Fix tinycap dir

tinycap/.gitignore

+target
\ No newline at end of file

tinycap/pom.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+
+    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.
+
+-->
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <parent>
+        <artifactId>Biopet</artifactId>
+        <groupId>nl.lumc.sasc</groupId>
+        <version>0.7.0-SNAPSHOT</version>
+    </parent>
+    <modelVersion>4.0.0</modelVersion>
+
+    <inceptionYear>2016</inceptionYear>
+    <artifactId>TinyCap</artifactId>
+
+    <dependencies>
+        <dependency>
+            <groupId>nl.lumc.sasc</groupId>
+            <artifactId>Mapping</artifactId>
+            <version>${project.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>nl.lumc.sasc</groupId>
+            <artifactId>Gentrap</artifactId>
+            <version>${project.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.testng</groupId>
+            <artifactId>testng</artifactId>
+            <version>6.8</version>
+            <scope>test</scope>
+        </dependency>
+        <dependency>
+            <groupId>org.scalatest</groupId>
+            <artifactId>scalatest_2.10</artifactId>
+            <version>2.2.1</version>
+            <scope>test</scope>
+        </dependency>
+    </dependencies>
+
+</project>
\ No newline at end of file

tinycap/src/main/resources/nl/lumc/sasc/biopet/pipelines/tinycap/tinycapFront.ssp

+#import(nl.lumc.sasc.biopet.utils.summary.Summary)
+#import(nl.lumc.sasc.biopet.core.report.ReportPage)
+<%@ var summary: Summary %>
+<%@ var rootPath: String %>
+<%@ var pipeline: String %>
+
+<table class="table">
+<tbody>
+    <tr><th>Pipeline</th><td>${pipeline}</td></tr>
+    <tr><th>Version</th><td>${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(pipeline, "settings", "reference", "species")} - ${summary.getValue(pipeline, "settings", "reference", "name")}</td></tr>
+    <tr><th>Number of samples</th><td>${summary.samples.size}</td></tr>
+</tbody>
+</table>
+<br/>
+<div class="row">
+    <div class="col-md-1"></div>
+    <div class="col-md-10">
+    <p>
+        In this web document you can find your <em><strong>${pipeline}</strong></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.
+        Futhermore, you can view all versions of software tools used by selecting <em><a href="./Versions/index.html">Versions</a></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 class="col-md-1"></div>
+</div>
\ No newline at end of file

tinycap/src/main/scala/nl/lumc/sasc/biopet/pipelines/tinycap/TinyCap.scala

+/**
+ * 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.tinycap
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.annotations.{ AnnotationGff, AnnotationGtf, AnnotationRefFlat }
+import nl.lumc.sasc.biopet.core.report.ReportBuilderExtension
+import nl.lumc.sasc.biopet.core.{ PipelineCommand, Reference }
+import nl.lumc.sasc.biopet.pipelines.gentrap.measures.{ BaseCounts, FragmentsPerGene }
+import nl.lumc.sasc.biopet.pipelines.mapping.MultisampleMappingTrait
+import nl.lumc.sasc.biopet.pipelines.tinycap.measures.FragmentsPerSmallRna
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+import picard.analysis.directed.RnaSeqMetricsCollector.StrandSpecificity
+
+/**
+ * Created by pjvan_thof on 12/29/15.
+ * Design based on work from Henk Buermans (e-Mir)
+ * Implementation by wyleung started 19/01/16
+ */
+class TinyCap(val root: Configurable) extends QScript
+  with MultisampleMappingTrait
+  with AnnotationRefFlat
+  with AnnotationGff
+  with AnnotationGtf
+  with Reference {
+  qscript =>
+  def this() = this(null)
+
+  var annotateSam: Boolean = config("annotate_sam", default = false)
+
+  override def defaults = Map(
+    "igvtoolscount" -> Map(
+      "strands" -> "reads",
+      "includeDuplicates" -> true
+    ),
+    "merge_strategy" -> "preprocessmergesam",
+    "keep_merged_files" -> true,
+    "mapping" -> Map(
+      "aligner" -> "bowtie",
+      "generate_wig" -> true,
+      "skip_markduplicates" -> true
+    ),
+    "bammetrics" -> Map(
+      "wgs_metrics" -> false,
+      "rna_metrics" -> false,
+      "collectrnaseqmetrics" -> Map(
+        "strand_specificity" -> StrandSpecificity.SECOND_READ_TRANSCRIPTION_STRAND.toString
+      )
+    ),
+    "bowtie" -> Map(
+      "chunkmbs" -> 256,
+      "seedmms" -> 3,
+      "seedlen" -> 25,
+      "k" -> 5,
+      "best" -> true
+    ),
+    "sickle" -> Map(
+      "lengthThreshold" -> 15
+    ),
+    "fastqc" -> Map(
+      "sensitiveAdapterSearch" -> true
+    ),
+    "cutadapt" -> Map(
+      "error_rate" -> 0.2,
+      "minimum_length" -> 15,
+      "q" -> 30,
+      "default_clip_mode" -> "both",
+      "times" -> 2
+    )
+  )
+
+  lazy val fragmentsPerGene = new FragmentsPerGene(this)
+  lazy val fragmentsPerSmallRna = new FragmentsPerSmallRna(this)
+  lazy val baseCounts = new BaseCounts(this)
+
+  def executedMeasures = (fragmentsPerGene :: fragmentsPerSmallRna :: baseCounts :: Nil)
+
+  override def init = {
+    super.init()
+    executedMeasures.foreach(x => x.outputDir = new File(outputDir, "expression_measures" + File.separator + x.name))
+  }
+
+  override def makeSample(id: String) = new Sample(id)
+
+  class Sample(sampleId: String) extends super.Sample(sampleId) {
+    override def addJobs(): Unit = {
+      super.addJobs()
+
+      preProcessBam.foreach { file =>
+        executedMeasures.foreach(_.addBamfile(sampleId, file))
+      }
+    }
+  }
+
+  override def summaryFile = new File(outputDir, "tinycap.summary.json")
+
+  override def summaryFiles: Map[String, File] = super.summaryFiles ++ Map(
+    "annotation_refflat" -> annotationRefFlat(),
+    "annotationGtf" -> annotationGtf,
+    "annotationGff" -> annotationGff
+  )
+
+  override def reportClass: Option[ReportBuilderExtension] = {
+    val report = new TinyCapReport(this)
+    report.outputDir = new File(outputDir, "report")
+    report.summaryFile = summaryFile
+    Some(report)
+  }
+
+  override def addMultiSampleJobs = {
+    super.addMultiSampleJobs
+    executedMeasures.foreach(add)
+  }
+}
+
+object TinyCap extends PipelineCommand
\ No newline at end of file

tinycap/src/main/scala/nl/lumc/sasc/biopet/pipelines/tinycap/TinyCapReport.scala

+/**
+ * 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.tinycap
+
+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
+
+/**
+ * Created by wyleung on 4-2-16.
+ */
+class TinyCapReport(val root: Configurable) extends ReportBuilderExtension {
+  def builder = TinyCapReport
+
+}
+
+object TinyCapReport extends MultisampleMappingReportTrait {
+  /** Name of the report */
+  def reportName = "TinyCap Report"
+
+  /** Front section for the report */
+  override def frontSection: ReportSection = ReportSection("/nl/lumc/sasc/biopet/pipelines/tinycap/tinycapFront.ssp")
+
+  override def additionalSections = List(
+    "Fragments per gene" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gentrap/measure_plotreport.ssp",
+      Map("pipelineName" -> pipelineName,
+        "plotName" -> "fragmentspergene",
+        "plotPath" -> summary.getValue("fragmentspergene", "files", "pipeline", "fragments_per_gene_heatmap", "path")
+      )),
+    "Fragments per microRNA" -> ReportSection("/nl/lumc/sasc/biopet/pipelines/gentrap/measure_plotreport.ssp",
+      Map("pipelineName" -> pipelineName,
+        "plotName" -> "fragmentspersmallrna",
+        "plotPath" -> summary.getValue("fragmentspersmallrna", "files", "pipeline", "fragments_per_smallrna_heatmap", "path")))
+  )
+
+  override def pipelineName = "tinycap"
+}

tinycap/src/main/scala/nl/lumc/sasc/biopet/pipelines/tinycap/measures/FragmentsPerSmallRna.scala

+/**
+ * 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.tinycap.measures
+
+import nl.lumc.sasc.biopet.core.annotations.AnnotationGff
+import nl.lumc.sasc.biopet.extensions.HtseqCount
+import nl.lumc.sasc.biopet.pipelines.gentrap.measures.Measurement
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by wyleung on 11-2-16.
+ */
+class FragmentsPerSmallRna(val root: Configurable) extends QScript with Measurement with AnnotationGff {
+  def mergeArgs = MergeArgs(List(1), 2, numHeaderLines = 1, fallback = "0")
+
+  /** Pipeline itself */
+  def biopetScript(): Unit = {
+    val jobs = bamFiles.map {
+      case (id, file) =>
+        // Do expression counting for miRNA and siRNA
+        val job = new HtseqCount(this)
+        job.inputAlignment = file
+        job.inputAnnotation = annotationGff
+        job.format = Option("bam")
+        job.stranded = Option("yes")
+        job.featuretype = Option("miRNA")
+        job.idattr = Option("Name")
+        job.output = new File(outputDir, s"$id.$name.counts")
+        add(job)
+
+        id -> job
+    }
+
+    addMergeTableJob(jobs.values.map(_.output).toList, mergedTable, "fragments_per_smallrna", s".$name.counts")
+    addHeatmapJob(mergedTable, heatmap, "fragments_per_smallrna")
+
+    addSummaryJobs()
+  }
+
+  def mergedTable = new File(outputDir, s"$name.fragments_per_smallrna.tsv")
+  def heatmap = new File(outputDir, s"$name.fragments_per_smallrna.png")
+}

tinycap/src/test/resources/log4j.properties

+#
+# 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=ERROR, A1
+
+# A1 is set to be a ConsoleAppender.
+log4j.appender.A1=org.apache.log4j.ConsoleAppender
+
+# 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

tinycap/src/test/scala/nl/lumc/sasc/biopet/pipelines/tinycap/TinyCapTest.scala

+/**
+ * Created by wyleung on 11-2-16.
+ */
+
+/**
+ * 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.tinycap
+
+import java.io.File
+
+import com.google.common.io.Files
+import nl.lumc.sasc.biopet.extensions.HtseqCount
+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.{ AfterClass, DataProvider, Test }
+
+class TinyCapTest extends TestNGSuite with Matchers {
+
+  def initPipeline(map: Map[String, Any]): TinyCap = {
+    new TinyCap() {
+      override def configNamespace = "tinycap"
+
+      override def globalConfig = new Config(map)
+
+      qSettings = new QSettings
+      qSettings.runName = "test"
+    }
+  }
+
+  @DataProvider(name = "tinyCapOptions")
+  def tinyCapOptions = {
+    val bool = Array(true)
+
+    for (
+      s1 <- bool
+    ) yield Array("", s1)
+  }
+
+  @Test(dataProvider = "tinyCapOptions")
+  def testTinyCap(dummy: String, sample1: Boolean): Unit = {
+    val map = {
+      var m: Map[String, Any] = TinyCapTest.config
+      if (sample1) m = ConfigUtils.mergeMaps(TinyCapTest.sample1, m)
+      m
+    }
+
+    if (!sample1) { // When no samples
+      intercept[IllegalArgumentException] {
+        initPipeline(map).script()
+      }
+    }
+
+    val pipeline = initPipeline(map)
+    pipeline.script()
+    // expect 2 instances of HtSeqCount, one for mirna.gff other for transcripts.gtf
+    pipeline.functions.count(_.isInstanceOf[HtseqCount]) shouldBe 2
+
+  }
+
+  // remove temporary run directory all tests in the class have been run
+  @AfterClass def removeTempOutputDir() = {
+    FileUtils.deleteDirectory(TinyCapTest.outputDir)
+  }
+
+}
+
+object TinyCapTest {
+  val outputDir = Files.createTempDir()
+  new File(outputDir, "input").mkdirs()
+
+  val r1 = new File(outputDir, "input" + File.separator + "R1.fq.gz")
+  Files.touch(r1)
+  val bam = new File(outputDir, "input" + File.separator + "bamfile.bam")
+  Files.touch(bam)
+
+  val referenceFasta = new File(outputDir, "ref.fa")
+  Files.touch(referenceFasta)
+  val referenceFastaDict = new File(outputDir, "ref.dict")
+  Files.touch(referenceFastaDict)
+  val bowtieIndex = new File(outputDir, "ref.1.ebwt")
+  Files.touch(bowtieIndex)
+
+  val annotationGFF = new File(outputDir, "annot.gff")
+  val annotationGTF = new File(outputDir, "annot.gtf")
+  val annotationRefflat = new File(outputDir, "annot.refflat")
+  Files.touch(annotationGFF)
+  Files.touch(annotationGTF)
+  Files.touch(annotationRefflat)
+
+  val config = Map(
+    "output_dir" -> outputDir,
+    "reference_fasta" -> (referenceFasta.getAbsolutePath),
+    "bowtie_index" -> (bowtieIndex.getAbsolutePath),
+
+    "annotation_gff" -> annotationGFF,
+    "annotation_gtf" -> annotationGTF,
+    "annotation_refflat" -> annotationRefflat,
+
+    "md5sum" -> Map("exe" -> "test"),
+    "fastqc" -> Map("exe" -> "test"),
+    "seqtk" -> Map("exe" -> "test"),
+    "sickle" -> Map("exe" -> "test"),
+    "cutadapt" -> Map("exe" -> "test"),
+    "bowtie" -> Map("exe" -> "test"),
+    "htseqcount" -> Map("exe" -> "test"),
+    "igvtools" -> Map("exe" -> "test"),
+    "wigtobigwig" -> Map("exe" -> "test")
+  )
+
+  val sample1 = Map(
+    "samples" -> Map("sample1" -> Map("libraries" -> Map(
+      "lib1" -> Map(
+        "R1" -> r1.getAbsolutePath
+      )
+    )
+    )))
+
+}
\ No newline at end of file