self._adjust_counts(alns, reads)
- self.aln_qc_counts = alns_qc
- if self.validate:
- assert self.validate_counts()
-
- def _count_unsorted(self):
- """Counts read and alignment statistics for non-ID-sorted BAM file."""
- flags = self.flags
- reads_total, reads_unmap, reads_map, reads_pair_map, reads_pair_proper, \
- reads_sgltn, reads_total_splice, reads_pair_proper_splice, \
- reads_sgltn_splice, reads_pair_diffchr, reads_pair_diffchr_h = \
- set(), set(), set(), set(), set(), set(), set(), set(), set(), \
- set(), set()
-
- reads, alns, alns_qc = {}, {}, {}
- for flag in flags:
- reads[flag], alns[flag], alns_qc[flag] = 0, 0, 0
- # index for suffix removal, if suffix exist (> 0)
- if self.suflen:
- sufslice = slice(-self.suflen)
- else:
- sufslice = slice(None)
- for rec in pysam.Samfile(self.bamfile, 'rb'):
- # remove '/1' or '/2' suffixes, to collapse read pair counts
- pass
- # do countings on alns and reads directly
- hname = hash(rec.qname[sufslice])
- # total, total splice
- alns['total'] += 1
- alns_qc['total'] += func_qc(rec)
- if hname not in reads_total:
- reads_total.add(hname)
- if func_splice(rec):
- alns['totalSplice'] += 1
- alns_qc['totalSplice'] += func_qc(rec)
- reads_total_splice.add(hname)
- # unmapped
- if func_nunmap(rec):
- alns['unmapped'] += 1
- alns_qc['unmapped'] += func_qc(rec)
- reads_unmap.add(hname)
- else:
- # mapped
- if func_nmap(rec):
- alns['mapped'] += 1
- alns_qc['mapped'] += func_qc(rec)
- reads_map.add(hname)
- # mapped pairs
- if func_nmap_pair(rec):
- alns['mappedPair'] += 1
- alns_qc['mappedPair'] += func_qc(rec)
- reads_pair_map.add(hname)
- # proper pairs, proper pairs splice
- if func_nmap_pair_ok(rec):
- alns['mappedPairProper'] += 1
- alns_qc['mappedPairProper'] += func_qc(rec)
- reads_pair_proper.add(hname)
- if func_splice(rec):
- alns['splicePairProper'] += 1
- alns_qc['splicePairProper'] += func_qc(rec)
- reads_pair_proper_splice.add(hname)
- # mapped to different chromosomes
- elif func_nmap_diffchr(rec):
- alns['mappedDiffChr'] += 1
- alns_qc['mappedDiffChr'] += func_qc(rec)
- reads_pair_diffchr.add(hname)
- if rec.mapq >= 5:
- alns['mappedDiffChrQ'] += 1
- alns_qc['mappedDiffChrQ'] += func_qc(rec)
- reads_pair_diffchr_h.add(hname)
- # singletons, singletons splice
- elif func_nmap_sgltn(rec):
- alns['singleton'] += 1
- alns_qc['singleton'] += func_qc(rec)
- reads_sgltn.add(hname)
- if func_splice(rec):
- alns['spliceSingleton'] += 1
- alns_qc['spliceSingleton'] += func_qc(rec)
- reads_sgltn_splice.add(hname)
-
- # set counts for reads
- reads['total'] = len(reads_total)
- reads['totalSplice'] = len(reads_total_splice)
- reads['unmapped'] = len(reads_unmap)
- reads['mapped'] = len(reads_map)
- reads['mappedPair'] = len(reads_pair_map)
- reads['mappedPairProper'] = len(reads_pair_proper)
- reads['mappedDiffChr'] = len(reads_pair_diffchr)
- reads['mappedDiffChrQ'] = len(reads_pair_diffchr_h)
- reads['splicePairProper'] = len(reads_pair_proper_splice)
- reads['singleton'] = len(reads_sgltn)
- reads['spliceSingleton'] = len(reads_sgltn_splice)
-
- # free the memory
- del reads_total, reads_map, reads_pair_map, reads_pair_proper, \
- reads_sgltn, reads_total_splice, reads_pair_proper_splice, \
- reads_sgltn_splice, reads_unmap, reads_pair_diffchr, \
- reads_pair_diffchr_h
-
- self.aln_counts, self.read_counts = self._adjust_counts(alns, reads)
- self.aln_qc_counts = alns_qc
- if self.validate:
- assert self.validate_counts()
-
- def validate_counts(self):
- """Checks whether all reads and alignment counts add up."""
- for ctype in ('read_counts', 'aln_counts'):
- count = getattr(self, ctype)
- ntotal = count['total']
- nmap = count['mapped']
- nunmap = count['unmapped']
- nmap_pair = count['mappedPair']
- nmap_pair_ok = count['mappedPairProper']
- nmap_pair_diffchr = count['mappedDiffChr']
- nmap_sgltn = count['singleton']
- nsplice_total = count['totalSplice']
- nsplice_pair_ok = count['splicePairProper']
- nsplice_sgltn = count['spliceSingleton']
-
- assert nmap == nmap_pair + nmap_sgltn, \
- "Mismatch: %r == %r + %r" % (nmap, nmap_pair, nmap_sgltn)
- assert nmap_pair_ok + nmap_pair_diffchr <= nmap_pair
- assert nsplice_total <= ntotal
- assert nsplice_pair_ok <= nmap_pair_ok
- assert nsplice_sgltn <= nmap_sgltn
- # total is always == unmapped + mapped pair + singletons
- assert ntotal == nunmap + nmap_pair + nmap_sgltn, "Mismatch: " \
- "%r == %r + %r + %r" % (ntotal, nunmap, nmap_pair,
- nmap_sgltn)
-
- return True
-
- def show(self):
- """Prints the read and alignment counts in human-readable format to
- stdout."""
- import pprint
- pprint.pprint(dict(self.counts.items()))
-
- def write_json(self, out_file):
- """Writes JSON to the output file."""
- with open(out_file, 'w') as outfile:
- json.dump(self.counts, outfile, sort_keys=True, indent=4,
- separators=(',', ': '))
-
- def _format_counts(self):
- """Formats read and alignment counts into nice-looking numbers."""
- counts = OrderedDict()
- flags = self.flags
- for ctype in ('read_counts', 'aln_counts', 'aln_qc_counts'):
- count = getattr(self, ctype)
-
- ntotal = count['total']
- cont = {}
- lvl = 'aln' if ctype == 'aln_counts' else 'read'
-
- if ctype == 'aln_qc_counts':
- lvl = 'aln_qc'
- else:
- pct = lambda x: x * 100.0 / ntotal
- if ctype == 'read_counts':
- lvl = 'read'
- elif ctype == 'aln_counts':
- lvl = 'aln'
-
- for flag in flags:
- # format all counts
- cont[flag] = int_fmt(value=count[flag])
- # and add percentage values
- if lvl != 'aln_qc':
- if flag == 'total':
- cont['totalPct'] = '100'
- else:
- cont[flag + 'Pct'] = float_fmt(value=pct(count[flag]))
-
- counts[lvl] = cont
-
- self.counts = counts
-
-
-if __name__ == '__main__':
-
- parser = argparse.ArgumentParser()
- parser.add_argument('bamfile', help='Path to BAM file')
- parser.add_argument('--id-sorted', action='store_true',
- dest='id_sorted', help='Whether the BAM file is ID-sorted or not')
- parser.add_argument('--suffix-len', type=int, dest='suffix_len', default=0,
- help='Length of read pair suffix, if present')
- parser.add_argument('-o', '--outfile', dest='out_file', type=str,
- help='Path to output file')
- parser.add_argument('-f', '--outfmt', dest='out_fmt', type=str,
- choices=['json'], default='json',
- help='Format of output file')
- args = parser.parse_args()
-
- bamstat = BarnStat(args.bamfile, args.suffix_len, args.id_sorted)
-
- if args.out_file is None:
- bamstat.show()
- elif args.out_fmt == 'json':
- bamstat.write_json(args.out_file)
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/gc_dist.py b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/gc_dist.py
deleted file mode 100755
index 27f2d482867f0250b1ed8df9ff6f921de103191f..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/gc_dist.py
+++ /dev/null
@@ -1,173 +0,0 @@
-#!/usr/bin/env python
-#
-# Biopet is built on top of GATK Queue for building bioinformatic
-# pipelines. It is mainly intended to support LUMC SHARK cluster which is running
-# SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
-# should also be able to execute Biopet tools and pipelines.
-#
-# Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
-#
-# Contact us at: sasc@lumc.nl
-#
-# A dual licensing mode is applied. The source code within this project that are
-# not part of GATK Queue is freely available for non-commercial use under an AGPL
-# license; For commercial users or users who do not want to follow the AGPL
-# license, please contact us to obtain a separate license.
-#
-
-#
-# gc_dist.py
-#
-# Given a path to a FASTQ file, create plots of GC percentages.
-#
-# Part of the Gentrap pipeline.
-#
-# (c) 2013 Wibowo Arindrarto [SASC - LUMC]
-
-import argparse
-import locale
-import os
-import textwrap
-
-import numpy as np
-# for headless matplotlib
-import matplotlib
-matplotlib.use("Agg")
-import matplotlib.pyplot as plt
-import matplotlib.gridspec as gs
-
-from matplotlib.ticker import FuncFormatter, MultipleLocator
-
-
-# set locale and formatter to do digit grouping
-locale.setlocale(locale.LC_ALL, '')
-groupdig = lambda x, pos: locale.format('%d', x, grouping=True)
-major_formatter = FuncFormatter(groupdig)
-
-
-def read_seq(fp):
- """Given a FASTQ file, yield its sequences."""
- if isinstance(fp, basestring):
- assert os.path.exists(fp)
- fp = open(fp, 'r')
- for counter, line in enumerate(fp):
- if (counter + 3) % 4 == 0:
- yield line.strip()
-
-
-def drange(start, stop, step):
- """Like `range` but for floats."""
- cur = start
- while cur < stop:
- yield cur
- cur += step
-
-
-def graph_gc(fname, outname='test.png'):
- """Graphs the GC percentages of the given FASTQ file."""
- # count GC percentages per sequence
- gcs = []
- for seq in read_seq(fname):
- gc = sum(seq.lower().count(x) for x in ('g', 'c', 's'))
- gcs.append(gc * 100.0 / len(seq))
- # grab mean and std dev for plotting
- mean = np.mean(gcs)
- stdev = np.std(gcs)
-
- # set the subplots in the figure; top is histogram, bottom is boxplot
- fig = plt.figure(figsize=(8, 8))
- grids = gs.GridSpec(2, 1, height_ratios=[5, 1])
-
- ax0 = plt.subplot(grids[0])
- # set title and adjust distance to plot
- title = 'Distribution of GC Percentage'
- t = plt.title('\n'.join([title] + textwrap.wrap('%r' %
- os.path.basename(fname), 50)), fontsize=15)
- t.set_y(1.05)
-
- # start counting bins for width measurement
- total = len(gcs)
- min_hist = min(gcs)
- max_hist = max(gcs)
- low = high = np.median(gcs)
- step = 1
- widths = dict.fromkeys(range(20, 100, 20) + [99], (0, 0))
-
- while low >= min_hist or high <= max_hist:
- # cap the width marker at min or max gc values
- if high > max_hist: high = max_hist
- if low < min_hist: low = min_hist
-
- range_count = len([x for x in gcs if low < x < high])
- coverage = float(range_count) / total
-
- if coverage >= 0.2 and not any(widths[20]):
- widths[20] = (low, high)
- if coverage >= 0.4 and not any(widths[40]):
- widths[40] = (low, high)
- if coverage >= 0.6 and not any(widths[60]):
- widths[60] = (low, high)
- if coverage >= 0.8 and not any(widths[80]):
- widths[80] = (low, high)
- if coverage >= 0.99 and not any(widths[99]):
- widths[99] = (low, high)
-
- low -= step
- high += step
-
- # use the bin coordinates for partial background coloring
- for hstart, hend in widths.values():
- plt.axvspan(hstart, hend, facecolor='#0099ff', linestyle='dotted',
- linewidth=2.0, edgecolor='black', alpha=0.2)
-
- # plot the histogram
- bins = [0] + list(drange(2.5, 100, 5)) + [100]
- n, bins, patches = ax0.hist(gcs, bins=bins, facecolor='#009933', alpha=0.9)
- # set Y-axis ticks label formatting
- ax0.yaxis.set_major_formatter(major_formatter)
- ax0.yaxis.grid(True)
- plt.ylabel('Read count')
- ax0.text(0.02, 0.9, 'Mean: %.2f\nStdev: %.2f' % (mean, stdev),
- transform=ax0.transAxes, bbox=dict(facecolor='grey', alpha=0.5,
- edgecolor='none'), size=14)
-
- # plot the boxplot
- # shared X-axis, but invisible
- ax1 = plt.subplot(grids[1], sharex=ax0)
- plt.setp(ax1.get_xticklabels(), visible=False)
- # and set the Y-axis to be invisible completely
- ax1.axes.get_yaxis().set_visible(False)
- plot = ax1.boxplot(gcs, vert=False, widths=0.6, sym='r.')
- # line width and color settings for boxplot
- plot['fliers'][0].set_color('#e62e00')
- plot['fliers'][1].set_color('#e62e00')
- plot['boxes'][0].set_color('black')
- plot['boxes'][0].set_linewidth(1.2)
- plot['medians'][0].set_linewidth(1.2)
- plot['medians'][0].set_color('black')
- plot['whiskers'][0].set_color('black')
- plot['whiskers'][0].set_linewidth(1.2)
- plot['whiskers'][1].set_color('black')
- plot['whiskers'][1].set_linewidth(1.2)
- plot['caps'][0].set_linewidth(1.2)
- plot['caps'][1].set_linewidth(1.2)
- # set X-axis label and ticks
- ax0.xaxis.set_major_locator(MultipleLocator(10))
- ax0.xaxis.set_minor_locator(MultipleLocator(5))
- plt.xlabel('% GC')
-
- grids.update(hspace=0.075)
- plt.savefig(outname, bbox_inches='tight')
-
- return gcs
-
-
-if __name__ == '__main__':
-
- parser = argparse.ArgumentParser()
- parser.add_argument('input', help='input FASTQ file', default='reads.fq')
- parser.add_argument('output', help='output image file', default='test.png')
-
- args = parser.parse_args()
-
- gcs = graph_gc(args.input, args.output)
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/hist2count.py b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/hist2count.py
deleted file mode 100644
index e91519742c77c6d2bd7fdce66728ac927771118e..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/hist2count.py
+++ /dev/null
@@ -1,107 +0,0 @@
-#!/usr/bin/env python
-#
-# Biopet is built on top of GATK Queue for building bioinformatic
-# pipelines. It is mainly intended to support LUMC SHARK cluster which is running
-# SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
-# should also be able to execute Biopet tools and pipelines.
-#
-# Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
-#
-# Contact us at: sasc@lumc.nl
-#
-# A dual licensing mode is applied. The source code within this project that are
-# not part of GATK Queue is freely available for non-commercial use under an AGPL
-# license; For commercial users or users who do not want to follow the AGPL
-# license, please contact us to obtain a separate license.
-#
-
-"""
-Convert a histogram generated by coverageBed to counts per region.
-
-
-A histogram file can be generated with the following command:
-coverageBed -split -hist -abam sample.bam -b selection.bed > selection.hist
-
-The output consists of four columns:
-- Chromosome name.
-- Start position.
-- End position.
-- Number of nucleotides mapped to this region.
-- Normalised expression for this region.
-
-If the -c option is used, additional columns can be added.
-"""
-
-import argparse
-import sys
-
-def hist2count(inputHandle, outputHandle, copy):
- """
- Split a fasta file on length.
-
- @arg inputHandle: Open readable handle to a histogram file.
- @type inputHandle: stream
- @arg outputHandle: Open writable handle to the counts file.
- @type outputHandle: stream
- @arg outputHandle: List of columns to copy to the output file.
- @type outputHandle: list[int]
- """
- def __copy():
- copyList = ""
- for i in copy:
- copyList += "\t%s" % data[i]
- return copyList
- #__copy
-
- def __write():
- outputHandle.write("%s\t%i\t%i\t%i\t%f%s\n" % (chromosome, start,
- end, count, float(count) / (end - start), copyList))
-
- chromosome = ""
- start = 0
- end = 0
- count = 0
-
- for line in inputHandle.readlines():
- data = line.split()
-
- if not data[0] == "all":
- start_temp = int(data[1])
- end_temp = int(data[2])
-
- if data[0] != chromosome or start_temp != start or end_temp != end:
- if chromosome:
- __write()
- chromosome = data[0]
- start = start_temp
- end = end_temp
- count = 0
- copyList = __copy()
- #if
- count += int(data[-4]) * int(data[-3])
- #if
- #for
- __write()
-#hist2count
-
-def main():
- """
- Main entry point.
- """
- usage = __doc__.split("\n\n\n")
- parser = argparse.ArgumentParser(
- formatter_class=argparse.RawDescriptionHelpFormatter,
- description=usage[0], epilog=usage[1])
- parser.add_argument("-i", dest="input", type=argparse.FileType("r"),
- default=sys.stdin, help="histogram input file (default=<stdin>)")
- parser.add_argument("-o", dest="output", type=argparse.FileType("w"),
- default=sys.stdout, help="file used as output (default=<stdout>)")
- parser.add_argument("-c", dest="copy", type=int, nargs="+", default=[],
- help="copy a column to the output file")
- args = parser.parse_args()
-
- hist2count(args.input, args.output, args.copy)
-#main
-
-if __name__ == '__main__':
- main()
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/insert_dist.py b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/insert_dist.py
deleted file mode 100755
index 332e7313409b84847ce899ebc3e51ba033fe78fc..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/insert_dist.py
+++ /dev/null
@@ -1,187 +0,0 @@
-#!/usr/bin/env python
-#
-# Biopet is built on top of GATK Queue for building bioinformatic
-# pipelines. It is mainly intended to support LUMC SHARK cluster which is running
-# SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
-# should also be able to execute Biopet tools and pipelines.
-#
-# Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
-#
-# Contact us at: sasc@lumc.nl
-#
-# A dual licensing mode is applied. The source code within this project that are
-# not part of GATK Queue is freely available for non-commercial use under an AGPL
-# license; For commercial users or users who do not want to follow the AGPL
-# license, please contact us to obtain a separate license.
-#
-
-#
-# insert_dist.py
-#
-# Given path to a text file containing Picard's CollectInsertSizeMetrics
-# results, create a new graph.
-#
-# (c) 2013 Wibowo Arindrarto [SASC - LUMC]
-
-import argparse
-import locale
-import os
-import re
-import textwrap
-
-from collections import namedtuple
-from functools import partial
-
-# for headless matplotlib
-import matplotlib
-matplotlib.use("Agg")
-import matplotlib.pyplot as plt
-
-from matplotlib.ticker import FuncFormatter
-
-# set locale and formatter for axis ticks
-locale.setlocale(locale.LC_ALL, '')
-groupdig = lambda x, pos: locale.format('%d', x, grouping=True)
-major_formatter = FuncFormatter(groupdig)
-int_fmt = partial(locale.format, grouping=True, percent='%i')
-
-
-def multi_annotate(ax, title, xy_arr=[], *args, **kwargs):
- """Axis annotation function that targets multiple data points."""
- ans = []
- an = ax.annotate(title, xy_arr[0], *args, **kwargs)
- ans.append(an)
- d = {}
- if 'xycoords' in kwargs:
- d['xycoords'] = kwargs['xycoords']
- if 'arrowprops' in kwargs:
- d['arrowprops'] = kwargs['arrowprops']
- for xy in xy_arr[1:]:
- an = ax.annotate(title, xy, alpha=0.0, xytext=(0, 0), textcoords=an, **d)
- ans.append(an)
-
- return ans
-
-
-def parse_insert_sizes_histogram(fname):
- """Given a filename or a file object of a Picard COllectInsertSizeMetrics
- output, return the filename, the histogram column names, and the histogram
- data."""
-
- if isinstance(fname, basestring):
- fp = open(fname, 'r')
- else:
- fp = fname
-
- line = fp.readline()
- while True:
- if not line:
- raise ValueError("Unexpected end of file")
- # try to get the original bam file name
- elif 'net.sf.picard.analysis.CollectInsertSizeMetrics' in line:
- input = re.search('INPUT=([^\s]*)', line).group(1)
- bamname = os.path.basename(input)
- elif line.startswith('## HISTOGRAM'):
- break
- line = fp.readline()
-
- # get column names
- colnames = fp.readline().strip().split('\t')
-
- # iterate over the histogram data lines
- # and fill up missing data with 0s
- data = []
- counter = 0
- for line in fp:
- if not line.strip():
- break
- # bin number starts at 1
- tokens = [int(x) for x in line.split('\t')]
- numcol = len(tokens) - 1
- if counter == tokens[0] - 1:
- data.append(tokens[1:])
- counter += 1
- else:
- while tokens[0] - counter != 1:
- data.append([0] * numcol)
- counter += 1
- data.append(tokens[1:])
- counter += 1
-
- histogram = data
-
- return bamname, colnames, histogram
-
-
-def graph_insert_sizes(fname, outname='test.png'):
- """Given a Picard CollectInsertSizes text output filename, write graph(s)
- for the histogram."""
- bamname, colnames, hist = parse_insert_sizes_histogram(fname)
-
- # map Picard's insert type (based on its column name)
- # to our own name and color
- InsType = namedtuple('InsType', ['label', 'color'])
- design_map = {
- # 5' --F--> <--R-- 5
- 'fr_count': InsType('inward', '#009933'),
- # <--R-- 5' 5' --F-->
- 'rf_count': InsType('outward', 'orange'),
- # 5' --F--> 5' --F--> or <--R-- 5' <--R-- 5'
- 'tandem_count': InsType('same directions', '#e62e00'),
- }
-
- fig = plt.figure()
- ax = plt.subplot(111)
- for idx, col in enumerate(colnames[1:]):
- pcd_name = col.split('.')[-1]
- try:
- label = design_map[pcd_name].label
- color = design_map[pcd_name].color
- except KeyError:
- raise ValueError("Unexpected column name: %r" % col)
-
- data = [m[idx] for m in hist]
- plt.bar(range(len(hist)), data, width=1, linewidth=0, color=color,
- alpha=0.6, label=label)
-
- max_val = max(data)
- max_val_size = data.index(max_val)
- highest_points = [(idx, max_val) for idx, val in enumerate(data) if val == max_val]
- x_adj = int(len(data) * 0.1)
- y_adj = int(max_val * 0.1)
- bbox_props = dict(boxstyle="round", fc="w", edgecolor='black', alpha=1.0)
- multi_annotate(ax,
- 'max count: {0}\nsize: {1} bp'.format(int_fmt(value=max_val),
- ', '.join([str(x[0]) for x in highest_points])),
- xy_arr=highest_points,
- xytext=(max_val_size + x_adj, max_val + y_adj),
- fontsize=9, bbox=bbox_props,
- horizontalalignment='left', verticalalignment='center',
- arrowprops=dict(color='black', shrink=0.1, width=0.5, headwidth=2.5, ),)
-
- # adjust ylim to account for annotation box
- init_ylim = ax.get_ylim()
- ax.set_ylim(0, init_ylim[1] * 1.08)
-
- # set title and its spacing
- title = 'Insert Sizes Distribution'
- t = plt.title('\n'.join([title] + textwrap.wrap('%r' % bamname, 50)),
- fontsize=15)
- t.set_y(1.05)
- plt.legend()
- plt.xlabel("Insert Size")
- plt.ylabel("Alignment Count")
- ax.yaxis.set_major_formatter(major_formatter)
- ax.grid(True)
- plt.savefig(outname, bbox_inches='tight')
-
-
-if __name__ == '__main__':
-
- parser = argparse.ArgumentParser()
- parser.add_argument('input', help='input file')
- parser.add_argument('output', help='output image file', default='test.png')
-
- args = parser.parse_args()
-
- graph_insert_sizes(args.input, args.output)
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/parse_cuffcmp.py b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/parse_cuffcmp.py
deleted file mode 100755
index 81ff276046b29ccfa269a9eca8d9293edba58067..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/parse_cuffcmp.py
+++ /dev/null
@@ -1,157 +0,0 @@
-#!/usr/bin/env python
-#
-# Biopet is built on top of GATK Queue for building bioinformatic
-# pipelines. It is mainly intended to support LUMC SHARK cluster which is running
-# SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
-# should also be able to execute Biopet tools and pipelines.
-#
-# Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
-#
-# Contact us at: sasc@lumc.nl
-#
-# A dual licensing mode is applied. The source code within this project that are
-# not part of GATK Queue is freely available for non-commercial use under an AGPL
-# license; For commercial users or users who do not want to follow the AGPL
-# license, please contact us to obtain a separate license.
-#
-
-#
-# oarse_cuffcmp.py
-#
-# Parses cuffcompare's cuffcmp.stats output into a JSON file.
-#
-# Part of the Gentrap pipeline.
-#
-# (c) 2013 by Wibowo Arindrarto [LUMC - SASC]
-
-import argparse
-import json
-import locale
-import os
-import re
-
-
-# set locale to group digits
-locale.setlocale(locale.LC_ALL, '')
-
-# precompiled regex patterns
-_base_qr = '\s+(\d+)/(\d+)'
-_base_table = '\s+(.*?)\s+(.*?)\s+(.*?)\s+(.*?)\s+'
-# source transcripts gtf
-_re_dataset = re.compile(r'Summary for dataset:\s+(.*?)\s+:')
-# ref exons not covered by query exons, total ref exons
-_re_rexons = re.compile(r'Missed exons:%s' % _base_qr)
-# query exons not covered by ref exons, total query exons
-_re_qexons = re.compile(r'Novel exons:%s' % _base_qr)
-# ref introns not covered by query introns, total ref introns
-_re_rintrons = re.compile(r'Missed introns:%s' % _base_qr)
-# query introns not covered by ref introns, total query introns
-_re_qintrons = re.compile(r'Novel introns:%s' % _base_qr)
-# ref loci not covered by query loci, total ref loci
-_re_rloci = re.compile(r'Missed loci:%s' % _base_qr)
-# query loci not covered by ref loci, total query loci
-_re_qloci = re.compile(r'Novel loci:%s' % _base_qr)
-# base level metrics
-_re_base = re.compile(r'Base level:%s' % _base_table)
-# exon level metrics
-_re_exon = re.compile(r'Exon level:%s' % _base_table)
-# intron level metrics
-_re_intron = re.compile(r'Intron level:%s' % _base_table)
-# intron chain level metrics
-_re_intron_chain = re.compile(r'Intron chain level:%s' % _base_table)
-# transcript level metrics
-_re_transcript = re.compile(r'Transcript level:%s' % _base_table)
-# locus level metrics
-_re_locus = re.compile(r'Locus level:%s' % _base_table)
-
-
-def _fallback_search(re_pattern, string, match_type, fallback_str, group,
- replacement=None):
- """Function to handle cases when the regex match is of a different type,
- e.g. '-' instead of an integer."""
- match = re.search(re_pattern, string).group(group)
-
- if match == fallback_str:
- return replacement
- else:
- return match_type(match)
-
-
-def parse_cuffcmp_stats(stat_file):
- """Parses the statistics in the given cuffcmp.stats file into a
- dictionary."""
- assert os.path.exists(stat_file), "File %r not found" % stat_file
-
- with open(stat_file, 'r') as source:
- # not expecting a huge output, we can store everything in memory
- stat_str = source.read()
-
- stats = {
- 'dataSet': re.search(_re_dataset, stat_str).group(1),
- 'refExonsNotInQuery': int(re.search(_re_rexons, stat_str).group(1)),
- 'refExonsTotal': int(re.search(_re_rexons, stat_str).group(2)),
- 'queryExonsNotInRef': int(re.search(_re_qexons, stat_str).group(1)),
- 'queryExonsTotal': int(re.search(_re_qexons, stat_str).group(2)),
-
- 'refIntronsNotInQuery': int(re.search(_re_rintrons, stat_str).group(1)),
- 'refIntronsTotal': int(re.search(_re_rintrons, stat_str).group(2)),
- 'queryIntronsNotInRef': int(re.search(_re_qintrons, stat_str).group(1)),
- 'queryIntronsTotal': int(re.search(_re_qintrons, stat_str).group(2)),
-
- 'refLociNotInQuery': int(re.search(_re_rloci, stat_str).group(1)),
- 'refLociTotal': int(re.search(_re_rloci, stat_str).group(2)),
- 'queryLociNotInRef': int(re.search(_re_qloci, stat_str).group(1)),
- 'queryLociTotal': int(re.search(_re_qloci, stat_str).group(2)),
-
- 'baseLevelSn': _fallback_search(_re_base, stat_str, float, '-', 1),
- 'baseLevelSp': _fallback_search(_re_base, stat_str, float, '-', 2),
- 'baseLevelFSn': _fallback_search(_re_base, stat_str, float, '-', 3),
- 'baseLevelFSp': _fallback_search(_re_base, stat_str, float, '-', 4),
-
- 'exonLevelSn': _fallback_search(_re_exon, stat_str, float, '-', 1),
- 'exonLevelSp': _fallback_search(_re_exon, stat_str, float, '-', 2),
- 'exonLevelFSn': _fallback_search(_re_exon, stat_str, float, '-', 3),
- 'exonLevelFSp': _fallback_search(_re_exon, stat_str, float, '-', 4),
-
- 'intronLevelSn': _fallback_search(_re_intron, stat_str, float, '-', 1),
- 'intronLevelSp': _fallback_search(_re_intron, stat_str, float, '-', 2),
- 'intronLevelFSn': _fallback_search(_re_intron, stat_str, float, '-', 3),
- 'intronLevelFSp': _fallback_search(_re_intron, stat_str, float, '-', 4),
-
- 'intronChainLevelSn': _fallback_search(_re_intron_chain, stat_str, float, '-', 1),
- 'intronChainLevelSp': _fallback_search(_re_intron_chain, stat_str, float, '-', 2),
- 'intronChainLevelFSn': _fallback_search(_re_intron_chain, stat_str, float, '-', 3),
- 'intronChainLevelFSp': _fallback_search(_re_intron_chain, stat_str, float, '-', 4),
-
- 'transcriptLevelSn': _fallback_search(_re_transcript, stat_str, float, '-', 1),
- 'transcriptLevelSp': _fallback_search(_re_transcript, stat_str, float, '-', 2),
- 'transcriptLevelFSn': _fallback_search(_re_transcript, stat_str, float, '-', 3),
- 'transcriptLevelFSp': _fallback_search(_re_transcript, stat_str, float, '-', 4),
-
- 'locusLevelSn': _fallback_search(_re_locus, stat_str, float, '-', 1),
- 'locusLevelSp': _fallback_search(_re_locus, stat_str, float, '-', 2),
- 'locusLevelFSn': _fallback_search(_re_locus, stat_str, float, '-', 3),
- 'locusLevelFSp': _fallback_search(_re_locus, stat_str, float, '-', 4),
- }
-
- return stats
-
-
-if __name__ == '__main__':
-
- parser = argparse.ArgumentParser()
- parser.add_argument('input', type=str,
- help='Path to input cuffcmp.stats file')
- parser.add_argument('-o', '--output-json', dest='output', type=str,
- help='Path to JSON output file', default=None)
- args = parser.parse_args()
-
- stats = parse_cuffcmp_stats(args.input)
-
- if args.output is not None:
- with open(args.output, 'w') as jsonfile:
- json.dump(stats, jsonfile, sort_keys=True, indent=4,
- separators=(',', ': '))
- else:
- print json.dumps(stats, sort_keys=True, indent=4,
- separators=(',', ': '))
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/pdf_report.py b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/pdf_report.py
deleted file mode 100755
index b0c2b2e82e431d6340c74575ad07c0e48a19b623..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/pdf_report.py
+++ /dev/null
@@ -1,586 +0,0 @@
-#!/usr/bin/env python
-#
-# Biopet is built on top of GATK Queue for building bioinformatic
-# pipelines. It is mainly intended to support LUMC SHARK cluster which is running
-# SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
-# should also be able to execute Biopet tools and pipelines.
-#
-# Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
-#
-# Contact us at: sasc@lumc.nl
-#
-# A dual licensing mode is applied. The source code within this project that are
-# not part of GATK Queue is freely available for non-commercial use under an AGPL
-# license; For commercial users or users who do not want to follow the AGPL
-# license, please contact us to obtain a separate license.
-#
-
-from __future__ import print_function
-
-import argparse
-import json
-import locale
-import os
-import re
-import sys
-from os import path
-
-from jinja2 import Environment, FileSystemLoader
-
-
-# set locale for digit grouping
-locale.setlocale(locale.LC_ALL, "")
-
-
-class FastQCModule(object):
-
- """Class representing a FastQC analysis module."""
-
- def __init__(self, raw_lines, end_mark='>>END_MODULE'):
- """
-
- :param raw_lines: list of lines in the module
- :type raw_lines: list of str
- :param end_mark: mark of the end of the module
- :type end_mark: str
-
- """
- self.raw_lines = raw_lines
- self.end_mark = end_mark
- self._status = None
- self._name = None
- self._data = self._parse()
-
- def __repr__(self):
- return '%s(%s)' % (self.__class__.__name__,
- '[%r, ...]' % self.raw_lines[0])
-
- def __str__(self):
- return ''.join(self.raw_lines)
-
- @property
- def name(self):
- """Name of the module."""
- return self._name
-
- @property
- def columns(self):
- """Columns in the module."""
- return self._columns
-
- @property
- def data(self):
- """FastQC data."""
- return self._data
-
- @property
- def status(self):
- """FastQC run status."""
- return self._status
-
- def _parse(self):
- """Common parser for a FastQC module."""
- # check that the last line is a proper end mark
- assert self.raw_lines[-1].startswith(self.end_mark)
- # parse name and status from first line
- tokens = self.raw_lines[0].strip().split('\t')
- name = tokens[0][2:]
- self._name = name
- status = tokens[-1]
- assert status in ('pass', 'fail', 'warn'), "Unknown module status: %r" \
- % status
- self._status = status
- # and column names from second line
- columns = self.raw_lines[1][1:].strip().split('\t')
- self._columns = columns
- # the rest of the lines except the last one
- data = []
- for line in self.raw_lines[2:-1]:
- cols = line.strip().split('\t')
- data.append(cols)
-
- # optional processing for different modules
- if self.name == 'Basic Statistics':
- data = {k: v for k, v in data}
-
- return data
-
-
-class FastQC(object):
-
- """Class representing results from a FastQC run."""
-
- # module name -- attribute name mapping
- _mod_map = {
- '>>Basic Statistics': 'basic_statistics',
- '>>Per base sequence quality': 'per_base_sequence_quality',
- '>>Per sequence quality scores': 'per_sequence_quality_scores',
- '>>Per base sequence content': 'per_base_sequence_content',
- '>>Per base GC content': 'per_base_gc_content',
- '>>Per sequence GC content': 'per_sequence_gc_content',
- '>>Per base N content': 'per_base_n_content',
- '>>Sequence Length Distribution': 'sequence_length_distribution',
- '>>Sequence Duplication Levels': 'sequence_duplication_levels',
- '>>Overrepresented sequences': 'overrepresented_sequences',
- '>>Kmer content': 'kmer_content',
- }
-
- def __init__(self, fname):
- """
-
- :param fp: open file handle pointing to the FastQC data file
- :type fp: file handle
-
- """
- # get file name
- self.fname = fname
- self._modules = {}
-
- with open(fname, "r") as fp:
- line = fp.readline()
- while True:
-
- tokens = line.strip().split('\t')
- # break on EOF
- if not line:
- break
- # parse version
- elif line.startswith('##FastQC'):
- self.version = line.strip().split()[1]
- # parse individual modules
- elif tokens[0] in self._mod_map:
- attr = self._mod_map[tokens[0]]
- raw_lines = self._read_module(fp, line, tokens[0])
- self._modules[attr] = FastQCModule(raw_lines)
-
- line = fp.readline()
-
- def __repr__(self):
- return '%s(%r)' % (self.__class__.__name__, self.fname)
-
- def _filter_by_status(self, status):
- """Filter out modules whose status is different from the given status.
-
- :param status: module status
- :type status: str
- :returns: a list of FastQC module names with the given status
- :rtype: list of str
-
- """
- return [x.name for x in self._modules.values() if x.status == status]
-
- def _read_module(self, fp, line, start_mark):
- """Returns a list of lines in a module.
-
- :param fp: open file handle pointing to the FastQC data file
- :type fp: file handle
- :param line: first line in the module
- :type line: str
- :param start_mark: string denoting start of the module
- :type start_mark: str
- :returns: a list of lines in the module
- :rtype: list of str
-
- """
- raw = [line]
- while not line.startswith('>>END_MODULE'):
- line = fp.readline()
- raw.append(line)
-
- if not line:
- raise ValueError("Unexpected end of file in module %r" % line)
-
- return raw
-
- @property
- def modules(self):
- """All modules in the FastQC results."""
- return self._modules
-
- @property
- def passes(self):
- """All module names that pass QC."""
- return self._filter_by_status('pass')
-
- @property
- def passes_num(self):
- """How many modules have pass status."""
- return len(self.passes)
-
- @property
- def warns(self):
- """All module names with warning status."""
- return self._filter_by_status('warn')
-
- @property
- def warns_num(self):
- """How many modules have warn status."""
- return len(self.warns)
-
- @property
- def fails(self):
- """All names of failed modules."""
- return self._filter_by_status('fail')
-
- @property
- def fails_num(self):
- """How many modules failed."""
- return len(self.fails)
-
- @property
- def basic_statistics(self):
- """Basic statistics module results."""
- return self._modules['basic_statistics']
-
- @property
- def per_base_sequence_quality(self):
- """Per base sequence quality module results."""
- return self._modules['per_base_sequence_quality']
-
- @property
- def per_sequence_quality_scores(self):
- """Per sequence quality scores module results."""
- return self._modules['per_sequence_quality_scores']
-
- @property
- def per_base_sequence_content(self):
- """Per base sequence content module results."""
- return self._modules['per_base_sequence_content']
-
- @property
- def per_base_gc_content(self):
- """Per base GC content module results."""
- return self._modules['per_base_gc_content']
-
- @property
- def per_sequence_gc_content(self):
- """Per sequence GC content module results."""
- return self._modules['per_sequence_gc_content']
-
- @property
- def per_base_n_content(self):
- """Per base N content module results."""
- return self._modules['per_base_n_content']
-
- @property
- def sequence_length_distribution(self):
- """Per sequence length distribution module results."""
- return self._modules['sequence_length_distribution']
-
- @property
- def sequence_duplication_levels(self):
- """Sequence duplication module results."""
- return self._modules['sequence_duplication_levels']
-
- @property
- def overrepresented_sequences(self):
- """Overrepresented sequences module results."""
- return self._modules['overrepresented_sequences']
-
- @property
- def kmer_content(self):
- """Kmer content module results."""
- return self._modules['kmer_content']
-
-
-# HACK: remove this and use jinja2 only for templating
-class LongTable(object):
-
- """Class representing a longtable in LaTeX."""
-
- def __init__(self, caption, label, header, aln, colnum):
- self.lines = [
- "\\begin{center}",
- "\\captionof{table}{%s}" % caption,
- "\\label{%s}" % label,
- "\\begin{longtable}{%s}" % aln,
- "\\hline",
- "%s" % header,
- "\\hline \\hline",
- "\\endhead",
- "\\hline \\multicolumn{%i}{c}{\\textit{Continued on next page}}\\\\" % \
- colnum,
- "\\hline",
- "\\endfoot",
- "\\hline",
- "\\endlastfoot",
- ]
-
- def __str__(self):
- return "\n".join(self.lines)
-
- def add_row(self, row):
- self.lines.append(row)
-
- def end(self):
- self.lines.extend(["\\end{longtable}", "\\end{center}",
- "\\addtocounter{table}{-1}"])
-
-
-# filter functions for the jinja environment
-def nice_int(num, default="None"):
- if num is None:
- return default
- try:
- return locale.format("%i", int(num), grouping=True)
- except:
- return default
-
-
-def nice_flt(num, default="None"):
- if num is None:
- return default
- try:
- return locale.format("%.2f", float(num), grouping=True)
- except:
- return default
-
-
-def float2nice_pct(num, default="None"):
- if num is None:
- return default
- try:
- return locale.format("%.2f", float(num) * 100.0, grouping=True)
- except:
- return default
-
-
-# and some handy functions
-def natural_sort(inlist):
- key = lambda x: [int(a) if a.isdigit() else a.lower() for a in
- re.split("([0-9]+)", x)]
- inlist.sort(key=key)
- return inlist
-
-
-def write_template(run, template_file, logo_file):
-
- template_file = path.abspath(path.realpath(template_file))
- template_dir = path.dirname(template_file)
- # spawn environment and create output directory
- env = Environment(loader=FileSystemLoader(template_dir))
-
- # change delimiters since LaTeX may use "{{", "{%", or "{#"
- env.block_start_string = "((*"
- env.block_end_string = "*))"
- env.variable_start_string = "((("
- env.variable_end_string = ")))"
- env.comment_start_string = "((="
- env.comment_end_string = "=))"
-
- # trim all block-related whitespaces
- env.trim_blocks = True
- env.lstrip_blocks = True
-
- # put in out filter functions
- env.filters["nice_int"] = nice_int
- env.filters["nice_flt"] = nice_flt
- env.filters["float2nice_pct"] = float2nice_pct
- env.filters["basename"] = path.basename
-
- # write tex template for pdflatex
- jinja_template = env.get_template(path.basename(template_file))
- run.logo = logo_file
- render_vars = {
- "run": run,
- }
- rendered = jinja_template.render(**render_vars)
-
- print(rendered, file=sys.stdout)
-
-
-class GentrapLib(object):
-
- def __init__(self, run, sample, name, summary):
- assert isinstance(run, GentrapRun)
- assert isinstance(sample, GentrapSample)
- self.run = run
- self.sample = sample
- self.name = name
- self._raw = summary
- # flexiprep settings
- self.flexiprep = summary.get("flexiprep", {})
- self.flexiprep_files = summary.get("flexiprep", {}).get("files", {}).get("pipeline", {})
- self.clipping = not self.flexiprep["settings"]["skip_clip"]
- self.trimming = not self.flexiprep["settings"]["skip_trim"]
- self.is_paired_end = self.flexiprep["settings"]["paired"]
- if "fastqc_R1" in self.flexiprep["files"]:
- self.fastqc_r1_files = self.flexiprep["files"]["fastqc_R1"]
- self.fastqc_r1 = FastQC(self.fastqc_r1_files["fastqc_data"]["path"])
- if "fastqc_R2" in self.flexiprep["files"]:
- self.fastqc_r2_files = self.flexiprep["files"]["fastqc_R2"]
- self.fastqc_r2 = FastQC(self.fastqc_r2_files["fastqc_data"]["path"])
- if "fastqc_R1_qc" in self.flexiprep["files"]:
- self.fastqc_r1_qc_files = self.flexiprep["files"]["fastqc_R1_qc"]
- self.fastqc_r1_qc = FastQC(self.fastqc_r1_qc_files["fastqc_data"]["path"])
- if "fastqc_R2_qc" in self.flexiprep["files"]:
- self.fastqc_r2_qc_files = self.flexiprep["files"]["fastqc_R2_qc"]
- self.fastqc_r2_qc = FastQC(self.fastqc_r2_qc_files["fastqc_data"]["path"])
- # mapping metrics settings
- self.aln_metrics = summary.get("bammetrics", {}).get("stats", {}).get("CollectAlignmentSummaryMetrics", {})
- for k, v in self.aln_metrics.items():
- self.aln_metrics[k] = {a.lower(): b for a, b in v.items()}
- # insert size metrics files
- self.inserts_metrics_files = \
- summary.get("bammetrics", {}).get("files", {}).get("multi_metrics", {})
- # rna metrics files and stats
- self.rna_metrics_files = summary.get("bammetrics", {}).get("files", {}).get("rna", {})
- _rmetrics = summary.get("bammetrics", {}).get("stats", {}).get("rna", {})
- if _rmetrics:
- if "metrics" in _rmetrics:
- _rmetrics = _rmetrics["metrics"]
- if _rmetrics:
- _rmetrics = {k.lower(): v for k, v in _rmetrics.items() }
- self.rna_metrics = _rmetrics
- pf_bases = float(_rmetrics["pf_bases"])
- exonic_bases = int(_rmetrics.get("coding_bases", 0)) + int(_rmetrics.get("utr_bases", 0))
- # picard uses pct_ but it's actually ratio ~ we follow their convention
- pct_exonic_bases_all = exonic_bases / float(_rmetrics["pf_bases"])
- pct_exonic_bases = exonic_bases / float(_rmetrics.get("pf_aligned_bases", 0))
- self.rna_metrics.update({
- "exonic_bases": exonic_bases,
- "pct_exonic_bases_all": pct_exonic_bases_all,
- "pct_exonic_bases": pct_exonic_bases,
- "pct_aligned_bases": 1.0,
- "pct_aligned_bases_all": float(_rmetrics.get("pf_aligned_bases", 0.0)) / pf_bases,
- "pct_coding_bases_all": float(_rmetrics.get("coding_bases", 0.0)) / pf_bases,
- "pct_utr_bases_all": float(_rmetrics.get("utr_bases", 0.0)) / pf_bases,
- "pct_intronic_bases_all": float(_rmetrics.get("intronic_bases", 0.0)) / pf_bases,
- "pct_intergenic_bases_all": float(_rmetrics.get("intergenic_bases", 0.0)) / pf_bases,
- })
- if _rmetrics.get("ribosomal_bases", "") != "":
- self.rna_metrics["pct_ribosomal_bases_all"] = float(_rmetrics.get("pf_ribosomal_bases", 0.0)) / pf_bases
-
- def __repr__(self):
- return "{0}(sample=\"{1}\", lib=\"{2}\")".format(
- self.__class__.__name__, self.sample.name, self.name)
-
-
-class GentrapSample(object):
-
- def __init__(self, run, name, summary):
- assert isinstance(run, GentrapRun)
- self.run = run
- self.name = name
- self._raw = summary
- self.is_paired_end = summary.get("gentrap", {}).get("stats", {}).get("pipeline", {})["all_paired"]
- # mapping metrics settings
- self.aln_metrics = summary.get("bammetrics", {}).get("stats", {}).get("CollectAlignmentSummaryMetrics", {})
- for k, v in self.aln_metrics.items():
- self.aln_metrics[k] = {a.lower(): b for a, b in v.items()}
- # insert size metrics files
- self.inserts_metrics_files = \
- summary.get("bammetrics", {}).get("files", {}).get("multi_metrics", {})
- # rna metrics files and stats
- self.rna_metrics_files = summary.get("bammetrics", {}).get("files", {}).get("rna", {})
- _rmetrics = summary.get("bammetrics", {}).get("stats", {}).get("rna", {})
- if _rmetrics:
- if "metrics" in _rmetrics:
- _rmetrics = _rmetrics["metrics"]
- if _rmetrics:
- _rmetrics = {k.lower(): v for k, v in _rmetrics.items() }
- self.rna_metrics = _rmetrics
- pf_bases = float(_rmetrics["pf_bases"])
- exonic_bases = int(_rmetrics.get("coding_bases", 0)) + int(_rmetrics.get("utr_bases", 0))
- # picard uses pct_ but it's actually ratio ~ we follow their convention
- pct_exonic_bases_all = exonic_bases / float(_rmetrics["pf_bases"])
- pct_exonic_bases = exonic_bases / float(_rmetrics.get("pf_aligned_bases", 0))
- self.rna_metrics.update({
- "exonic_bases": exonic_bases,
- "pct_exonic_bases_all": pct_exonic_bases_all,
- "pct_exonic_bases": pct_exonic_bases,
- "pct_aligned_bases": 1.0,
- "pct_aligned_bases_all": float(_rmetrics.get("pf_aligned_bases", 0.0)) / pf_bases,
- "pct_coding_bases_all": float(_rmetrics.get("coding_bases", 0.0)) / pf_bases,
- "pct_utr_bases_all": float(_rmetrics.get("utr_bases", 0.0)) / pf_bases,
- "pct_intronic_bases_all": float(_rmetrics.get("intronic_bases", 0.0)) / pf_bases,
- "pct_intergenic_bases_all": float(_rmetrics.get("intergenic_bases", 0.0)) / pf_bases,
- })
- if _rmetrics.get("ribosomal_bases", "") != "":
- self.rna_metrics["pct_ribosomal_bases_all"] = float(_rmetrics.get("pf_ribosomal_bases", 0.0)) / pf_bases
-
- self.lib_names = sorted(summary["libraries"].keys())
- self.libs = \
- {l: GentrapLib(self.run, self, l, summary["libraries"][l]) \
- for l in self.lib_names}
-
- def __repr__(self):
- return "{0}(\"{1}\")".format(self.__class__.__name__, self.name)
-
-
-class GentrapRun(object):
-
- def __init__(self, summary_file):
-
- with open(summary_file, "r") as src:
- summary = json.load(src)
-
- self._raw = summary
- self.summary_file = summary_file
-
- self.files = summary["gentrap"].get("files", {}).get("pipeline", {})
- self.settings = summary["gentrap"]["settings"]
- self.version = self.settings.get("version", "unknown")
- # list containing all exes
- self.all_executables = summary["gentrap"]["executables"]
- # list containing exes we want to display
- executables = [
- ("cutadapt", "adapter clipping"),
- ("sickle", "base quality trimming"),
- ("fastqc", "sequence metrics collection"),
- ("gsnap", "alignment"),
- ("tophat", "alignment"),
- ("star", "alignment"),
- ("htseqcount", "fragment counting"),
- ]
- self.executables = {}
- for k, desc in executables:
- in_summary = self.all_executables.get(k)
- if in_summary is not None:
- self.executables[k] = in_summary
- self.executables[k]["desc"] = desc
- # since we get the version from the tools we use
- if self.all_executables.get("collectalignmentsummarymetrics") is not None:
- self.executables["picard"] = self.all_executables["collectalignmentsummarymetrics"]
- self.executables["picard"]["desc"] = "alignment_metrics_collection"
- # None means we are using the Queue built in Picard
- if self.executables["picard"].get("version") is None:
- self.executables["picard"]["version"] = "built-in"
- # since we get the version from the sub tools we use
- if self.all_executables.get("samtoolsview") is not None:
- self.executables["samtools"] = self.all_executables["samtoolsview"]
- self.executables["samtools"]["desc"] = "various post-alignment processing"
-
- self.sample_names = sorted(summary["samples"].keys())
- self.samples = \
- {s: GentrapSample(self, s, summary["samples"][s]) \
- for s in self.sample_names}
- self.libs = []
- for sample in self.samples.values():
- self.libs.extend(sample.libs.values())
- if all([s.is_paired_end for s in self.samples.values()]):
- self.lib_type = "all paired end"
- elif all([not s.is_paired_end for s in self.samples.values()]):
- self.lib_type = "all single end"
- else:
- self.lib_type = "mixed (single end and paired end)"
-
- def __repr__(self):
- return "{0}(\"{1}\")".format(self.__class__.__name__,
- self.summary_file)
-
-
-if __name__ == "__main__":
-
- parser = argparse.ArgumentParser()
- parser.add_argument("summary_file", type=str,
- help="Path to Gentrap summary file")
- parser.add_argument("template_file", type=str,
- help="Path to main template file")
- parser.add_argument("logo_file", type=str,
- help="Path to main logo file")
- args = parser.parse_args()
-
- run = GentrapRun(args.summary_file)
- write_template(run, args.template_file, args.logo_file)
-
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/plot_pca.R b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/plot_pca.R
deleted file mode 100755
index 419ec5b2cb30baf2cbde032b7e5ba11abba6c305..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/plot_pca.R
+++ /dev/null
@@ -1,45 +0,0 @@
-#!/usr/bin/env Rscript
-#
-# Script for plotting PCA plots for the Gentrap pipeline
-
-
-# General function to install package if it does not exist
-# Otherwise, it only loads the package
-usePackage <- function(p) {
- r <- getOption("repos")
- r["CRAN"] <- "http://cran.us.r-project.org"
- options(repos = r)
- rm(r)
- if (!is.element(p, installed.packages()[,1]))
- install.packages(p, dep = TRUE)
- require(p, character.only = TRUE)
-}
-
-usePackage("getopt")
-usePackage("edgeR")
-usePackage("ggplot2")
-usePackage("gplots")
-usePackage("grid")
-usePackage("jsonlite")
-usePackage("reshape2")
-usePackage("MASS")
-usePackage("RColorBrewer")
-
-# create spec for arg parsing
-spec <- matrix(c(
- # input table (merge of all samples)
- 'input-table', 'I', 1, 'character',
- # output plot file
- 'output-plot', 'O', 1, 'character',
- # perform TMM-normalization (only if we are dealing with count data)
- 'tmm-normalize', 'T', 0, 'logical'
- # help
- 'help', 'H', 0, 'logical'
-), byrow=TRUE, ncol=4)
-opt <- getopt(spec)
-
-# print help if requested
-if (!is.null(opt[['help']])) {
- cat(getopt(spec, usage=TRUE))
- q(status=1)
-}
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/rna_metrics.py b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/rna_metrics.py
deleted file mode 100755
index 862bf7e0134a0b403cc925d69ce21f8d713ccedd..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/rna_metrics.py
+++ /dev/null
@@ -1,517 +0,0 @@
-#!/usr/bin/env python2
-#
-# Biopet is built on top of GATK Queue for building bioinformatic
-# pipelines. It is mainly intended to support LUMC SHARK cluster which is running
-# SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
-# should also be able to execute Biopet tools and pipelines.
-#
-# Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
-#
-# Contact us at: sasc@lumc.nl
-#
-# A dual licensing mode is applied. The source code within this project that are
-# not part of GATK Queue is freely available for non-commercial use under an AGPL
-# license; For commercial users or users who do not want to follow the AGPL
-# license, please contact us to obtain a separate license.
-#
-
-
-# rna_metrics.py
-#
-# Given a sorted, indexed BAM file from an RNA seq experiment,
-# output the annotation metrics using Picard CollectRnaSeqMetrics per chromosome
-
-import argparse
-import json
-import functools
-import locale
-import os
-import subprocess
-import threading
-import time
-import tempfile
-import warnings
-import Queue
-
-# valid column names
-# from http://picard.sourceforge.net/picard-metric-definitions.shtml#RnaSeqMetrics
-COL_NAMES = {
- 'PF_BASES': 'pfBases',
- 'PF_ALIGNED_BASES': 'pfAlignedBases',
- 'RIBOSOMAL_BASES': 'ribosomalBases',
- 'CODING_BASES': 'codingBases',
- 'UTR_BASES': 'utrBases',
- 'INTRONIC_BASES': 'intronicBases',
- 'INTERGENIC_BASES': 'intergenicBases',
- 'IGNORED_READS': 'ignoredReads',
- 'CORRECT_STRAND_READS': 'correctStrandReads',
- 'INCORRECT_STRAND_READS': 'incorrectStrandReads',
- 'PCT_RIBOSOMAL_BASES': 'pctRibosomalBases',
- 'PCT_CODING_BASES': 'pctCodingBases',
- 'PCT_UTR_BASES': 'pctUtrBases',
- 'PCT_INTRONIC_BASES': 'pctIntronicBases',
- 'PCT_INTERGENIC_BASES': 'pctIntergenicBases',
- 'PCT_MRNA_BASES': 'pctMrnaBases',
- 'PCT_USABLE_BASES': 'pctUsableBases',
- 'PCT_CORRECT_STRAND_READS': 'pctCorrectStrandReads',
- 'MEDIAN_CV_COVERAGE': 'medianCvCoverage',
- 'MEDIAN_5PRIME_BIAS': 'median5PrimeBias',
- 'MEDIAN_3PRIME_BIAS': 'median3PrimeBias',
- 'MEDIAN_5PRIME_TO_3PRIME_BIAS': 'median5PrimeTo3PrimeBias',
-}
-# executables, default to ones in PATH
-EXE_SAMTOOLS = 'samtools'
-EXE_JAVA = 'java'
-
-# set locale to group digits
-locale.setlocale(locale.LC_ALL, '')
-int_fmt = functools.partial(locale.format, grouping=True, percent='%i')
-float_fmt = functools.partial(locale.format, grouping=True, percent='%.2f')
-
-
-class MetricsTracker(object):
-
- """Class to track metrics file output."""
-
- def __init__(self, main_bams, chrs):
- self.lock = threading.Lock()
- self.chrs = chrs
- self.files = {}
- for rtype, bam in main_bams.items():
- self.files[bam] = {
- 'chrs': dict.fromkeys(chrs),
- 'strand': rtype,
- }
-
- def add_stat_file(self, main_bam, chr, chr_stat):
- self.lock.acquire()
- self.files[main_bam]['chrs'][chr] = chr_stat
- self.lock.release()
-
- def check_files(self):
- # only for strand-specific rna-seq
- for bam, data in self.files.items():
- for chr, path in data['chrs'].items():
- assert path is not None, "Missing statistics file for {0}, " \
- "chromosome {1}".format(bam, chr)
-
-
-class Worker(threading.Thread):
-
- """Class representing worker to execute jobs."""
-
- def __init__(self, queue, group=None, target=None, name=None, args=(),
- kwargs={}):
- threading.Thread.__init__(self, group, target, name, args, kwargs)
- self.queue = queue
- self.setDaemon(True)
- self.start()
-
- def run(self):
- while True:
- func, args, kwargs = self.queue.get()
- func(*args, **kwargs)
- self.queue.task_done()
-
-
-class ThreadPool(object):
-
- """Class representing thread pool to execute."""
-
- def __init__(self, num_threads):
- self.queue = Queue.Queue()
- for _ in range(num_threads):
- Worker(self.queue)
-
- def add_task(self, func, *args, **kwargs):
- self.queue.put((func, args, kwargs))
-
- def wait_completion(self):
- self.queue.join()
-
-
-def picard_metrics_worker(in_bam, chr, tracker, annot, jar,
- samtools_exe, java_exe):
- """Worker for collecting RNA-seq metrics."""
- # check if index exists
- assert os.path.exists(in_bam + '.bai')
- # create output directory, contains all chr stats
- out_dir = os.path.splitext(in_bam)[0] + '.rna_metrics'
- # create output directory
- try:
- os.makedirs(out_dir)
- except OSError:
- if not os.path.exists(out_dir):
- raise
- # if chr is none, do stat on all regions
- if chr is None:
- chr = 'ALL'
- out_stat = os.path.join(out_dir, chr + '.rna_metrics.txt')
- # split BAM file per chr, write to tmp file
- if chr != 'ALL':
- bam = tempfile.NamedTemporaryFile(prefix='tmp_rna_metrics_', delete=True)
- name = bam.name
- tokens = [samtools_exe, 'view', '-bh', '-o', bam.name, in_bam, chr]
- proc = subprocess.Popen(tokens, stdout=bam)
- while proc.poll() is None:
- time.sleep(1)
- else:
- name = in_bam
- picard_toks = [java_exe, '-jar', jar]
- for key, value in os.environ.items():
- if key.startswith('OPT_PICARD_COLLECTRNASEQMETRICS_'):
- # input, output, and annotation are handled separately
- if key.endswith('INPUT') or key.endswith('OUTPUT') or \
- key.endswith('REF_FLAT'):
- continue
- if value:
- picard_toks.append('%s=%s' %
- (key.replace('OPT_PICARD_COLLECTRNASEQMETRICS_', ''), value))
-
- picard_toks += ['REF_FLAT={0}'.format(annot),
- 'STRAND_SPECIFICITY=SECOND_READ_TRANSCRIPTION_STRAND',
- 'I={0}'.format(name), 'O={0}'.format(out_stat)]
- picard = subprocess.Popen(picard_toks)
- while picard.poll() is None:
- time.sleep(1)
- assert os.path.exists(out_stat)
- if chr != 'ALL':
- bam.close()
- tracker.add_stat_file(in_bam, chr, out_stat)
-
-
-def samtools_reads_per_region_count(bam_files, chrs, samtools_exe):
- """Counts read per chromosome using samtools (simple count of mapped read
- per region."""
- tokens = [samtools_exe, 'view', '-c', '-F', '0x4']
- keys = ['fwd', 'rev', 'mix']
- all_dict = dict.fromkeys(keys)
- for rtype, bam in bam_files.items():
- assert rtype in keys, "Unknown key: {0}".format(rtype)
- aggr_dict = {}
- for chr in chrs:
- if chr == 'ALL':
- continue
- proc = subprocess.Popen(tokens + [bam, chr], stdout=subprocess.PIPE)
- count = int(proc.stdout.read())
- aggr_dict[chr] = {
- 'metrics': {'countMapped': count}
- }
- name = os.path.basename(os.path.splitext(bam)[0])
- all_dict[rtype] = {}
- all_dict[rtype]['bamFile'] = name
- all_dict[rtype]['allMetrics'] = aggr_dict
-
- return all_dict
-
-
-def picard_reads_per_region_count(bam_files, chrs, annot, jar, samtools_exe, java_exe):
- """Counts read per chromosome using Picard and annotation files."""
- assert os.path.exists(annot), "Annotation file {0} not found".format(annot)
- # only analyze sense and antisense reads
- bam_files = {'fwd': bam_files['fwd'], 'rev': bam_files['rev']}
- # create tracker for metric files
- metrics_tracker = MetricsTracker(bam_files, chrs)
- # create main task pool
- metrics_pool = ThreadPool(args.threads)
- # add tasks to the pool
- for bam in bam_files.values():
- for chr in chrs:
- metrics_pool.add_task(picard_metrics_worker, in_bam=bam, chr=chr,
- tracker=metrics_tracker, annot=annot, jar=jar,
- samtools_exe=samtools_exe, java_exe=java_exe)
- metrics_pool.wait_completion()
- # checks whether all required stat files are present
- metrics_tracker.check_files()
- return aggregate_metrics(metrics_tracker, chrs)
-
-
-def prep_bam_file(bams, strand_spec, samtools_exe):
- """Index input BAM files and return a dictionary of BAM files to process."""
- for in_bam in in_bams.values():
- bam = os.path.abspath(in_bam)
- assert os.path.exists(bam), "File {0} does not exist".format(in_bam)
- if not os.path.exists(bam + '.bai'):
- subprocess.call([samtools_exe, 'index', bam])
- return bams
-
-
-def parse_metrics_file(metrics_path):
- """Given a path to a Picard CollectRnaSeqMetrics output file, return a
- dictionary consisting of its column, value mappings.
- """
- data_mark = 'PF_BASES'
- tokens = []
- with open(metrics_path, 'r') as source:
- line = source.readline().strip()
- fsize = os.fstat(source.fileno()).st_size
- while True:
- if not line.startswith(data_mark):
- # encountering EOF before metrics is an error
- if source.tell() == fsize:
- raise ValueError("Metrics not found inside %r" % \
- metrics_path)
- line = source.readline().strip()
- else:
- break
-
- assert line.startswith(data_mark)
- # split header line and append to tokens
- tokens.append(line.split('\t'))
- # and the values (one row after)
- tokens.append(source.readline().strip().split('\t'))
- data = {}
- for col, value in zip(tokens[0], tokens[1]):
- if not value:
- data[COL_NAMES[col]] = None
- elif col.startswith('PCT') or col.startswith('MEDIAN'):
- if value != '?':
- data[COL_NAMES[col]] = float(value)
- else:
- warnings.warn("Undefined value for %s in %s: %s" % (col,
- metrics_path, value))
- data[COL_NAMES[col]] = None
- else:
- assert col in COL_NAMES, 'Unknown column: %s' % col
- data[COL_NAMES[col]] = int(value)
-
- return data
-
-
-def write_json(out_file, data, **kwargs):
- with open(out_file, 'w') as jsonfile:
- json.dump(data, jsonfile, sort_keys=True, indent=4,
- separators=(',', ': '))
-
-
-def write_html(out_file, data, chrs, is_strand_spec):
- if is_strand_spec:
- table_func = build_table_html_ss
- tpl = open(prog_path('rna_metrics.html')).read()
- else:
- table_func = build_table_html_nonss
- tpl = open(prog_path('rna_metrics_nonss.html')).read()
-
- html_data = table_func(data, chrs)
- with open(out_file, 'w') as htmlfile:
- htmlfile.write(tpl.format(**html_data))
-
-
-def get_base_counts(metrics):
- res = {
- 'total': metrics['pfAlignedBases'],
- 'exonic': metrics['utrBases'] + metrics['codingBases'],
- 'intronic': metrics['intronicBases'],
- 'intergenic': metrics['intergenicBases'],
- }
- # count percentages
- for reg in ('exonic', 'intronic', 'intergenic'):
- res[reg + '_pct'] = res[reg] * 100.0 / res['total']
- # format for display
- for key, value in res.items():
- if key.endswith('_pct'):
- res[key] = float_fmt(value=value)
- else:
- res[key] = int_fmt(value=value)
-
- return res
-
-
-def build_table_html_nonss(data, chrs):
- assert data['mix'] is not None and (data['fwd'] is None and data['rev'] is
- None), "Invalid data %r" % data
- mix = data['mix']['allMetrics']
- read_table = [
- '<table>',
- '<tr>',
- '<th>Chromosome</th>',
- '<th>Reads</th>',
- '</tr>'
- ]
- rrow_tpl = '<tr><td>{0}</td><td>{1}</td>'
- for chr in chrs:
- # not showing all stats in table, per chr only
- if chr == 'ALL':
- continue
- count = int_fmt(value=mix[chr]['metrics']['countMapped'])
- read_table.append(rrow_tpl.format(chr, count))
- read_table.append('</table>')
-
- return {'table_read_count': '\n'.join(read_table),
- 'css': open(prog_path('rna_metrics.css')).read()}
-
-
-def build_table_html_ss(data, chrs):
- read_table = [
- '<table>',
- '<tr>',
- '<th rowspan="2">Chromosome</th>',
- '<th>Mapped</th>',
- '<th>Sense Annotation Only</th>',
- '<th>Antisense Annotation Only</th>',
- '</tr>'
- '<tr>',
- '<th>Both strands</th>',
- '<th><green>Sense</green> / <red>Antisense</red> Reads</th>',
- '<th><green>Antisense</green> / <red>Sense</red> Reads</th>',
- '</tr>'
- ]
- rrow_tpl = '<tr><td>{0}</td><td>{1}</td><td>{2}</td><td>{3}</td></tr>'
- rcell_tpl = '<green>{0}</green> / <red>{1}</red>'
-
- fwd_data, rev_data = data['fwd']['allMetrics'], data['rev']['allMetrics']
- mix_data = data['mix']['allMetrics']
- for chr in chrs:
- # not showing all stats in table, per chr only
- if chr == 'ALL':
- continue
- cur_fwd = fwd_data[chr]['metrics']
- cur_rev = rev_data[chr]['metrics']
- mix_count = mix_data[chr]['metrics']['countMapped']
- sense = rcell_tpl.format(
- int_fmt(value=cur_fwd['correctStrandReads']),
- int_fmt(value=cur_fwd['incorrectStrandReads']))
- antisense = rcell_tpl.format(
- int_fmt(value=cur_rev['correctStrandReads']),
- int_fmt(value=cur_rev['incorrectStrandReads']))
- read_table.append(rrow_tpl.format(chr, int_fmt(value=mix_count),
- sense, antisense))
- read_table.append('</table>')
-
- base_table = [
- '<table>',
- '<tr>',
- '<th rowspan="2">Region</th>',
- '<th colspan="2">Sense Annotation</th>',
- '<th colspan="2">Antisense Annotation</th>',
- '</tr>'
- '<tr>',
- '<th>Count</th>', '<th>%</th>',
- '<th>Count</th>', '<th>%</th>',
- '</tr>'
- ]
- crow_tpl = [
- '<tr>',
- '<td>{0}</td>', '<td>{1}</td>',
- '<td>{2}</td>', '<td>{3}</td>',
- '<td>{4}</td>',
- '</tr>',
- ]
- crow_tpl = ''.join(crow_tpl)
- fwd_bcounts = get_base_counts(fwd_data['ALL']['metrics'])
- rev_bcounts = get_base_counts(rev_data['ALL']['metrics'])
- for reg in ('exonic', 'intronic', 'intergenic'):
- pct = reg + '_pct'
- base_table.append(
- crow_tpl.format(reg.capitalize(), fwd_bcounts[reg],
- fwd_bcounts[pct], rev_bcounts[reg],
- rev_bcounts[pct]))
- base_table.append('</table>')
-
- return {'table_read_count': '\n'.join(read_table),
- 'table_base_count': '\n'.join(base_table),
- 'css': open(prog_path('rna_metrics.css')).read()}
-
-
-def aggregate_metrics(tracker, chrs):
- """Aggregates all RNA seq metrics data into a single file."""
- all_dict = {}
- keys = ['fwd', 'rev', 'mix']
- all_dict = dict.fromkeys(keys)
- for bam, stats in tracker.files.items():
- assert stats['strand'] in keys
- aggr_dict = {}
- for chr, source in stats['chrs'].items():
- aggr_dict[chr] = {
- 'fileName': os.path.basename(source),
- 'metrics': parse_metrics_file(source),
- }
- name = os.path.basename(os.path.splitext(bam)[0])
- all_dict[stats['strand']] = {}
- all_dict[stats['strand']]['bamFile'] = name
- all_dict[stats['strand']]['allMetrics'] = aggr_dict
-
- return all_dict
-
-
-def prog_path(fname):
- prog_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)))
- return os.path.join(prog_dir, fname)
-
-
-if __name__ == '__main__':
- # params:
- # main bam file
- # thread num
- # option to compare with annotation source (produces correct/incorrect counts)
- # strand specific or not strand specific
- # path to picard's collectrnaseqmetrics
- # json output path
- # samtools binary (default: environment samtools)
- # java binary (default: environment java)
- # picard options:
- parser = argparse.ArgumentParser()
-
- parser.add_argument('m_bam', type=str,
- help='Path to BAM file containing both sense and antisense reads')
- parser.add_argument('--s-bam', dest='s_bam', type=str,
- help='Path to BAM file containing sense reads')
- parser.add_argument('--as-bam', dest='as_bam', type=str,
- help='Path to BAM file containing antisense reads')
- parser.add_argument('-o', '--outfile', dest='out_file', type=str,
- help='Path to output file')
- parser.add_argument('-t', '--threads', dest='threads',
- default=1, type=int, help='Number of threads to use')
- parser.add_argument('--chrs', dest='chrs',
- default=prog_path('chrs.txt'),
- help='Path to file containing chromosome names')
- parser.add_argument('-a', '--annotation', dest='annot',
- help='Annotation source')
- parser.add_argument('--html', dest='is_html',
- action='store_true',
- help='Output HTML file')
- parser.add_argument('--jar', dest='jar', type=str,
- help='Path to Picard\'s CollectRnaSeqMetrics.jar')
- parser.add_argument('--java', dest='java', type=str,
- default=EXE_JAVA,
- help='Path to java executable')
- parser.add_argument('--samtools', dest='samtools', type=str,
- default=EXE_SAMTOOLS,
- help='Path to samtools executable')
-
- args = parser.parse_args()
-
- if args.s_bam is not None and args.as_bam is not None:
- is_strand_spec = True
- in_bams = {'mix': args.m_bam, 'fwd': args.s_bam, 'rev': args.as_bam}
- elif args.s_bam is None and args.as_bam is None:
- is_strand_spec = False
- in_bams = {'mix': args.m_bam}
- else:
- raise ValueError("Incomplete argument: either sense or antisense BAM "
- "files are not specified.")
-
- chrs = [line.strip() for line in open(args.chrs, 'r')] + ['ALL']
- # check for paths and indices
- bam_files = prep_bam_file(in_bams, is_strand_spec, args.samtools)
- # use picard and samtools if it's strand-specific
- if is_strand_spec:
- aggr_data = picard_reads_per_region_count(bam_files, chrs, args.annot,
- args.jar, args.samtools, args.java)
- sam_data = samtools_reads_per_region_count(bam_files, chrs,
- args.samtools)
- aggr_data['mix'] = sam_data['mix']
- # otherwise use samtools only
- else:
- aggr_data = samtools_reads_per_region_count(bam_files, chrs,
- args.samtools)
-
- # write to output file
- if args.out_file is None:
- ext = '.html' if args.is_html else '.json'
- out_file = 'rna_metrics_out' + ext
- else:
- out_file = args.out_file
-
- write_func = write_html if args.is_html else write_json
- write_func(out_file, aggr_data, chrs=chrs, is_strand_spec=is_strand_spec)
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/gentrap_front.png b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/gentrap_front.png
deleted file mode 100644
index 7ecf40f6998c6b6ce833d1f352efe672b4e32859..0000000000000000000000000000000000000000
Binary files a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/gentrap_front.png and /dev/null differ
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/lib.tex b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/lib.tex
deleted file mode 100644
index 7650cbc6bb0125aadcdaa78ece93436cde2c0551..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/lib.tex
+++ /dev/null
@@ -1,32 +0,0 @@
-\section{Library "((( lib.name )))" Results}
-\label{lib:(((lib.name)))}
-
-\subsection{Input information}
-\label{sec:seq}
-
-\begin{center}
- \captionof{table}{Input files}
- \label{tab:annotfiles}
- \begin{longtable}{ l l p{0.4\textwidth} }
- \hline
- File & Checksum & Name\\
- \hline \hline
- \endhead
- \hline
- \multicolumn{3}{c}{\textit{Continued on next page}}\\
- \hline
- \endfoot
- \hline
- \endlastfoot
- Read 1 file & ((( lib.flexiprep_files.input_R1.md5|truncate(7, True, "") ))) & ((( lib.flexiprep_files.input_R1.path|basename )))\\
- ((* if lib.flexiprep_files.input_R2 *))
- Read 2 file & ((( lib.flexiprep_files.input_R2.md5|truncate(7, True, "") ))) & ((( lib.flexiprep_files.input_R2.path|basename )))\\
- ((* endif *))
- \end{longtable}
-\end{center}
-% HACK: to keep table counters in sync
-\addtocounter{table}{-1}
-
-((* include "lib_mapping.tex" *))
-\clearpage
-((* include "lib_seqeval.tex" *))
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/lib_mapping.tex b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/lib_mapping.tex
deleted file mode 100644
index 39ec179065ba964b6c9cf31af5451ee6227f827f..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/lib_mapping.tex
+++ /dev/null
@@ -1,112 +0,0 @@
-\subsection{Mapping}
-\label{sec:map-((( lib.sample.name )))-((( lib.name )))}
-
-\subsubsection{Mapping statistics}
-
-\indent
-
-% number + percentage of reads mapped to genome
-% number + percentage of properly paired reads
-\begin{center}
- \captionof{table}{Mapping Overview}
- \label{tab:bamstat-((( lib.sample.name )))-((( lib.name )))}
- \setlength{\tabcolsep}{11pt}
- ((* if lib.is_paired_end *))
- \begin{tabular}{ l r r r }
- \hline
- \multirow{2}{*}{Parameter} & \multicolumn{1}{c}{All Pairs} & \multicolumn{1}{c}{First in Pairs} & \multicolumn{1}{c}{Second in Pairs} \\
- & Value & Value & Value \\
- \hline \hline
- Total reads & ((( lib.aln_metrics.PAIR.total_reads|nice_int ))) & ((( lib.aln_metrics.FIRST_OF_PAIR.total_reads|nice_int ))) & ((( lib.aln_metrics.SECOND_OF_PAIR.total_reads|nice_int ))) \\
- Mean read length & ((( lib.aln_metrics.PAIR.mean_read_length|nice_flt ))) & ((( lib.aln_metrics.FIRST_OF_PAIR.mean_read_length|nice_flt ))) & ((( lib.aln_metrics.SECOND_OF_PAIR.mean_read_length|nice_flt ))) \\
- Strand balance & ((( lib.aln_metrics.PAIR.strand_balance|nice_flt ))) & ((( lib.aln_metrics.FIRST_OF_PAIR.strand_balance|nice_flt ))) & ((( lib.aln_metrics.SECOND_OF_PAIR.strand_balance|nice_flt ))) \\
- \% Mapped to reference & ((( lib.aln_metrics.PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( lib.aln_metrics.FIRST_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( lib.aln_metrics.SECOND_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% \\
- \% Mapped to reference (MAPQ >= 20) & ((( lib.aln_metrics.PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( lib.aln_metrics.FIRST_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( lib.aln_metrics.SECOND_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% \\
- Mismatch rate & ((( lib.aln_metrics.PAIR.pf_mismatch_rate|float2nice_pct )))\% & ((( lib.aln_metrics.FIRST_OF_PAIR.pf_mismatch_rate|float2nice_pct )))\% & ((( lib.aln_metrics.SECOND_OF_PAIR.pf_mismatch_rate|float2nice_pct )))\% \\
- Indel rate & ((( lib.aln_metrics.PAIR.pf_indel_rate|float2nice_pct )))\% & ((( lib.aln_metrics.FIRST_OF_PAIR.pf_indel_rate|float2nice_pct )))\% & ((( lib.aln_metrics.SECOND_OF_PAIR.pf_indel_rate|float2nice_pct )))\% \\
- Chimeras & ((( lib.aln_metrics.PAIR.pct_chimeras|float2nice_pct )))\% & ((( lib.aln_metrics.FIRST_OF_PAIR.pct_chimeras|float2nice_pct )))\% & ((( lib.aln_metrics.SECOND_OF_PAIR.pct_chimeras|float2nice_pct )))\% \\
- \hline
- ((* else *))
- \begin{tabular}{ l r }
- \hline
- \multirow{1}{*}{Parameter} & \multicolumn{1}{c}{Value} \\
- \hline \hline
- Total reads & ((( lib.aln_metrics.UNPAIRED.total_reads|nice_int ))) \\
- Mean read length & ((( lib.aln_metrics.UNPAIRED.mean_read_length|nice_flt ))) \\
- Strand balance & ((( lib.aln_metrics.UNPAIRED.strand_balance|nice_flt ))) \\
- \% Mapped to reference & ((( lib.aln_metrics.UNPAIRED.pct_pf_reads_aligned|float2nice_pct )))\% \\
- \% Mapped to reference (MAPQ >= 20) & ((( lib.aln_metrics.UNPAIRED.pct_pf_reads_aligned|float2nice_pct )))\% \\
- Mismatch rate & ((( lib.aln_metrics.UNPAIRED.pf_mismatch_rate|float2nice_pct )))\% \\
- Indel rate & ((( lib.aln_metrics.UNPAIRED.pf_indel_rate|float2nice_pct )))\% \\
- \hline
- ((* endif *))
- \end{tabular}
-\end{center}
-
-((* if lib.is_paired_end *))
-% inferred insert size distribution
-\subsubsection{Insert size distribution}
-
-\IfFileExists{((( lib.inserts_metrics_files.insert_size_histogram.path )))}
-{
- \begin{figure}[h!]
- \centering
- \includegraphics[width=0.7\textwidth]{((( lib.inserts_metrics_files.insert_size_histogram.path )))}
- \caption{Distribution of insert size length of paired-end reads mapped to opposite strands.}
- \end{figure}
-}
-((= TODO: strand-specific stats
-%{
-% \IfFileExists{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).f.insertsizes.png}
-% {
-% \begin{figure}[h!]
-% \centering
-% \includegraphics[width=0.7\textwidth]{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).f.insertsizes.png}
-% \caption{Distribution of insert size length of paired-end reads whose first read maps to the minus strand.}
-% \end{figure}
-% }{}
-% \IfFileExists{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).r.insertsizes.png}
-% {
-% \begin{figure}[h!]
-% \centering
-% \includegraphics[width=0.7\textwidth]{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).r.insertsizes.png}
-% \caption{Distribution of insert size length of paired-end reads whose first read maps to the plus strand.}
-% \end{figure}
-% }{}
-%}
-=))
-((* endif *))
-
-\subsubsection{RNA-specific metrics}
-
-\IfFileExists{((( lib.rna_metrics_files.output_chart.path )))}
-{
- \begin{figure}[h!]
- \centering
- \includegraphics[width=0.7\textwidth]{((( lib.rna_metrics_files.output_chart.path )))}
- \caption{Normalized coverage bias plot.}
- \end{figure}
-}
-
-\begin{center}
- \captionof{table}{Functional annotation metrics}
- \label{tab:fannot-((( lib.sample.name )))-((( lib.name ))))}
- \setlength{\tabcolsep}{11pt}
- \begin{tabular}{ l r r r }
- \hline
- \multirow{2}{*}{Parameter} & \multicolumn{3}{c}{Value} \\
- & Count & \% of all & \% of aligned \\
- \hline \hline
- Total bases & ((( lib.rna_metrics.pf_bases|nice_int ))) & 100\% & - \\
- Aligned bases & ((( lib.rna_metrics.pf_aligned_bases|nice_int ))) & ((( lib.rna_metrics.pct_aligned_bases_all|float2nice_pct )))\% & ((( lib.rna_metrics.pct_aligned_bases|float2nice_pct )))\% \\
- Exonic bases & ((( lib.rna_metrics.exonic_bases|nice_int ))) & ((( lib.rna_metrics.pct_exonic_bases_all|float2nice_pct )))\% & ((( lib.rna_metrics.pct_exonic_bases|float2nice_pct )))\% \\
- \hspace*{4mm}Coding bases & ((( lib.rna_metrics.coding_bases|nice_int ))) & ((( lib.rna_metrics.pct_coding_bases_all|float2nice_pct )))\% & ((( lib.rna_metrics.pct_coding_bases|float2nice_pct )))\% \\
- \hspace*{4mm}UTR bases & ((( lib.rna_metrics.utr_bases|nice_int ))) & ((( lib.rna_metrics.pct_utr_bases_all|float2nice_pct )))\% & ((( lib.rna_metrics.pct_utr_bases|float2nice_pct )))\% \\
- Intronic bases & ((( lib.rna_metrics.intronic_bases|nice_int ))) & ((( lib.rna_metrics.pct_intronic_bases_all|float2nice_pct )))\% & ((( lib.rna_metrics.pct_intronic_bases|float2nice_pct )))\% \\
- Intergenic bases & ((( lib.rna_metrics.intergenic_bases|nice_int ))) & ((( lib.rna_metrics.pct_intergenic_bases_all|float2nice_pct )))\% & ((( lib.rna_metrics.pct_intergenic_bases|float2nice_pct )))\% \\
- ((* if lib.rna_metrics.ribosomal_bases != "" *))
- Ribosomal bases & ((( lib.rna_metrics.ribosomal_bases|nice_int ))) & ((( lib.rna_metrics.pct_ribosomal_bases_all|float2nice_pct )))\% & ((( lib.rna_metrics.pct_ribosomal_bases|float2nice_pct )))\% \\
- ((* endif *))
- \hline
- \end{tabular}
-\end{center}
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/lib_seqeval.tex b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/lib_seqeval.tex
deleted file mode 100644
index 8e28e56e9defea0295be0a38005b4bcc6b68e59c..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/lib_seqeval.tex
+++ /dev/null
@@ -1,456 +0,0 @@
-\subsection{Sequencing Results Evaluation}
-\label{sec:seq}
-
-This section contains statistics of the raw sequencing results. Statistics of
-the preprocessing step(s) may be shown as well, depending on which preprocessing
-steps were performed.
-(Table~\ref{tab:pipelineparams}).
-
-\indent
-
-All statistics, except for the per sequence \%GC graph, were collected using
-FastQC. Visit the
-\href{http://www.bioinformatics.babraham.ac.uk/projects/fastqc/}{FastQC website}
-for more detailed explanations of them.
-
-\subsubsection{Overview}
-\label{subsec:seq-overview}
-There are four types of preprocessing that may be done:
-
-\begin{description}
- \item[\textit{none}] \hfill \\
- No preprocessing step.
- \item[\textit{adapter clipping}] \hfill \\
- Removal of known adapter sequences present in the sequencing
- reads. The list of sequences are retrieved from the FastQC contaminant
- list, which is packaged with the FastQC released used in this pipeline.
- \item[\textit{quality trimming}] \hfill \\
- Removal of all low-quality bases that are often found in the 5'
- or 3' ends of the reads.
- \item[\textit{adapter clipping followed by quality trimming}] \hfill \\
- Both adapter clipping and base quality trimming.
-\end{description}
-\indent
-Your chosen preprocessing method was:\textbf{
-((* if lib.clipping *))adapter clipping
-((* elif lib.trimming *))quality trimming
-((* elif lib.clipping and lib.trimming *))adapter clipping followed by quality trimming((* endif *))}.
-
-((* if lib.clipping *))
-\subsubsection{Adapter removal}
-Known adapter sequences found in the raw data are listed in
-Table~\ref{tab:adapters}. For each adapter sequence, the count of its
-occurence (partially or whole) is also listed. The presence of these
-adapters do not always result in the FASTQ records to be discarded.
-FASTQ records are only discarded if clipping of the adapter sequence
-results in sequences shorter than the threshold set in cutadapt.
-
-\indent
-
-For the complete list of known adapter sequences, consult the
-\href{http://www.bioinformatics.babraham.ac.uk/projects/fastqc/}{official FastQC website}.
-More information about clipping using cutadapt is available on the
-\href{https://code.google.com/p/cutadapt/}{official cutadapt website}.
-
-%\ClipContamTable
-\begin{center}
- \captionof{table}{Adapter Sequences Present in the Sample}
- \label{tab:adapters}
- \begin{longtable}{ p{14mm} r p{0.4\textwidth} r }
- \hline
- Read & Discarded & Adapter & Occurence\\
- \hline \hline
- \endhead
- \hline
- \multicolumn{4}{c}{\textit{Continued on next page}}\\
- \hline
- \endfoot
- \hline
- \endlastfoot
- ((* if lib.flexiprep.stats.clipping_R1 *))
- ((* if lib.flexiprep.stats.clipping_R1.adapters *))
- Read 1 & ((( lib.flexiprep.stats.clipping_R1.num_reads_affected|nice_int )))
- ((* for adapter, stat in lib.flexiprep.stats.clipping_R1.adapters.iteritems() *))
- ((* if loop.first *))
- & ((( adapter ))) & ((( stat|nice_int )))\\
- ((* else *))
- & & ((( adapter ))) & ((( stat|nice_int )))\\
- ((* endif *))
- ((* endfor *))
- ((* else *))
- Read 1 & 0 & \textit{none found} & 0\\
- ((* endif *))
- ((* if lib.is_paired_end *))
- ((* if lib.flexiprep.stats.clipping_R2.adapters *))
- Read 2 & ((( lib.flexiprep.stats.clipping_R2.num_reads_affected|nice_int )))
- ((* for adapter, stat in lib.flexiprep.stats.clipping_R2.adapters.iteritems() *))
- ((* if loop.first *))
- & ((( adapter ))) & ((( stat|nice_int )))\\
- ((* else *))
- & & ((( adapter ))) & ((( stat|nice_int )))\\
- ((* endif *))
- ((* endfor *))
- ((* else *))
- Read 2 & 0 & \textit{none found} & 0\\
- ((* endif *))
- ((* endif *))
- ((* endif *))
- \end{longtable}
-\end{center}
-\addtocounter{table}{-1}
-
-((* endif *))
-
-\vspace{2mm}
-((* if lib.trimming and lib.is_paired_end *))
-\subsubsection{Base quality trimming}
- Summary of the trimming step is available in Table~\ref{tab:trim}. In short,
- sickle is used to trim the 5' and 3' ends of each FASTQ records so that low
- quality bases are trimmed off. If after trimming the FASTQ record becomes
- shorter than the threshold set by sickle, the entire sequence is discarded. For this
- step, read pair completeness check was done along with trimming.
-
- \indent
-
- More information about sickle is available on the
- \href{https://github.com/najoshi/sickle}{official sickle website}.
-
- \begin{center}
- \captionof{table}{Summary of quality trimming step}
- \label{tab:trim}
- \begin{tabular}{ l r }
- \hline
- Parameter & Count\\ \hline \hline
- Discarded FASTQ records from read 1 & ((( lib.flexiprep.stats.trimming_R1.num_reads_discarded_total|nice_int )))\\
- Discarded FASTQ records from read 2 & ((( lib.flexiprep.stats.trimming_R2.num_reads_discarded_total|nice_int )))\\
- \hline
- \end{tabular}
- \end{center}
-((* endif *))
-%\vspace{2mm}
-
-\subsubsection{Basic statistics}
-%\label{subsec:seq_basic}
-
-Basic statistics on the FASTQ files are shown below. For paired-end reads, the
-read count numbers of read 1 and read 2, both before and after preprocessing,
-must match. Read lengths are likely to vary after preprocessing, due to selective
-clipping and trimming of the reads.
-
-\begin{center}
- \captionof{table}{Basic Run Statistics}
- %\label{tab:basestats}
-((* if lib.clipping or lib.trimming *))
- \begin{longtable}{ l r r }
- \hline
- Parameter & Raw & Preprocessed \\ \hline \hline
- \hline \hline
- \endhead
- \hline
- \multicolumn{3}{c}{\textit{Continued on next page}}\\
- \hline
- \endfoot
- \hline
- \endlastfoot
- Read 1 count & ((( lib.fastqc_r1.basic_statistics.data["Total Sequences"] ))) & ((( lib.fastqc_r1_qc.basic_statistics.data["Total Sequences"] )))\\
- Read 1 overall \%GC & ((( lib.fastqc_r1.basic_statistics.data["%GC"] ))) & ((( lib.fastqc_r1_qc.basic_statistics.data["%GC"] )))\\
- Read 1 length range & ((( lib.fastqc_r1.basic_statistics.data["Sequence length"] ))) & ((( lib.fastqc_r1_qc.basic_statistics.data["Sequence length"] )))\\
- \hline
- ((* if lib.is_paired_end *))
- Read 2 count & ((( lib.fastqc_r2.basic_statistics.data["Total Sequences"] ))) & ((( lib.fastqc_r2_qc.basic_statistics.data["Total Sequences"] )))\\
- Read 2 overall \%GC & ((( lib.fastqc_r2.basic_statistics.data["%GC"] ))) & ((( lib.fastqc_r2_qc.basic_statistics.data["%GC"] )))\\
- Read 2 length range & ((( lib.fastqc_r2.basic_statistics.data["Sequence length"] ))) & ((( lib.fastqc_r2_qc.basic_statistics.data["Sequence length"] )))\\
- \hline
- ((* endif *))
-((* else *))
- \begin{longtable}{ l r }
- \hline
- Parameter & Raw \\ \hline \hline
- \hline \hline
- \endhead
- \hline
- \multicolumn{2}{c}{\textit{Continued on next page}}\\
- \hline
- \endfoot
- \hline
- \endlastfoot
- Read 1 count & ((( lib.fastqc_r1.basic_statistics.data["Total Sequences"] )))\\
- Read 1 overall \%GC & ((( lib.fastqc_r1.basic_statistics.data["%GC"] )))\\
- Read 1 length range & ((( lib.fastqc_r1.basic_statistics.data["Sequence length"] )))\\
- \hline
- ((* if lib.is_paired_end *))
- Read 1 count & ((( lib.fastqc_r1.basic_statistics.data["Total Sequences"] )))\\
- Read 1 overall \%GC & ((( lib.fastqc_r1.basic_statistics.data["%GC"] )))\\
- Read 1 length range & ((( lib.fastqc_r1.basic_statistics.data["Sequence length"] )))\\
- \hline
- ((* endif *))
-((* endif *))
- \end{longtable}
-\end{center}
-
-% sequence length distribution
-\subsubsection{Read length distribution}
- Read length distribution for the raw read pair data are shown below.
- Depending on your chosen preprocessing step, the length distribution for the
- preprocessed data may be shown as well. The length distribution for the
- preprocessed data usually becomes less uniform compared to the raw data due
- to the variable removal of the bases in each read.
- \begin{figure}[h!]
- \centering
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Raw read 1]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r1_files.plot_sequence_length_distribution.path )))}
- }
- \end{minipage}
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- ((* if lib.trimming or lib.clipping *))
- \subfloat[Preprocessed read 1]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r1_qc_files.plot_sequence_length_distribution.path )))}
- }
- ((* endif *))
- \end{minipage}
- \caption{Read length distribution for read 1.}
- %\label{fig:length_dist_before_and_after_1}
- \end{figure}
-
-((* if lib.is_paired_end *))
- \begin{figure}[h!]
- \centering
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Raw read 2]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r2_files.plot_sequence_length_distribution.path )))}
- }
- \end{minipage}
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- ((* if lib.trimming or lib.clipping *))
- \subfloat[Preprocessed read 2]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r2_qc_files.plot_sequence_length_distribution.path )))}
- }
- ((* endif *))
- \end{minipage}
- \caption{Read length distribution for read 2.}
- %\label{fig:length_dist_before_and_after_2}
- \end{figure}
-((* endif *))
-
-% per base sequence quality
-\subsubsection{Per base sequence quality}
- Here, the sequence quality for different base positions in all read pairs
- are shown. For each figure, the central line represents the median value,
- the blue represents the mean, the yellow box represents the inter-quartile
- range (25\%-75\%), and the upper and lower whiskers represent the 10\% and
- 90\% points respectively. The green-shaded region marks good quality calls,
- orange-shaded regins mark reasonable quality calls, and red-shaded regions
- mark poor quality calls.
-
- \indent
-
- Note that the latter base positions shown in the figures are
- sometimes aggregates of multiple positions.
- \begin{figure}[h!]
- \centering
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Raw read 1]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r1_files.plot_per_base_quality.path )))}
- }
- \end{minipage}
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- ((* if lib.trimming or lib.clipping *))
- \subfloat[Preprocessed read 1]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r1_qc_files.plot_per_base_quality.path )))}
- }
- ((* endif *))
- \end{minipage}
- \caption{Per base quality before and after processing read 1.}
- %\label{fig:per_base_qual_before_and_after_1}
- \end{figure}
-
-((* if lib.is_paired_end *))
- \begin{figure}[h!]
- \centering
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Raw read 2]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r2_files.plot_per_base_quality.path )))}
- }
- \end{minipage}
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- ((* if lib.trimming or lib.clipping *))
- \subfloat[Preprocessed read 2]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r2_qc_files.plot_per_base_quality.path )))}
- }
- ((* endif *))
- \end{minipage}
- \caption{Per base quality before and after processing for read 2.}
- %\label{fig:per_base_qual_before_and_after_2}
- \end{figure}
-((* endif *))
-
-% per sequence quality scores
-\subsubsection{Per sequence quality scores}
- The read quality score distributions are shown below.
- \begin{figure}[h!]
- \centering
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Raw read 1]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r1_files.plot_per_sequence_quality.path )))}
- }
- \end{minipage}
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- ((* if lib.trimming or lib.clipping *))
- \subfloat[Preprocessed read 1]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r1_qc_files.plot_per_sequence_quality.path )))}
- }
- ((* endif *))
- \end{minipage}
- \caption{Per sequence quality scores before and after preprocessing read 1.}
- %\label{fig:per_seq_qual_before_and_after_1}
- \end{figure}
-
-((* if lib.is_paired_end *))
- \begin{figure}[h!]
- \centering
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Raw read 2]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r2_files.plot_per_sequence_quality.path )))}
- }
- \end{minipage}
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- ((* if lib.trimming or lib.clipping *))
- \subfloat[Preprocessed read 2]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r2_qc_files.plot_per_sequence_quality.path )))}
- }
- ((* endif *))
- \end{minipage}
- \caption{Per sequence quality scores before and after preprocessing for read 2.}
- %\label{fig:per_seq_qual_before_and_after_2}
- \end{figure}
-((* endif *))
-
-% per base sequence content
-\subsubsection{Per base sequence content}
- The figures below plot the occurence of each nucleotide in each position in
- the reads. In a completely random library, you would expect the differences
- among each nucleotide to be minor. You may sometimes see a skewed
- proportion of nucleotides near the start of the read due to the use of
- non-random cDNA during sample preparation.
-
- \indent
-
- Note that the latter base positions shown in the figures are
- sometimes aggregates of multiple positions.
- \begin{figure}[h!]
- \centering
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Raw read 1]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r1_files.plot_per_base_sequence_content.path )))}
- }
- \end{minipage}
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- ((* if lib.trimming or lib.clipping *))
- \subfloat[Preprocessed read 1]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r1_qc_files.plot_per_base_sequence_content.path )))}
- }
- ((* endif *))
- \end{minipage}
- \caption{Per base sequence content before and after preprocessing for read 1.}
- %\label{fig:per_base_content_before_and_after_1}
- \end{figure}
-
-((* if lib.is_paired_end *))
- \begin{figure}[h!]
- \centering
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Raw read 2]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r2_files.plot_per_base_sequence_content.path )))}
- }
- \end{minipage}
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- ((* if lib.trimming or lib.clipping *))
- \subfloat[Preprocessed read 2]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r2_qc_files.plot_per_base_sequence_content.path )))}
- }
- ((* endif *))
- \end{minipage}
- \caption{Per base sequence content before and after preprocessing for read 2.}
- %\label{fig:per_base_content_before_and_after_2}
- \end{figure}
-((* endif *))
-
-
-% per sequence GC content
-\subsubsection{Per sequence GC content}
- The figures below show the GC percentage distribution of all the read pair
- data.
- \begin{figure}[h!]
- \centering
- ((* if lib.trimming or lib.clipping *))
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Raw read 1]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r1_files.plot_per_sequence_gc_content.path )))}
- }
- \end{minipage}
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Preprocessed read 1]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r1_qc_files.plot_per_sequence_gc_content.path )))}
- }
- \end{minipage}
- ((* else *)))
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Raw read 1]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r1_files.plot_per_sequence_gc_content.path )))}
- }
- \end{minipage}
- ((* endif *))
- \caption{Per sequence GC content before and after preprocessing for read 1.}
- %\label{fig:per_base_content_before_and_after_1}
- \end{figure}
-
-((* if lib.is_paired_end *))
- \begin{figure}[h!]
- \centering
- ((* if lib.trimming or lib.clipping *))
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Raw read 2]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r2_files.plot_per_sequence_gc_content.path )))}
- }
- \end{minipage}
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Preprocessed read 2]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r2_qc_files.plot_per_sequence_gc_content.path )))}
- }
- \end{minipage}
- ((* else *))
- \begin{minipage}[b]{0.48\textwidth}
- \centering
- \subfloat[Raw read 2]{
- \includegraphics[width=\textwidth]{((( lib.fastqc_r2_files.plot_per_sequence_gc_content.path )))}
- }
- \end{minipage}
- ((* endif *))
- \caption{Per sequence GC content before and after preprocessing for read 2.}
- %\label{fig:per_base_content_before_and_after_2}
- \end{figure}
-((* endif *))
-
-
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/main.tex b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/main.tex
deleted file mode 100644
index d9365883b62103c1272e330628b6d772b5fd1632..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/main.tex
+++ /dev/null
@@ -1,307 +0,0 @@
-\documentclass[a4paper,12pt]{article}
-\usepackage[a4paper,margin=1in]{geometry}
-\usepackage[T1]{fontenc}
-\usepackage[usenames,dvipsnames]{xcolor}
-\usepackage{longtable}
-\usepackage{graphicx}
-\usepackage{subfig}
-\usepackage{listings}
-\usepackage{verbatim}
-\usepackage{multirow}
-\usepackage{url}
-\usepackage{grffile}
-\usepackage[superscript]{cite}
-% must be located here, so we can handle filenames with underscores
-\newcommand{\UnderscoreCommands}{\do\IfFileExists \do\verbatiminput%
- \do\verbatimtabinput \do\citeNP \do\citeA \do\citeANP \do\citeN%
- \do\shortcite \do\shortciteNP \do\shortciteA \do\shortciteANP%
- \do\shortciteN \do\citeyear \do\citeyearNP%
-}
-\usepackage[strings]{underscore}
-
-\usepackage{fancyhdr}
-\usepackage{hyperref}
-
-\setlength{\tabcolsep}{20pt}
-\renewcommand{\arraystretch}{1.3}
-\renewcommand{\familydefault}{\sfdefault}
-
-% requires the titling package, for subtitles
-%\newcommand{\subtitle}[1]{
-% \posttitle{
-% \par\end{center}
-% \begin{center}\large#1\end{center}
-% \vskip0.5em}}
-
-\pagestyle{fancy}
-\setlength{\headheight}{15.2pt}
-
-\fancyhf{}
-\fancyhead[LE,RO]{\thepage}
-\fancyhead[RE]{\textit{\nouppercase{\leftmark}}}
-\fancyhead[LO]{\textit{\nouppercase{\rightmark}}}
-
-\begin{document}
-\setlength{\parindent}{0in}
-%\title{\Huge Gentrap Run Report}
-\title{\resizebox{0.7\linewidth}{!}{\itshape Gentrap Run Report}}
-\author{LUMC Sequencing Analysis Support Core}
-\maketitle
-\begin{center}
- {\LARGE version ((( run.version )))}
-\end{center}
-\begin{figure}[h!]
- \centering
- \includegraphics[width=0.8\textwidth]{((( run.logo )))}
-\end{figure}
-\thispagestyle{empty}
-\clearpage
-
-\addtocontents{toc}{\protect\hypertarget{toc}{}}
-\tableofcontents
-\clearpage
-
-
-\part{Overview}
-\label{sec:overview}
-
-This document outlines the results obtained from running Gentrap, a generic
-pipeline for transcriptome analysis. The pipeline itself is composed of several
-programs, listed in Table~\ref{tab:programs}. Note that the list only contains
-the programs used in this pipeline run. General pipeline settings that applies
-to all samples are shown in Table~\ref{tab:runparams}, while general annotation
-files are shown in Table~\ref{tab:annotfiles}.
-
-\begin{center}
- \captionof{table}{Programs in Gentrap}
- \label{tab:programs}
- \begin{longtable}{ l l l p{0.2\textwidth} }
- \hline
- Program & Version & Checksum & Usage\\
- \hline \hline
- \endhead
- \hline
- \multicolumn{3}{c}{\textit{Continued on next page}}\\
- \hline
- \endfoot
- \hline
- \endlastfoot
- Gentrap & ((( run.version ))) & - & the full pipeline\\
- ((* for program, info in run.executables.items()|sort *))
- ((( program ))) & ((( info.version ))) & ((( info.md5|truncate(7, True, "") ))) & ((( info.desc )))\\
- ((* endfor *))
- \end{longtable}
-\end{center}
-% HACK: to keep table counters in sync
-\addtocounter{table}{-1}
-
-\begin{center}
- \captionof{table}{General Run Parameters}
- \label{tab:runparams}
- \begin{longtable}{ p{0.4\textwidth} p{0.4\textwidth} }
- \hline
- Parameter & Value\\
- \hline \hline
- \endhead
- \hline
- \multicolumn{2}{c}{\textit{Continued on next page}}\\
- \hline
- \endfoot
- \hline
- \endlastfoot
- Number of samples & ((( run.samples|length )))\\
- Number of libraries & ((( run.libs|length )))\\
- Library types & ((( run.lib_type )))\\
- Expression value measures & ((( run.settings.expression_measures|join(", ") )))\\
- Strand protocol & ((( run.settings.strand_protocol|lower )))\\
- Variant calling & ((* if run.settings.variant_calling *))enabled((* else *))disabled((* endif *))\\
- Ribosomal reads removal & ((* if run.settings.remove_ribosomal_reads *))enabled((* else *))disabled((* endif *))\\
- \end{longtable}
-\end{center}
-\addtocounter{table}{-1}
-
-
-\begin{center}
- \captionof{table}{Annotation Files}
- \label{tab:annotfiles}
- \begin{longtable}{ l l p{0.4\textwidth} }
- \hline
- File & Checksum & Name\\
- \hline \hline
- \endhead
- \hline
- \multicolumn{3}{c}{\textit{Continued on next page}}\\
- \hline
- \endfoot
- \hline
- \endlastfoot
- General refFlat file & ((( run.files.annotation_refflat.md5|truncate(7, True, "") ))) & ((( run.files.annotation_refflat.path|basename )))\\
- ((* if run.files.annotation_gtf *))
- General GTF file & ((( run.files.annotation_gtf.md5|truncate(7, True, "") ))) & ((( run.files.annotation_gtf.path|basename )))\\
- ((* endif *))
- ((* if run.files.annotation_bed *))
- General BED file & ((( run.files.annotation_bed.md5|truncate(7, True, "") ))) & ((( run.files.annotation_bed.path|basename )))\\
- ((* endif *))
- ((* if run.files.ribosome_refflat *))
- Ribosome refFlat & ((( run.files.ribosome_refflat.md5|truncate(7, True, "") ))) & ((( run.files.ribosome_refflat.path|basename )))\\
- ((* endif *))
- \end{longtable}
-\end{center}
-% HACK: to keep table counters in sync
-\addtocounter{table}{-1}
-
-\clearpage
-
-((* if run.samples|length > 2 and run.settings.expression_measures|length > 0 *))
-\part{Multi Sample Results}
-\label{sec:msr}
-This section shows results that are computed from multiple samples.
-
-\begin{center}
- \captionof{table}{Multi Sample Result Files}
- \label{tab:annotfiles}
- \begin{longtable}{ l l p{0.4\textwidth} }
- \hline
- File & Checksum & Name\\
- \hline \hline
- \endhead
- \hline
- \multicolumn{3}{c}{\textit{Continued on next page}}\\
- \hline
- \endfoot
- \hline
- \endlastfoot
- ((* if run.files.gene_fragments_count *))
- Fragments per gene & ((( run.files.gene_fragments_count.md5|truncate(7, True, "") ))) & ((( run.files.gene_fragments_count.path|basename )))\\
- ((* endif *))
-
- ((* if run.files.exon_fragments_count *))
- Fragments per exon & ((( run.files.exon_fragments_count.md5|truncate(7, True, "") ))) & ((( run.files.exon_fragments_count.path|basename )))\\
- ((* endif *))
-
- ((* if run.files.gene_bases_count *))
- Bases per gene & ((( run.files.gene_bases_count.md5|truncate(7, True, "") ))) & ((( run.files.gene_bases_count.path|basename )))\\
- ((* endif *))
-
- ((* if run.files.exon_bases_count *))
- Bases per exon & ((( run.files.exon_bases_count.md5|truncate(7, True, "") ))) & ((( run.files.exon_bases_count.path|basename )))\\
- ((* endif *))
-
- ((* if run.files.gene_fpkm_cufflinks_strict *))
- Cufflinks (strict, gene) & ((( run.files.gene_fpkm_cufflinks_strict.md5|truncate(7, True, "") ))) & ((( run.files.gene_fpkm_cufflinks_strict.path|basename )))\\
- ((* endif *))
- ((* if run.files.isoform_fpkm_cufflinks_strict *))
- Cufflinks (strict, isoform) & ((( run.files.isoform_fpkm_cufflinks_strict.md5|truncate(7, True, "") ))) & ((( run.files.isoform_fpkm_cufflinks_strict.path|basename )))\\
- ((* endif *))
-
- ((* if run.files.gene_fpkm_cufflinks_guided *))
- Cufflinks (guided, gene) & ((( run.files.gene_fpkm_cufflinks_guided.md5|truncate(7, True, "") ))) & ((( run.files.gene_fpkm_cufflinks_guided.path|basename )))\\
- ((* endif *))
- ((* if run.files.isoform_fpkm_cufflinks_guided *))
- Cufflinks (guided, isoform) & ((( run.files.isoform_fpkm_cufflinks_guided.md5|truncate(7, True, "") ))) & ((( run.files.isoform_fpkm_cufflinks_guided.path|basename )))\\
- ((* endif *))
-
- ((* if run.files.gene_fpkm_cufflinks_blind *))
- Cufflinks (blind, gene) & ((( run.files.gene_fpkm_cufflinks_blind.md5|truncate(7, True, "") ))) & ((( run.files.gene_fpkm_cufflinks_blind.path|basename )))\\
- ((* endif *))
- ((* if run.files.isoform_fpkm_cufflinks_blind *))
- Cufflinks (blind, isoform) & ((( run.files.isoform_fpkm_cufflinks_blind.md5|truncate(7, True, "") ))) & ((( run.files.isoform_fpkm_cufflinks_blind.path|basename )))\\
- ((* endif *))
- \end{longtable}
-\end{center}
-% HACK: to keep table counters in sync
-\addtocounter{table}{-1}
-
-((* if run.files.gene_fragments_count *))
-\begin{figure}[h!]
- \centering
- \includegraphics[width=0.65\textwidth]{((( run.files.gene_fragments_count_heatmap.path )))}
- \caption{Between-samples correlation of fragment count per gene.}
-\end{figure}
-((* endif *))
-
-((* if run.files.exon_fragments_count *))
-\begin{figure}[h!]
- \centering
- \includegraphics[width=0.65\textwidth]{((( run.files.exon_fragments_count_heatmap.path )))}
- \caption{Between-samples correlation of fragment count per exon.}
-\end{figure}
-((* endif *))
-
-((* if run.files.gene_bases_count *))
-\begin{figure}[h!]
- \centering
- \includegraphics[width=0.65\textwidth]{((( run.files.gene_bases_count_heatmap.path )))}
- \caption{Between-samples correlation of base count per gene.}
-\end{figure}
-((* endif *))
-
-((* if run.files.exon_bases_count *))
-\begin{figure}[h!]
- \centering
- \includegraphics[width=0.65\textwidth]{((( run.files.exon_bases_count_heatmap.path )))}
- \caption{Between-samples correlation of base count per exon.}
-\end{figure}
-((* endif *))
-
-((* if run.files.gene_fpkm_cufflinks_strict_heatmap *))
-\begin{figure}[h!]
- \centering
- \includegraphics[width=0.65\textwidth]{((( run.files.gene_fpkm_cufflinks_strict_heatmap.path )))}
- \caption{Between-samples correlation of the gene level FPKM (Cufflinks strict mode).}
-\end{figure}
-((* endif *))
-
-((* if run.files.gene_fpkm_cufflinks_guided_heatmap *))
-\begin{figure}[h!]
- \centering
- \includegraphics[width=0.65\textwidth]{((( run.files.gene_fpkm_cufflinks_guided_heatmap.path )))}
- \caption{Between-samples correlation of the gene level FPKM (Cufflinks guided mode).}
-\end{figure}
-((* endif *))
-
-((* if run.files.gene_fpkm_cufflinks_blind_heatmap *))
-\begin{figure}[h!]
- \centering
- \includegraphics[width=0.65\textwidth]{((( run.files.gene_fpkm_cufflinks_blind_heatmap.path )))}
- \caption{Between-samples correlation of the gene level FPKM (Cufflinks blind mode).}
-\end{figure}
-((* endif *))
-
-((* endif *))
-
-\clearpage
-
-((* for sample in run.samples.values()|sort *))
-((* include "sample.tex" *))
-\clearpage
-((* endfor *))
-
-
-\part{About Gentrap}
-\label{apx:about}
-
-The Generic Transcriptome Analysis Pipeline (Gentrap) is a
-generic pipeline for analyzing transcripts from RNA-seq experiments. \\
-
-Gentrap was developed by Wibowo Arindrarto (\href{mailto:w.arindrarto@lumc.nl}{w.arindrarto@lumc.nl})
-based on raw scripts written by Jeroen Laros
-(\href{mailto:j.f.j.laros@lumc.nl}{j.f.j.laros@lumc.nl}) and
-Peter-Bram 't Hoen
-(\href{mailto:p.a.c._t_hoen@lumc.nl}{p.a.c._t_hoen@lumc.nl}) as part of the
-\href{https://git.lumc/nl/biopet/biopet}{Biopet framework}. \\
-
-The Biopet framework is developed by the
-\href{http://sasc.lumc.nl}{Sequencing Analysis Support Core} of the
-\href{http://lumc.nl}{Leiden University Medical Center}, by extending the
-\href{http://http://gatkforums.broadinstitute.org/discussion/1306/overview-of-queue}{Queue framework}.
-Please see the respective web sites for licensing information.
-
-\indent
-
-Cover page image: T7 RNA Polymerase and a dsDNA template (PDB ID \texttt{1msw}).
-Created by Thomas Splettstoesser, taken from
-\href{http://commons.wikimedia.org/wiki/File:T7_RNA_polymerase.jpg}{Wikimedia Commons}.
-
-
-\end{document}
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/sample.tex b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/sample.tex
deleted file mode 100644
index b5f31e50efa563c748fa03ada85b61a6139510fe..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/sample.tex
+++ /dev/null
@@ -1,11 +0,0 @@
-\part{Sample "((( sample.name )))" Results}
-\label{sample:(((sample.name)))}
-
-((* if sample.libs|length > 1 *))
-((* include "sample_mapping.tex" *))
-((* endif *))
-
-((* for lib in sample.libs.values() *))
-((* include "lib.tex" *))
-\clearpage
-((* endfor *))
diff --git a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/sample_mapping.tex b/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/sample_mapping.tex
deleted file mode 100644
index 4f4da850da797c3fb1a355bd32b94955d367f5b2..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/sample_mapping.tex
+++ /dev/null
@@ -1,122 +0,0 @@
-\section{Mapping}
-\label{sec:map-((( sample.name )))}
-
-\subsection{Mapping statistics}
-
-\indent
-
-% number + percentage of reads mapped to genome
-% number + percentage of properly paired reads
-\begin{center}
- \captionof{table}{Mapping Overview}
- \label{tab:bamstat-((( sample.name )))}
- \setlength{\tabcolsep}{11pt}
- ((* if sample.is_paired_end *))
- \begin{tabular}{ l r r r }
- \hline
- \multirow{2}{*}{Parameter} & \multicolumn{1}{c}{All Pairs} & \multicolumn{1}{c}{First in Pairs} & \multicolumn{1}{c}{Second in Pairs} \\
- & Value & Value & Value \\
- \hline \hline
- Total reads & ((( sample.aln_metrics.PAIR.total_reads|nice_int ))) & ((( sample.aln_metrics.FIRST_OF_PAIR.total_reads|nice_int ))) & ((( sample.aln_metrics.SECOND_OF_PAIR.total_reads|nice_int ))) \\
- Mean read length & ((( sample.aln_metrics.PAIR.mean_read_length|nice_flt ))) & ((( sample.aln_metrics.FIRST_OF_PAIR.mean_read_length|nice_flt ))) & ((( sample.aln_metrics.SECOND_OF_PAIR.mean_read_length|nice_flt ))) \\
- Strand balance & ((( sample.aln_metrics.PAIR.strand_balance|nice_flt ))) & ((( sample.aln_metrics.FIRST_OF_PAIR.strand_balance|nice_flt ))) & ((( sample.aln_metrics.SECOND_OF_PAIR.strand_balance|nice_flt ))) \\
- \% Mapped to reference & ((( sample.aln_metrics.PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( sample.aln_metrics.FIRST_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( sample.aln_metrics.SECOND_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% \\
- \% Mapped to reference (MAPQ >= 20) & ((( sample.aln_metrics.PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( sample.aln_metrics.FIRST_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( sample.aln_metrics.SECOND_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% \\
- Mismatch rate & ((( sample.aln_metrics.PAIR.pf_mismatch_rate|float2nice_pct )))\% & ((( sample.aln_metrics.FIRST_OF_PAIR.pf_mismatch_rate|float2nice_pct )))\% & ((( sample.aln_metrics.SECOND_OF_PAIR.pf_mismatch_rate|float2nice_pct )))\% \\
- Indel rate & ((( sample.aln_metrics.PAIR.pf_indel_rate|float2nice_pct )))\% & ((( sample.aln_metrics.FIRST_OF_PAIR.pf_indel_rate|float2nice_pct )))\% & ((( sample.aln_metrics.SECOND_OF_PAIR.pf_indel_rate|float2nice_pct )))\% \\
- Chimeras & ((( sample.aln_metrics.PAIR.pct_chimeras|float2nice_pct )))\% & ((( sample.aln_metrics.FIRST_OF_PAIR.pct_chimeras|float2nice_pct )))\% & ((( sample.aln_metrics.SECOND_OF_PAIR.pct_chimeras|float2nice_pct )))\% \\
- \hline
- ((* else *))
- \begin{tabular}{ l r }
- \hline
- \multirow{1}{*}{Parameter} & \multicolumn{1}{c}{Value} \\
- \hline \hline
- Total reads & ((( sample.aln_metrics.UNPAIRED.total_reads|nice_int ))) \\
- Mean read length & ((( sample.aln_metrics.UNPAIRED.mean_read_length|nice_flt ))) \\
- Strand balance & ((( sample.aln_metrics.UNPAIRED.strand_balance|nice_flt ))) \\
- \% Mapped to reference & ((( sample.aln_metrics.UNPAIRED.pct_pf_reads_aligned|float2nice_pct )))\% \\
- \% Mapped to reference (MAPQ >= 20) & ((( sample.aln_metrics.UNPAIRED.pct_pf_reads_aligned|float2nice_pct )))\% \\
- Mismatch rate & ((( sample.aln_metrics.UNPAIRED.pf_mismatch_rate|float2nice_pct )))\% \\
- Indel rate & ((( sample.aln_metrics.UNPAIRED.pf_indel_rate|float2nice_pct )))\% \\
- \hline
- ((* endif *))
- \end{tabular}
-\end{center}
-
-((* if sample.is_paired_end *))
-% inferred insert size distribution
-\subsubsection{Insert size distribution}
-
-\IfFileExists{((( sample.inserts_metrics_files.insert_size_histogram.path )))}
-{
- \begin{figure}[h!]
- \centering
- \includegraphics[width=0.7\textwidth]{((( sample.inserts_metrics_files.insert_size_histogram.path )))}
- \caption{Distribution of insert size length of paired-end reads mapped to opposite strands.}
- \end{figure}
-}
-((= TODO: strand-specific stats
-%{
-% \IfFileExists{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).f.insertsizes.png}
-% {
-% \begin{figure}[h!]
-% \centering
-% \includegraphics[width=0.7\textwidth]{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).f.insertsizes.png}
-% \caption{Distribution of insert size length of paired-end reads whose first read maps to the minus strand.}
-% \end{figure}
-% }{}
-% \IfFileExists{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).r.insertsizes.png}
-% {
-% \begin{figure}[h!]
-% \centering
-% \includegraphics[width=0.7\textwidth]{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).r.insertsizes.png}
-% \caption{Distribution of insert size length of paired-end reads whose first read maps to the plus strand.}
-% \end{figure}
-% }{}
-%}
-=))
-((* endif *))
-
-
-\subsection{RNA-specific metrics}
-
-\IfFileExists{((( sample.rna_metrics_files.output_chart.path )))}
-{
- \begin{figure}[h!]
- \centering
- \includegraphics[width=0.7\textwidth]{((( sample.rna_metrics_files.output_chart.path )))}
- \caption{Normalized coverage bias plot.}
- \end{figure}
-}
-
-\begin{center}
- \captionof{table}{Functional annotation metrics}
- \label{tab:fannot-((( sample.name )))}
- \setlength{\tabcolsep}{11pt}
- \begin{tabular}{ l r r r }
- \hline
- \multirow{2}{*}{Parameter} & \multicolumn{3}{c}{Value} \\
- & Count & \% of all & \% of aligned \\
- \hline \hline
- Total bases & ((( sample.rna_metrics.pf_bases|nice_int ))) & 100\% & - \\
- Aligned bases & ((( sample.rna_metrics.pf_aligned_bases|nice_int ))) & ((( sample.rna_metrics.pct_aligned_bases_all|float2nice_pct )))\% & ((( sample.rna_metrics.pct_aligned_bases|float2nice_pct )))\% \\
- Exonic bases & ((( sample.rna_metrics.exonic_bases|nice_int ))) & ((( sample.rna_metrics.pct_exonic_bases_all|float2nice_pct )))\% & ((( sample.rna_metrics.pct_exonic_bases|float2nice_pct )))\% \\
- \hspace*{4mm}Coding bases & ((( sample.rna_metrics.coding_bases|nice_int ))) & ((( sample.rna_metrics.pct_coding_bases_all|float2nice_pct )))\% & ((( sample.rna_metrics.pct_coding_bases|float2nice_pct )))\% \\
- \hspace*{4mm}UTR bases & ((( sample.rna_metrics.utr_bases|nice_int ))) & ((( sample.rna_metrics.pct_utr_bases_all|float2nice_pct )))\% & ((( sample.rna_metrics.pct_utr_bases|float2nice_pct )))\% \\
- Intronic bases & ((( sample.rna_metrics.intronic_bases|nice_int ))) & ((( sample.rna_metrics.pct_intronic_bases_all|float2nice_pct )))\% & ((( sample.rna_metrics.pct_intronic_bases|float2nice_pct )))\% \\
- Intergenic bases & ((( sample.rna_metrics.intergenic_bases|nice_int ))) & ((( sample.rna_metrics.pct_intergenic_bases_all|float2nice_pct )))\% & ((( sample.rna_metrics.pct_intergenic_bases|float2nice_pct )))\% \\
- ((* if sample.rna_metrics.ribosomal_bases != "" *))
- Ribosomal bases & ((( sample.rna_metrics.ribosomal_bases|nice_int ))) & ((( sample.rna_metrics.pct_ribosomal_bases_all|float2nice_pct )))\% & ((( sample.rna_metrics.pct_ribosomal_bases|float2nice_pct )))\% \\
- ((* endif *))
- \hline
- Median 5' bias & ((( sample.rna_metrics.median_5prime_bias ))) & - & - \\
- Median 3' bias & ((( sample.rna_metrics.median_3prime_bias ))) & - & - \\
- Median 5' to 3' bias & ((( sample.rna_metrics.median_5prime_to_3prime_bias ))) & - & - \\
- \hline
- ((* if sample.run.settings.strand_protocol != "non_specific" *))
- Correct strand reads & ((( sample.rna_metrics.correct_strand_reads|nice_int ))) & - & - \\
- Incorrect strand reads & ((( sample.rna_metrics.incorrect_strand_reads|nice_int ))) & - & - \\
- ((* endif *))
- \hline
- \end{tabular}
-\end{center}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/CufflinksProducer.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/CufflinksProducer.scala
deleted file mode 100644
index 2640c8f21224b7a504bb73c2a07c0e38e674fcbf..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/CufflinksProducer.scala
+++ /dev/null
@@ -1,101 +0,0 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
-package nl.lumc.sasc.biopet.pipelines.gentrap
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.extensions.{ Cufflinks, Ln }
-
-/** General trait for containing cufflinks results */
-trait CufflinksProducer {
-
- import Gentrap.ExpMeasures._
- import Gentrap.StrandProtocol._
- import Gentrap._
-
- //TODO: move vars that are used in gentrep
- protected def sampleDir: File
- protected def sampleId: String
- protected def pipeline: Gentrap
- protected def alnFile: File
-
- /** Valid cufflink measure types */
- protected val cufflinksMeasures = Set(CufflinksStrict, CufflinksGuided, CufflinksBlind)
-
- /** Cufflink's terms for strand specificity */
- lazy val strandedness: String = {
- //require(pipeline.config.contains("strand_protocol"))
- pipeline.strandProtocol match {
- case NonSpecific => "fr-unstranded"
- case Dutp => "fr-firststrand"
- case otherwise => throw new IllegalStateException("Unexpected strand type for cufflinks: " + otherwise.toString)
- }
- }
-
- /** Case class for containing cufflinks + its output symlink jobs */
- protected case class CufflinksJobSet(cuffType: ExpMeasures.Value) {
-
- require(cufflinksMeasures.contains(cuffType),
- "Cufflinks measurement type is either " + cufflinksMeasures.mkString(", ") + s"; not $cuffType")
-
- /** Base name for output file extensions and config path */
- lazy val name: String = cuffType match {
- case CufflinksStrict => "cufflinks_strict"
- case CufflinksGuided => "cufflinks_guided"
- case CufflinksBlind => "cufflinks_blind"
- case otherwise => throw new IllegalStateException("Unexpected cufflinks type: " + otherwise.toString)
- }
-
- /** Container for all jobs in this job set */
- def jobs = Seq(cufflinksJob, geneFpkmJob, isoformFpkmJob)
-
- /** The main cufflinks job */
- lazy val cufflinksJob: Cufflinks = {
- val job = new Cufflinks(pipeline) {
- override def configName = "cufflinks"
- override def configPath: List[String] = super.configPath ::: name :: Nil
- }
- job.input = alnFile
- job.library_type = Option(strandedness)
- job.output_dir = new File(sampleDir, name)
- job.GTF = cuffType match {
- case CufflinksStrict => pipeline.annotationGtf
- case otherwise => None
- }
- job.GTF_guide = cuffType match {
- case CufflinksGuided => pipeline.annotationGtf
- case otherwise => None
- }
- job
- }
-
- /** Job for symlinking gene FPKM results so that it contains a standard filename (with the sample ID) */
- lazy val geneFpkmJob: Ln = {
- val job = new Ln(pipeline)
- job.input = cufflinksJob.outputGenesFpkm
- job.output = new File(cufflinksJob.output_dir, s"$sampleId.genes_fpkm_$name")
- job
- }
-
- /** Job for symlinking isoforms FPKM results so that it contains a standard filename (with the sample ID) */
- lazy val isoformFpkmJob: Ln = {
- val job = new Ln(pipeline)
- job.input = cufflinksJob.outputIsoformsFpkm
- job.output = new File(cufflinksJob.output_dir, s"$sampleId.isoforms_fpkm_$name")
- job
- }
- }
-}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/Gentrap.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/Gentrap.scala
index fbb095945778b9dcb727cccf668f50184990e161..c2e12f35df694cfeea9d92aa3264126fa63c9261 100644
--- a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/Gentrap.scala
+++ b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/Gentrap.scala
@@ -15,26 +15,21 @@
*/
package nl.lumc.sasc.biopet.pipelines.gentrap
-import java.io.File
-
-import nl.lumc.sasc.biopet.FullVersion
import nl.lumc.sasc.biopet.core._
-import nl.lumc.sasc.biopet.extensions.picard.{ MergeSamFiles, SortSam }
-import nl.lumc.sasc.biopet.extensions.samtools.SamtoolsView
-import nl.lumc.sasc.biopet.extensions.tools.{ MergeTables, WipeReads }
-import nl.lumc.sasc.biopet.extensions.{ HtseqCount, Ln }
-import nl.lumc.sasc.biopet.pipelines.bamtobigwig.Bam2Wig
-import nl.lumc.sasc.biopet.pipelines.gentrap.extensions.{ CustomVarScan, Pdflatex, RawBaseCounter }
-import nl.lumc.sasc.biopet.pipelines.gentrap.scripts.{ AggrBaseCount, PdfReportTemplateWriter, PlotHeatmap }
+import nl.lumc.sasc.biopet.core.annotations.{ RibosomalRefFlat, AnnotationRefFlat }
+import nl.lumc.sasc.biopet.core.report.ReportBuilderExtension
+import nl.lumc.sasc.biopet.extensions.tools.WipeReads
+import nl.lumc.sasc.biopet.pipelines.gentrap.Gentrap.{ StrandProtocol, ExpMeasures }
+import nl.lumc.sasc.biopet.pipelines.gentrap.measures._
import nl.lumc.sasc.biopet.pipelines.mapping.MultisampleMappingTrait
-import nl.lumc.sasc.biopet.utils.Logging
+import nl.lumc.sasc.biopet.pipelines.shiva.ShivaVariantcalling
+import nl.lumc.sasc.biopet.utils.{ LazyCheck, Logging }
import nl.lumc.sasc.biopet.utils.config._
import org.broadinstitute.gatk.queue.QScript
-import org.broadinstitute.gatk.queue.function.QFunction
import picard.analysis.directed.RnaSeqMetricsCollector.StrandSpecificity
+import java.io.File
import scala.language.reflectiveCalls
-import scalaz.Scalaz._
/**
* Gentrap pipeline
@@ -44,78 +39,77 @@ import scalaz.Scalaz._
* @author Wibowo Arindrarto <w.arindrarto@lumc.nl>
*/
class Gentrap(val root: Configurable) extends QScript
- with MultisampleMappingTrait { qscript =>
-
- import Gentrap.ExpMeasures._
- import Gentrap.StrandProtocol._
- import Gentrap._
+ with MultisampleMappingTrait with AnnotationRefFlat with RibosomalRefFlat { qscript =>
// alternative constructor for initialization with empty configuration
def this() = this(null)
- /** Split aligner to use */
- var aligner: String = config("aligner", default = "gsnap")
+ override def reportClass: Option[ReportBuilderExtension] = {
+ val report = new GentrapReport(this)
+ report.outputDir = new File(outputDir, "report")
+ report.summaryFile = summaryFile
+ Some(report)
+ }
/** Expression measurement modes */
// see the enumeration below for valid modes
- var expMeasures: Set[ExpMeasures.Value] = {
- if (config.contains("expression_measures"))
- config("expression_measures")
- .asStringList
- .flatMap { makeExpMeasure }
- .toSet
- else {
- Logging.addError("'expression_measures' is missing in the config")
- Set()
- }
- }
+ lazy val expMeasures = new LazyCheck({
+ config("expression_measures", default = Nil).asStringList.map(value =>
+ ExpMeasures.values.find(_.toString == Gentrap.camelize(value)) match {
+ case Some(v) => v
+ case _ => throw new IllegalArgumentException(s"'$value' is not a valid Expression measurement")
+ }
+ ).toSet
+ })
/** Strandedness modes */
- var strandProtocol: StrandProtocol.Value = {
- if (config.contains("strand_protocol"))
- makeStrandProtocol(config("strand_protocol").asString).getOrElse(StrandProtocol.NonSpecific)
- else {
- Logging.addError("'strand_protocol' is missing in the config")
- StrandProtocol.NonSpecific
+ lazy val strandProtocol = new LazyCheck({
+ val value: String = config("strand_protocol")
+ StrandProtocol.values.find(_.toString == Gentrap.camelize(value)) match {
+ case Some(v) => v
+ case other =>
+ Logging.addError(s"'$other' is no strand_protocol or strand_protocol is not given")
+ StrandProtocol.NonSpecific
}
- }
-
- /** GTF reference file */
- var annotationGtf: Option[File] = config("annotation_gtf")
-
- /** BED reference file */
- var annotationBed: Option[File] = config("annotation_bed")
-
- /** refFlat reference file */
- var annotationRefFlat: File = config("annotation_refflat")
-
- /** rRNA refFlat annotation */
- var ribosomalRefFlat: Option[File] = config("ribosome_refflat")
+ })
/** Whether to remove rRNA regions or not */
- var removeRibosomalReads: Boolean = config("remove_ribosomal_reads", default = false)
-
- /** Whether to do simple variant calling on RNA or not */
- var callVariants: Boolean = config("call_variants", default = false)
+ lazy val removeRibosomalReads: Boolean = config("remove_ribosomal_reads", default = false)
/** Default pipeline config */
override def defaults = Map(
+ "htseqcount" -> (if (strandProtocol.isSet) Map("stranded" -> (strandProtocol() match {
+ case StrandProtocol.NonSpecific => "no"
+ case StrandProtocol.Dutp => "reverse"
+ case otherwise => throw new IllegalStateException(otherwise.toString)
+ }))
+ else Map()),
+ "cufflinks" -> (if (strandProtocol.isSet) Map("library_type" -> (strandProtocol() match {
+ case StrandProtocol.NonSpecific => "fr-unstranded"
+ case StrandProtocol.Dutp => "fr-firststrand"
+ case otherwise => throw new IllegalStateException(otherwise.toString)
+ }))
+ else Map()),
"merge_strategy" -> "preprocessmergesam",
"gsnap" -> Map(
"novelsplicing" -> 1,
- "batch" -> 4,
- "format" -> "sam"
+ "batch" -> 4
+ ),
+ "shivavariantcalling" -> Map(
+ "variantcallers" -> List("varscan_cns_singlesample"),
+ "name_prefix" -> "multisample"
),
"bammetrics" -> Map(
- "transcript_refflat" -> annotationRefFlat,
- "collectrnaseqmetrics" -> ((if (strandProtocol != null) Map(
- "strand_specificity" -> (strandProtocol match {
- case NonSpecific => StrandSpecificity.NONE.toString
- case Dutp => StrandSpecificity.SECOND_READ_TRANSCRIPTION_STRAND.toString
- case otherwise => throw new IllegalStateException(otherwise.toString)
+ "wgs_metrics" -> false,
+ "rna_metrics" -> true,
+ "collectrnaseqmetrics" -> ((if (strandProtocol.isSet) Map(
+ "strand_specificity" -> (strandProtocol() match {
+ case StrandProtocol.NonSpecific => StrandSpecificity.NONE.toString
+ case StrandProtocol.Dutp => StrandSpecificity.SECOND_READ_TRANSCRIPTION_STRAND.toString
+ case otherwise => throw new IllegalStateException(otherwise.toString)
})
)
- else Map()) ++ (if (ribosomalRefFlat != null) ribosomalRefFlat.map("ribosomal_intervals" -> _.getAbsolutePath).toList else Nil))
+ else Map()))
),
"cutadapt" -> Map("minimum_length" -> 20),
// avoid conflicts when merging since the MarkDuplicate tags often cause merges to fail
@@ -124,261 +118,74 @@ class Gentrap(val root: Configurable) extends QScript
),
// disable markduplicates since it may not play well with all aligners (this can still be overriden via config)
"mapping" -> Map(
- "skip_markduplicates" -> true,
- "skip_metrics" -> true
+ "skip_markduplicates" -> true
)
)
- /** Adds output merge jobs for the given expression mode */
- // TODO: can we combine the enum with the file extension (to reduce duplication and potential errors)
- private def makeMergeTableJob(inFunc: (Sample => Option[File]), ext: String, idCols: List[Int], valCol: Int,
- numHeaderLines: Int = 0, outBaseName: String = "all_samples",
- fallback: String = "-"): Option[MergeTables] = {
- val tables = samples.values.map { inFunc }.toList.flatten
- tables.nonEmpty
- .option {
- val job = new MergeTables(qscript)
- job.inputTables = tables
- job.output = new File(outputDir, "expression_estimates" + File.separator + outBaseName + ext)
- job.idColumnIndices = idCols.map(_.toString)
- job.valueColumnIndex = valCol
- job.fileExtension = Option(ext)
- job.fallbackString = Option(fallback)
- job.numHeaderLines = Option(numHeaderLines)
- // TODO: separate the addition into another function?
- job
- }
- }
+ lazy val fragmentsPerGene = if (expMeasures().contains(ExpMeasures.FragmentsPerGene))
+ Some(new FragmentsPerGene(this)) else None
- /** Expression measures which are subject to TMM normalization during correlation calculation */
- protected lazy val forTmmNormalization: Set[ExpMeasures.Value] =
- Set(FragmentsPerGene, FragmentsPerExon, BasesPerGene, BasesPerExon)
-
- /** Returns a QFunction to generate heatmaps */
- private def makeHeatmapJob(mergeJob: Option[MergeTables], outName: String,
- expMeasure: ExpMeasures.Value, isCuffIsoform: Boolean = false): Option[PlotHeatmap] =
- (mergeJob.isDefined && samples.size > 2)
- .option {
- val job = new PlotHeatmap(qscript)
- job.input = mergeJob.get.output
- job.output = new File(outputDir, "heatmaps" + File.separator + s"heatmap_$outName.png")
- job.tmmNormalize = forTmmNormalization.contains(expMeasure)
- job.useLog = job.tmmNormalize
- job.countType =
- if (expMeasure.toString.startsWith("Cufflinks")) {
- if (isCuffIsoform) Option("CufflinksIsoform")
- else Option("CufflinksGene")
- } else Option(expMeasure.toString)
- job
- }
+ lazy val fragmentsPerExon = if (expMeasures().contains(ExpMeasures.FragmentsPerExon))
+ Some(new FragmentsPerExon(this)) else None
- /** Merged gene fragment count table */
- private lazy val geneFragmentsCountJob =
- makeMergeTableJob((s: Sample) => s.geneFragmentsCount, ".fragments_per_gene", List(1), 2, numHeaderLines = 0,
- fallback = "0")
-
- /** Heatmap job for gene fragment count */
- private lazy val geneFragmentsCountHeatmapJob =
- makeHeatmapJob(geneFragmentsCountJob, "fragments_per_gene", FragmentsPerGene)
-
- /** Merged exon fragment count table */
- private lazy val exonFragmentsCountJob =
- makeMergeTableJob((s: Sample) => s.exonFragmentsCount, ".fragments_per_exon", List(1), 2, numHeaderLines = 0,
- fallback = "0")
-
- /** Heatmap job for exon fragment count */
- private lazy val exonFragmentsCountHeatmapJob =
- makeHeatmapJob(exonFragmentsCountJob, "fragments_per_exon", FragmentsPerExon)
-
- /** Merged gene base count table */
- private lazy val geneBasesCountJob =
- makeMergeTableJob((s: Sample) => s.geneBasesCount, ".bases_per_gene", List(1), 2, numHeaderLines = 1,
- fallback = "0")
-
- /** Heatmap job for gene base count */
- private lazy val geneBasesCountHeatmapJob =
- makeHeatmapJob(geneBasesCountJob, "bases_per_gene", BasesPerGene)
-
- /** Merged exon base count table */
- private lazy val exonBasesCountJob =
- makeMergeTableJob((s: Sample) => s.exonBasesCount, ".bases_per_exon", List(1), 2, numHeaderLines = 1,
- fallback = "0")
-
- /** Heatmap job for exon base count */
- private lazy val exonBasesCountHeatmapJob =
- makeHeatmapJob(exonBasesCountJob, "bases_per_exon", BasesPerExon)
-
- /** Merged gene FPKM table for Cufflinks, strict mode */
- private lazy val geneFpkmCufflinksStrictJob =
- makeMergeTableJob((s: Sample) => s.geneFpkmCufflinksStrict, ".genes_fpkm_cufflinks_strict", List(1, 7), 10,
- numHeaderLines = 1, fallback = "0.0")
-
- /** Heatmap job for gene FPKM Cufflinks, strict mode */
- private lazy val geneFpkmCufflinksStrictHeatmapJob =
- makeHeatmapJob(geneFpkmCufflinksStrictJob, "genes_fpkm_cufflinks_strict", CufflinksStrict)
-
- /** Merged exon FPKM table for Cufflinks, strict mode */
- private lazy val isoFpkmCufflinksStrictJob =
- makeMergeTableJob((s: Sample) => s.isoformFpkmCufflinksStrict, ".isoforms_fpkm_cufflinks_strict", List(1, 7), 10,
- numHeaderLines = 1, fallback = "0.0")
-
- /** Heatmap job for isoform FPKM Cufflinks, strict mode */
- private lazy val isoFpkmCufflinksStrictHeatmapJob =
- makeHeatmapJob(isoFpkmCufflinksStrictJob, "isoforms_fpkm_cufflinks_strict", CufflinksStrict, isCuffIsoform = true)
-
- /** Merged gene FPKM table for Cufflinks, guided mode */
- private lazy val geneFpkmCufflinksGuidedJob =
- makeMergeTableJob((s: Sample) => s.geneFpkmCufflinksGuided, ".genes_fpkm_cufflinks_guided", List(1, 7), 10,
- numHeaderLines = 1, fallback = "0.0")
-
- /** Heatmap job for gene FPKM Cufflinks, guided mode */
- private lazy val geneFpkmCufflinksGuidedHeatmapJob =
- makeHeatmapJob(geneFpkmCufflinksGuidedJob, "genes_fpkm_cufflinks_guided", CufflinksGuided)
-
- /** Merged isoforms FPKM table for Cufflinks, guided mode */
- private lazy val isoFpkmCufflinksGuidedJob =
- makeMergeTableJob((s: Sample) => s.isoformFpkmCufflinksGuided, ".isoforms_fpkm_cufflinks_guided", List(1, 7), 10,
- numHeaderLines = 1, fallback = "0.0")
-
- /** Heatmap job for isoform FPKM Cufflinks, guided mode */
- private lazy val isoFpkmCufflinksGuidedHeatmapJob =
- makeHeatmapJob(isoFpkmCufflinksGuidedJob, "isoforms_fpkm_cufflinks_guided", CufflinksGuided, isCuffIsoform = true)
-
- /** Merged gene FPKM table for Cufflinks, blind mode */
- private lazy val geneFpkmCufflinksBlindJob =
- makeMergeTableJob((s: Sample) => s.geneFpkmCufflinksBlind, ".genes_fpkm_cufflinks_blind", List(1, 7), 10,
- numHeaderLines = 1, fallback = "0.0")
-
- /** Heatmap job for gene FPKM Cufflinks, blind mode */
- private lazy val geneFpkmCufflinksBlindHeatmapJob =
- makeHeatmapJob(geneFpkmCufflinksBlindJob, "genes_fpkm_cufflinks_blind", CufflinksBlind)
-
- /** Merged isoforms FPKM table for Cufflinks, blind mode */
- private lazy val isoFpkmCufflinksBlindJob =
- makeMergeTableJob((s: Sample) => s.isoformFpkmCufflinksBlind, ".isoforms_fpkm_cufflinks_blind", List(1, 7), 10,
- numHeaderLines = 1, fallback = "0.0")
-
- /** Heatmap job for isoform FPKM Cufflinks, blind mode */
- private lazy val isoFpkmCufflinksBlindHeatmapJob =
- makeHeatmapJob(isoFpkmCufflinksBlindJob, "isoforms_fpkm_cufflinks_blind", CufflinksBlind, isCuffIsoform = true)
-
- /** Container for merge table jobs */
- private lazy val mergeTableJobs: Map[String, Option[MergeTables]] = Map(
- "gene_fragments_count" -> geneFragmentsCountJob,
- "exon_fragments_count" -> exonFragmentsCountJob,
- "gene_bases_count" -> geneBasesCountJob,
- "exon_bases_count" -> exonBasesCountJob,
- "gene_fpkm_cufflinks_strict" -> geneFpkmCufflinksStrictJob,
- "isoform_fpkm_cufflinks_strict" -> isoFpkmCufflinksStrictJob,
- "gene_fpkm_cufflinks_guided" -> geneFpkmCufflinksGuidedJob,
- "isoform_fpkm_cufflinks_guided" -> isoFpkmCufflinksGuidedJob,
- "gene_fpkm_cufflinks_blind" -> geneFpkmCufflinksBlindJob,
- "isoform_fpkm_cufflinks_blind" -> isoFpkmCufflinksBlindJob
- )
+ lazy val baseCounts = if (expMeasures().contains(ExpMeasures.BaseCounts))
+ Some(new BaseCounts(this)) else None
- /** Container for heatmap jobs */
- private lazy val heatmapJobs: Map[String, Option[PlotHeatmap]] = Map(
- "gene_fragments_count_heatmap" -> geneFragmentsCountHeatmapJob,
- "exon_fragments_count_heatmap" -> exonFragmentsCountHeatmapJob,
- "gene_bases_count_heatmap" -> geneBasesCountHeatmapJob,
- "exon_bases_count_heatmap" -> exonBasesCountHeatmapJob,
- "gene_fpkm_cufflinks_strict_heatmap" -> geneFpkmCufflinksStrictHeatmapJob,
- "isoform_fpkm_cufflinks_strict_heatmap" -> isoFpkmCufflinksStrictHeatmapJob,
- "gene_fpkm_cufflinks_guided_heatmap" -> geneFpkmCufflinksGuidedHeatmapJob,
- "isoform_fpkm_cufflinks_guided_heatmap" -> isoFpkmCufflinksGuidedHeatmapJob,
- "gene_fpkm_cufflinks_blind_heatmap" -> geneFpkmCufflinksBlindHeatmapJob,
- "isoform_fpkm_cufflinks_blind_heatmap" -> isoFpkmCufflinksBlindHeatmapJob
- )
+ lazy val cufflinksBlind = if (expMeasures().contains(ExpMeasures.CufflinksBlind))
+ Some(new CufflinksBlind(this)) else None
+
+ lazy val cufflinksGuided = if (expMeasures().contains(ExpMeasures.CufflinksGuided))
+ Some(new CufflinksGuided(this)) else None
+
+ lazy val cufflinksStrict = if (expMeasures().contains(ExpMeasures.CufflinksStrict))
+ Some(new CufflinksStrict(this)) else None
+
+ def executedMeasures = (fragmentsPerGene :: fragmentsPerExon :: baseCounts :: cufflinksBlind ::
+ cufflinksGuided :: cufflinksStrict :: Nil).flatten
+
+ /** Whether to do simple variant calling on RNA or not */
+ lazy val shivaVariantcalling = if (config("call_variants", default = false)) {
+ val pipeline = new ShivaVariantcalling(this)
+ pipeline.outputDir = new File(outputDir, "variantcalling")
+ Some(pipeline)
+ } else None
/** Output summary file */
def summaryFile: File = new File(outputDir, "gentrap.summary.json")
/** Files that will be listed in the summary file */
override def summaryFiles: Map[String, File] = super.summaryFiles ++ Map(
- "annotation_refflat" -> annotationRefFlat
+ "annotation_refflat" -> annotationRefFlat()
) ++ Map(
- "annotation_gtf" -> annotationGtf,
- "annotation_bed" -> annotationBed,
- "ribosome_refflat" -> ribosomalRefFlat
- ).collect { case (key, Some(value)) => key -> value } ++
- mergeTableJobs.collect { case (key, Some(value)) => key -> value.output } ++
- heatmapJobs.collect { case (key, Some(value)) => key -> value.output }
-
- /** Statistics shown in the summary file */
- def summaryStats: Map[String, Any] = Map()
+ "ribosome_refflat" -> ribosomalRefFlat()
+ ).collect { case (key, Some(value)) => key -> value }
/** Pipeline settings shown in the summary file */
override def summarySettings: Map[String, Any] = super.summarySettings ++ Map(
- "aligner" -> aligner,
- "expression_measures" -> expMeasures.toList.map(_.toString),
- "strand_protocol" -> strandProtocol.toString,
- "call_variants" -> callVariants,
- "remove_ribosomal_reads" -> removeRibosomalReads,
- "version" -> FullVersion
+ "expression_measures" -> expMeasures().toList.map(_.toString),
+ "strand_protocol" -> strandProtocol().toString,
+ "call_variants" -> shivaVariantcalling.isDefined,
+ "remove_ribosomal_reads" -> removeRibosomalReads
)
- /** Job for writing PDF report template */
- protected lazy val pdfTemplateJob: PdfReportTemplateWriter = {
- val job = new PdfReportTemplateWriter(qscript)
- job.summaryFile = summaryFile
- job.output = new File(outputDir, "gentrap_report.tex")
- job
- }
-
- /** Job for writing PDF report */
- protected def pdfReportJob: Pdflatex = {
- val job = new Pdflatex(qscript)
- job.input = pdfTemplateJob.output
- job.outputDir = new File(outputDir, "report")
- job.name = "gentrap_report"
- job
- }
-
/** Steps to run before biopetScript */
override def init(): Unit = {
super.init()
- // TODO: validate that exons are flattened or not (depending on another option flag?)
- // validate required annotation files
- if (expMeasures.contains(FragmentsPerGene) && annotationGtf.isEmpty)
- Logging.addError("GTF file must be defined for counting fragments per gene, config key: 'annotation_gtf'")
-
- if (expMeasures.contains(FragmentsPerExon) && annotationGtf.isEmpty)
- Logging.addError("GTF file must be defined for counting fragments per exon, config key: 'annotation_gtf'")
- // TODO: validate that GTF file contains exon features
-
- if (expMeasures.contains(BasesPerGene) && annotationBed.isEmpty)
- Logging.addError("BED file must be defined for counting bases per gene, config key: 'annotation_bed'")
+ if (expMeasures().isEmpty) Logging.addError("'expression_measures' is missing in the config")
+ require(Gentrap.StrandProtocol.values.contains(strandProtocol()))
+ if (removeRibosomalReads && ribosomalRefFlat().isEmpty)
+ Logging.addError("removeRibosomalReads is enabled but no ribosomalRefFlat is given")
- if (expMeasures.contains(BasesPerExon) && annotationBed.isEmpty)
- Logging.addError("BED file must be defined for counting bases per exon, config key: 'annotation_bed'")
-
- if ((expMeasures.contains(CufflinksBlind) || expMeasures.contains(CufflinksGuided) || expMeasures.contains(CufflinksStrict)) && annotationGtf.isEmpty)
- Logging.addError("GTF file must be defined for Cufflinks-based modes, config key: 'annotation_gtf'")
-
- if (removeRibosomalReads && ribosomalRefFlat.isEmpty)
- Logging.addError("rRNA intervals must be supplied if removeRibosomalReads is set, config key: 'ribosome_refflat'")
-
- annotationGtf.foreach(inputFiles :+= new InputFile(_))
- annotationBed.foreach(inputFiles :+= new InputFile(_))
- ribosomalRefFlat.foreach(inputFiles :+= new InputFile(_))
- if (annotationRefFlat.getName.nonEmpty) inputFiles :+= new InputFile(annotationRefFlat)
+ executedMeasures.foreach(x => x.outputDir = new File(outputDir, "expression_measures" + File.separator + x.name))
}
/** Pipeline run for multiple samples */
override def addMultiSampleJobs(): Unit = {
- super.addMultiSampleJobs
+ super.addMultiSampleJobs()
// merge expression tables
- mergeTableJobs.values.foreach { case maybeJob => maybeJob.foreach(add(_)) }
- // add heatmap jobs
- heatmapJobs.values.foreach { case maybeJob => maybeJob.foreach(add(_)) }
- // plot heatmap for each expression measure if sample is > 1
- if (samples.size > 1) {
- geneFragmentsCountJob
- }
- // TODO: use proper notation
- //add(pdfTemplateJob)
- //add(pdfReportJob)
+ executedMeasures.foreach(add)
+ shivaVariantcalling.foreach(add)
}
/** Returns a [[Sample]] object */
@@ -389,10 +196,7 @@ class Gentrap(val root: Configurable) extends QScript
*
* @param sampleId Unique identifier of the sample
*/
- class Sample(sampleId: String) extends super.Sample(sampleId) with CufflinksProducer {
-
- /** Shortcut to qscript object */
- protected def pipeline: Gentrap = qscript
+ class Sample(sampleId: String) extends super.Sample(sampleId) {
/** Summary stats of the sample */
override def summaryStats: Map[String, Any] = super.summaryStats ++ Map(
@@ -400,334 +204,15 @@ class Gentrap(val root: Configurable) extends QScript
"all_single" -> allSingle
)
- /** Summary files of the sample */
- override def summaryFiles: Map[String, File] = super.summaryFiles ++ Map(
- "alignment" -> alnFile
- ) ++ Map(
- "gene_fragments_count" -> geneFragmentsCount,
- "exon_fragments_count" -> exonFragmentsCount,
- "gene_bases_count" -> geneBasesCount,
- "exon_bases_count" -> exonBasesCount,
- "gene_fpkm_cufflinks_strict" -> cufflinksStrictJobSet.collect { case js => js.geneFpkmJob.output },
- "isoform_fpkm_cufflinks_strict" -> cufflinksStrictJobSet.collect { case js => js.isoformFpkmJob.output },
- "gene_fpkm_cufflinks_guided" -> cufflinksGuidedJobSet.collect { case js => js.geneFpkmJob.output },
- "isoform_fpkm_cufflinks_guided" -> cufflinksGuidedJobSet.collect { case js => js.isoformFpkmJob.output },
- "gene_fpkm_cufflinks_blind" -> cufflinksBlindJobSet.collect { case js => js.geneFpkmJob.output },
- "isoform_fpkm_cufflinks_blind" -> cufflinksBlindJobSet.collect { case js => js.isoformFpkmJob.output },
- "variant_calls" -> variantCalls
- ).collect { case (key, Some(value)) => key -> value }
-
- /** Per-sample alignment file, post rRNA cleanup (if chosen) */
- lazy val alnFile: File = wipeJob match {
- case Some(j) => j.outputBam
- case None => preProcessBam.get
- }
-
- /** Read count per gene file */
- def geneFragmentsCount: Option[File] = fragmentsPerGeneJob
- .collect { case job => job.output }
-
- /** Read count per exon file */
- def exonFragmentsCount: Option[File] = fragmentsPerExonJob
- .collect { case job => job.output }
-
- /** Base count per gene file */
- def geneBasesCount: Option[File] = basesPerGeneJob
- .collect { case job => job.output }
-
- /** Base count per exon file */
- def exonBasesCount: Option[File] = basesPerExonJob
- .collect { case job => job.output }
-
- /** JobSet for Cufflinks strict mode */
- protected lazy val cufflinksStrictJobSet: Option[CufflinksJobSet] = expMeasures
- .find(_ == CufflinksStrict)
- .collect { case found => new CufflinksJobSet(found) }
-
- /** Gene tracking file from Cufflinks strict mode */
- def geneFpkmCufflinksStrict: Option[File] = cufflinksStrictJobSet
- .collect { case jobSet => jobSet.geneFpkmJob.output }
-
- /** Isoforms tracking file from Cufflinks strict mode */
- def isoformFpkmCufflinksStrict: Option[File] = cufflinksStrictJobSet
- .collect { case jobSet => jobSet.isoformFpkmJob.output }
-
- /** JobSet for Cufflinks strict mode */
- protected lazy val cufflinksGuidedJobSet: Option[CufflinksJobSet] = expMeasures
- .find(_ == CufflinksGuided)
- .collect { case found => new CufflinksJobSet(found) }
-
- /** Gene tracking file from Cufflinks guided mode */
- def geneFpkmCufflinksGuided: Option[File] = cufflinksGuidedJobSet
- .collect { case jobSet => jobSet.geneFpkmJob.output }
-
- /** Isoforms tracking file from Cufflinks guided mode */
- def isoformFpkmCufflinksGuided: Option[File] = cufflinksGuidedJobSet
- .collect { case jobSet => jobSet.isoformFpkmJob.output }
-
- /** JobSet for Cufflinks blind mode */
- protected lazy val cufflinksBlindJobSet: Option[CufflinksJobSet] = expMeasures
- .find(_ == CufflinksBlind)
- .collect { case found => new CufflinksJobSet(found) }
-
- /** Gene tracking file from Cufflinks guided mode */
- def geneFpkmCufflinksBlind: Option[File] = cufflinksBlindJobSet
- .collect { case jobSet => jobSet.geneFpkmJob.output }
-
- /** Isoforms tracking file from Cufflinks blind mode */
- def isoformFpkmCufflinksBlind: Option[File] = cufflinksBlindJobSet
- .collect { case jobSet => jobSet.isoformFpkmJob.output }
-
- /** Raw variant calling file */
- def variantCalls: Option[File] = varCallJob
- .collect { case job => job.output }
-
- /** ID-sorting job for HTseq-count jobs */
- private def idSortingJob: Option[SortSam] = (expMeasures.contains(FragmentsPerExon) || expMeasures.contains(FragmentsPerGene))
- .option {
- val job = new SortSam(qscript)
- job.input = alnFile
- job.output = createFile(".idsorted.bam")
- job.sortOrder = "queryname"
- job.isIntermediate = true
- job
- }
-
- /** Read counting job per gene */
- private def fragmentsPerGeneJob: Option[HtseqCount] = expMeasures
- .contains(FragmentsPerGene)
- .option {
- require(idSortingJob.nonEmpty)
- val job = new HtseqCount(qscript)
- annotationGtf.foreach(job.inputAnnotation = _)
- job.inputAlignment = idSortingJob.get.output
- job.output = createFile(".fragments_per_gene")
- job.format = Option("bam")
- // We are forcing the sort order to be ID-sorted, since HTSeq-count often chokes when using position-sorting due
- // to its buffer not being large enough.
- job.order = Option("name")
- job.stranded = strandProtocol match {
- case NonSpecific => Option("no")
- case Dutp => Option("reverse")
- case _ => throw new IllegalStateException
- }
- job
- }
-
- /** Read counting job per exon */
- private def fragmentsPerExonJob: Option[HtseqCount] = expMeasures
- .contains(FragmentsPerExon)
- .option {
- require(idSortingJob.nonEmpty)
- val job = new HtseqCount(qscript)
- job.inputAnnotation = annotationGtf.get
- job.inputAlignment = idSortingJob.get.output
- job.output = createFile(".fragments_per_exon")
- job.format = Option("bam")
- job.order = Option("name")
- job.stranded = strandProtocol match {
- case NonSpecific => Option("no")
- case Dutp => Option("reverse")
- case _ => throw new IllegalStateException
- }
- // TODO: ensure that the "exon_id" attributes exist for all exons in the GTF
- job.idattr = Option("exon_id")
- job
- }
-
- /** Container for strand-separation jobs */
- private case class StrandSeparationJobSet(pair1Job: SamtoolsView, pair2Job: Option[SamtoolsView],
- combineJob: QFunction { def output: File }) {
- def addAllJobs(): Unit = {
- add(pair1Job); pair2Job.foreach(add(_)); add(combineJob)
- }
- }
-
- /** Alignment file of reads from the plus strand, only defined when run is strand-specific */
- def alnFilePlusStrand: Option[File] = alnPlusStrandJobs
- .collect { case jobSet => jobSet.combineJob.output }
-
- /** Jobs for generating reads from the plus strand, only defined when run is strand-specific */
- private def alnPlusStrandJobs: Option[StrandSeparationJobSet] = strandProtocol match {
- case Dutp =>
- val r2Job = this.allPaired
- .option {
- val job = new SamtoolsView(qscript)
- job.input = alnFile
- job.b = true
- job.h = true
- job.f = List("0x80")
- job.F = List("0x10")
- job.output = createFile(".r2.bam")
- job.isIntermediate = true
- job
- }
-
- val f1Job = new SamtoolsView(qscript)
- f1Job.input = alnFile
- f1Job.b = true
- f1Job.h = true
- f1Job.f = if (this.allSingle) List("0x10") else List("0x50")
- f1Job.output = createFile(".f1.bam")
- // since we are symlinking if the other pair does not exist,
- // we want to keep this job as non-intermediate as well
- f1Job.isIntermediate = r2Job.isDefined
-
- val perStrandFiles = r2Job match {
- case Some(r2j) => List(f1Job.output, r2j.output)
- case None => List(f1Job.output)
- }
- val combineJob = makeCombineJob(perStrandFiles, createFile(".plus_strand.bam"))
-
- Option(StrandSeparationJobSet(f1Job, r2Job, combineJob.alnJob))
-
- case NonSpecific => None
- case _ => throw new IllegalStateException
- }
-
- /** Alignment file of reads from the minus strand, only defined when run is strand-specific */
- def alnFileMinusStrand: Option[File] = alnMinusStrandJobs
- .collect { case jobSet => jobSet.combineJob.output }
-
- /** Jobs for generating reads from the minus, only defined when run is strand-specific */
- private def alnMinusStrandJobs: Option[StrandSeparationJobSet] = strandProtocol match {
- case Dutp =>
- val r1Job = this.allPaired
- .option {
- val job = new SamtoolsView(qscript)
- job.input = alnFile
- job.b = true
- job.h = true
- job.f = List("0x40")
- job.F = List("0x10")
- job.output = createFile(".r1.bam")
- job.isIntermediate = true
- job
- }
-
- val f2Job = new SamtoolsView(qscript)
- f2Job.input = alnFile
- f2Job.b = true
- f2Job.h = true
- f2Job.output = createFile(".f2.bam")
- // since we are symlinking if the other pair does not exist,
- // we want to keep this job as non-intermediate as well
- f2Job.isIntermediate = r1Job.isDefined
- if (this.allSingle) f2Job.F = List("0x10")
- else f2Job.f = List("0x90")
-
- val perStrandFiles = r1Job match {
- case Some(r1j) => List(f2Job.output, r1j.output)
- case None => List(f2Job.output)
- }
- val combineJob = makeCombineJob(perStrandFiles, createFile(".minus_strand.bam"))
-
- Option(StrandSeparationJobSet(f2Job, r1Job, combineJob.alnJob))
-
- case NonSpecific => None
- case _ => throw new IllegalStateException
- }
- /** Raw base counting job */
- private def rawBaseCountJob: Option[RawBaseCounter] = strandProtocol match {
- case NonSpecific =>
- (expMeasures.contains(BasesPerExon) || expMeasures.contains(BasesPerGene))
- .option {
- val job = new RawBaseCounter(qscript)
- job.inputBoth = alnFile
- annotationBed.foreach(job.annotationBed = _)
- job.output = createFile(".raw_base_count")
- job
- }
- case Dutp =>
- (expMeasures.contains(BasesPerExon) || expMeasures.contains(BasesPerGene))
- .option {
- require(alnFilePlusStrand.isDefined && alnFileMinusStrand.isDefined)
- val job = new RawBaseCounter(qscript)
- job.inputPlus = alnFilePlusStrand.get
- job.inputMinus = alnFileMinusStrand.get
- annotationBed.foreach(job.annotationBed = _)
- job.output = createFile(".raw_base_count")
- job
- }
- case _ => throw new IllegalStateException
- }
-
- /** Base counting job per gene */
- private def basesPerGeneJob: Option[AggrBaseCount] = expMeasures
- .contains(BasesPerGene)
- .option {
- require(rawBaseCountJob.nonEmpty)
- val job = new AggrBaseCount(qscript)
- job.input = rawBaseCountJob.get.output
- job.output = createFile(".bases_per_gene")
- job.inputLabel = sampleId
- job.mode = "gene"
- job
- }
-
- /** Base counting job per exon */
- private def basesPerExonJob: Option[AggrBaseCount] = expMeasures
- .contains(BasesPerExon)
- .option {
- require(rawBaseCountJob.nonEmpty)
- val job = new AggrBaseCount(qscript)
- job.input = rawBaseCountJob.get.output
- job.output = createFile(".bases_per_exon")
- job.inputLabel = sampleId
- job.mode = "exon"
- job
- }
-
- /** Variant calling job */
- private def varCallJob: Option[CustomVarScan] = callVariants
- .option {
- val job = new CustomVarScan(qscript)
- job.input = alnFile
- job.output = createFile(".raw.vcf.gz")
- job
- }
-
- /** Job for removing ribosomal reads */
- private def wipeJob: Option[WipeReads] = removeRibosomalReads
- .option {
- //require(ribosomalRefFlat.isDefined)
- val job = new WipeReads(qscript)
- job.inputBam = bamFile.get
- ribosomalRefFlat.foreach(job.intervalFile = _)
- job.outputBam = createFile(".cleaned.bam")
- job.discardedBam = createFile(".rrna.bam")
- job
- }
-
- /** Super type of Ln and MergeSamFiles */
- case class CombineFileJobSet(alnJob: QFunction { def output: File }, idxJob: Option[Ln]) {
- /** Adds all jobs in this jobset */
- def addAll(): Unit = { add(alnJob); idxJob.foreach(add(_)) }
- }
-
- /** Ln or MergeSamFile job, depending on how many inputs are supplied */
- private def makeCombineJob(inFiles: List[File], outFile: File,
- mergeSortOrder: String = "coordinate"): CombineFileJobSet = {
- require(inFiles.nonEmpty, "At least one input files required for combine job")
- if (inFiles.size == 1) {
-
- val jobBam = new Ln(qscript)
- jobBam.input = inFiles.head.getAbsoluteFile
- jobBam.output = outFile
-
- val jobIdx = new Ln(qscript)
- jobIdx.input = swapExt(libraries.values.head.libDir, jobBam.input, ".bam", ".bai")
- jobIdx.output = swapExt(sampleDir, jobBam.output, ".bam", ".bai")
-
- CombineFileJobSet(jobBam, Some(jobIdx))
- } else {
- val job = new MergeSamFiles(qscript)
- job.input = inFiles
- job.output = outFile
- job.sortOrder = mergeSortOrder
- CombineFileJobSet(job, None)
- }
- }
+ override lazy val preProcessBam = if (removeRibosomalReads) {
+ val job = new WipeReads(qscript)
+ job.inputBam = bamFile.get
+ ribosomalRefFlat().foreach(job.intervalFile = _)
+ job.outputBam = createFile("cleaned.bam")
+ job.discardedBam = createFile("rrna.bam")
+ add(job)
+ Some(job.outputBam)
+ } else bamFile
/** Whether all libraries are paired or not */
def allPaired: Boolean = libraries.values.forall(_.mapping.forall(_.input_R2.isDefined))
@@ -735,35 +220,17 @@ class Gentrap(val root: Configurable) extends QScript
/** Whether all libraries are single or not */
def allSingle: Boolean = libraries.values.forall(_.mapping.forall(_.input_R2.isEmpty))
- // TODO: add warnings or other messages for config values that are hard-coded by the pipeline
/** Adds all jobs for the sample */
override def addJobs(): Unit = {
super.addJobs()
// TODO: this is our requirement since it's easier to calculate base counts when all libraries are either paired or single
require(allPaired || allSingle, s"Sample $sampleId contains only single-end or paired-end libraries")
- // merge or symlink per-library alignments
// add bigwig output, also per-strand when possible
- addAll(Bam2Wig(qscript, alnFile).functions)
- alnFilePlusStrand.collect { case f => addAll(Bam2Wig(qscript, f).functions) }
- alnFileMinusStrand.collect { case f => addAll(Bam2Wig(qscript, f).functions) }
- // add strand-specific jobs if defined
- alnPlusStrandJobs.foreach(_.addAllJobs())
- alnMinusStrandJobs.foreach(_.addAllJobs())
- // add htseq-count jobs, if defined
- idSortingJob.foreach(add(_))
- fragmentsPerGeneJob.foreach(add(_))
- fragmentsPerExonJob.foreach(add(_))
- // add custom base count jobs, if defined
- rawBaseCountJob.foreach(add(_))
- basesPerGeneJob.foreach(add(_))
- basesPerExonJob.foreach(add(_))
- // symlink results with distinct extensions ~ actually to make it easier to use MergeTables on these as well
- // since the Queue argument parser doesn't play nice with Map[_, _] types
- cufflinksStrictJobSet.foreach(_.jobs.foreach(add(_)))
- cufflinksGuidedJobSet.foreach(_.jobs.foreach(add(_)))
- cufflinksBlindJobSet.foreach(_.jobs.foreach(add(_)))
- // add variant calling job if requested
- varCallJob.foreach(add(_))
+
+ preProcessBam.foreach { file =>
+ executedMeasures.foreach(_.addBamfile(sampleId, file))
+ shivaVariantcalling.foreach(_.inputBams += sampleId -> file)
+ }
}
}
}
@@ -772,15 +239,12 @@ object Gentrap extends PipelineCommand {
/** Enumeration of available expression measures */
object ExpMeasures extends Enumeration {
- val FragmentsPerGene, FragmentsPerExon, BasesPerGene, BasesPerExon, CufflinksStrict, CufflinksGuided, CufflinksBlind = Value
- //Cuffquant,
- //Rsem = Value
+ val FragmentsPerGene, FragmentsPerExon, BaseCounts, CufflinksStrict, CufflinksGuided, CufflinksBlind = Value
}
/** Enumeration of available strandedness */
object StrandProtocol extends Enumeration {
// for now, only non-strand specific and dUTP stranded protocol is supported
- // TODO: other strandedness protocol?
val NonSpecific, Dutp = Value
}
@@ -789,28 +253,4 @@ object Gentrap extends PipelineCommand {
.split("_")
.map(_.toLowerCase.capitalize)
.mkString("")
-
- /** Conversion from raw user-supplied expression measure string to enum value */
- private def makeExpMeasure(rawName: String): Option[ExpMeasures.Value] = {
- try {
- Some(ExpMeasures.withName(camelize(rawName)))
- } catch {
- case nse: NoSuchElementException =>
- Logging.addError(s"Invalid expression measure: $rawName")
- None
- case e: Exception => throw e
- }
- }
-
- /** Conversion from raw user-supplied expression measure string to enum value */
- private def makeStrandProtocol(rawName: String): Option[StrandProtocol.Value] = {
- try {
- Some(StrandProtocol.withName(camelize(rawName)))
- } catch {
- case nse: NoSuchElementException =>
- Logging.addError(s"Invalid strand protocol: $rawName")
- None
- case e: Exception => throw e
- }
- }
}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/GentrapReport.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/GentrapReport.scala
index 55f50882862db3bdc787fffdbeb6be35cf24d009..16b8a6fff7076ae9aa9d09a59c4d8fb52c4b75f9 100644
--- a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/GentrapReport.scala
+++ b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/GentrapReport.scala
@@ -15,10 +15,9 @@
*/
package nl.lumc.sasc.biopet.pipelines.gentrap
+import nl.lumc.sasc.biopet.core.report.{ ReportBuilderExtension, ReportSection }
+import nl.lumc.sasc.biopet.pipelines.mapping.MultisampleMappingReportTrait
import nl.lumc.sasc.biopet.utils.config.Configurable
-import nl.lumc.sasc.biopet.core.report.{ ReportBuilderExtension, ReportSection, ReportPage, MultisampleReportBuilder }
-import nl.lumc.sasc.biopet.pipelines.bammetrics.BammetricsReport
-import nl.lumc.sasc.biopet.pipelines.flexiprep.FlexiprepReport
/**
* Class to generate report for [[Gentrap]]
@@ -29,69 +28,12 @@ class GentrapReport(val root: Configurable) extends ReportBuilderExtension {
def builder = GentrapReport
}
-object GentrapReport extends MultisampleReportBuilder {
+object GentrapReport extends MultisampleMappingReportTrait {
- /** Root page for the carp report */
- def indexPage = {
- //Source.fromInputStream(getClass.getResourceAsStream("/nl/lumc/sasc/biopet/pipelines/carp/carpFont.ssp")).foreach(print(_))
- ReportPage(
- List("Samples" -> generateSamplesPage(pageArgs)) ++
- Map("Files" -> filesPage,
- "Versions" -> ReportPage(List(), List("Executables" -> ReportSection("/nl/lumc/sasc/biopet/core/report/executables.ssp"
- )), Map())
- ),
- List(
- "Report" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gentrap/gentrapFront.ssp"),
- "Alignment" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp",
- Map("sampleLevel" -> true, "showPlot" -> true, "showTable" -> false)
- ),
- "Insert Size" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/insertSize.ssp",
- Map("sampleLevel" -> true, "showPlot" -> true, "showTable" -> false)),
- "QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp",
- Map("showPlot" -> true, "showTable" -> false)),
- "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp",
- Map("showPlot" -> true, "showTable" -> false))
- ),
- pageArgs
- )
- }
-
- /** Files page, can be used general or at sample level */
- def filesPage: ReportPage = ReportPage(List(), List(
- "Input fastq files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepInputfiles.ssp"),
- "After QC fastq files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepOutputfiles.ssp"),
- "Bam files per lib" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/mapping/outputBamfiles.ssp", Map("sampleLevel" -> false)) //,
- //"Preprocessed bam files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/mapping/outputBamfiles.ssp",
- // Map("pipelineName" -> "shiva", "fileTag" -> "preProcessBam"))
- ), Map())
-
- /** Single sample page */
- def samplePage(sampleId: String, args: Map[String, Any]): ReportPage = {
- ReportPage(List(
- "Libraries" -> generateLibraryPage(args),
- "Alignment" -> BammetricsReport.bamMetricsPage(summary, Some(sampleId), None),
- "Files" -> filesPage
- ), List(
- "Alignment" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp",
- if (summary.libraries(sampleId).size > 1) Map("showPlot" -> true) else Map()),
- "Preprocessing" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp", Map("sampleLevel" -> true)),
- "QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp"),
- "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp")
- ), args)
- }
-
- /** Library page */
- def libraryPage(sampleId: String, libId: String, args: Map[String, Any]): ReportPage = {
- ReportPage(List(
- "Alignment" -> BammetricsReport.bamMetricsPage(summary, Some(sampleId), Some(libId)),
- "QC" -> FlexiprepReport.flexiprepPage
- ), List(
- "Alignment" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp"),
- "QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp"),
- "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp")
- ), args)
- }
+ override def frontSection = ReportSection("/nl/lumc/sasc/biopet/pipelines/gentrap/gentrapFront.ssp")
/** Name of the report */
def reportName = "Gentrap Report"
+
+ override def pipelineName = "gentrap"
}
\ No newline at end of file
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/extensions/CustomVarScan.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/extensions/CustomVarScan.scala
deleted file mode 100644
index f2f11a03e775ebe5a7fa4161813a0157c8f7976a..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/extensions/CustomVarScan.scala
+++ /dev/null
@@ -1,102 +0,0 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
-package nl.lumc.sasc.biopet.pipelines.gentrap.extensions
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.core.{ Reference, BiopetCommandLineFunction }
-import nl.lumc.sasc.biopet.core.extensions.PythonCommandLineFunction
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import nl.lumc.sasc.biopet.extensions.samtools.SamtoolsMpileup
-import nl.lumc.sasc.biopet.extensions.varscan.Mpileup2cns
-import nl.lumc.sasc.biopet.extensions.{ Bgzip, Tabix }
-import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
-
-/** Ad-hoc extension for VarScan variant calling that involves 6-command pipe */
-// FIXME: generalize piping instead of building something by hand like this!
-// Better to do everything quick and dirty here rather than something half-implemented with the objects
-class CustomVarScan(val root: Configurable) extends BiopetCommandLineFunction with Reference { wrapper =>
-
- override def configName = "customvarscan"
-
- @Input(doc = "Input BAM file", required = true)
- var input: File = null
-
- @Output(doc = "Output VCF file", required = true)
- var output: File = null
-
- @Output(doc = "Output VCF file index", required = true)
- lazy val outputIndex: File = new File(output.toString + ".tbi")
-
- // mpileup, varscan, fix_mpileup.py, binom_test.py, bgzip, tabix
- private def mpileup = new SamtoolsMpileup(wrapper.root) {
- this.input = List(wrapper.input)
- override def configName = wrapper.configName
- disableBaq = true
- depth = Option(1000000)
- outputMappingQuality = true
-
- }
-
- private def fixMpileup = new PythonCommandLineFunction {
- setPythonScript("fix_mpileup.py", "/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/")
- override val root: Configurable = wrapper.root
- override def configName = wrapper.configName
- def cmdLine = getPythonCommand
- }
-
- private def removeEmptyPile() = new BiopetCommandLineFunction {
- override val root: Configurable = wrapper.root
- override def configName = wrapper.configName
- executable = config("exe", default = "grep", freeVar = false)
- override def cmdLine: String = required(executable) + required("-vP") + required("""\t\t""")
- }
-
- private val varscan = new Mpileup2cns(wrapper.root) {
- override def configName = wrapper.configName
- strandFilter = Option(0)
- outputVcf = Option(1)
- }
-
- private val compress = new Bgzip(wrapper.root)
-
- private val index = new Tabix(wrapper.root) {
- override def configName = wrapper.configName
- p = Option("vcf")
- }
-
- override def freezeFieldValues(): Unit = {
- varscan.output = Option(new File(wrapper.output.toString.stripSuffix(".gz")))
- compress.input = List(varscan.output.get)
- compress.output = this.output
- index.input = compress.output
- super.freezeFieldValues()
- varscan.qSettings = this.qSettings
- varscan.freezeFieldValues()
- }
-
- override def beforeGraph(): Unit = {
- super.beforeGraph()
- require(output.toString.endsWith(".gz"), "Output must have a .gz file extension")
- deps :+= referenceFasta()
- }
-
- def cmdLine: String = {
- // FIXME: manual trigger of commandLine for version retrieval
- mpileup.commandLine
- (mpileup | fixMpileup | removeEmptyPile() | varscan).commandLine + " && " + compress.commandLine + " && " + index.commandLine
- }
-}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/extensions/Pdflatex.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/extensions/Pdflatex.scala
deleted file mode 100644
index 4747856d6f58943b33f0407b63c37311ab1f67fb..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/extensions/Pdflatex.scala
+++ /dev/null
@@ -1,55 +0,0 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
-package nl.lumc.sasc.biopet.pipelines.gentrap.extensions
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.utils.commandline.{ Argument, Input, Output }
-
-/**
- * Wrapper for the pdflatex executable
- */
-class Pdflatex(val root: Configurable) extends BiopetCommandLineFunction {
-
- executable = config("exe", default = "pdflatex", freeVar = false)
- override val executableToCanonicalPath = false
-
- @Input(doc = "Input LaTeX template", required = true)
- var input: File = null
-
- @Output(doc = "Output directory", required = true)
- var outputDir: File = null
-
- @Argument(doc = "Job name", required = true)
- var name: String = null
-
- @Output(doc = "Output PDF file")
- lazy val outputPdf: File = {
- require(name != null && outputDir != null, "Job name and output directory must be defined")
- new File(outputDir, name + ".pdf")
- }
-
- def cmdLine = {
- // repeating command 3x times to get internal references working correctly
- val singleCommand = required(executable) +
- required("-output-directory", outputDir) +
- required("-jobname", name) +
- required(input)
- Seq(singleCommand, singleCommand, singleCommand).mkString(" && ")
- }
-}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/extensions/RScriptCommandLineFunction.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/extensions/RScriptCommandLineFunction.scala
deleted file mode 100644
index 3f44845bcc1c5c39fe498b496c573a7f3109f2b4..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/extensions/RScriptCommandLineFunction.scala
+++ /dev/null
@@ -1,57 +0,0 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
-package nl.lumc.sasc.biopet.pipelines.gentrap.extensions
-
-import java.io.{ File, FileOutputStream }
-
-import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
-import org.broadinstitute.gatk.utils.commandline.Input
-
-/**
- * Trait for RScript wrappers
- */
-trait RScriptCommandLineFunction extends BiopetCommandLineFunction {
-
- @Input(doc = "R script file", required = false)
- var RScript: File = _
-
- executable = config("exe", default = "Rscript", submodule = "rscript")
-
- protected var RScriptName: String = _
-
- def setRScript(script: String) {
- setRScript(script, "")
- }
-
- def setRScript(script: String, subpackage: String) {
- RScriptName = script
- // TODO: set .queue/tmp as a library-wide constant
- RScript = new File(".queue/tmp/" + subpackage + RScriptName)
-
- if (!RScript.getParentFile.exists)
- RScript.getParentFile.mkdirs
-
- val is = getClass.getResourceAsStream(subpackage + RScriptName)
- val os = new FileOutputStream(RScript)
-
- org.apache.commons.io.IOUtils.copy(is, os)
- os.close()
- }
-
- def RScriptCommand: String = {
- required(executable) + required(RScript)
- }
-}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/extensions/RawBaseCounter.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/extensions/RawBaseCounter.scala
deleted file mode 100644
index 8be307a9d1323f0252d5b7f2e24f52c07148adcc..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/extensions/RawBaseCounter.scala
+++ /dev/null
@@ -1,114 +0,0 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
-package nl.lumc.sasc.biopet.pipelines.gentrap.extensions
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
-import nl.lumc.sasc.biopet.utils.Logging
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import nl.lumc.sasc.biopet.core.extensions.PythonCommandLineFunction
-import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
-
-import scala.language.reflectiveCalls
-
-/** Ad-hoc extension for counting bases that involves 3-command pipe */
-// FIXME: generalize piping instead of building something by hand like this!
-// Better to do everything quick and dirty here rather than something half-implemented with the objects
-class RawBaseCounter(val root: Configurable) extends BiopetCommandLineFunction { wrapper =>
-
- override def configName = "rawbasecounter"
-
- @Input(doc = "Reference BED file", required = true)
- var annotationBed: File = null
-
- @Input(doc = "Input BAM file from both strands", required = false)
- var inputBoth: File = null
-
- @Input(doc = "Input BAM file from the plus strand", required = false)
- var inputPlus: File = null
-
- @Input(doc = "Input BAM file from the minus strand", required = false)
- var inputMinus: File = null
-
- @Output(doc = "Output base count file", required = true)
- var output: File = null
-
- /** Internal flag for mixed strand mode */
- private lazy val mixedStrand: Boolean = inputBoth != null && inputPlus == null && inputMinus == null
-
- /** Internal flag for distinct strand / strand-specific mode */
- private lazy val distinctStrand: Boolean = inputBoth == null && inputPlus != null && inputMinus != null
-
- private def grepForStrand = new BiopetCommandLineFunction {
- var strand: String = null
- override val root: Configurable = wrapper.root
- override def configName = wrapper.configName
- executable = config("exe", default = "grep", freeVar = false)
- override def cmdLine: String = required(executable) +
- required("-P", """\""" + strand + """$""") +
- required(annotationBed)
- }
-
- private def bedtoolsCovHist = new BiopetCommandLineFunction {
- var bam: File = null
- override def configName = "bedtoolscoverage"
- override val root: Configurable = wrapper.root
- executable = config("exe", default = "coverageBed", freeVar = false)
- override def cmdLine: String = required(executable) +
- required("-split") +
- required("-hist") +
- required("-abam", bam) +
- required("-b", if (mixedStrand) annotationBed else "stdin")
- }
-
- private def hist2Count = new PythonCommandLineFunction {
- setPythonScript("hist2count.py", "/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/")
- override def configName = wrapper.configName
- override val root: Configurable = wrapper.root
- def cmdLine = getPythonCommand + optional("-c", "3")
- }
-
- override def beforeGraph(): Unit = {
- if (annotationBed == null) Logging.addError("Annotation BED must be supplied")
- require(output != null, "Output must be defined")
- require((mixedStrand && !distinctStrand) || (!mixedStrand && distinctStrand),
- "Invalid input BAM combinations for RawBaseCounter")
- }
-
- def cmdLine: String =
- if (mixedStrand && !distinctStrand) {
-
- val btCov = bedtoolsCovHist
- btCov.bam = inputBoth
- btCov.commandLine + "|" + hist2Count.commandLine + " > " + output
-
- } else {
-
- val plusGrep = grepForStrand
- plusGrep.strand = "+"
- val plusBtCov = bedtoolsCovHist
- plusBtCov.bam = inputPlus
-
- val minusGrep = grepForStrand
- minusGrep.strand = "-"
- val minusBtCov = bedtoolsCovHist
- minusBtCov.bam = inputMinus
-
- plusGrep.commandLine + "|" + plusBtCov.commandLine + "|" + hist2Count.commandLine + " > " + required(output) + " && " +
- minusGrep.commandLine + "|" + minusBtCov.commandLine + "|" + hist2Count.commandLine + " >> " + required(output)
- }
-}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/BaseCounts.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/BaseCounts.scala
new file mode 100644
index 0000000000000000000000000000000000000000..ef1d47e45d7cc953d24725debb89e92499dbfafd
--- /dev/null
+++ b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/BaseCounts.scala
@@ -0,0 +1,73 @@
+package nl.lumc.sasc.biopet.pipelines.gentrap.measures
+
+import nl.lumc.sasc.biopet.core.annotations.AnnotationRefFlat
+import nl.lumc.sasc.biopet.extensions.tools.BaseCounter
+import nl.lumc.sasc.biopet.pipelines.gentrap.Gentrap
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by pjvan_thof on 1/12/16.
+ */
+class BaseCounts(val root: Configurable) extends QScript with Measurement with AnnotationRefFlat {
+
+ def mergeArgs = MergeArgs(List(1), 2, numHeaderLines = 0, fallback = "0")
+
+ /** Pipeline itself */
+ def biopetScript(): Unit = {
+ val jobs = bamFiles.map {
+ case (id, file) =>
+ val baseCounter = new BaseCounter(this)
+ baseCounter.bamFile = file
+ baseCounter.outputDir = new File(outputDir, id)
+ baseCounter.prefix = id
+ baseCounter.refFlat = annotationRefFlat()
+ add(baseCounter)
+ id -> baseCounter
+ }
+
+ def addTableAndHeatmap(countFiles: List[File], outputName: String): Unit = {
+ val mergedTable = new File(outputDir, s"$name.$outputName.tsv")
+ val heatmapFile = new File(outputDir, s"$name.$outputName.png")
+ addMergeTableJob(countFiles, mergedTable, outputName, countFiles.head.getName.stripPrefix(jobs.head._1))
+ addHeatmapJob(mergedTable, heatmapFile, outputName)
+ }
+
+ addTableAndHeatmap(jobs.values.map(_.transcriptTotalCounts).toList, "transcriptTotalCounts")
+ addTableAndHeatmap(jobs.values.map(_.transcriptTotalSenseCounts).toList, "transcriptTotalSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.transcriptTotalAntiSenseCounts).toList, "transcriptTotalAntiSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.transcriptExonicCounts).toList, "transcriptExonicCounts")
+ addTableAndHeatmap(jobs.values.map(_.transcriptExonicSenseCounts).toList, "transcriptExonicSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.transcriptExonicAntiSenseCounts).toList, "transcriptExonicAntiSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.transcriptIntronicCounts).toList, "transcriptIntronicCounts")
+ addTableAndHeatmap(jobs.values.map(_.transcriptIntronicSenseCounts).toList, "transcriptIntronicSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.transcriptIntronicAntiSenseCounts).toList, "transcriptIntronicAntiSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.exonCounts).toList, "exonCounts")
+ addTableAndHeatmap(jobs.values.map(_.exonSenseCounts).toList, "exonSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.exonAntiSenseCounts).toList, "exonAntiSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.intronCounts).toList, "intronCounts")
+ addTableAndHeatmap(jobs.values.map(_.intronSenseCounts).toList, "intronSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.intronAntiSenseCounts).toList, "intronAntiSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.geneTotalCounts).toList, "geneTotalCounts")
+ addTableAndHeatmap(jobs.values.map(_.geneTotalSenseCounts).toList, "geneTotalSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.geneTotalAntiSenseCounts).toList, "geneTotalAntiSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.geneExonicCounts).toList, "geneExonicCounts")
+ addTableAndHeatmap(jobs.values.map(_.geneExonicSenseCounts).toList, "geneExonicSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.geneExonicAntiSenseCounts).toList, "geneExonicAntiSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.geneIntronicCounts).toList, "geneIntronicCounts")
+ addTableAndHeatmap(jobs.values.map(_.geneIntronicSenseCounts).toList, "geneIntronicSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.geneIntronicAntiSenseCounts).toList, "geneIntronicAntiSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.mergeExonCounts).toList, "mergeExonCounts")
+ addTableAndHeatmap(jobs.values.map(_.mergeExonSenseCounts).toList, "mergeExonSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.mergeExonAntiSenseCounts).toList, "mergeExonAntiSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.mergeIntronCounts).toList, "mergeIntronCounts")
+ addTableAndHeatmap(jobs.values.map(_.mergeIntronSenseCounts).toList, "mergeIntronSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.mergeIntronAntiSenseCounts).toList, "mergeIntronAntiSenseCounts")
+ addTableAndHeatmap(jobs.values.map(_.nonStrandedMetaExonCounts).toList, "nonStrandedMetaExonCounts")
+ addTableAndHeatmap(jobs.values.map(_.strandedMetaExonCounts).toList, "strandedMetaExonCounts")
+ addTableAndHeatmap(jobs.values.map(_.strandedSenseMetaExonCounts).toList, "strandedSenseMetaExonCounts")
+ addTableAndHeatmap(jobs.values.map(_.strandedAntiSenseMetaExonCounts).toList, "strandedAntiSenseMetaExonCounts")
+
+ addSummaryJobs()
+ }
+}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/CufflinksBlind.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/CufflinksBlind.scala
new file mode 100644
index 0000000000000000000000000000000000000000..8b963c3315a33cf8c484aa2ce1cb68b9abdc8e90
--- /dev/null
+++ b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/CufflinksBlind.scala
@@ -0,0 +1,12 @@
+package nl.lumc.sasc.biopet.pipelines.gentrap.measures
+
+import nl.lumc.sasc.biopet.core.annotations.AnnotationGtf
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by pjvan_thof on 1/12/16.
+ */
+class CufflinksBlind(val root: Configurable) extends QScript with CufflinksMeasurement with AnnotationGtf {
+
+}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/CufflinksGuided.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/CufflinksGuided.scala
new file mode 100644
index 0000000000000000000000000000000000000000..30bdcb5893227c0c53e052317ac8984b088c4610
--- /dev/null
+++ b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/CufflinksGuided.scala
@@ -0,0 +1,16 @@
+package nl.lumc.sasc.biopet.pipelines.gentrap.measures
+
+import nl.lumc.sasc.biopet.core.annotations.AnnotationGtf
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by pjvan_thof on 1/12/16.
+ */
+class CufflinksGuided(val root: Configurable) extends QScript with CufflinksMeasurement with AnnotationGtf {
+ override def makeCufflinksJob(id: String, bamFile: File) = {
+ val cufflinks = super.makeCufflinksJob(id, bamFile)
+ cufflinks.GTF_guide = Some(annotationGtf)
+ cufflinks
+ }
+}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/CufflinksMeasurement.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/CufflinksMeasurement.scala
new file mode 100644
index 0000000000000000000000000000000000000000..26616991e3b74985e38431e4cc19e99bc785d389
--- /dev/null
+++ b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/CufflinksMeasurement.scala
@@ -0,0 +1,57 @@
+package nl.lumc.sasc.biopet.pipelines.gentrap.measures
+
+import nl.lumc.sasc.biopet.extensions.{ Ln, Cufflinks }
+import nl.lumc.sasc.biopet.extensions.tools.MergeTables
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by pjvanthof on 20/01/16.
+ */
+trait CufflinksMeasurement extends QScript with Measurement {
+ def makeCufflinksJob(id: String, bamFile: File) = {
+ val cufflinks = new Cufflinks(this)
+ cufflinks.input = bamFile
+ cufflinks.output_dir = new File(outputDir, id)
+ cufflinks
+ }
+
+ def biopetScript(): Unit = {
+ val jobs = bamFiles.map {
+ case (id, file) =>
+ val cufflinks = makeCufflinksJob(id, file)
+ add(cufflinks)
+ id -> cufflinks
+ }
+
+ val genesFpkmFiles = jobs.toList.map {
+ case (id, job) =>
+ val file = new File(job.output_dir, s"$id.genes_fpkm.counts")
+ add(Ln(this, job.outputGenesFpkm, file))
+ file
+ }
+
+ val isoFormFpkmFiles = jobs.toList.map {
+ case (id, job) =>
+ val file = new File(job.output_dir, s"$id.iso_form_fpkn.counts")
+ add(Ln(this, job.outputIsoformsFpkm, file))
+ file
+ }
+
+ addMergeTableJob(genesFpkmFiles, mergeGenesFpkmTable, "genes_fpkm", ".genes_fpkm.counts")
+ addMergeTableJob(isoFormFpkmFiles, mergeIsoFormFpkmTable, "iso_form_fpkn", ".iso_form_fpkn.counts")
+
+ addHeatmapJob(mergeGenesFpkmTable, genesFpkmHeatmap, "genes_fpkm")
+ addHeatmapJob(mergeIsoFormFpkmTable, isoFormFpkmHeatmap, "iso_form_fpkm")
+
+ addSummaryJobs()
+ }
+
+ def mergeGenesFpkmTable: File = new File(outputDir, s"$name.genes.fpkm.tsv")
+ def genesFpkmHeatmap: File = new File(outputDir, s"$name.genes.fpkm.png")
+
+ def mergeIsoFormFpkmTable: File = new File(outputDir, s"$name.iso_form.fpkm.tsv")
+ def isoFormFpkmHeatmap: File = new File(outputDir, s"$name.iso_form.fpkm.png")
+
+ def mergeArgs = MergeArgs(List(1, 7), 10, numHeaderLines = 1, fallback = "0.0")
+
+}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/CufflinksStrict.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/CufflinksStrict.scala
new file mode 100644
index 0000000000000000000000000000000000000000..7a531820f4a1317d0a5c8730c6829ef4fe2415aa
--- /dev/null
+++ b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/CufflinksStrict.scala
@@ -0,0 +1,16 @@
+package nl.lumc.sasc.biopet.pipelines.gentrap.measures
+
+import nl.lumc.sasc.biopet.core.annotations.AnnotationGtf
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by pjvan_thof on 1/12/16.
+ */
+class CufflinksStrict(val root: Configurable) extends QScript with CufflinksMeasurement with AnnotationGtf {
+ override def makeCufflinksJob(id: String, bamFile: File) = {
+ val cufflinks = super.makeCufflinksJob(id, bamFile)
+ cufflinks.GTF = Some(annotationGtf)
+ cufflinks
+ }
+}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/FragmentsPerExon.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/FragmentsPerExon.scala
new file mode 100644
index 0000000000000000000000000000000000000000..dbca36eed14d1203473b5b1d5d5ddaa33846733a
--- /dev/null
+++ b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/FragmentsPerExon.scala
@@ -0,0 +1,14 @@
+package nl.lumc.sasc.biopet.pipelines.gentrap.measures
+
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by pjvan_thof on 1/12/16.
+ */
+class FragmentsPerExon(val root: Configurable) extends QScript with Measurement {
+ def mergeArgs = MergeArgs(List(1), 2, numHeaderLines = 1, fallback = "0")
+
+ /** Pipeline itself */
+ def biopetScript(): Unit = ???
+}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/FragmentsPerGene.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/FragmentsPerGene.scala
new file mode 100644
index 0000000000000000000000000000000000000000..e6323699e4a488cf2c26b20ceb0ebeab3fbbf1b9
--- /dev/null
+++ b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/FragmentsPerGene.scala
@@ -0,0 +1,41 @@
+package nl.lumc.sasc.biopet.pipelines.gentrap.measures
+
+import nl.lumc.sasc.biopet.core.annotations.AnnotationGtf
+import nl.lumc.sasc.biopet.extensions.HtseqCount
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by pjvan_thof on 1/12/16.
+ */
+class FragmentsPerGene(val root: Configurable) extends QScript with Measurement with AnnotationGtf {
+ def mergeArgs = MergeArgs(List(1), 2, numHeaderLines = 1, fallback = "0")
+
+ /** Pipeline itself */
+ def biopetScript(): Unit = {
+ val jobs = bamFiles.map {
+ case (id, file) =>
+ //TODO: ID sorting job
+
+ val job = new HtseqCount(this)
+ job.inputAnnotation = annotationGtf
+ job.inputAlignment = file
+ job.output = new File(outputDir, s"$id.$name.counts")
+ job.format = Option("bam")
+ add(job)
+ // We are forcing the sort order to be ID-sorted, since HTSeq-count often chokes when using position-sorting due
+ // to its buffer not being large enough.
+ //TODO: ID sorting job
+ //job.order = Option("name")
+ id -> job
+ }
+
+ addMergeTableJob(jobs.values.map(_.output).toList, mergedTable, "fragments_per_gene", s".$name.counts")
+ addHeatmapJob(mergedTable, heatmap, "fragments_per_gene")
+
+ addSummaryJobs()
+ }
+
+ def mergedTable = new File(outputDir, s"$name.fragments_per_gene.tsv")
+ def heatmap = new File(outputDir, s"$name.fragments_per_gene.png")
+}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/Measurement.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/Measurement.scala
new file mode 100644
index 0000000000000000000000000000000000000000..c3d389b0e8219320df6b945a74bda72a496293db
--- /dev/null
+++ b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/Measurement.scala
@@ -0,0 +1,68 @@
+package nl.lumc.sasc.biopet.pipelines.gentrap.measures
+
+import nl.lumc.sasc.biopet.core.Reference
+import nl.lumc.sasc.biopet.core.summary.SummaryQScript
+import nl.lumc.sasc.biopet.extensions.tools.MergeTables
+import nl.lumc.sasc.biopet.pipelines.gentrap.scripts.PlotHeatmap
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by pjvan_thof on 1/12/16.
+ */
+trait Measurement extends SummaryQScript with Reference { qscript: QScript =>
+ protected var bamFiles: Map[String, File] = Map()
+
+ /**
+ * Method to add a bamFile to the pipeline
+ * @param id Uniqe id used for this bam file, most likly to be a sampleName
+ * @param file Location of the bam file
+ */
+ def addBamfile(id: String, file: File): Unit = {
+ require(!bamFiles.contains(id), s"'$id' already exist")
+ bamFiles += id -> file
+ }
+
+ /** Name of job, this is used as prefix for most of the files */
+ def name: String = this.getClass.getSimpleName.toLowerCase
+
+ /** Class to store args for MergeTables */
+ case class MergeArgs(idCols: List[Int], valCol: Int, numHeaderLines: Int = 0, fallback: String = "-")
+
+ /** This should contain the args for MergeTables */
+ def mergeArgs: MergeArgs
+
+ /** Init for pipeline */
+ def init(): Unit = {
+ require(bamFiles.nonEmpty)
+ }
+
+ private var extraSummaryFiles: Map[String, File] = Map()
+
+ def addMergeTableJob(countFiles: List[File],
+ outputFile: File,
+ name: String,
+ fileExtension: String,
+ args: MergeArgs = mergeArgs): Unit = {
+ add(MergeTables(this, countFiles, outputFile,
+ args.idCols, args.valCol, args.numHeaderLines, args.fallback, fileExtension = Some(fileExtension)))
+ extraSummaryFiles += s"${name}_table" -> outputFile
+ }
+
+ def addHeatmapJob(countTable: File, outputFile: File, name: String, countType: Option[String] = None): Unit = {
+ val job = new PlotHeatmap(qscript)
+ job.input = countTable
+ job.output = outputFile
+ job.countType = countType
+ add(job)
+ extraSummaryFiles += s"${name}_heatmap" -> outputFile
+ }
+
+ /** Must return a map with used settings for this pipeline */
+ def summarySettings: Map[String, Any] = Map()
+
+ /** File to put in the summary for thie pipeline */
+ def summaryFiles: Map[String, File] = extraSummaryFiles ++ bamFiles.map { case (id, file) => s"input_bam_$id" -> file }
+
+ /** Name of summary output file */
+ def summaryFile: File = new File(outputDir, s"$name.summary.json")
+}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/AggrBaseCount.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/AggrBaseCount.scala
deleted file mode 100644
index 84941f6beeb080c1ffa2b7681eb8bb9e404d6449..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/AggrBaseCount.scala
+++ /dev/null
@@ -1,51 +0,0 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
-package nl.lumc.sasc.biopet.pipelines.gentrap.scripts
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import nl.lumc.sasc.biopet.pipelines.gentrap.extensions.RScriptCommandLineFunction
-import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
-
-/**
- * Wrapper for the aggr_base_count.R script, used internally in Gentrap
- */
-class AggrBaseCount(val root: Configurable) extends RScriptCommandLineFunction {
-
- setRScript("aggr_base_count.R", "/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/")
-
- @Input(doc = "Raw base count files", required = true)
- var input: File = null
-
- @Output(doc = "Output count file", required = false)
- var output: File = null
-
- var inputLabel: String = null
- var mode: String = null
-
- override def beforeGraph(): Unit = {
- require(mode == "exon" || mode == "gene", "Mode must be either exon or gene")
- require(input != null, "Input raw base count table must be defined")
- }
-
- def cmdLine = {
- RScriptCommand +
- required("-I", input) +
- required("-N", inputLabel) +
- optional(if (mode == "gene") "-G" else "-E", output)
- }
-}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/PdfReportTemplateWriter.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/PdfReportTemplateWriter.scala
deleted file mode 100644
index eeab93c18279cf3e0510e810ef1199dbb27ee58a..0000000000000000000000000000000000000000
--- a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/PdfReportTemplateWriter.scala
+++ /dev/null
@@ -1,76 +0,0 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
-package nl.lumc.sasc.biopet.pipelines.gentrap.scripts
-
-import java.io.{ File, FileOutputStream }
-
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import nl.lumc.sasc.biopet.core.extensions.PythonCommandLineFunction
-import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
-
-/**
- * Wrapper for the pdf_report.py script, used internally in Gentrap
- */
-class PdfReportTemplateWriter(val root: Configurable) extends PythonCommandLineFunction {
-
- @Input(doc = "Input summary file", required = true)
- var summaryFile: File = null
-
- @Input(doc = "Main report template", required = true) // def since we hard-code the template
- def mainTemplateFile: File = new File(templateWorkDir, "main.tex")
-
- @Input(doc = "Main report logo", required = true) // def since we hard-code the logo
- def logoFile: File = new File(templateWorkDir, "gentrap_front.png")
-
- @Output(doc = "Output file", required = true)
- var output: File = null
-
- val templateWorkDir: File = new File(".queue/tmp/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf")
- val templateFiles: Seq[String] = Seq(
- "main.tex", "gentrap_front.png",
- "sample.tex", "sample_mapping.tex",
- "lib.tex", "lib_seqeval.tex", "lib_mapping.tex"
- )
-
- protected def prepTemplate(name: String,
- subPackage: String = "/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf"): Unit = {
- val target = new File(".queue/tmp" + subPackage, name)
- if (!target.getParentFile.exists) target.getParentFile.mkdirs()
- val is = getClass.getResourceAsStream(subPackage + "/" + name)
- val os = new FileOutputStream(target)
- org.apache.commons.io.IOUtils.copy(is, os)
- os.close()
-
- //python_script_name = script
- //python_script = new File(".queue/tmp/" + subpackage + python_script_name)
- //if (!python_script.getParentFile.exists) python_script.getParentFile.mkdirs
- //val is = getClass.getResourceAsStream(subpackage + python_script_name)
- //val os = new FileOutputStream(python_script)
- //org.apache.commons.io.IOUtils.copy(is, os)
- //os.close()
- }
-
- def cmdLine = {
- getPythonCommand +
- required(summaryFile) +
- required(mainTemplateFile) +
- required(logoFile.getAbsoluteFile) +
- " > " + required(output)
- }
-
- setPythonScript("pdf_report.py")
- templateFiles.foreach(t => prepTemplate(t))
-}
diff --git a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/PlotHeatmap.scala b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/PlotHeatmap.scala
index e93049732b32bfe4451fdb6d18a122d070f98c13..decd56a55b74c4fe3103e041850c22f0e10e9fa1 100644
--- a/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/PlotHeatmap.scala
+++ b/public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/PlotHeatmap.scala
@@ -17,16 +17,16 @@ package nl.lumc.sasc.biopet.pipelines.gentrap.scripts
import java.io.File
+import nl.lumc.sasc.biopet.core.extensions.RscriptCommandLineFunction
import nl.lumc.sasc.biopet.utils.config.Configurable
-import nl.lumc.sasc.biopet.pipelines.gentrap.extensions.RScriptCommandLineFunction
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
/**
* Wrapper for the plot_heatmap.R script, used internally in Gentrap
*/
-class PlotHeatmap(val root: Configurable) extends RScriptCommandLineFunction {
+class PlotHeatmap(val root: Configurable) extends RscriptCommandLineFunction {
- setRScript("plot_heatmap.R", "/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/")
+ protected var script: File = config("script", default = "plot_heatmap.R")
@Input(doc = "Input table", required = true)
var input: File = null
@@ -38,12 +38,12 @@ class PlotHeatmap(val root: Configurable) extends RScriptCommandLineFunction {
var useLog: Boolean = config("use_log", default = false)
var tmmNormalize: Boolean = config("tmm_normalize", default = false)
- def cmdLine = {
- RScriptCommand +
- conditional(tmmNormalize, "-T") +
- conditional(useLog, "-L") +
- required("-C", countType) +
- required("-I", input) +
- required("-O", output)
- }
+ override def cmd = super.cmd ++
+ (if (tmmNormalize) Seq("-T") else Seq()) ++
+ (if (useLog) Seq("-L") else Seq()) ++
+ (countType match {
+ case Some(t) => Seq("-C", t)
+ case _ => Seq()
+ }) ++
+ Seq("-I", input.getAbsolutePath, "-O", output.getAbsolutePath)
}
diff --git a/public/gentrap/src/test/scala/nl/lumc/sasc/biopet/pipelines/gentrap/GentrapTest.scala b/public/gentrap/src/test/scala/nl/lumc/sasc/biopet/pipelines/gentrap/GentrapTest.scala
index 321fea8ba5b815d4dd71bf6f7cbdb85e293a9a8f..b15b7bac8f4e3b3c8994c31fb7c56a31a4f23767 100644
--- a/public/gentrap/src/test/scala/nl/lumc/sasc/biopet/pipelines/gentrap/GentrapTest.scala
+++ b/public/gentrap/src/test/scala/nl/lumc/sasc/biopet/pipelines/gentrap/GentrapTest.scala
@@ -18,10 +18,9 @@ package nl.lumc.sasc.biopet.pipelines.gentrap
import java.io.{ File, FileOutputStream }
import com.google.common.io.Files
+import nl.lumc.sasc.biopet.extensions.tools.BaseCounter
import nl.lumc.sasc.biopet.utils.config.Config
import nl.lumc.sasc.biopet.extensions._
-import nl.lumc.sasc.biopet.extensions.gmap.Gsnap
-import nl.lumc.sasc.biopet.pipelines.gentrap.scripts.AggrBaseCount
import nl.lumc.sasc.biopet.utils.ConfigUtils
import org.apache.commons.io.FileUtils
import org.broadinstitute.gatk.queue.QSettings
@@ -72,7 +71,7 @@ abstract class GentrapTestAbstract(val expressionMeasure: String) extends TestNG
)
val validExpressionMeasures = Set(
- "fragments_per_gene", "fragments_per_exon", "bases_per_gene", "bases_per_exon",
+ "fragments_per_gene", "fragments_per_exon", "base_counts",
"cufflinks_strict", "cufflinks_guided", "cufflinks_blind")
@DataProvider(name = "expMeasuresstrandProtocol")
@@ -119,54 +118,28 @@ abstract class GentrapTestAbstract(val expressionMeasure: String) extends TestNG
val functions = gentrap.functions.groupBy(_.getClass)
val numSamples = sampleConfig("samples").size
- if (expMeasures.contains("fragments_per_gene")) {
- gentrap.functions
- .collect { case x: HtseqCount => x.output.toString.endsWith(".fragments_per_gene") }.size shouldBe numSamples
- }
+ if (expMeasures.contains("fragments_per_gene"))
+ assert(gentrap.functions.exists(_.isInstanceOf[HtseqCount]))
- if (expMeasures.contains("fragments_per_exon")) {
- gentrap.functions
- .collect { case x: HtseqCount => x.output.toString.endsWith(".fragments_per_exon") }.size shouldBe numSamples
- }
+ if (expMeasures.contains("fragments_per_exon"))
+ assert(gentrap.functions.exists(_.isInstanceOf[HtseqCount]))
- if (expMeasures.contains("bases_per_gene")) {
- gentrap.functions
- .collect { case x: AggrBaseCount => x.output.toString.endsWith(".bases_per_gene") }.size shouldBe numSamples
- }
-
- if (expMeasures.contains("bases_per_exon")) {
- gentrap.functions
- .collect { case x: AggrBaseCount => x.output.toString.endsWith(".bases_per_exon") }.size shouldBe numSamples
- }
+ if (expMeasures.contains("base_counts"))
+ gentrap.functions.count(_.isInstanceOf[BaseCounter]) shouldBe numSamples
if (expMeasures.contains("cufflinks_strict")) {
- gentrap.functions
- .collect {
- case x: Cufflinks => x.outputGenesFpkm.getParentFile.toString.endsWith("cufflinks_strict")
- case x: Ln => x.output.toString.endsWith(".genes_fpkm_cufflinks_strict") ||
- x.output.toString.endsWith(".isoforms_fpkm_cufflinks_strict")
- }
- .count(identity) shouldBe numSamples * 3 // three types of jobs per sample
+ assert(gentrap.functions.exists(_.isInstanceOf[Cufflinks]))
+ assert(gentrap.functions.exists(_.isInstanceOf[Ln]))
}
if (expMeasures.contains("cufflinks_guided")) {
- gentrap.functions
- .collect {
- case x: Cufflinks => x.outputGenesFpkm.getParentFile.toString.endsWith("cufflinks_guided")
- case x: Ln => x.output.toString.endsWith(".genes_fpkm_cufflinks_guided") ||
- x.output.toString.endsWith(".isoforms_fpkm_cufflinks_guided")
- }
- .count(identity) shouldBe numSamples * 3 // three types of jobs per sample
+ assert(gentrap.functions.exists(_.isInstanceOf[Cufflinks]))
+ assert(gentrap.functions.exists(_.isInstanceOf[Ln]))
}
if (expMeasures.contains("cufflinks_blind")) {
- gentrap.functions
- .collect {
- case x: Cufflinks => x.outputGenesFpkm.getParentFile.toString.endsWith("cufflinks_blind")
- case x: Ln => x.output.toString.endsWith(".genes_fpkm_cufflinks_blind") ||
- x.output.toString.endsWith(".isoforms_fpkm_cufflinks_blind")
- }
- .count(identity) shouldBe numSamples * 3 // three types of jobs per sample
+ assert(gentrap.functions.exists(_.isInstanceOf[Cufflinks]))
+ assert(gentrap.functions.exists(_.isInstanceOf[Ln]))
}
}
@@ -177,9 +150,8 @@ abstract class GentrapTestAbstract(val expressionMeasure: String) extends TestNG
}
class GentrapFragmentsPerGeneTest extends GentrapTestAbstract("fragments_per_gene")
-class GentrapFragmentsPerExonTest extends GentrapTestAbstract("fragments_per_exon")
-class GentrapBasesPerGeneTest extends GentrapTestAbstract("bases_per_gene")
-class GentrapBasesPerExonTest extends GentrapTestAbstract("bases_per_exon")
+//class GentrapFragmentsPerExonTest extends GentrapTestAbstract("fragments_per_exon")
+class GentrapBaseCountsTest extends GentrapTestAbstract("base_counts")
class GentrapCufflinksStrictTest extends GentrapTestAbstract("cufflinks_strict")
class GentrapCufflinksGuidedTest extends GentrapTestAbstract("cufflinks_guided")
class GentrapCufflinksBlindTest extends GentrapTestAbstract("cufflinks_blind")
diff --git a/public/mapping/src/main/resources/nl/lumc/sasc/biopet/pipelines/mapping/multisampleMappingFront.ssp b/public/mapping/src/main/resources/nl/lumc/sasc/biopet/pipelines/mapping/multisampleMappingFront.ssp
new file mode 100644
index 0000000000000000000000000000000000000000..a7027c4681c22f8119456fd445c5ddf83bb2366b
--- /dev/null
+++ b/public/mapping/src/main/resources/nl/lumc/sasc/biopet/pipelines/mapping/multisampleMappingFront.ssp
@@ -0,0 +1,36 @@
+#import(nl.lumc.sasc.biopet.utils.summary.Summary)
+#import(nl.lumc.sasc.biopet.core.report.ReportPage)
+<%@ var summary: Summary %>
+<%@ var rootPath: String %>
+
+<table class="table">
+<tbody>
+ <tr><th>Pipeline</th><td>Shiva</td></tr>
+ <tr><th>Version</th><td>${summary.getValue("meta", "pipeline_version")}</td></tr>
+ <tr><th>Last commit hash</th><td>${summary.getValue("meta", "last_commit_hash")}</td></tr>
+ <tr><th>Output directory</th><td>${summary.getValue("meta", "output_dir")}</td></tr>
+ <tr><th>Reference</th><td>${summary.getValue("shiva", "settings", "reference", "species")} - ${summary.getValue("shiva", "settings", "reference", "name")}</td></tr>
+ <tr><th>Number of samples</th><td>${summary.samples.size}</td></tr>
+</tbody>
+</table>
+<br/>
+<div class="row">
+ <div class="col-md-1"></div>
+ <div class="col-md-6">
+ <p>
+ In this web document you can find your <em>Shiva</em> pipeline report.
+ Different categories of data can be found in the left-side menu.
+ Statistics per sample and library can be accessed through the top-level menu.
+ Some statistics for target regions can be found in the regions tab.
+ Futhermore, you can view all versions of software tools used by selecting <em>Versions</em> from the top menu.
+ </p>
+
+ <p>
+ <small>Brought to you by <a href="https://sasc.lumc.nl" target="_blank"><abbr
+ title="Sequence Analysis Support Core">SASC</abbr></a> and <a
+ href="https://www.lumc.nl/org/klinische-genetica/" target="_blank"><abbr title="Clinical Genetics LUMC">KG</abbr></a>,
+ LUMC.
+ </small>
+ </p>
+ </div>
+</div>
\ No newline at end of file
diff --git a/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala b/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala
index 559c15ff35fbf1fdc9649db8cb3ed4ac166d9559..d37f8031b0f22bc06384b1d2febe7f7a58c49196 100644
--- a/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala
+++ b/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala
@@ -29,7 +29,7 @@ import nl.lumc.sasc.biopet.extensions._
import nl.lumc.sasc.biopet.pipelines.bammetrics.BamMetrics
import nl.lumc.sasc.biopet.pipelines.bamtobigwig.Bam2Wig
import nl.lumc.sasc.biopet.pipelines.flexiprep.Flexiprep
-import nl.lumc.sasc.biopet.pipelines.gears.Gears
+import nl.lumc.sasc.biopet.pipelines.gears.GearsSingle
import nl.lumc.sasc.biopet.pipelines.mapping.scripts.TophatRecondition
import nl.lumc.sasc.biopet.utils.config.Configurable
import org.broadinstitute.gatk.queue.QScript
@@ -107,7 +107,7 @@ class Mapping(val root: Configurable) extends QScript with SummaryQScript with S
)
/** File to add to the summary */
- def summaryFiles: Map[String, File] = Map("output_bamfile" -> finalBamFile, "input_R1" -> input_R1,
+ def summaryFiles: Map[String, File] = Map("output_bam" -> finalBamFile, "input_R1" -> input_R1,
"reference" -> referenceFasta()) ++
(if (input_R2.isDefined) Map("input_R2" -> input_R2.get) else Map())
@@ -262,13 +262,12 @@ class Mapping(val root: Configurable) extends QScript with SummaryQScript with S
outputFiles += ("finalBamFile" -> finalBamFile.getAbsoluteFile)
if (config("unmapped_to_gears", default = false).asBoolean) {
- val gears = new Gears(this)
+ val gears = new GearsSingle(this)
gears.bamFile = Some(finalBamFile)
+ gears.sampleId = sampleId
+ gears.libId = libId
gears.outputDir = new File(outputDir, "gears")
- gears.init()
- gears.biopetScript()
- addAll(gears.functions)
- addSummaryQScript(gears)
+ add(gears)
}
if (config("generate_wig", default = false).asBoolean)
diff --git a/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/MultisampleMappingReport.scala b/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/MultisampleMappingReport.scala
new file mode 100644
index 0000000000000000000000000000000000000000..d3c574e2462d7f0aed716b645876d30d5b256e03
--- /dev/null
+++ b/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/MultisampleMappingReport.scala
@@ -0,0 +1,117 @@
+package nl.lumc.sasc.biopet.pipelines.mapping
+
+import nl.lumc.sasc.biopet.core.report.{ ReportBuilderExtension, ReportSection, ReportPage, MultisampleReportBuilder }
+import nl.lumc.sasc.biopet.pipelines.bammetrics.BammetricsReport
+import nl.lumc.sasc.biopet.pipelines.flexiprep.FlexiprepReport
+import nl.lumc.sasc.biopet.utils.config.Configurable
+
+/**
+ * Created by pjvanthof on 11/01/16.
+ */
+class MultisampleMappingReport(val root: Configurable) extends ReportBuilderExtension {
+ def builder = MultisampleMappingReport
+}
+
+object MultisampleMappingReport extends MultisampleMappingReportTrait {
+ /** Name of the report */
+ def reportName = "Mapping Report"
+}
+
+trait MultisampleMappingReportTrait extends MultisampleReportBuilder {
+ /** Front section for the report */
+ def frontSection: ReportSection = ReportSection("/nl/lumc/sasc/biopet/pipelines/mapping/multisampleMappingFront.ssp")
+
+ def additionalSections: List[(String, ReportSection)] = Nil
+
+ def pipelineName = "multisamplemapping"
+
+ /** Root page for the carp report */
+ def indexPage = {
+
+ val wgsExecuted = summary.getSampleValues("bammetrics", "stats", "wgs").values.exists(_.isDefined)
+ val rnaExecuted = summary.getSampleValues("bammetrics", "stats", "rna").values.exists(_.isDefined)
+ val insertsizeExecuted = summary.getSampleValues("bammetrics", "stats", "CollectInsertSizeMetrics", "metrics").values.exists(_ != Some(None))
+ val flexiprepExecuted = summary.getLibraryValues("flexiprep")
+ .exists { case ((sample, lib), value) => value.isDefined }
+
+ ReportPage(
+ List("Samples" -> generateSamplesPage(pageArgs)) ++
+ Map("Reference" -> ReportPage(List(), List(
+ "Reference" -> ReportSection("/nl/lumc/sasc/biopet/core/report/reference.ssp", Map("pipeline" -> pipelineName))
+ ), Map()),
+ "Files" -> filesPage,
+ "Versions" -> ReportPage(List(), List("Executables" -> ReportSection("/nl/lumc/sasc/biopet/core/report/executables.ssp"
+ )), Map())
+ ),
+ List(
+ "Report" -> frontSection) ++
+ additionalSections ++
+ List("Alignment" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp",
+ Map("sampleLevel" -> true, "showPlot" -> true, "showTable" -> false)
+ )) ++
+ (if (insertsizeExecuted) List("Insert Size" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/insertSize.ssp",
+ Map("sampleLevel" -> true, "showPlot" -> true, "showTable" -> false)))
+ else Nil) ++
+ (if (wgsExecuted) List("Whole genome coverage" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/wgsHistogram.ssp",
+ Map("sampleLevel" -> true, "showPlot" -> true, "showTable" -> false)))
+ else Nil) ++
+ (if (rnaExecuted) List("Rna coverage" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/rnaHistogram.ssp",
+ Map("sampleLevel" -> true, "showPlot" -> true, "showTable" -> false)))
+ else Nil) ++
+ (if (flexiprepExecuted) List("QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp",
+ Map("showPlot" -> true, "showTable" -> false)),
+ "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp",
+ Map("showPlot" -> true, "showTable" -> false))
+ )
+ else Nil),
+ pageArgs
+ )
+ }
+
+ /** Files page, can be used general or at sample level */
+ def filesPage: ReportPage = {
+ val flexiprepExecuted = summary.getLibraryValues("flexiprep")
+ .exists { case ((sample, lib), value) => value.isDefined }
+
+ ReportPage(List(), (if (flexiprepExecuted) List(
+ "Input fastq files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepInputfiles.ssp"),
+ "After QC fastq files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepOutputfiles.ssp"))
+ else Nil) :::
+ List("Bam files per lib" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/mapping/outputBamfiles.ssp", Map("sampleLevel" -> false)),
+ "Preprocessed bam files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/mapping/outputBamfiles.ssp",
+ Map("pipelineName" -> pipelineName, "fileTag" -> "output_bam_preprocess"))), Map())
+ }
+
+ /** Single sample page */
+ def samplePage(sampleId: String, args: Map[String, Any]): ReportPage = {
+ val flexiprepExecuted = summary.getLibraryValues("flexiprep")
+ .exists { case ((sample, lib), value) => sample == sampleId && value.isDefined }
+
+ ReportPage(List(
+ "Libraries" -> generateLibraryPage(args),
+ "Alignment" -> BammetricsReport.bamMetricsPage(summary, Some(sampleId), None),
+ "Files" -> filesPage
+ ), List(
+ "Alignment" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp",
+ Map("showPlot" -> true)),
+ "Preprocessing" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp", Map("sampleLevel" -> true))) ++
+ (if (flexiprepExecuted) List("QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp"),
+ "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp")
+ )
+ else Nil), args)
+ }
+
+ /** Library page */
+ def libraryPage(sampleId: String, libId: String, args: Map[String, Any]): ReportPage = {
+ val flexiprepExecuted = summary.getValue(Some(sampleId), Some(libId), "flexiprep").isDefined
+
+ ReportPage(
+ ("Alignment" -> BammetricsReport.bamMetricsPage(summary, Some(sampleId), Some(libId))) ::
+ (if (flexiprepExecuted) List("QC" -> FlexiprepReport.flexiprepPage) else Nil),
+ "Alignment" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp") ::
+ (if (flexiprepExecuted) List("QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp"),
+ "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp"))
+ else Nil),
+ args)
+ }
+}
\ No newline at end of file
diff --git a/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/MultisampleMappingTrait.scala b/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/MultisampleMappingTrait.scala
index 22066304263f234d000f2111f061e78f4ed54cb5..270783b74db15304eb5a09d4d32b2332d5d55cd2 100644
--- a/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/MultisampleMappingTrait.scala
+++ b/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/MultisampleMappingTrait.scala
@@ -3,10 +3,13 @@ package nl.lumc.sasc.biopet.pipelines.mapping
import java.io.File
import htsjdk.samtools.SamReaderFactory
+import nl.lumc.sasc.biopet.core.report.ReportBuilderExtension
import nl.lumc.sasc.biopet.core.{ PipelineCommand, Reference, MultiSampleQScript }
import nl.lumc.sasc.biopet.extensions.Ln
import nl.lumc.sasc.biopet.extensions.picard.{ MarkDuplicates, MergeSamFiles, AddOrReplaceReadGroups, SamToFastq }
import nl.lumc.sasc.biopet.pipelines.bammetrics.BamMetrics
+import nl.lumc.sasc.biopet.pipelines.bamtobigwig.Bam2Wig
+import nl.lumc.sasc.biopet.pipelines.gears.GearsSingle
import nl.lumc.sasc.biopet.utils.Logging
import nl.lumc.sasc.biopet.utils.config.Configurable
import org.broadinstitute.gatk.queue.QScript
@@ -21,6 +24,7 @@ import scala.collection.JavaConversions._
trait MultisampleMappingTrait extends MultiSampleQScript
with Reference { qscript: QScript =>
+ /** With this method the merge strategy for libraries to samples is defined. This can be overriden to fix the merge strategy. */
def mergeStrategy: MergeStrategy.Value = {
val value: String = config("merge_strategy", default = "preprocessmarkduplicates")
MergeStrategy.values.find(_.toString.toLowerCase == value) match {
@@ -32,17 +36,29 @@ trait MultisampleMappingTrait extends MultiSampleQScript
def init(): Unit = {
}
+ /** Is there are jobs that needs to be added before the rest of the jobs this methods can be overriden, to let the sample jobs this work the super call should be done also */
def biopetScript(): Unit = {
addSamplesJobs()
addSummaryJobs()
}
+ /** This is de default multisample mapping report, this can be extended by other pipelines */
+ override def reportClass: Option[ReportBuilderExtension] = {
+ val report = new MultisampleMappingReport(this)
+ report.outputDir = new File(outputDir, "report")
+ report.summaryFile = summaryFile
+ Some(report)
+ }
+
+ /** In a default multisample mapping run there are no multsample jobs. This method can be overriden by other pipelines */
def addMultiSampleJobs(): Unit = {
// this code will be executed after all code of all samples is executed
}
+ /** By default only the reference is put in the summary, when extending pippeline specific files can be added */
def summaryFiles: Map[String, File] = Map("referenceFasta" -> referenceFasta())
+ /** By default only the reference is put in the summary, when extending pippeline specific settings can be added */
def summarySettings: Map[String, Any] = Map(
"reference" -> referenceSummary,
"merge_strategy" -> mergeStrategy.toString)
@@ -52,9 +68,11 @@ trait MultisampleMappingTrait extends MultiSampleQScript
def makeLibrary(id: String) = new Library(id)
class Library(libId: String) extends AbstractLibrary(libId) {
+
+ /** By default the bams files are put in the summary, more files can be added here */
def summaryFiles: Map[String, File] = (inputR1.map("input_R1" -> _) :: inputR2.map("input_R2" -> _) ::
inputBam.map("input_bam" -> _) :: bamFile.map("output_bam" -> _) ::
- preProcessBam.map("output_preProcessBam" -> _) :: Nil).flatten.toMap
+ preProcessBam.map("output_bam_preprocess" -> _) :: Nil).flatten.toMap
def summaryStats: Map[String, Any] = Map()
@@ -78,8 +96,10 @@ trait MultisampleMappingTrait extends MultiSampleQScript
case _ => None
}
+ /** By default the preProcessBam is the same as the normal bamFile. A pipeline can extend this is there are preprocess steps */
def preProcessBam = bamFile
+ /** This method can be extended to add jobs to the pipeline, to do this the super call of this function must be called by the pipelines */
def addJobs(): Unit = {
inputR1.foreach(inputFiles :+= new InputFile(_, config("R1_md5")))
inputR2.foreach(inputFiles :+= new InputFile(_, config("R2_md5")))
@@ -145,25 +165,32 @@ trait MultisampleMappingTrait extends MultiSampleQScript
bamMetrics.inputBam = bamFile.get
bamMetrics.outputDir = new File(libDir, "metrics")
add(bamMetrics)
+
+ if (config("execute_bam2wig", default = true)) add(Bam2Wig(qscript, bamFile.get))
}
} else logger.warn(s"Sample '$sampleId' does not have any input files")
}
}
+ /** By default the bams files are put in the summary, more files can be added here */
def summaryFiles: Map[String, File] = (bamFile.map("output_bam" -> _) ::
- preProcessBam.map("output_preProcessBam" -> _) :: Nil).flatten.toMap
+ preProcessBam.map("output_bam_preprocess" -> _) :: Nil).flatten.toMap
def summaryStats: Map[String, Any] = Map()
+ /** This is the merged bam file, None if the merged bam file is NA */
def bamFile = if (libraries.flatMap(_._2.bamFile).nonEmpty &&
mergeStrategy != MultisampleMapping.MergeStrategy.None)
Some(new File(sampleDir, s"$sampleId.bam"))
else None
+ /** By default the preProcessBam is the same as the normal bamFile. A pipeline can extend this is there are preprocess steps */
def preProcessBam = bamFile
+ /** Default is set to keep the merged files, user can set this in the config. To change the default this method can be overriden */
def keepMergedFiles: Boolean = config("keep_merged_files", default = true)
+ /** This method can be extended to add jobs to the pipeline, to do this the super call of this function must be called by the pipelines */
def addJobs(): Unit = {
addPerLibJobs() // This add jobs for each library
@@ -174,13 +201,13 @@ trait MultisampleMappingTrait extends MultiSampleQScript
case (MergeStrategy.PreProcessMergeSam | MergeStrategy.PreProcessMarkDuplicates) if libraries.flatMap(_._2.preProcessBam).size == 1 =>
add(Ln.linkBamFile(qscript, libraries.flatMap(_._2.preProcessBam).head, bamFile.get): _*)
case MergeStrategy.MergeSam =>
- add(MergeSamFiles(qscript, libraries.flatMap(_._2.bamFile).toList, bamFile.get, isIntermediate = keepMergedFiles))
+ add(MergeSamFiles(qscript, libraries.flatMap(_._2.bamFile).toList, bamFile.get, isIntermediate = !keepMergedFiles))
case MergeStrategy.PreProcessMergeSam =>
- add(MergeSamFiles(qscript, libraries.flatMap(_._2.preProcessBam).toList, bamFile.get, isIntermediate = keepMergedFiles))
+ add(MergeSamFiles(qscript, libraries.flatMap(_._2.preProcessBam).toList, bamFile.get, isIntermediate = !keepMergedFiles))
case MergeStrategy.MarkDuplicates =>
- add(MarkDuplicates(qscript, libraries.flatMap(_._2.bamFile).toList, bamFile.get, isIntermediate = keepMergedFiles))
+ add(MarkDuplicates(qscript, libraries.flatMap(_._2.bamFile).toList, bamFile.get, isIntermediate = !keepMergedFiles))
case MergeStrategy.PreProcessMarkDuplicates =>
- add(MarkDuplicates(qscript, libraries.flatMap(_._2.preProcessBam).toList, bamFile.get, isIntermediate = keepMergedFiles))
+ add(MarkDuplicates(qscript, libraries.flatMap(_._2.preProcessBam).toList, bamFile.get, isIntermediate = !keepMergedFiles))
case _ => throw new IllegalStateException("This should not be possible, unimplemented MergeStrategy?")
}
@@ -190,11 +217,22 @@ trait MultisampleMappingTrait extends MultiSampleQScript
bamMetrics.inputBam = preProcessBam.get
bamMetrics.outputDir = new File(sampleDir, "metrics")
add(bamMetrics)
+
+ if (config("execute_bam2wig", default = true)) add(Bam2Wig(qscript, preProcessBam.get))
+ }
+
+ if (config("unmapped_to_gears", default = false) && libraries.flatMap(_._2.bamFile).nonEmpty) {
+ val gears = new GearsSingle(qscript)
+ gears.bamFile = preProcessBam
+ gears.sampleId = Some(sampleId)
+ gears.outputDir = new File(sampleDir, "gears")
+ add(gears)
}
}
}
}
+/** This class is the default implementation that can be used on the command line */
class MultisampleMapping(val root: Configurable) extends QScript with MultisampleMappingTrait {
def this() = this(null)
@@ -207,6 +245,7 @@ object MultisampleMapping extends PipelineCommand {
val None, MergeSam, MarkDuplicates, PreProcessMergeSam, PreProcessMarkDuplicates = Value
}
+ /** When file is not absolute an error is raise att the end of the script of a pipeline */
def fileMustBeAbsolute(file: Option[File]): Option[File] = {
if (file.forall(_.isAbsolute)) file
else {
diff --git a/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaReport.scala b/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaReport.scala
index 5c88189833b1b6bd169c3da475c6c2370957abf9..890257549c5ac09a8ae5254d85ec8ed6fcb1fb48 100644
--- a/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaReport.scala
+++ b/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaReport.scala
@@ -17,12 +17,11 @@ package nl.lumc.sasc.biopet.pipelines.shiva
import java.io.{ File, PrintWriter }
-import nl.lumc.sasc.biopet.utils.config.Configurable
import nl.lumc.sasc.biopet.core.report._
-import nl.lumc.sasc.biopet.utils.summary.{ Summary, SummaryValue }
+import nl.lumc.sasc.biopet.pipelines.mapping.MultisampleMappingReportTrait
+import nl.lumc.sasc.biopet.utils.config.Configurable
import nl.lumc.sasc.biopet.utils.rscript.StackedBarPlot
-import nl.lumc.sasc.biopet.pipelines.bammetrics.BammetricsReport
-import nl.lumc.sasc.biopet.pipelines.flexiprep.FlexiprepReport
+import nl.lumc.sasc.biopet.utils.summary.{ Summary, SummaryValue }
/**
* With this extension the report is executed within a pipeline
@@ -34,52 +33,32 @@ class ShivaReport(val root: Configurable) extends ReportBuilderExtension {
}
/** Object for report generation for Shiva pipeline */
-object ShivaReport extends MultisampleReportBuilder {
+object ShivaReport extends MultisampleMappingReportTrait {
def variantcallingExecuted = summary.getValue("shiva", "settings", "multisample_variantcalling") match {
case Some(true) => true
case _ => false
}
+ override def frontSection = ReportSection("/nl/lumc/sasc/biopet/pipelines/shiva/shivaFront.ssp")
+
+ override def pipelineName = "shiva"
+
override def extFiles = super.extFiles ++ List("js/gears.js")
.map(x => ExtFile("/nl/lumc/sasc/biopet/pipelines/gears/report/ext/" + x, x))
+ override def additionalSections = super.additionalSections ++ (if (variantcallingExecuted) List("Variantcalling" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/shiva/sampleVariants.ssp",
+ Map("showPlot" -> true, "showTable" -> false)))
+ else Nil)
+
/** Root page for the shiva report */
- def indexPage = {
+ override def indexPage = {
val regions = regionsPage
- ReportPage(
- List("Samples" -> generateSamplesPage(pageArgs)) ++
- (if (regions.isDefined) Map(regions.get) else Map()) ++
- Map("Reference" -> ReportPage(List(), List(
- "Reference" -> ReportSection("/nl/lumc/sasc/biopet/core/report/reference.ssp", Map("pipeline" -> "shiva"))
- ), Map()),
- "Files" -> filesPage,
- "Versions" -> ReportPage(List(), List(
- "Executables" -> ReportSection("/nl/lumc/sasc/biopet/core/report/executables.ssp")
- ), Map())
- ),
- List(
- "Report" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/shiva/shivaFront.ssp")) ++
- (if (variantcallingExecuted) List("Variantcalling" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/shiva/sampleVariants.ssp",
- Map("showPlot" -> true, "showTable" -> false)))
- else Nil) ++
- List("Alignment" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp",
- Map("sampleLevel" -> true, "showPlot" -> true, "showTable" -> false)
- ),
- "Insert Size" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/insertSize.ssp",
- Map("sampleLevel" -> true, "showPlot" -> true, "showTable" -> false)),
- "Whole genome coverage" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/wgsHistogram.ssp",
- Map("sampleLevel" -> true, "showPlot" -> true, "showTable" -> false)),
- "QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp",
- Map("showPlot" -> true, "showTable" -> false)),
- "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp",
- Map("showPlot" -> true, "showTable" -> false))
- ),
- pageArgs
- )
+ val oldPage = super.indexPage
+
+ oldPage.copy(subPages = oldPage.subPages ++ regionsPage)
}
- //TODO: Add variants per target
/** Generate a page with all target coverage stats */
def regionsPage: Option[(String, ReportPage)] = {
val roi = summary.getValue("shiva", "settings", "regions_of_interest")
@@ -121,49 +100,19 @@ object ShivaReport extends MultisampleReportBuilder {
}
/** Files page, can be used general or at sample level */
- def filesPage: ReportPage = ReportPage(List(), List(
- "Input fastq files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepInputfiles.ssp"),
- "After QC fastq files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepOutputfiles.ssp"),
- "Bam files per lib" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/mapping/outputBamfiles.ssp", Map("sampleLevel" -> false)),
- "Preprocessed bam files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/mapping/outputBamfiles.ssp",
- Map("pipelineName" -> "shiva", "fileTag" -> "preProcessBam"))) ++
- (if (variantcallingExecuted) List("VCF files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/shiva/outputVcfFiles.ssp",
+ override def filesPage: ReportPage = {
+ val vcfFilesSection = if (variantcallingExecuted) List("VCF files" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/shiva/outputVcfFiles.ssp",
Map("sampleId" -> None)))
- else Nil), Map())
-
- /** Single sample page */
- def samplePage(sampleId: String, args: Map[String, Any]): ReportPage = {
- ReportPage(List(
- "Libraries" -> generateLibraryPage(args),
- "Alignment" -> BammetricsReport.bamMetricsPage(summary, Some(sampleId), None),
- "Files" -> filesPage
- ), List(
- "Alignment" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp",
- if (summary.libraries(sampleId).size > 1) Map("showPlot" -> true) else Map()),
- "Preprocessing" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp", Map("sampleLevel" -> true))) ++
- (if (variantcallingExecuted) List("Variantcalling" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/shiva/sampleVariants.ssp")) else Nil) ++
- List("QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp"),
- "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp")
- ), args)
+ else Nil
+ val oldPage = super.filesPage
+ oldPage.copy(sections = oldPage.sections ++ vcfFilesSection)
}
- /** Library page */
- def libraryPage(sampleId: String, libId: String, args: Map[String, Any]): ReportPage = {
- val flexiprepExecuted = summary.getLibraryValue(sampleId, libId, "flexiprep").isDefined
- val krakenExecuted = summary.getValue(Some(sampleId), Some(libId), "gears", "stats", "krakenreport").isDefined
-
- ReportPage(
- "Alignment" -> BammetricsReport.bamMetricsPage(summary, Some(sampleId), Some(libId)) ::
- (if (flexiprepExecuted) List("QC" -> FlexiprepReport.flexiprepPage) else Nil
- ) ::: (if (krakenExecuted) List("Gears - Metagenomics" -> ReportPage(List(), List(
- "Sunburst analysis" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gears/gearsSunburst.ssp"
- )), Map()))
- else Nil), "Alignment" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/bammetrics/alignmentSummary.ssp") ::
- (if (flexiprepExecuted) List(
- "QC reads" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepReadSummary.ssp"),
- "QC bases" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/flexiprep/flexiprepBaseSummary.ssp")
- )
- else Nil), args)
+ /** Single sample page */
+ override def samplePage(sampleId: String, args: Map[String, Any]): ReportPage = {
+ val variantcallingSection = if (variantcallingExecuted) List("Variantcalling" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/shiva/sampleVariants.ssp")) else Nil
+ val oldPage = super.samplePage(sampleId, args)
+ oldPage.copy(sections = variantcallingSection ++ oldPage.sections)
}
/** Name of the report */
diff --git a/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaSvCalling.scala b/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaSvCalling.scala
index 27b43c37057cc9e6596df33abc037e6d70e1169e..42000d42aa4745e1892c0c94df234f1209ea9cd7 100644
--- a/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaSvCalling.scala
+++ b/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaSvCalling.scala
@@ -34,7 +34,7 @@ class ShivaSvCalling(val root: Configurable) extends QScript with SummaryQScript
def this() = this(null)
@Input(doc = "Bam files (should be deduped bams)", shortName = "BAM", required = true)
- protected var inputBamsArg: List[File] = Nil
+ protected[shiva] var inputBamsArg: List[File] = Nil
var inputBams: Map[String, File] = Map()
@@ -59,6 +59,7 @@ class ShivaSvCalling(val root: Configurable) extends QScript with SummaryQScript
require(callers.nonEmpty, "must select at least 1 SV caller, choices are: " + callersList.map(_.name).mkString(", "))
callers.foreach { caller =>
+ caller.inputBams = inputBams
caller.outputDir = new File(outputDir, caller.name)
add(caller)
}
diff --git a/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaTrait.scala b/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaTrait.scala
index 58a4710cad1019ed79dba8a46a1c06053d14e436..f0fe2c1291d647815f8d336902fbd944f6312f3f 100644
--- a/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaTrait.scala
+++ b/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaTrait.scala
@@ -16,8 +16,9 @@
package nl.lumc.sasc.biopet.pipelines.shiva
import nl.lumc.sasc.biopet.core.Reference
+import nl.lumc.sasc.biopet.core.report.ReportBuilderExtension
import nl.lumc.sasc.biopet.pipelines.bammetrics.TargetRegions
-import nl.lumc.sasc.biopet.pipelines.mapping.{ MultisampleMappingTrait }
+import nl.lumc.sasc.biopet.pipelines.mapping.MultisampleMappingTrait
import nl.lumc.sasc.biopet.pipelines.toucan.Toucan
import org.broadinstitute.gatk.queue.QScript
@@ -28,7 +29,7 @@ import org.broadinstitute.gatk.queue.QScript
*/
trait ShivaTrait extends MultisampleMappingTrait with Reference with TargetRegions { qscript: QScript =>
- override def reportClass = {
+ override def reportClass: Option[ReportBuilderExtension] = {
val shiva = new ShivaReport(this)
shiva.outputDir = new File(outputDir, "report")
shiva.summaryFile = summaryFile
diff --git a/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTrait.scala b/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTrait.scala
index 31ba0a53f0fc034b406cca237656722ca9de9d6f..f08b4cc18402e995375f14f1095e922883b8dc98 100644
--- a/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTrait.scala
+++ b/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTrait.scala
@@ -156,7 +156,12 @@ trait ShivaVariantcallingTrait extends SummaryQScript
}
/** Will generate all available variantcallers */
- protected def callersList: List[Variantcaller] = List(new Freebayes(this), new RawVcf(this), new Bcftools(this), new BcftoolsSingleSample(this))
+ protected def callersList: List[Variantcaller] = List(
+ new Freebayes(this),
+ new RawVcf(this),
+ new Bcftools(this),
+ new BcftoolsSingleSample(this),
+ new VarscanCnsSingleSample(this))
/** Location of summary file */
def summaryFile = new File(outputDir, "ShivaVariantcalling.summary.json")
diff --git a/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/svcallers/Delly.scala b/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/svcallers/Delly.scala
index 14a9b9b50d6309cd68873bbb8dfddd7726513cfc..3ae0ab968f1510d7cb18b6d42cc7e4d80dd15488 100644
--- a/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/svcallers/Delly.scala
+++ b/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/svcallers/Delly.scala
@@ -53,6 +53,8 @@ class Delly(val root: Configurable) extends SvCaller {
add(delly)
}
+ require(catVariants.inputFiles.nonEmpty, "Must atleast 1 SV-type be selected for Delly")
+
add(catVariants)
addVCF(sample, catVariants.outputFile)
}
diff --git a/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/VarscanCnsSingleSample.scala b/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/VarscanCnsSingleSample.scala
new file mode 100644
index 0000000000000000000000000000000000000000..157013e5bbd0f22c8d74bf04355872f4bdb6cfaa
--- /dev/null
+++ b/public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/VarscanCnsSingleSample.scala
@@ -0,0 +1,61 @@
+package nl.lumc.sasc.biopet.pipelines.shiva.variantcallers
+
+import java.io.PrintWriter
+
+import nl.lumc.sasc.biopet.extensions.gatk.CombineVariants
+import nl.lumc.sasc.biopet.extensions.samtools.SamtoolsMpileup
+import nl.lumc.sasc.biopet.extensions.varscan.{ FixMpileup, VarscanMpileup2cns }
+import nl.lumc.sasc.biopet.extensions.{ Bgzip, Tabix }
+import nl.lumc.sasc.biopet.utils.config.Configurable
+
+/**
+ * Created by sajvanderzeeuw on 15-1-16.
+ */
+class VarscanCnsSingleSample(val root: Configurable) extends Variantcaller {
+ val name = "varscan_cns_singlesample"
+ protected def defaultPrio = 25
+
+ override def defaults = Map(
+ "samtoolsmpileup" -> Map(
+ "disable_baq" -> true,
+ "depth" -> 1000000
+ ),
+ "varscanmpileup2cns" -> Map("strand_filter" -> 0)
+ )
+
+ override def fixedValues = Map(
+ "samtoolsmpileup" -> Map("output_mapping_quality" -> true),
+ "varscanmpileup2cns" -> Map("output_vcf" -> 1)
+ )
+
+ def biopetScript: Unit = {
+ val sampleVcfs = for ((sample, inputBam) <- inputBams.toList) yield {
+ val mpileup = new SamtoolsMpileup(this)
+ mpileup.input = List(inputBam)
+
+ val sampleVcf = new File(outputDir, s"${name}_$sample.vcf.gz")
+
+ val sampleFile = new File(outputDir, s"$sample.name.txt")
+ sampleFile.getParentFile.mkdirs()
+ sampleFile.deleteOnExit()
+ val writer = new PrintWriter(sampleFile)
+ writer.println(sample)
+ writer.close()
+
+ val varscan = new VarscanMpileup2cns(this)
+ varscan.vcfSampleList = Some(sampleFile)
+
+ add(mpileup | new FixMpileup(this) | varscan | new Bgzip(this) > sampleVcf)
+ add(Tabix(this, sampleVcf))
+
+ sampleVcf
+ }
+
+ val cv = new CombineVariants(this)
+ cv.inputFiles = sampleVcfs
+ cv.outputFile = outputFile
+ cv.setKey = "null"
+ cv.excludeNonVariants = true
+ add(cv)
+ }
+}
diff --git a/public/shiva/src/test/resources/paired01.bam b/public/shiva/src/test/resources/paired01.bam
new file mode 100644
index 0000000000000000000000000000000000000000..5d70b4512cb0f8ab620cd6d64c0efd9016432715
Binary files /dev/null and b/public/shiva/src/test/resources/paired01.bam differ
diff --git a/public/shiva/src/test/resources/paired01.bam.bai b/public/shiva/src/test/resources/paired01.bam.bai
new file mode 100644
index 0000000000000000000000000000000000000000..a64a2d9734ce39938b3408e8be3bb580f05374fa
Binary files /dev/null and b/public/shiva/src/test/resources/paired01.bam.bai differ
diff --git a/public/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaScCallingTest.scala b/public/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaScCallingTest.scala
new file mode 100644
index 0000000000000000000000000000000000000000..8c0b6c24a463c5175a23ee1e2561c40b92c50f19
--- /dev/null
+++ b/public/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaScCallingTest.scala
@@ -0,0 +1,215 @@
+/**
+ * Biopet is built on top of GATK Queue for building bioinformatic
+ * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
+ * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
+ * should also be able to execute Biopet tools and pipelines.
+ *
+ * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
+ *
+ * Contact us at: sasc@lumc.nl
+ *
+ * A dual licensing mode is applied. The source code within this project that are
+ * not part of GATK Queue is freely available for non-commercial use under an AGPL
+ * license; For commercial users or users who do not want to follow the AGPL
+ * license, please contact us to obtain a separate license.
+ */
+package nl.lumc.sasc.biopet.pipelines.shiva
+
+import java.io.{ File, FileOutputStream }
+import java.nio.file.Paths
+
+import com.google.common.io.Files
+import nl.lumc.sasc.biopet.extensions.breakdancer.{ BreakdancerVCF, BreakdancerConfig, BreakdancerCaller }
+import nl.lumc.sasc.biopet.extensions.clever.CleverCaller
+import nl.lumc.sasc.biopet.extensions.delly.DellyCaller
+import nl.lumc.sasc.biopet.utils.config.Config
+import nl.lumc.sasc.biopet.extensions.Freebayes
+import nl.lumc.sasc.biopet.extensions.gatk.CombineVariants
+import nl.lumc.sasc.biopet.extensions.tools.VcfFilter
+import nl.lumc.sasc.biopet.utils.ConfigUtils
+import org.apache.commons.io.FileUtils
+import org.broadinstitute.gatk.queue.QSettings
+import org.scalatest.Matchers
+import org.scalatest.testng.TestNGSuite
+import org.testng.annotations.{ AfterClass, DataProvider, Test }
+
+import scala.collection.mutable.ListBuffer
+
+/**
+ * Test class for [[ShivaVariantcalling]]
+ *
+ * Created by pjvan_thof on 3/2/15.
+ */
+class ShivaSvCallingTest extends TestNGSuite with Matchers {
+ def initPipeline(map: Map[String, Any]): ShivaSvCalling = {
+ new ShivaSvCalling {
+ override def configName = "shivasvcalling"
+ override def globalConfig = new Config(ConfigUtils.mergeMaps(map, ShivaSvCallingTest.config))
+ qSettings = new QSettings
+ qSettings.runName = "test"
+ }
+ }
+
+ @DataProvider(name = "shivaSvCallingOptions")
+ def shivaSvCallingOptions = {
+ val bool = Array(true, false)
+ (for (
+ bams <- 0 to 3;
+ delly <- bool;
+ clever <- bool;
+ breakdancer <- bool
+ ) yield Array(bams, delly, clever, breakdancer)).toArray
+ }
+
+ @Test(dataProvider = "shivaSvCallingOptions")
+ def testShivaSvCalling(bams: Int,
+ delly: Boolean,
+ clever: Boolean,
+ breakdancer: Boolean) = {
+ val callers: ListBuffer[String] = ListBuffer()
+ if (delly) callers.append("delly")
+ if (clever) callers.append("clever")
+ if (breakdancer) callers.append("breakdancer")
+ val map = Map("sv_callers" -> callers.toList)
+ val pipeline = initPipeline(map)
+
+ pipeline.inputBams = (for (n <- 1 to bams) yield n.toString -> ShivaSvCallingTest.inputTouch("bam_" + n + ".bam")).toMap
+
+ val illegalArgumentException = pipeline.inputBams.isEmpty || (!delly && !clever && !breakdancer)
+
+ if (illegalArgumentException) intercept[IllegalArgumentException] {
+ pipeline.init()
+ pipeline.script()
+ }
+
+ if (!illegalArgumentException) {
+ pipeline.init()
+ pipeline.script()
+
+ val summaryCallers = pipeline.summarySettings("sv_callers")
+ if (delly) assert(summaryCallers.contains("delly"))
+ else assert(!summaryCallers.contains("delly"))
+ if (clever) assert(summaryCallers.contains("clever"))
+ else assert(!summaryCallers.contains("clever"))
+ if (breakdancer) assert(summaryCallers.contains("breakdancer"))
+ else assert(!summaryCallers.contains("breakdancer"))
+
+ pipeline.functions.count(_.isInstanceOf[BreakdancerCaller]) shouldBe (if (breakdancer) bams else 0)
+ pipeline.functions.count(_.isInstanceOf[BreakdancerConfig]) shouldBe (if (breakdancer) bams else 0)
+ pipeline.functions.count(_.isInstanceOf[BreakdancerVCF]) shouldBe (if (breakdancer) bams else 0)
+ pipeline.functions.count(_.isInstanceOf[CleverCaller]) shouldBe (if (clever) bams else 0)
+ pipeline.functions.count(_.isInstanceOf[DellyCaller]) shouldBe (if (delly) (bams * 4) else 0)
+
+ }
+ }
+
+ @DataProvider(name = "dellyOptions")
+ def dellyOptions = {
+ val bool = Array(true, false)
+ (for (
+ del <- bool;
+ dup <- bool;
+ inv <- bool;
+ tra <- bool
+ ) yield Array(1, del, dup, inv, tra)).toArray
+ }
+
+ @Test(dataProvider = "dellyOptions")
+ def testShivaDelly(bams: Int, del: Boolean, dup: Boolean, inv: Boolean, tra: Boolean): Unit = {
+
+ val map = Map("sv_callers" -> List("delly"), "delly" ->
+ Map("DEL" -> del, "DUP" -> dup, "INV" -> inv, "TRA" -> tra)
+ )
+ val pipeline = initPipeline(map)
+
+ pipeline.inputBams = Map("bam" -> ShivaVariantcallingTest.inputTouch("bam" + ".bam"))
+
+ if (!del && !dup && !inv && !tra) intercept[IllegalArgumentException] {
+ pipeline.init()
+ pipeline.script()
+ }
+ else {
+ pipeline.init()
+ pipeline.script()
+
+ pipeline.functions.count(_.isInstanceOf[DellyCaller]) shouldBe
+ ((if (del) 1 else 0) + (if (dup) 1 else 0) + (if (inv) 1 else 0) + (if (tra) 1 else 0))
+ }
+ }
+
+ @Test
+ def testWrongCaller(): Unit = {
+ val map = Map("sv_callers" -> List("this is not a caller"))
+ val pipeline = initPipeline(map)
+
+ pipeline.inputBams = Map("bam" -> ShivaVariantcallingTest.inputTouch("bam" + ".bam"))
+
+ intercept[IllegalArgumentException] {
+ pipeline.init()
+ pipeline.script()
+ }
+ }
+
+ private def resourcePath(p: String): String = {
+ Paths.get(getClass.getResource(p).toURI).toString
+ }
+
+ @Test
+ def testInputBamsArg(): Unit = {
+ val pipeline = initPipeline(Map())
+
+ pipeline.inputBamsArg :+= new File(resourcePath("/paired01.bam"))
+
+ pipeline.init()
+ pipeline.script()
+
+ val summaryCallers = pipeline.summarySettings("sv_callers")
+ assert(summaryCallers.contains("delly"))
+ assert(summaryCallers.contains("clever"))
+ assert(summaryCallers.contains("breakdancer"))
+ }
+
+ @AfterClass def removeTempOutputDir() = {
+ FileUtils.deleteDirectory(ShivaSvCallingTest.outputDir)
+ }
+}
+
+object ShivaSvCallingTest {
+ val outputDir = Files.createTempDir()
+ new File(outputDir, "input").mkdirs()
+ def inputTouch(name: String): File = {
+ val file = new File(outputDir, "input" + File.separator + name).getAbsoluteFile
+ Files.touch(file)
+ file
+ }
+
+ private def copyFile(name: String): Unit = {
+ val is = getClass.getResourceAsStream("/" + name)
+ val os = new FileOutputStream(new File(outputDir, name))
+ org.apache.commons.io.IOUtils.copy(is, os)
+ os.close()
+ }
+
+ copyFile("ref.fa")
+ copyFile("ref.dict")
+ copyFile("ref.fa.fai")
+
+ val config = Map(
+ "name_prefix" -> "test",
+ "output_dir" -> outputDir,
+ "cache" -> true,
+ "dir" -> "test",
+ "vep_script" -> "test",
+ "reference_fasta" -> (outputDir + File.separator + "ref.fa"),
+ "gatk_jar" -> "test",
+ "samtools" -> Map("exe" -> "test"),
+ "md5sum" -> Map("exe" -> "test"),
+ "bgzip" -> Map("exe" -> "test"),
+ "tabix" -> Map("exe" -> "test"),
+ "breakdancerconfig" -> Map("exe" -> "test"),
+ "breakdancercaller" -> Map("exe" -> "test"),
+ "clever" -> Map("exe" -> "test"),
+ "delly" -> Map("exe" -> "test"),
+ "varscan_jar" -> "test"
+ )
+}
\ No newline at end of file
diff --git a/public/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTest.scala b/public/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTest.scala
index 94edda97a3e893ab8bba6d4016f003c2b0242b57..976bf16583984cfc718b3f8c59de5a809b449088 100644
--- a/public/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTest.scala
+++ b/public/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTest.scala
@@ -53,37 +53,42 @@ class ShivaVariantcallingTest extends TestNGSuite with Matchers {
bams <- 0 to 3;
raw <- bool;
bcftools <- bool;
- bcftools_singlesample <- bool;
- freebayes <- bool
- ) yield Array(bams, raw, bcftools, bcftools_singlesample, freebayes)).toArray
+ bcftoolsSinglesample <- bool;
+ freebayes <- bool;
+ varscanCnsSinglesample <- bool
+ ) yield Array(bams, raw, bcftools, bcftoolsSinglesample, freebayes, varscanCnsSinglesample)).toArray
}
@Test(dataProvider = "shivaVariantcallingOptions")
def testShivaVariantcalling(bams: Int,
raw: Boolean,
bcftools: Boolean,
- bcftools_singlesample: Boolean,
- freebayes: Boolean) = {
+ bcftoolsSinglesample: Boolean,
+ freebayes: Boolean,
+ varscanCnsSinglesample: Boolean) = {
val callers: ListBuffer[String] = ListBuffer()
if (raw) callers.append("raw")
if (bcftools) callers.append("bcftools")
- if (bcftools_singlesample) callers.append("bcftools_singlesample")
+ if (bcftoolsSinglesample) callers.append("bcftools_singlesample")
if (freebayes) callers.append("freebayes")
+ if (varscanCnsSinglesample) callers.append("varscan_cns_singlesample")
val map = Map("variantcallers" -> callers.toList)
val pipeline = initPipeline(map)
pipeline.inputBams = (for (n <- 1 to bams) yield n.toString -> ShivaVariantcallingTest.inputTouch("bam_" + n + ".bam")).toMap
- val illegalArgumentException = pipeline.inputBams.isEmpty || (!raw && !bcftools && !bcftools_singlesample && !freebayes)
+ val illegalArgumentException = pipeline.inputBams.isEmpty || (!raw && !bcftools && !bcftoolsSinglesample && !freebayes && !varscanCnsSinglesample)
if (illegalArgumentException) intercept[IllegalArgumentException] {
+ pipeline.init()
pipeline.script()
}
if (!illegalArgumentException) {
+ pipeline.init()
pipeline.script()
- pipeline.functions.count(_.isInstanceOf[CombineVariants]) shouldBe 1 + (if (raw) 1 else 0)
+ pipeline.functions.count(_.isInstanceOf[CombineVariants]) shouldBe (1 + (if (raw) 1 else 0) + (if (varscanCnsSinglesample) 1 else 0))
//pipeline.functions.count(_.isInstanceOf[Bcftools]) shouldBe (if (bcftools) 1 else 0)
//FIXME: Can not check for bcftools because of piping
pipeline.functions.count(_.isInstanceOf[Freebayes]) shouldBe (if (freebayes) 1 else 0)
@@ -130,6 +135,7 @@ object ShivaVariantcallingTest {
"freebayes" -> Map("exe" -> "test"),
"md5sum" -> Map("exe" -> "test"),
"bgzip" -> Map("exe" -> "test"),
- "tabix" -> Map("exe" -> "test")
+ "tabix" -> Map("exe" -> "test"),
+ "varscan_jar" -> "test"
)
}
\ No newline at end of file
diff --git a/public/toucan/src/main/scala/nl/lumc/sasc/biopet/pipelines/toucan/Toucan.scala b/public/toucan/src/main/scala/nl/lumc/sasc/biopet/pipelines/toucan/Toucan.scala
index 763f7e9adaa8578551de713c728118063fba747c..7464366e69387664569796b1b523191abec7bb80 100644
--- a/public/toucan/src/main/scala/nl/lumc/sasc/biopet/pipelines/toucan/Toucan.scala
+++ b/public/toucan/src/main/scala/nl/lumc/sasc/biopet/pipelines/toucan/Toucan.scala
@@ -37,7 +37,7 @@ class Toucan(val root: Configurable) extends QScript with BiopetQScript with Sum
@Input(doc = "Input VCF file", shortName = "Input", required = true)
var inputVCF: File = _
- @Input(doc = "Input GVCF file", shortName = "Input", required = false)
+ @Input(doc = "Input GVCF file", shortName = "gvcf", required = false)
var inputGvcf: Option[File] = None
var sampleIds: List[String] = Nil