From 1144a30ee2d9b88451eb2b18fba68efb7be04e2c Mon Sep 17 00:00:00 2001
From: Peter van 't Hof <p.j.van_t_hof@lumc.nl>
Date: Mon, 9 Feb 2015 15:18:12 +0100
Subject: [PATCH] Added link to final file when only 1 lib
---
.../biopet/pipelines/gatk/GatkPipeline.scala | 2 +-
.../pipelines/gatk/GatkVariantcalling.scala | 82 +++++++++++--------
2 files changed, 49 insertions(+), 35 deletions(-)
diff --git a/protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkPipeline.scala b/protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkPipeline.scala
index c76139133..fd82a58f0 100644
--- a/protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkPipeline.scala
+++ b/protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkPipeline.scala
@@ -50,6 +50,7 @@ class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScri
/** Library variantcalling */
val gatkVariantcalling = new GatkVariantcalling(qscript)
+ gatkVariantcalling.doublePreProces = false
gatkVariantcalling.sampleID = sampleId
gatkVariantcalling.outputDir = libDir
@@ -112,7 +113,6 @@ class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScri
if (bamFile.isDefined) {
gatkVariantcalling.inputBams = List(bamFile.get)
gatkVariantcalling.variantcalling = config("library_variantcalling", default = false)
- gatkVariantcalling.preProcesBams = true
gatkVariantcalling.init
gatkVariantcalling.biopetScript
addAll(gatkVariantcalling.functions)
diff --git a/protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantcalling.scala b/protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantcalling.scala
index 8bac4aaf6..4f1fce023 100644
--- a/protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantcalling.scala
+++ b/protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantcalling.scala
@@ -7,6 +7,7 @@ package nl.lumc.sasc.biopet.pipelines.gatk
import nl.lumc.sasc.biopet.core.{ BiopetQScript, PipelineCommand }
import java.io.File
+import nl.lumc.sasc.biopet.extensions.Ln
import nl.lumc.sasc.biopet.tools.{ VcfStats, MpileupToVcf, VcfFilter, MergeAlleles }
import nl.lumc.sasc.biopet.core.config.Configurable
import nl.lumc.sasc.biopet.extensions.gatk.{ AnalyzeCovariates, BaseRecalibrator, GenotypeGVCFs, HaplotypeCaller, IndelRealigner, PrintReads, RealignerTargetCreator, SelectVariants, CombineVariants, UnifiedGenotyper }
@@ -38,12 +39,12 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
@Argument(doc = "Sample name", required = false)
var sampleID: String = _
- var preProcesBams: Option[Boolean] = config("pre_proces_bams", default = true)
+ var preProcesBams: Boolean = config("pre_proces_bams", default = true)
var variantcalling: Boolean = true
- var doublePreProces: Option[Boolean] = config("double_pre_proces", default = true)
- var useHaplotypecaller: Option[Boolean] = config("use_haplotypecaller", default = true)
- var useUnifiedGenotyper: Option[Boolean] = config("use_unifiedgenotyper", default = false)
- var useAllelesOption: Option[Boolean] = config("use_alleles_option", default = false)
+ var doublePreProces: Boolean = config("double_pre_proces", default = true)
+ var useHaplotypecaller: Boolean = config("use_haplotypecaller", default = true)
+ var useUnifiedGenotyper: Boolean = config("use_unifiedgenotyper", default = false)
+ var useAllelesOption: Boolean = config("use_alleles_option", default = false)
var useMpileup: Boolean = config("use_mpileup", default = true)
var useIndelRealigner: Boolean = config("use_indel_realign", default = true)
var useBaseRecalibration: Boolean = config("use_base_recalibration", default = true)
@@ -62,42 +63,55 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
}
private def doublePreProces(files: List[File]): List[File] = {
- if (files.size == 1) return files
if (files.isEmpty) throw new IllegalStateException("Files can't be empty")
- if (!doublePreProces.get) return files
- val markDup = MarkDuplicates(this, files, new File(outputDir + outputName + ".dedup.bam"))
- markDup.isIntermediate = useIndelRealigner
- add(markDup)
- if (useIndelRealigner) {
- List(addIndelRealign(markDup.output, outputDir, isIntermediate = false))
+ else if (!doublePreProces) files
+ else if (files.size == 1) {
+ val bamFile: File = outputDir + files.head.getName
+ if (bamFile != files.head) {
+ val oldIndex: File = files.head.getAbsolutePath.stripSuffix(".bam") + ".bai"
+ val newIndex: File = bamFile.getAbsolutePath.stripSuffix(".bam") + ".bai"
+ add(Ln(this, oldIndex, newIndex))
+
+ val bamLn = Ln(this, files.head, bamFile)
+ bamLn.deps :+= newIndex
+ add(bamLn)
+ }
+ List(bamFile)
} else {
- List(markDup.output)
+ val markDup = MarkDuplicates(this, files, new File(outputDir + outputName + ".dedup.bam"))
+ markDup.isIntermediate = useIndelRealigner
+ add(markDup)
+ if (useIndelRealigner) {
+ List(addIndelRealign(markDup.output, outputDir, isIntermediate = false))
+ } else {
+ List(markDup.output)
+ }
}
}
def biopetScript() {
- scriptOutput.bamFiles = if (preProcesBams.get) {
- var bamFiles: List[File] = Nil
- for (inputBam <- inputBams) {
- var bamFile = inputBam
- if (useIndelRealigner) {
- bamFile = addIndelRealign(bamFile, outputDir, isIntermediate = useBaseRecalibration)
- }
- if (useBaseRecalibration) {
- bamFile = addBaseRecalibrator(bamFile, outputDir, isIntermediate = bamFiles.size > 1)
+ scriptOutput.bamFiles = {
+ doublePreProces(if (preProcesBams) {
+ //var bamFiles: List[File] = Nil
+ for (inputBam <- inputBams) yield {
+ var bamFile = inputBam
+ if (useIndelRealigner)
+ bamFile = addIndelRealign(bamFile, outputDir, isIntermediate = useBaseRecalibration)
+ if (useBaseRecalibration)
+ bamFile = addBaseRecalibrator(bamFile, outputDir, isIntermediate = inputBams.size > 1)
+ bamFile
}
- bamFiles :+= bamFile
- }
- doublePreProces(bamFiles)
- } else if (inputBams.size > 1 && doublePreProces.get) {
- doublePreProces(inputBams)
- } else inputBams
+ //bamFiles
+ } else {
+ inputBams
+ })
+ }
if (variantcalling) {
var mergBuffer: SortedMap[String, File] = SortedMap()
def mergeList = mergBuffer map { case (key, file) => TaggedFile(removeNoneVariants(file), "name=" + key) }
- if (sampleID != null && (useHaplotypecaller.get || config("joint_genotyping", default = false).asBoolean)) {
+ if (sampleID != null && (useHaplotypecaller || config("joint_genotyping", default = false).asBoolean)) {
val hcGvcf = new HaplotypeCaller(this)
hcGvcf.useGvcf
hcGvcf.input_file = scriptOutput.bamFiles
@@ -106,7 +120,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
scriptOutput.gvcfFile = hcGvcf.out
}
- if (useHaplotypecaller.get) {
+ if (useHaplotypecaller) {
if (sampleID != null) {
val genotypeGVCFs = GenotypeGVCFs(this, List(scriptOutput.gvcfFile), outputDir + outputName + ".hc.discovery.vcf.gz")
add(genotypeGVCFs)
@@ -121,7 +135,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
mergBuffer += ("1.HC-Discovery" -> scriptOutput.hcVcfFile)
}
- if (useUnifiedGenotyper.get) {
+ if (useUnifiedGenotyper) {
val ugVcf = new UnifiedGenotyper(this)
ugVcf.input_file = scriptOutput.bamFiles
ugVcf.out = outputDir + outputName + ".ug.discovery.vcf.gz"
@@ -156,12 +170,12 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
}
// Allele mode
- if (useAllelesOption.get) {
+ if (useAllelesOption) {
val mergeAlleles = MergeAlleles(this, mergeList.toList, outputDir + "raw.allele__temp_only.vcf.gz")
mergeAlleles.isIntermediate = true
add(mergeAlleles)
- if (useHaplotypecaller.get) {
+ if (useHaplotypecaller) {
val hcAlleles = new HaplotypeCaller(this)
hcAlleles.input_file = scriptOutput.bamFiles
hcAlleles.out = outputDir + outputName + ".hc.allele.vcf.gz"
@@ -172,7 +186,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
mergBuffer += ("3.HC-alleles" -> hcAlleles.out)
}
- if (useUnifiedGenotyper.get) {
+ if (useUnifiedGenotyper) {
val ugAlleles = new UnifiedGenotyper(this)
ugAlleles.input_file = scriptOutput.bamFiles
ugAlleles.out = outputDir + outputName + ".ug.allele.vcf.gz"
--
GitLab