From 0e7a025e7ed7a5e6006924d8b7f1740063ff4131 Mon Sep 17 00:00:00 2001
From: Peter van 't Hof <p.j.van_t_hof@lumc.nl>
Date: Wed, 27 Jan 2016 15:29:34 +0100
Subject: [PATCH] Give mergeTables a extension
---
.../biopet/extensions/tools/MergeTables.scala | 4 +++-
.../lumc/sasc/biopet/tools/BaseCounter.scala | 2 +-
.../gentrap/measures/BaseCounts.scala | 2 +-
.../measures/CufflinksMeasurement.scala | 20 ++++++++++++++++---
.../gentrap/measures/FragmentsPerGene.scala | 4 ++--
.../gentrap/measures/Measurement.scala | 1 +
6 files changed, 25 insertions(+), 8 deletions(-)
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 e1b94b874..96abaf1ed 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
@@ -85,7 +85,8 @@ object MergeTables {
idCols: List[Int],
valCol: Int,
numHeaderLines: Int = 0,
- fallback: String = "-"): MergeTables = {
+ fallback: String = "-",
+ fileExtension: Option[String] = None): MergeTables = {
val job = new MergeTables(root)
job.inputTables = tables
job.output = outputFile
@@ -93,6 +94,7 @@ object MergeTables {
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/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
index 8bfc3158e..a88563eb8 100644
--- 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
@@ -307,7 +307,7 @@ object BaseCounter extends ToolCommand {
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
+ else Nil
def addRecord(samRecord: SAMRecord, sense: Boolean): Unit = {
bamRecordBasesOverlap(samRecord, transcript.start, transcript.end, counts, sense)
exonCounts.foreach(_.addRecord(samRecord, sense))
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
index 3ad9146b6..98d1aeed3 100644
--- 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
@@ -29,7 +29,7 @@ class BaseCounts(val root: Configurable) extends QScript with Measurement with A
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)
+ addMergeTableJob(countFiles, mergedTable, outputName, countFiles.head.getName.stripPrefix(jobs.head._1))
addHeatmapJob(mergedTable, heatmapFile, outputName)
}
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
index d1cf59fdd..2d4f40973 100644
--- 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
@@ -1,6 +1,6 @@
package nl.lumc.sasc.biopet.pipelines.gentrap.measures
-import nl.lumc.sasc.biopet.extensions.Cufflinks
+import nl.lumc.sasc.biopet.extensions.{ Ln, Cufflinks }
import nl.lumc.sasc.biopet.extensions.tools.MergeTables
import org.broadinstitute.gatk.queue.QScript
@@ -23,8 +23,22 @@ trait CufflinksMeasurement extends QScript with Measurement {
id -> cufflinks
}
- addMergeTableJob(jobs.values.map(_.outputGenesFpkm).toList, mergeGenesFpkmTable, "genes_fpkm")
- addMergeTableJob(jobs.values.map(_.outputIsoformsFpkm).toList, mergeIsoFormFpkmTable, "iso_form")
+ 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")
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
index a383874f1..9ed01b496 100644
--- 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
@@ -20,7 +20,7 @@ class FragmentsPerGene(val root: Configurable) extends QScript with Measurement
val job = new HtseqCount(this)
job.inputAnnotation = annotationGtf
job.inputAlignment = file
- job.output = new File(outputDir, s"$name.$id.counts")
+ 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
@@ -30,7 +30,7 @@ class FragmentsPerGene(val root: Configurable) extends QScript with Measurement
id -> job
}
- addMergeTableJob(jobs.values.map(_.output).toList, mergedTable, "fragments_per_gene")
+ addMergeTableJob(jobs.values.map(_.output).toList, mergedTable, "fragments_per_gene", s".$name.counts")
addHeatmapJob(mergedTable, heatmap, "fragments_per_gene")
}
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
index 095a01fdb..768fa98b1 100644
--- 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
@@ -41,6 +41,7 @@ trait Measurement extends SummaryQScript with Reference { qscript: QScript =>
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))
--
GitLab