From 5a4744154798a75118cf7f28cb8a9de34a344566 Mon Sep 17 00:00:00 2001
From: Peter van 't Hof <p.j.van_t_hof@lumc.nl>
Date: Sat, 22 Nov 2014 16:06:33 +0100
Subject: [PATCH] Remove protected source file from public artifacts
---
.../extensions/gatk/AnalyzeCovariates.scala | 17 --
.../extensions/gatk/ApplyRecalibration.scala | 34 ---
.../extensions/gatk/BaseRecalibrator.scala | 23 --
.../biopet/extensions/gatk/CombineGVCFs.scala | 17 --
.../extensions/gatk/CombineVariants.scala | 17 --
.../biopet/extensions/gatk/GatkGeneral.scala | 18 --
.../extensions/gatk/GenotypeGVCFs.scala | 28 --
.../extensions/gatk/HaplotypeCaller.scala | 48 ----
.../extensions/gatk/IndelRealigner.scala | 18 --
.../biopet/extensions/gatk/PrintReads.scala | 21 --
.../gatk/RealignerTargetCreator.scala | 22 --
.../extensions/gatk/SelectVariants.scala | 17 --
.../extensions/gatk/UnifiedGenotyper.scala | 34 ---
.../extensions/gatk/VariantAnnotator.scala | 19 --
.../biopet/extensions/gatk/VariantEval.scala | 37 ---
.../extensions/gatk/VariantRecalibrator.scala | 40 ---
.../sasc/biopet/pipelines/basty/Basty.scala | 147 -----------
.../gatk/GatkBenchmarkGenotyping.scala | 58 -----
.../pipelines/gatk/GatkGenotyping.scala | 58 -----
.../biopet/pipelines/gatk/GatkPipeline.scala | 237 -----------------
.../gatk/GatkVariantRecalibration.scala | 76 ------
.../pipelines/gatk/GatkVariantcalling.scala | 244 ------------------
.../pipelines/gatk/GatkVcfSampleCompare.scala | 82 ------
.../pipelines/gatk/SampleCompareMetrics.scala | 148 -----------
24 files changed, 1460 deletions(-)
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/AnalyzeCovariates.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ApplyRecalibration.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BaseRecalibrator.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineGVCFs.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineVariants.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GatkGeneral.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeGVCFs.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/HaplotypeCaller.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/IndelRealigner.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/PrintReads.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/RealignerTargetCreator.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/SelectVariants.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/UnifiedGenotyper.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantAnnotator.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantEval.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantRecalibrator.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/basty/Basty.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkBenchmarkGenotyping.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkGenotyping.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkPipeline.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantRecalibration.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantcalling.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVcfSampleCompare.scala
delete mode 100644 public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/SampleCompareMetrics.scala
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/AnalyzeCovariates.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/AnalyzeCovariates.scala
deleted file mode 100644
index 525c357a9..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/AnalyzeCovariates.scala
+++ /dev/null
@@ -1,17 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-
-class AnalyzeCovariates(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.AnalyzeCovariates with GatkGeneral {
-}
-
-object AnalyzeCovariates {
- def apply(root: Configurable, before: File, after: File, plots: File): AnalyzeCovariates = {
- val ac = new AnalyzeCovariates(root)
- ac.before = before
- ac.after = after
- ac.plots = plots
- return ac
- }
-}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ApplyRecalibration.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ApplyRecalibration.scala
deleted file mode 100644
index b0e3a71fc..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ApplyRecalibration.scala
+++ /dev/null
@@ -1,34 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-
-class ApplyRecalibration(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.ApplyRecalibration with GatkGeneral {
- override def afterGraph {
- super.afterGraph
-
- if (config.contains("scattercount")) scatterCount = config("scattercount")
-
- nt = Option(getThreads(3))
- memoryLimit = Option(nt.getOrElse(1) * 2)
- ts_filter_level = config("ts_filter_level")
- }
-}
-
-object ApplyRecalibration {
- def apply(root: Configurable, input: File, output: File, recal_file: File, tranches_file: File, indel: Boolean = false): ApplyRecalibration = {
- val ar = if (indel) new ApplyRecalibration(root) {
- mode = org.broadinstitute.gatk.tools.walkers.variantrecalibration.VariantRecalibratorArgumentCollection.Mode.INDEL
- defaults ++= Map("ts_filter_level" -> 99.0)
- }
- else new ApplyRecalibration(root) {
- mode = org.broadinstitute.gatk.tools.walkers.variantrecalibration.VariantRecalibratorArgumentCollection.Mode.SNP
- defaults ++= Map("ts_filter_level" -> 99.5)
- }
- ar.input :+= input
- ar.recal_file = recal_file
- ar.tranches_file = tranches_file
- ar.out = output
- return ar
- }
-}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BaseRecalibrator.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BaseRecalibrator.scala
deleted file mode 100644
index 147ab732f..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BaseRecalibrator.scala
+++ /dev/null
@@ -1,23 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-
-class BaseRecalibrator(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.BaseRecalibrator with GatkGeneral {
- memoryLimit = Option(4)
- override val defaultVmem = "8G"
-
- if (config.contains("scattercount")) scatterCount = config("scattercount")
- if (config.contains("dbsnp")) knownSites :+= new File(config("dbsnp").asString)
- if (config.contains("known_sites")) knownSites :+= new File(config("known_sites").asString)
-}
-
-object BaseRecalibrator {
- def apply(root: Configurable, input: File, output: File): BaseRecalibrator = {
- val br = new BaseRecalibrator(root)
- br.input_file :+= input
- br.out = output
- br.afterGraph
- return br
- }
-}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineGVCFs.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineGVCFs.scala
deleted file mode 100644
index 5b3e4df4b..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineGVCFs.scala
+++ /dev/null
@@ -1,17 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-
-class CombineGVCFs(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.CombineGVCFs with GatkGeneral {
- if (config.contains("scattercount")) scatterCount = config("scattercount")
-}
-
-object CombineGVCFs {
- def apply(root: Configurable, input: List[File], output: File): CombineGVCFs = {
- val cg = new CombineGVCFs(root)
- cg.variant = input
- cg.o = output
- return cg
- }
-}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineVariants.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineVariants.scala
deleted file mode 100644
index 1ad7e42e7..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineVariants.scala
+++ /dev/null
@@ -1,17 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-
-class CombineVariants(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.CombineVariants with GatkGeneral {
- if (config.contains("scattercount")) scatterCount = config("scattercount")
-}
-
-object CombineVariants {
- def apply(root: Configurable, input: List[File], output: File): CombineVariants = {
- val cv = new CombineVariants(root)
- cv.variant = input
- cv.out = output
- return cv
- }
-}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GatkGeneral.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GatkGeneral.scala
deleted file mode 100644
index 75f5f07a9..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GatkGeneral.scala
+++ /dev/null
@@ -1,18 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import nl.lumc.sasc.biopet.core.BiopetJavaCommandLineFunction
-import org.broadinstitute.gatk.queue.extensions.gatk.CommandLineGATK
-
-trait GatkGeneral extends CommandLineGATK with BiopetJavaCommandLineFunction {
- memoryLimit = Option(3)
-
- if (config.contains("gatk_jar")) jarFile = config("gatk_jar")
-
- override val defaultVmem = "7G"
-
- if (config.contains("intervals", submodule = "gatk")) intervals = config("intervals", submodule = "gatk").asFileList
- if (config.contains("exclude_intervals", submodule = "gatk")) excludeIntervals = config("exclude_intervals", submodule = "gatk").asFileList
- reference_sequence = config("reference", submodule = "gatk")
- gatk_key = config("gatk_key", submodule = "gatk")
- if (config.contains("pedigree", submodule = "gatk")) pedigree = config("pedigree", submodule = "gatk").asFileList
-}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeGVCFs.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeGVCFs.scala
deleted file mode 100644
index d24913d23..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeGVCFs.scala
+++ /dev/null
@@ -1,28 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-
-class GenotypeGVCFs(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.GenotypeGVCFs with GatkGeneral {
- annotation ++= config("annotation", default = Seq("FisherStrand", "QualByDepth", "ChromosomeCounts")).asStringList
-
- if (config.contains("dbsnp")) dbsnp = config("dbsnp")
- if (config.contains("scattercount", "genotypegvcfs")) scatterCount = config("scattercount")
-
- if (config("inputtype", default = "dna").asString == "rna") {
- stand_call_conf = config("stand_call_conf", default = 20)
- stand_emit_conf = config("stand_emit_conf", default = 0)
- } else {
- stand_call_conf = config("stand_call_conf", default = 30)
- stand_emit_conf = config("stand_emit_conf", default = 0)
- }
-}
-
-object GenotypeGVCFs {
- def apply(root: Configurable, gvcfFiles: List[File], output: File): GenotypeGVCFs = {
- val gg = new GenotypeGVCFs(root)
- gg.variant = gvcfFiles
- gg.out = output
- return gg
- }
-}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/HaplotypeCaller.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/HaplotypeCaller.scala
deleted file mode 100644
index 087bf08e4..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/HaplotypeCaller.scala
+++ /dev/null
@@ -1,48 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import nl.lumc.sasc.biopet.core.config.Configurable
-import org.broadinstitute.gatk.utils.variant.GATKVCFIndexType
-
-class HaplotypeCaller(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.HaplotypeCaller with GatkGeneral {
- override def afterGraph {
- super.afterGraph
-
- min_mapping_quality_score = config("minMappingQualityScore", default = 20)
- if (config.contains("scattercount")) scatterCount = config("scattercount")
- if (config.contains("dbsnp")) this.dbsnp = config("dbsnp")
- this.sample_ploidy = config("ploidy")
- nct = config("threads", default = 1)
- bamOutput = config("bamOutput")
- memoryLimit = Option(nct.getOrElse(1) * 2)
- if (config.contains("allSitePLs")) this.allSitePLs = config("allSitePLs")
- if (config.contains("output_mode")) {
- import org.broadinstitute.gatk.tools.walkers.genotyper.OutputMode._
- config("output_mode").asString match {
- case "EMIT_ALL_CONFIDENT_SITES" => output_mode = EMIT_ALL_CONFIDENT_SITES
- case "EMIT_ALL_SITES" => output_mode = EMIT_ALL_SITES
- case "EMIT_VARIANTS_ONLY" => output_mode = EMIT_VARIANTS_ONLY
- case e => logger.warn("output mode '" + e + "' does not exist")
- }
- }
-
- if (config("inputtype", default = "dna").asString == "rna") {
- dontUseSoftClippedBases = config("dontusesoftclippedbases", default = true)
- stand_call_conf = config("stand_call_conf", default = 5)
- stand_emit_conf = config("stand_emit_conf", default = 0)
- } else {
- dontUseSoftClippedBases = config("dontusesoftclippedbases", default = false)
- stand_call_conf = config("stand_call_conf", default = 5)
- stand_emit_conf = config("stand_emit_conf", default = 0)
- }
- if (bamOutput != null && nct.getOrElse(1) > 1) {
- nct = Option(1)
- logger.warn("BamOutput is on, nct/threads is forced to set on 1, this option is only for debug")
- }
- }
-
- def useGvcf() {
- emitRefConfidence = org.broadinstitute.gatk.tools.walkers.haplotypecaller.ReferenceConfidenceMode.GVCF
- variant_index_type = GATKVCFIndexType.LINEAR
- variant_index_parameter = config("variant_index_parameter", default = 128000)
- }
-}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/IndelRealigner.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/IndelRealigner.scala
deleted file mode 100644
index f9f06daac..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/IndelRealigner.scala
+++ /dev/null
@@ -1,18 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-
-class IndelRealigner(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.IndelRealigner with GatkGeneral {
- if (config.contains("scattercount")) scatterCount = config("scattercount")
-}
-
-object IndelRealigner {
- def apply(root: Configurable, input: File, targetIntervals: File, outputDir: String): IndelRealigner = {
- val ir = new IndelRealigner(root)
- ir.input_file :+= input
- ir.targetIntervals = targetIntervals
- ir.out = new File(outputDir, input.getName.stripSuffix(".bam") + ".realign.bam")
- return ir
- }
-}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/PrintReads.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/PrintReads.scala
deleted file mode 100644
index 6f039932b..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/PrintReads.scala
+++ /dev/null
@@ -1,21 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-
-class PrintReads(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.PrintReads with GatkGeneral {
- memoryLimit = Option(4)
-
- override val defaultVmem = "8G"
-
- if (config.contains("scattercount")) scatterCount = config("scattercount")
-}
-
-object PrintReads {
- def apply(root: Configurable, input: File, output: File): PrintReads = {
- val br = new PrintReads(root)
- br.input_file :+= input
- br.out = output
- return br
- }
-}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/RealignerTargetCreator.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/RealignerTargetCreator.scala
deleted file mode 100644
index 7377389a0..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/RealignerTargetCreator.scala
+++ /dev/null
@@ -1,22 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-
-class RealignerTargetCreator(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.RealignerTargetCreator with GatkGeneral {
- override val defaultVmem = "6G"
- memoryLimit = Some(2.5)
-
- if (config.contains("scattercount")) scatterCount = config("scattercount")
-
- if (config.contains("known")) known ++= config("known").asFileList
-}
-
-object RealignerTargetCreator {
- def apply(root: Configurable, input: File, outputDir: String): RealignerTargetCreator = {
- val re = new RealignerTargetCreator(root)
- re.input_file :+= input
- re.out = new File(outputDir, input.getName.stripSuffix(".bam") + ".realign.intervals")
- return re
- }
-}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/SelectVariants.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/SelectVariants.scala
deleted file mode 100644
index cd056c429..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/SelectVariants.scala
+++ /dev/null
@@ -1,17 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-
-class SelectVariants(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.SelectVariants with GatkGeneral {
- if (config.contains("scattercount")) scatterCount = config("scattercount")
-}
-
-object SelectVariants {
- def apply(root: Configurable, input: File, output: File): SelectVariants = {
- val sv = new SelectVariants(root)
- sv.variant = input
- sv.out = output
- return sv
- }
-}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/UnifiedGenotyper.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/UnifiedGenotyper.scala
deleted file mode 100644
index 255fb100a..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/UnifiedGenotyper.scala
+++ /dev/null
@@ -1,34 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import nl.lumc.sasc.biopet.core.config.Configurable
-
-class UnifiedGenotyper(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.UnifiedGenotyper with GatkGeneral {
- override def afterGraph {
- super.afterGraph
-
- genotype_likelihoods_model = org.broadinstitute.gatk.tools.walkers.genotyper.GenotypeLikelihoodsCalculationModel.Model.BOTH
- if (config.contains("scattercount")) scatterCount = config("scattercount")
- if (config.contains("dbsnp")) this.dbsnp = config("dbsnp")
- this.sample_ploidy = config("ploidy")
- nct = config("threads", default = 1)
- memoryLimit = Option(nct.getOrElse(1) * 2)
- if (config.contains("allSitePLs")) this.allSitePLs = config("allSitePLs")
- if (config.contains("output_mode")) {
- import org.broadinstitute.gatk.tools.walkers.genotyper.OutputMode._
- config("output_mode").asString match {
- case "EMIT_ALL_CONFIDENT_SITES" => output_mode = EMIT_ALL_CONFIDENT_SITES
- case "EMIT_ALL_SITES" => output_mode = EMIT_ALL_SITES
- case "EMIT_VARIANTS_ONLY" => output_mode = EMIT_VARIANTS_ONLY
- case e => logger.warn("output mode '" + e + "' does not exist")
- }
- }
-
- if (config("inputtype", default = "dna").asString == "rna") {
- stand_call_conf = config("stand_call_conf", default = 5)
- stand_emit_conf = config("stand_emit_conf", default = 0)
- } else {
- stand_call_conf = config("stand_call_conf", default = 5)
- stand_emit_conf = config("stand_emit_conf", default = 0)
- }
- }
-}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantAnnotator.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantAnnotator.scala
deleted file mode 100644
index 3a829421c..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantAnnotator.scala
+++ /dev/null
@@ -1,19 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-
-class VariantAnnotator(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.VariantAnnotator with GatkGeneral {
- if (config.contains("scattercount")) scatterCount = config("scattercount")
- dbsnp = config("dbsnp")
-}
-
-object VariantAnnotator {
- def apply(root: Configurable, input: File, bamFiles: List[File], output: File): VariantAnnotator = {
- val va = new VariantAnnotator(root)
- va.variant = input
- va.input_file = bamFiles
- va.out = output
- return va
- }
-}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantEval.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantEval.scala
deleted file mode 100644
index 798771801..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantEval.scala
+++ /dev/null
@@ -1,37 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-
-class VariantEval(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.VariantEval with GatkGeneral {
- override def afterGraph {
- super.afterGraph
- }
-}
-
-object VariantEval {
- def apply(root: Configurable, sample: File, compareWith: File,
- output: File): VariantEval = {
- val vareval = new VariantEval(root)
- vareval.eval = Seq(sample)
- vareval.comp = Seq(compareWith)
- vareval.out = output
- vareval.afterGraph
- return vareval
- }
-
- def apply(root: Configurable, sample: File, compareWith: File,
- output: File, ST: Seq[String], EV: Seq[String]): VariantEval = {
- val vareval = new VariantEval(root)
- vareval.eval = Seq(sample)
- vareval.comp = Seq(compareWith)
- vareval.out = output
- vareval.noST = true
- vareval.ST = ST
- vareval.noEV = true
- vareval.EV = EV
- vareval.afterGraph
- return vareval
- }
-
-}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantRecalibrator.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantRecalibrator.scala
deleted file mode 100644
index b778dd4de..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantRecalibrator.scala
+++ /dev/null
@@ -1,40 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
-
-class VariantRecalibrator(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.VariantRecalibrator with GatkGeneral {
- nt = Option(getThreads(4))
- memoryLimit = Option(nt.getOrElse(1) * 2)
-
- if (config.contains("dbsnp")) resource :+= new TaggedFile(config("dbsnp").asString, "known=true,training=false,truth=false,prior=2.0")
-
- an = config("annotation", default = List("QD", "DP", "FS", "ReadPosRankSum", "MQRankSum")).asStringList
- minNumBadVariants = config("minnumbadvariants")
- maxGaussians = config("maxgaussians")
-}
-
-object VariantRecalibrator {
- def apply(root: Configurable, input: File, recal_file: File, tranches_file: File, indel: Boolean = false): VariantRecalibrator = {
- val vr = new VariantRecalibrator(root) {
- override lazy val configName = "variantrecalibrator"
- override def configPath: List[String] = (if (indel) "indel" else "snp") :: super.configPath
- if (indel) {
- mode = org.broadinstitute.gatk.tools.walkers.variantrecalibration.VariantRecalibratorArgumentCollection.Mode.INDEL
- defaults ++= Map("ts_filter_level" -> 99.0)
- if (config.contains("mills")) resource :+= new TaggedFile(config("mills").asString, "known=false,training=true,truth=true,prior=12.0")
- } else {
- mode = org.broadinstitute.gatk.tools.walkers.variantrecalibration.VariantRecalibratorArgumentCollection.Mode.SNP
- defaults ++= Map("ts_filter_level" -> 99.5)
- if (config.contains("hapmap")) resource +:= new TaggedFile(config("hapmap").asString, "known=false,training=true,truth=true,prior=15.0")
- if (config.contains("omni")) resource +:= new TaggedFile(config("omni").asString, "known=false,training=true,truth=true,prior=12.0")
- if (config.contains("1000G")) resource +:= new TaggedFile(config("1000G").asString, "known=false,training=true,truth=false,prior=10.0")
- }
- }
- vr.input :+= input
- vr.recal_file = recal_file
- vr.tranches_file = tranches_file
- return vr
- }
-}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/basty/Basty.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/basty/Basty.scala
deleted file mode 100644
index 874890746..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/basty/Basty.scala
+++ /dev/null
@@ -1,147 +0,0 @@
-package nl.lumc.sasc.biopet.pipelines.basty
-
-import java.io.File
-import nl.lumc.sasc.biopet.core.MultiSampleQScript
-import nl.lumc.sasc.biopet.core.PipelineCommand
-import nl.lumc.sasc.biopet.core.config.Configurable
-import nl.lumc.sasc.biopet.extensions.Cat
-import nl.lumc.sasc.biopet.extensions.Raxml
-import nl.lumc.sasc.biopet.pipelines.gatk.GatkPipeline
-import nl.lumc.sasc.biopet.tools.BastyGenerateFasta
-import org.broadinstitute.gatk.queue.QScript
-
-class Basty(val root: Configurable) extends QScript with MultiSampleQScript {
- def this() = this(null)
-
- class LibraryOutput extends AbstractLibraryOutput {
- }
-
- case class FastaOutput(variants: File, consensus: File, consensusVariants: File)
- class SampleOutput extends AbstractSampleOutput {
- var output: FastaOutput = _
- var outputSnps: FastaOutput = _
- }
-
- defaults ++= Map("ploidy" -> 1, "use_haplotypecaller" -> false, "use_unifiedgenotyper" -> true, "joint_variantcalling" -> true)
-
- var gatkPipeline: GatkPipeline = new GatkPipeline(this)
- gatkPipeline.jointVariantcalling = true
-
- def init() {
- gatkPipeline.outputDir = outputDir
- gatkPipeline.init
- }
-
- def biopetScript() {
- gatkPipeline.biopetScript
- addAll(gatkPipeline.functions)
-
- val refVariants = addGenerateFasta(null, outputDir + "reference/", outputName = "reference")
- val refVariantSnps = addGenerateFasta(null, outputDir + "reference/", outputName = "reference", snpsOnly = true)
-
- runSamplesJobs()
-
- val catVariants = Cat(this, refVariants.variants :: samplesOutput.map(_._2.output.variants).toList, outputDir + "fastas/variant.fasta")
- add(catVariants)
- val catVariantsSnps = Cat(this, refVariantSnps.variants :: samplesOutput.map(_._2.outputSnps.variants).toList, outputDir + "fastas/variant.snps_only.fasta")
- add(catVariantsSnps)
-
- val catConsensus = Cat(this, refVariants.consensus :: samplesOutput.map(_._2.output.consensus).toList, outputDir + "fastas/consensus.fasta")
- add(catConsensus)
- val catConsensusSnps = Cat(this, refVariantSnps.consensus :: samplesOutput.map(_._2.outputSnps.consensus).toList, outputDir + "fastas/consensus.snps_only.fasta")
- add(catConsensusSnps)
-
- val catConsensusVariants = Cat(this, refVariants.consensusVariants :: samplesOutput.map(_._2.output.consensusVariants).toList, outputDir + "fastas/consensus.variant.fasta")
- add(catConsensusVariants)
- val catConsensusVariantsSnps = Cat(this, refVariantSnps.consensusVariants :: samplesOutput.map(_._2.outputSnps.consensusVariants).toList, outputDir + "fastas/consensus.variant.snps_only.fasta")
- add(catConsensusVariantsSnps)
-
- val seed: Int = config("seed", default = 12345)
- def addRaxml(input: File, outputDir: String, outputName: String) {
- val raxmlMl = new Raxml(this)
- raxmlMl.input = input
- raxmlMl.m = config("raxml_ml_model", default = "GTRGAMMAX")
- raxmlMl.p = seed
- raxmlMl.n = outputName + "_ml"
- raxmlMl.w = outputDir
- raxmlMl.N = config("ml_runs", default = 20, submodule = "raxml")
- add(raxmlMl)
-
- val r = new scala.util.Random(seed)
- val numBoot = config("boot_runs", default = 100, submodule = "raxml").asInt
- val bootList = for (t <- 0 until numBoot) yield {
- val raxmlBoot = new Raxml(this)
- raxmlBoot.threads = 1
- raxmlBoot.input = input
- raxmlBoot.m = config("raxml_ml_model", default = "GTRGAMMAX")
- raxmlBoot.p = seed
- raxmlBoot.b = math.abs(r.nextInt)
- raxmlBoot.w = outputDir
- raxmlBoot.N = 1
- raxmlBoot.n = outputName + "_boot_" + t
- add(raxmlBoot)
- raxmlBoot.getBootstrapFile
- }
-
- val cat = Cat(this, bootList.toList, outputDir + "/boot_list")
- add(cat)
-
- val raxmlBi = new Raxml(this)
- raxmlBi.input = input
- raxmlBi.t = raxmlMl.getBestTreeFile
- raxmlBi.z = cat.output
- raxmlBi.m = config("raxml_ml_model", default = "GTRGAMMAX")
- raxmlBi.p = seed
- raxmlBi.f = "b"
- raxmlBi.n = outputName + "_bi"
- raxmlBi.w = outputDir
- add(raxmlBi)
- }
-
- addRaxml(catVariantsSnps.output, outputDir + "raxml", "snps")
- }
-
- // Called for each sample
- def runSingleSampleJobs(sampleConfig: Map[String, Any]): SampleOutput = {
- val sampleOutput = new SampleOutput
- val sampleID: String = sampleConfig("ID").toString
- val sampleDir = globalSampleDir + sampleID + "/"
-
- sampleOutput.libraries = runLibraryJobs(sampleConfig)
-
- sampleOutput.output = addGenerateFasta(sampleID, sampleDir)
- sampleOutput.outputSnps = addGenerateFasta(sampleID, sampleDir, snpsOnly = true)
-
- return sampleOutput
- }
-
- // Called for each run from a sample
- def runSingleLibraryJobs(runConfig: Map[String, Any], sampleConfig: Map[String, Any]): LibraryOutput = {
- val libraryOutput = new LibraryOutput
-
- val runID: String = runConfig("ID").toString
- val sampleID: String = sampleConfig("ID").toString
- val runDir: String = globalSampleDir + sampleID + "/run_" + runID + "/"
-
- return libraryOutput
- }
-
- def addGenerateFasta(sampleName: String, outputDir: String, outputName: String = null,
- snpsOnly: Boolean = false): FastaOutput = {
- val bastyGenerateFasta = new BastyGenerateFasta(this)
- bastyGenerateFasta.outputName = if (outputName != null) outputName else sampleName
- bastyGenerateFasta.inputVcf = gatkPipeline.multisampleVariantcalling.scriptOutput.finalVcfFile
- if (gatkPipeline.samplesOutput.contains(sampleName)) {
- bastyGenerateFasta.bamFile = gatkPipeline.samplesOutput(sampleName).variantcalling.bamFiles.head
- }
- bastyGenerateFasta.outputVariants = outputDir + bastyGenerateFasta.outputName + ".variants" + (if (snpsOnly) ".snps_only" else "") + ".fasta"
- bastyGenerateFasta.outputConsensus = outputDir + bastyGenerateFasta.outputName + ".consensus" + (if (snpsOnly) ".snps_only" else "") + ".fasta"
- bastyGenerateFasta.outputConsensusVariants = outputDir + bastyGenerateFasta.outputName + ".consensus_variants" + (if (snpsOnly) ".snps_only" else "") + ".fasta"
- bastyGenerateFasta.sampleName = sampleName
- bastyGenerateFasta.snpsOnly = snpsOnly
- add(bastyGenerateFasta)
- return FastaOutput(bastyGenerateFasta.outputVariants, bastyGenerateFasta.outputConsensus, bastyGenerateFasta.outputConsensusVariants)
- }
-}
-
-object Basty extends PipelineCommand
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkBenchmarkGenotyping.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkBenchmarkGenotyping.scala
deleted file mode 100644
index 8d7158f5a..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkBenchmarkGenotyping.scala
+++ /dev/null
@@ -1,58 +0,0 @@
-package nl.lumc.sasc.biopet.pipelines.gatk
-
-import nl.lumc.sasc.biopet.core.{ BiopetQScript, PipelineCommand }
-import nl.lumc.sasc.biopet.core.config.Configurable
-import org.broadinstitute.gatk.queue.QScript
-import org.broadinstitute.gatk.utils.commandline.{ Input, Argument }
-import scala.util.Random
-
-class GatkBenchmarkGenotyping(val root: Configurable) extends QScript with BiopetQScript {
- def this() = this(null)
-
- @Input(doc = "Sample gvcf file")
- var sampleGvcf: File = _
-
- @Argument(doc = "SampleName", required = true)
- var sampleName: String = _
-
- @Input(doc = "Gvcf files", shortName = "I", required = false)
- var gvcfFiles: List[File] = Nil
-
- var reference: File = config("reference")
-
- @Argument(doc = "Dbsnp", shortName = "dbsnp", required = false)
- var dbsnp: File = config("dbsnp")
-
- def init() {
- if (config.contains("gvcffiles")) for (file <- config("gvcffiles").asList) {
- gvcfFiles ::= file.toString
- }
- if (outputDir == null) throw new IllegalStateException("Missing Output directory on gatk module")
- else if (!outputDir.endsWith("/")) outputDir += "/"
- }
-
- def biopetScript() {
- var todoGvcfs = gvcfFiles
- var gvcfPool: List[File] = Nil
- addGenotypingPipeline(gvcfPool)
-
- while (todoGvcfs.size > 0) {
- val index = Random.nextInt(todoGvcfs.size)
- gvcfPool ::= todoGvcfs(index)
- addGenotypingPipeline(gvcfPool)
- todoGvcfs = todoGvcfs.filter(b => b != todoGvcfs(index))
- }
- }
-
- def addGenotypingPipeline(gvcfPool: List[File]) {
- val gatkGenotyping = new GatkGenotyping(this)
- gatkGenotyping.inputGvcfs = sampleGvcf :: gvcfPool
- gatkGenotyping.samples :+= sampleName
- gatkGenotyping.outputDir = outputDir + "samples_" + gvcfPool.size + "/"
- gatkGenotyping.init
- gatkGenotyping.biopetScript
- addAll(gatkGenotyping.functions)
- }
-}
-
-object GatkBenchmarkGenotyping extends PipelineCommand
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkGenotyping.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkGenotyping.scala
deleted file mode 100644
index 5ed4f0629..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkGenotyping.scala
+++ /dev/null
@@ -1,58 +0,0 @@
-package nl.lumc.sasc.biopet.pipelines.gatk
-
-import nl.lumc.sasc.biopet.core.{ BiopetQScript, PipelineCommand }
-import nl.lumc.sasc.biopet.core.config.Configurable
-import nl.lumc.sasc.biopet.extensions.gatk.{ GenotypeGVCFs, SelectVariants }
-import org.broadinstitute.gatk.queue.QScript
-import org.broadinstitute.gatk.utils.commandline.{ Input, Output, Argument }
-
-class GatkGenotyping(val root: Configurable) extends QScript with BiopetQScript {
- def this() = this(null)
-
- @Input(doc = "Gvcf files", shortName = "I")
- var inputGvcfs: List[File] = Nil
-
- @Argument(doc = "Reference", shortName = "R", required = false)
- var reference: File = config("reference")
-
- @Argument(doc = "Dbsnp", shortName = "dbsnp", required = false)
- var dbsnp: File = config("dbsnp")
-
- @Argument(doc = "OutputName", required = false)
- var outputName: String = "genotype"
-
- @Output(doc = "OutputFile", shortName = "O", required = false)
- var outputFile: File = _
-
- @Argument(doc = "Samples", shortName = "sample", required = false)
- var samples: List[String] = Nil
-
- def init() {
- if (outputFile == null) outputFile = outputDir + outputName + ".vcf.gz"
- if (outputDir == null) throw new IllegalStateException("Missing Output directory on gatk module")
- else if (!outputDir.endsWith("/")) outputDir += "/"
- }
-
- def biopetScript() {
- addGenotypeGVCFs(inputGvcfs, outputFile)
- if (!samples.isEmpty) {
- if (samples.size > 1) addSelectVariants(outputFile, samples, outputDir + "samples/", "all")
- for (sample <- samples) addSelectVariants(outputFile, List(sample), outputDir + "samples/", sample)
- }
- }
-
- def addGenotypeGVCFs(gvcfFiles: List[File], outputFile: File): File = {
- val genotypeGVCFs = GenotypeGVCFs(this, gvcfFiles, outputFile)
- add(genotypeGVCFs)
- return genotypeGVCFs.out
- }
-
- def addSelectVariants(inputFile: File, samples: List[String], outputDir: String, name: String) {
- val selectVariants = SelectVariants(this, inputFile, outputDir + name + ".vcf.gz")
- selectVariants.excludeNonVariants = true
- for (sample <- samples) selectVariants.sample_name :+= sample
- add(selectVariants)
- }
-}
-
-object GatkGenotyping extends PipelineCommand
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkPipeline.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkPipeline.scala
deleted file mode 100644
index 39d7465b0..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkPipeline.scala
+++ /dev/null
@@ -1,237 +0,0 @@
-package nl.lumc.sasc.biopet.pipelines.gatk
-
-import nl.lumc.sasc.biopet.core.MultiSampleQScript
-import nl.lumc.sasc.biopet.core.PipelineCommand
-import nl.lumc.sasc.biopet.core.config.Configurable
-import htsjdk.samtools.SamReaderFactory
-import scala.collection.JavaConversions._
-import java.io.File
-import nl.lumc.sasc.biopet.extensions.gatk.{ CombineVariants, CombineGVCFs }
-import nl.lumc.sasc.biopet.extensions.picard.AddOrReplaceReadGroups
-import nl.lumc.sasc.biopet.extensions.picard.SamToFastq
-import nl.lumc.sasc.biopet.pipelines.bammetrics.BamMetrics
-import nl.lumc.sasc.biopet.pipelines.mapping.Mapping
-import org.broadinstitute.gatk.queue.QScript
-import org.broadinstitute.gatk.utils.commandline.{ Argument }
-
-class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScript {
- def this() = this(null)
-
- @Argument(doc = "Only Sample", shortName = "sample", required = false)
- val onlySample: List[String] = Nil
-
- @Argument(doc = "Skip Genotyping step", shortName = "skipgenotyping", required = false)
- var skipGenotyping: Boolean = false
-
- @Argument(doc = "Merge gvcfs", shortName = "mergegvcfs", required = false)
- var mergeGvcfs: Boolean = false
-
- @Argument(doc = "Joint variantcalling", shortName = "jointVariantCalling", required = false)
- var jointVariantcalling: Boolean = config("joint_variantcalling", default = false)
-
- @Argument(doc = "Joint genotyping", shortName = "jointGenotyping", required = false)
- var jointGenotyping: Boolean = config("joint_genotyping", default = false)
-
- var singleSampleCalling = config("single_sample_calling", default = true)
- var reference: File = config("reference", required = true)
- var dbsnp: File = config("dbsnp")
- var gvcfFiles: List[File] = Nil
- var finalBamFiles: List[File] = Nil
- var useAllelesOption: Boolean = config("use_alleles_option", default = false)
-
- class LibraryOutput extends AbstractLibraryOutput {
- var mappedBamFile: File = _
- var variantcalling: GatkVariantcalling.ScriptOutput = _
- }
-
- class SampleOutput extends AbstractSampleOutput {
- var variantcalling: GatkVariantcalling.ScriptOutput = _
- }
-
- def init() {
- if (config.contains("target_bed")) {
- defaults ++= Map("gatk" -> Map(("intervals" -> config("target_bed").asStringList)))
- }
- if (config.contains("gvcfFiles"))
- for (file <- config("gvcfFiles").asList)
- gvcfFiles :+= file.toString
- if (outputDir == null) throw new IllegalStateException("Missing Output directory on gatk module")
- else if (!outputDir.endsWith("/")) outputDir += "/"
- }
-
- val multisampleVariantcalling = new GatkVariantcalling(this) {
- override protected lazy val configName = "gatkvariantcalling"
- override def configPath: List[String] = "multisample" :: super.configPath
- }
-
- def biopetScript() {
- if (onlySample.isEmpty) {
- runSamplesJobs
-
- //SampleWide jobs
- if (mergeGvcfs && gvcfFiles.size > 0) {
- val newFile = outputDir + "merged.gvcf.vcf.gz"
- add(CombineGVCFs(this, gvcfFiles, newFile))
- gvcfFiles = List(newFile)
- }
-
- if (!skipGenotyping && gvcfFiles.size > 0) {
- if (jointGenotyping) {
- val gatkGenotyping = new GatkGenotyping(this)
- gatkGenotyping.inputGvcfs = gvcfFiles
- gatkGenotyping.outputDir = outputDir + "genotyping/"
- gatkGenotyping.init
- gatkGenotyping.biopetScript
- addAll(gatkGenotyping.functions)
- var vcfFile = gatkGenotyping.outputFile
- }
- } else logger.warn("No gVCFs to genotype")
-
- if (jointVariantcalling) {
- val allBamfiles = for (
- (sampleID, sampleOutput) <- samplesOutput;
- file <- sampleOutput.variantcalling.bamFiles
- ) yield file
- val allRawVcfFiles = for ((sampleID, sampleOutput) <- samplesOutput) yield sampleOutput.variantcalling.rawFilterVcfFile
-
- val gatkVariantcalling = new GatkVariantcalling(this) {
- override protected lazy val configName = "gatkvariantcalling"
- override def configPath: List[String] = "multisample" :: super.configPath
- }
-
- if (gatkVariantcalling.useMpileup) {
- val cvRaw = CombineVariants(this, allRawVcfFiles.toList, outputDir + "variantcalling/multisample.raw.vcf.gz")
- add(cvRaw)
- gatkVariantcalling.rawVcfInput = cvRaw.out
- }
-
- multisampleVariantcalling.preProcesBams = false
- multisampleVariantcalling.doublePreProces = false
- multisampleVariantcalling.inputBams = allBamfiles.toList
- multisampleVariantcalling.outputDir = outputDir + "variantcalling"
- multisampleVariantcalling.outputName = "multisample"
- multisampleVariantcalling.init
- multisampleVariantcalling.biopetScript
- addAll(multisampleVariantcalling.functions)
-
- if (config("inputtype", default = "dna").asString != "rna" && config("recalibration", default = false).asBoolean) {
- val recalibration = new GatkVariantRecalibration(this)
- recalibration.inputVcf = multisampleVariantcalling.scriptOutput.finalVcfFile
- recalibration.bamFiles = finalBamFiles
- recalibration.outputDir = outputDir + "recalibration/"
- recalibration.init
- recalibration.biopetScript
- }
- }
- } else for (sample <- onlySample) runSingleSampleJobs(sample)
- }
-
- // Called for each sample
- def runSingleSampleJobs(sampleConfig: Map[String, Any]): SampleOutput = {
- val sampleOutput = new SampleOutput
- var libraryBamfiles: List[File] = List()
- val sampleID: String = sampleConfig("ID").toString
- sampleOutput.libraries = runLibraryJobs(sampleConfig)
- val sampleDir = globalSampleDir + sampleID
- for ((libraryID, libraryOutput) <- sampleOutput.libraries) {
- libraryBamfiles ++= libraryOutput.variantcalling.bamFiles
- }
-
- if (libraryBamfiles.size > 0) {
- finalBamFiles ++= libraryBamfiles
- val gatkVariantcalling = new GatkVariantcalling(this)
- gatkVariantcalling.inputBams = libraryBamfiles
- gatkVariantcalling.outputDir = sampleDir + "/variantcalling/"
- gatkVariantcalling.preProcesBams = false
- if (!singleSampleCalling) {
- gatkVariantcalling.useHaplotypecaller = false
- gatkVariantcalling.useUnifiedGenotyper = false
- }
- gatkVariantcalling.sampleID = sampleID
- gatkVariantcalling.init
- gatkVariantcalling.biopetScript
- addAll(gatkVariantcalling.functions)
- sampleOutput.variantcalling = gatkVariantcalling.scriptOutput
- gvcfFiles :+= gatkVariantcalling.scriptOutput.gvcfFile
- } else logger.warn("No bamfiles for variant calling for sample: " + sampleID)
- return sampleOutput
- }
-
- // Called for each run from a sample
- def runSingleLibraryJobs(runConfig: Map[String, Any], sampleConfig: Map[String, Any]): LibraryOutput = {
- val libraryOutput = new LibraryOutput
- val runID: String = runConfig("ID").toString
- val sampleID: String = sampleConfig("ID").toString
- val runDir: String = globalSampleDir + sampleID + "/run_" + runID + "/"
- var inputType = ""
- if (runConfig.contains("inputtype")) inputType = runConfig("inputtype").toString
- else inputType = config("inputtype", default = "dna").toString
- if (runConfig.contains("R1")) {
- val mapping = Mapping.loadFromLibraryConfig(this, runConfig, sampleConfig, runDir)
- addAll(mapping.functions) // Add functions of mapping to curent function pool
- libraryOutput.mappedBamFile = mapping.outputFiles("finalBamFile")
- } else if (runConfig.contains("bam")) {
- var bamFile = new File(runConfig("bam").toString)
- if (!bamFile.exists) throw new IllegalStateException("Bam in config does not exist, file: " + bamFile)
-
- if (config("bam_to_fastq", default = false).asBoolean) {
- val samToFastq = SamToFastq(this, bamFile, runDir + sampleID + "-" + runID + ".R1.fastq",
- runDir + sampleID + "-" + runID + ".R2.fastq")
- add(samToFastq, isIntermediate = true)
- val mapping = Mapping.loadFromLibraryConfig(this, runConfig, sampleConfig, runDir, startJobs = false)
- mapping.input_R1 = samToFastq.fastqR1
- mapping.input_R2 = samToFastq.fastqR2
- mapping.init
- mapping.biopetScript
- addAll(mapping.functions) // Add functions of mapping to curent function pool
- libraryOutput.mappedBamFile = mapping.outputFiles("finalBamFile")
- } else {
- var readGroupOke = true
- val inputSam = SamReaderFactory.makeDefault.open(bamFile)
- val header = inputSam.getFileHeader.getReadGroups
- for (readGroup <- inputSam.getFileHeader.getReadGroups) {
- if (readGroup.getSample != sampleID) logger.warn("Sample ID readgroup in bam file is not the same")
- if (readGroup.getLibrary != runID) logger.warn("Library ID readgroup in bam file is not the same")
- if (readGroup.getSample != sampleID || readGroup.getLibrary != runID) readGroupOke = false
- }
- inputSam.close
-
- if (!readGroupOke) {
- if (config("correct_readgroups", default = false)) {
- logger.info("Correcting readgroups, file:" + bamFile)
- val aorrg = AddOrReplaceReadGroups(this, bamFile, new File(runDir + sampleID + "-" + runID + ".bam"))
- aorrg.RGID = sampleID + "-" + runID
- aorrg.RGLB = runID
- aorrg.RGSM = sampleID
- if (runConfig.contains("PL")) aorrg.RGPL = runConfig("PL").toString
- else aorrg.RGPL = "illumina"
- if (runConfig.contains("PU")) aorrg.RGPU = runConfig("PU").toString
- else aorrg.RGPU = "na"
- if (runConfig.contains("CN")) aorrg.RGCN = runConfig("CN").toString
- add(aorrg, isIntermediate = true)
- bamFile = aorrg.output
- } else throw new IllegalStateException("Readgroup sample and/or library of input bamfile is not correct, file: " + bamFile +
- "\nPossible to set 'correct_readgroups' to true on config to automatic fix this")
- }
- addAll(BamMetrics(this, bamFile, runDir + "metrics/").functions)
-
- libraryOutput.mappedBamFile = bamFile
- }
- } else logger.error("Sample: " + sampleID + ": No R1 found for run: " + runConfig)
-
- val gatkVariantcalling = new GatkVariantcalling(this)
- gatkVariantcalling.inputBams = List(libraryOutput.mappedBamFile)
- gatkVariantcalling.outputDir = runDir
- gatkVariantcalling.variantcalling = config("library_variantcalling", default = false)
- gatkVariantcalling.preProcesBams = true
- gatkVariantcalling.sampleID = sampleID
- gatkVariantcalling.init
- gatkVariantcalling.biopetScript
- addAll(gatkVariantcalling.functions)
- libraryOutput.variantcalling = gatkVariantcalling.scriptOutput
-
- return libraryOutput
- }
-}
-
-object GatkPipeline extends PipelineCommand
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantRecalibration.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantRecalibration.scala
deleted file mode 100644
index d5dcdb9f2..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantRecalibration.scala
+++ /dev/null
@@ -1,76 +0,0 @@
-package nl.lumc.sasc.biopet.pipelines.gatk
-
-import nl.lumc.sasc.biopet.core.BiopetQScript
-import nl.lumc.sasc.biopet.core.PipelineCommand
-import nl.lumc.sasc.biopet.core.config.Configurable
-import nl.lumc.sasc.biopet.extensions.gatk.ApplyRecalibration
-import nl.lumc.sasc.biopet.extensions.gatk.VariantAnnotator
-import nl.lumc.sasc.biopet.extensions.gatk.VariantRecalibrator
-import org.broadinstitute.gatk.queue.QScript
-
-class GatkVariantRecalibration(val root: Configurable) extends QScript with BiopetQScript {
- def this() = this(null)
-
- @Input(doc = "input vcf file", shortName = "I")
- var inputVcf: File = _
-
- @Input(doc = "input vcf file", shortName = "BAM", required = false)
- var bamFiles: List[File] = Nil
-
- @Output(doc = "output vcf file", shortName = "out")
- var outputVcf: File = _
-
- def init() {
- if (inputVcf == null) throw new IllegalStateException("Missing Output directory on gatk module")
- if (outputDir == null) throw new IllegalStateException("Missing Output directory on gatk module")
- else if (!outputDir.endsWith("/")) outputDir += "/"
- }
-
- def biopetScript() {
- var vcfFile: File = if (!bamFiles.isEmpty) addVariantAnnotator(inputVcf, bamFiles, outputDir) else inputVcf
- vcfFile = addSnpVariantRecalibrator(vcfFile, outputDir)
- vcfFile = addIndelVariantRecalibrator(vcfFile, outputDir)
- }
-
- def addSnpVariantRecalibrator(inputVcf: File, dir: String): File = {
- val snpRecal = VariantRecalibrator(this, inputVcf, swapExt(dir, inputVcf, ".vcf", ".indel.recal"),
- swapExt(dir, inputVcf, ".vcf", ".indel.tranches"), indel = false)
- if (!snpRecal.resource.isEmpty) {
- add(snpRecal)
-
- val snpApply = ApplyRecalibration(this, inputVcf, swapExt(dir, inputVcf, ".vcf", ".indel.recal.vcf"),
- snpRecal.recal_file, snpRecal.tranches_file, indel = false)
- add(snpApply)
-
- return snpApply.out
- } else {
- logger.warn("Skipped snp Recalibration, resource is missing")
- return inputVcf
- }
- }
-
- def addIndelVariantRecalibrator(inputVcf: File, dir: String): File = {
- val indelRecal = VariantRecalibrator(this, inputVcf, swapExt(dir, inputVcf, ".vcf", ".indel.recal"),
- swapExt(dir, inputVcf, ".vcf", ".indel.tranches"), indel = true)
- if (!indelRecal.resource.isEmpty) {
- add(indelRecal)
-
- val indelApply = ApplyRecalibration(this, inputVcf, swapExt(dir, inputVcf, ".vcf", ".indel.recal.vcf"),
- indelRecal.recal_file, indelRecal.tranches_file, indel = true)
- add(indelApply)
-
- return indelApply.out
- } else {
- logger.warn("Skipped indel Recalibration, resource is missing")
- return inputVcf
- }
- }
-
- def addVariantAnnotator(inputvcf: File, bamfiles: List[File], dir: String): File = {
- val variantAnnotator = VariantAnnotator(this, inputvcf, bamfiles, swapExt(dir, inputvcf, ".vcf", ".anotated.vcf"))
- add(variantAnnotator)
- return variantAnnotator.out
- }
-}
-
-object GatkVariantRecalibration extends PipelineCommand
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantcalling.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantcalling.scala
deleted file mode 100644
index d34466a00..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantcalling.scala
+++ /dev/null
@@ -1,244 +0,0 @@
-package nl.lumc.sasc.biopet.pipelines.gatk
-
-import nl.lumc.sasc.biopet.core.{ BiopetQScript, PipelineCommand }
-import java.io.File
-import nl.lumc.sasc.biopet.tools.{ 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 }
-import nl.lumc.sasc.biopet.extensions.picard.MarkDuplicates
-import org.broadinstitute.gatk.queue.QScript
-import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
-import org.broadinstitute.gatk.utils.commandline.{ Input, Argument }
-import scala.collection.SortedMap
-import scala.language.reflectiveCalls
-
-class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScript {
- def this() = this(null)
-
- val scriptOutput = new GatkVariantcalling.ScriptOutput
-
- @Input(doc = "Bam files (should be deduped bams)", shortName = "BAM")
- var inputBams: List[File] = Nil
-
- @Input(doc = "Raw vcf file", shortName = "raw")
- var rawVcfInput: File = _
-
- @Argument(doc = "Reference", shortName = "R", required = false)
- var reference: File = config("reference", required = true)
-
- @Argument(doc = "Dbsnp", shortName = "dbsnp", required = false)
- var dbsnp: File = config("dbsnp")
-
- @Argument(doc = "OutputName", required = false)
- var outputName: String = _
-
- @Argument(doc = "Sample name", required = false)
- var sampleID: String = _
-
- var preProcesBams: Option[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 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)
-
- def init() {
- if (outputName == null && sampleID != null) outputName = sampleID
- else if (outputName == null) outputName = "noname"
- if (outputDir == null) throw new IllegalStateException("Missing Output directory on gatk module")
- else if (!outputDir.endsWith("/")) outputDir += "/"
-
- val baseRecalibrator = new BaseRecalibrator(this)
- if (preProcesBams && useBaseRecalibration && baseRecalibrator.knownSites.isEmpty) {
- logger.warn("No Known site found, skipping base recalibration")
- useBaseRecalibration = false
- }
- }
-
- 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"))
- add(markDup, isIntermediate = useIndelRealigner)
- 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)
- }
- bamFiles :+= bamFile
- }
- doublePreProces(bamFiles)
- } else if (inputBams.size > 1 && doublePreProces.get) {
- doublePreProces(inputBams)
- } 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)) {
- val hcGvcf = new HaplotypeCaller(this)
- hcGvcf.useGvcf
- hcGvcf.input_file = scriptOutput.bamFiles
- hcGvcf.out = outputDir + outputName + ".hc.discovery.gvcf.vcf.gz"
- add(hcGvcf)
- scriptOutput.gvcfFile = hcGvcf.out
- }
-
- if (useHaplotypecaller.get) {
- if (sampleID != null) {
- val genotypeGVCFs = GenotypeGVCFs(this, List(scriptOutput.gvcfFile), outputDir + outputName + ".hc.discovery.vcf.gz")
- add(genotypeGVCFs)
- scriptOutput.hcVcfFile = genotypeGVCFs.out
- } else {
- val hcGvcf = new HaplotypeCaller(this)
- hcGvcf.input_file = scriptOutput.bamFiles
- hcGvcf.out = outputDir + outputName + ".hc.discovery.vcf.gz"
- add(hcGvcf)
- scriptOutput.hcVcfFile = hcGvcf.out
- }
- mergBuffer += ("1.HC-Discovery" -> scriptOutput.hcVcfFile)
- }
-
- if (useUnifiedGenotyper.get) {
- val ugVcf = new UnifiedGenotyper(this)
- ugVcf.input_file = scriptOutput.bamFiles
- ugVcf.out = outputDir + outputName + ".ug.discovery.vcf.gz"
- add(ugVcf)
- scriptOutput.ugVcfFile = ugVcf.out
- mergBuffer += ("2.UG-Discovery" -> scriptOutput.ugVcfFile)
- }
-
- // Generate raw vcf
- if (useMpileup) {
- if (sampleID != null && scriptOutput.bamFiles.size == 1) {
- val m2v = new MpileupToVcf(this)
- m2v.inputBam = scriptOutput.bamFiles.head
- m2v.sample = sampleID
- m2v.output = outputDir + outputName + ".raw.vcf"
- add(m2v)
- scriptOutput.rawVcfFile = m2v.output
-
- val vcfFilter = new VcfFilter(this)
- vcfFilter.defaults ++= Map("min_sample_depth" -> 8,
- "min_alternate_depth" -> 2,
- "min_samples_pass" -> 1,
- "filter_ref_calls" -> true)
- vcfFilter.inputVcf = m2v.output
- vcfFilter.outputVcf = this.swapExt(outputDir, m2v.output, ".vcf", ".filter.vcf.gz")
- add(vcfFilter)
- scriptOutput.rawFilterVcfFile = vcfFilter.outputVcf
- } else if (rawVcfInput != null) scriptOutput.rawFilterVcfFile = rawVcfInput
- if (scriptOutput.rawFilterVcfFile == null) throw new IllegalStateException("Files can't be empty")
- mergBuffer += ("9.raw" -> scriptOutput.rawFilterVcfFile)
- }
-
- // Allele mode
- if (useAllelesOption.get) {
- val mergeAlleles = MergeAlleles(this, mergeList.toList, outputDir + "raw.allele__temp_only.vcf.gz")
- add(mergeAlleles, isIntermediate = true)
-
- if (useHaplotypecaller.get) {
- val hcAlleles = new HaplotypeCaller(this)
- hcAlleles.input_file = scriptOutput.bamFiles
- hcAlleles.out = outputDir + outputName + ".hc.allele.vcf.gz"
- hcAlleles.alleles = mergeAlleles.output
- hcAlleles.genotyping_mode = org.broadinstitute.gatk.tools.walkers.genotyper.GenotypingOutputMode.GENOTYPE_GIVEN_ALLELES
- add(hcAlleles)
- scriptOutput.hcAlleleVcf = hcAlleles.out
- mergBuffer += ("3.HC-alleles" -> hcAlleles.out)
- }
-
- if (useUnifiedGenotyper.get) {
- val ugAlleles = new UnifiedGenotyper(this)
- ugAlleles.input_file = scriptOutput.bamFiles
- ugAlleles.out = outputDir + outputName + ".ug.allele.vcf.gz"
- ugAlleles.alleles = mergeAlleles.output
- ugAlleles.genotyping_mode = org.broadinstitute.gatk.tools.walkers.genotyper.GenotypingOutputMode.GENOTYPE_GIVEN_ALLELES
- add(ugAlleles)
- scriptOutput.ugAlleleVcf = ugAlleles.out
- mergBuffer += ("4.UG-alleles" -> ugAlleles.out)
- }
- }
-
- def removeNoneVariants(input: File): File = {
- val output = input.getAbsolutePath.stripSuffix(".vcf.gz") + ".variants_only.vcf.gz"
- val sv = SelectVariants(this, input, output)
- sv.excludeFiltered = true
- sv.excludeNonVariants = true
- add(sv, isIntermediate = true)
- sv.out
- }
-
- val cvFinal = CombineVariants(this, mergeList.toList, outputDir + outputName + ".final.vcf.gz")
- cvFinal.genotypemergeoption = org.broadinstitute.gatk.utils.variant.GATKVariantContextUtils.GenotypeMergeType.UNSORTED
- add(cvFinal)
- scriptOutput.finalVcfFile = cvFinal.out
- }
- }
-
- def addIndelRealign(inputBam: File, dir: String, isIntermediate: Boolean = true): File = {
- val realignerTargetCreator = RealignerTargetCreator(this, inputBam, dir)
- add(realignerTargetCreator, isIntermediate = true)
-
- val indelRealigner = IndelRealigner.apply(this, inputBam, realignerTargetCreator.out, dir)
- add(indelRealigner, isIntermediate = isIntermediate)
-
- return indelRealigner.o
- }
-
- def addBaseRecalibrator(inputBam: File, dir: String, isIntermediate: Boolean = false): File = {
- val baseRecalibrator = BaseRecalibrator(this, inputBam, swapExt(dir, inputBam, ".bam", ".baserecal"))
-
- if (baseRecalibrator.knownSites.isEmpty) {
- logger.warn("No Known site found, skipping base recalibration, file: " + inputBam)
- return inputBam
- }
- add(baseRecalibrator)
-
- if (config("use_analyze_covariates", default = false).asBoolean) {
- val baseRecalibratorAfter = BaseRecalibrator(this, inputBam, swapExt(dir, inputBam, ".bam", ".baserecal.after"))
- baseRecalibratorAfter.BQSR = baseRecalibrator.o
- add(baseRecalibratorAfter)
-
- add(AnalyzeCovariates(this, baseRecalibrator.o, baseRecalibratorAfter.o, swapExt(dir, inputBam, ".bam", ".baserecal.pdf")))
- }
-
- val printReads = PrintReads(this, inputBam, swapExt(dir, inputBam, ".bam", ".baserecal.bam"))
- printReads.BQSR = baseRecalibrator.o
- add(printReads, isIntermediate = isIntermediate)
-
- return printReads.o
- }
-}
-
-object GatkVariantcalling extends PipelineCommand {
- class ScriptOutput {
- var bamFiles: List[File] = _
- var gvcfFile: File = _
- var hcVcfFile: File = _
- var ugVcfFile: File = _
- var rawVcfFile: File = _
- var rawFilterVcfFile: File = _
- var hcAlleleVcf: File = _
- var ugAlleleVcf: File = _
- var finalVcfFile: File = _
- }
-}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVcfSampleCompare.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVcfSampleCompare.scala
deleted file mode 100644
index 6fdbefd4c..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVcfSampleCompare.scala
+++ /dev/null
@@ -1,82 +0,0 @@
-package nl.lumc.sasc.biopet.pipelines.gatk
-
-import nl.lumc.sasc.biopet.core.{ BiopetQScript, PipelineCommand }
-import java.io.File
-import nl.lumc.sasc.biopet.core.config.Configurable
-import nl.lumc.sasc.biopet.extensions.gatk.CombineVariants
-import nl.lumc.sasc.biopet.extensions.gatk.SelectVariants
-import nl.lumc.sasc.biopet.extensions.gatk.VariantEval
-import org.broadinstitute.gatk.queue.QScript
-import org.broadinstitute.gatk.utils.commandline.{ Input, Argument }
-
-class GatkVcfSampleCompare(val root: Configurable) extends QScript with BiopetQScript {
- def this() = this(null)
-
- @Input(doc = "Sample vcf file(s)", shortName = "V")
- var vcfFiles: List[File] = _
-
- @Argument(doc = "Reference", shortName = "R", required = false)
- var reference: File = config("reference")
-
- @Argument(doc = "Target bed", shortName = "targetBed", required = false)
- var targetBed: List[File] = Nil
-
- @Argument(doc = "Samples", shortName = "sample", required = false)
- var samples: List[String] = Nil
-
- var vcfFile: File = _
- var sampleVcfs: Map[String, File] = Map()
- def generalSampleDir = outputDir + "samples/"
-
- def init() {
- if (config.contains("target_bed"))
- for (bed <- config("target_bed").asList)
- targetBed :+= bed.toString
- if (outputDir == null) throw new IllegalStateException("Missing Output directory on gatk module")
- else if (!outputDir.endsWith("/")) outputDir += "/"
- }
-
- def biopetScript() {
- vcfFile = if (vcfFiles.size > 1) {
- val combineVariants = CombineVariants(this, vcfFiles, outputDir + "merge.vcf")
- add(combineVariants)
- combineVariants.out
- } else vcfFiles.head
-
- for (sample <- samples) {
- sampleVcfs += (sample -> new File(generalSampleDir + sample + File.separator + sample + ".vcf"))
- val selectVariants = SelectVariants(this, vcfFile, sampleVcfs(sample))
- selectVariants.sample_name = Seq(sample)
- selectVariants.excludeNonVariants = true
- add(selectVariants)
- }
-
- val sampleCompareMetrics = new SampleCompareMetrics(this)
- sampleCompareMetrics.samples = samples
- sampleCompareMetrics.sampleDir = generalSampleDir
- sampleCompareMetrics.snpRelFile = outputDir + "compare.snp.rel.tsv"
- sampleCompareMetrics.snpAbsFile = outputDir + "compare.snp.abs.tsv"
- sampleCompareMetrics.indelRelFile = outputDir + "compare.indel.rel.tsv"
- sampleCompareMetrics.indelAbsFile = outputDir + "compare.indel.abs.tsv"
- sampleCompareMetrics.totalFile = outputDir + "total.tsv"
-
- for ((sample, sampleVcf) <- sampleVcfs) {
- val sampleDir = generalSampleDir + sample + File.separator
- for ((compareSample, compareSampleVcf) <- sampleVcfs) {
- val variantEval = VariantEval(this,
- sampleVcf,
- compareSampleVcf,
- new File(sampleDir + sample + "-" + compareSample + ".eval.txt"),
- Seq("VariantType", "CompRod"),
- Seq("CompOverlap")
- )
- if (targetBed != null) variantEval.L = targetBed
- add(variantEval)
- sampleCompareMetrics.deps ::= variantEval.out
- }
- }
- add(sampleCompareMetrics)
- }
-}
-
-object GatkVcfSampleCompare extends PipelineCommand
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/SampleCompareMetrics.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/SampleCompareMetrics.scala
deleted file mode 100644
index b66ac47c3..000000000
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/SampleCompareMetrics.scala
+++ /dev/null
@@ -1,148 +0,0 @@
-package nl.lumc.sasc.biopet.pipelines.gatk
-
-import java.io.File
-import java.io.PrintWriter
-import nl.lumc.sasc.biopet.core.BiopetJavaCommandLineFunction
-import nl.lumc.sasc.biopet.core.config.Configurable
-import org.broadinstitute.gatk.utils.R.RScriptExecutor
-import org.broadinstitute.gatk.utils.commandline.{ Output, Argument }
-import scala.io.Source
-import org.broadinstitute.gatk.utils.R.{ RScriptLibrary, RScriptExecutor }
-import org.broadinstitute.gatk.utils.io.Resource
-import scala.collection.mutable.Map
-import scala.math._
-
-class SampleCompareMetrics(val root: Configurable) extends BiopetJavaCommandLineFunction {
- javaMainClass = getClass.getName
-
- @Argument(doc = "Sample Dir", shortName = "sampleDir", required = true)
- var sampleDir: String = _
-
- @Argument(doc = "Samples", shortName = "sample", required = true)
- var samples: List[String] = Nil
-
- @Argument(doc = "File sufix", shortName = "sufix", required = false)
- var fileSufix: String = _
-
- @Output(doc = "snpRelFile", shortName = "snpRelFile", required = true)
- var snpRelFile: File = _
-
- @Output(doc = "snpAbsFile", shortName = "snpAbsFile", required = true)
- var snpAbsFile: File = _
-
- @Output(doc = "indelRelFile", shortName = "indelRelFile", required = true)
- var indelRelFile: File = _
-
- @Output(doc = "indelAbsFile", shortName = "indelAbsFile", required = true)
- var indelAbsFile: File = _
-
- @Output(doc = "totalFile", shortName = "totalFile", required = true)
- var totalFile: File = _
-
- override val defaultVmem = "8G"
- memoryLimit = Option(4.0)
-
- override def commandLine = super.commandLine +
- required("-sampleDir", sampleDir) +
- repeat("-sample", samples) +
- optional("-fileSufix", fileSufix) +
- required("-snpRelFile", snpRelFile) +
- required("-snpAbsFile", snpAbsFile) +
- required("-indelRelFile", indelRelFile) +
- required("-indelAbsFile", indelAbsFile) +
- required("-totalFile", totalFile)
-}
-
-object SampleCompareMetrics {
- var sampleDir: String = _
- var samples: List[String] = Nil
- var fileSufix: String = ".eval.txt"
- var snpRelFile: File = _
- var snpAbsFile: File = _
- var indelRelFile: File = _
- var indelAbsFile: File = _
- var totalFile: File = _
- /**
- * @param args the command line arguments
- */
- def main(args: Array[String]): Unit = {
-
- for (t <- 0 until args.size) {
- args(t) match {
- case "-sample" => samples +:= args(t + 1)
- case "-sampleDir" => sampleDir = args(t + 1)
- case "-fileSufix" => fileSufix = args(t + 1)
- case "-snpRelFile" => snpRelFile = new File(args(t + 1))
- case "-snpAbsFile" => snpAbsFile = new File(args(t + 1))
- case "-indelRelFile" => indelRelFile = new File(args(t + 1))
- case "-indelAbsFile" => indelAbsFile = new File(args(t + 1))
- case "-totalFile" => totalFile = new File(args(t + 1))
- case _ =>
- }
- }
- if (sampleDir == null) throw new IllegalStateException("No sampleDir, use -sampleDir")
- else if (!sampleDir.endsWith("/")) sampleDir += "/"
-
- val regex = """\W+""".r
- val snpsOverlap: Map[(String, String), Int] = Map()
- val indelsOverlap: Map[(String, String), Int] = Map()
- val snpsTotal: Map[String, Int] = Map()
- val indelsTotal: Map[String, Int] = Map()
- for (sample1 <- samples; sample2 <- samples) {
- val reader = Source.fromFile(new File(sampleDir + sample1 + "/" + sample1 + "-" + sample2 + fileSufix))
- for (line <- reader.getLines) {
- regex.split(line) match {
- case Array(_, _, _, varType, all, novel, overlap, rate, _*) => {
- varType match {
- case "SNP" => {
- snpsOverlap += (sample1, sample2) -> overlap.toInt
- snpsTotal += sample1 -> all.toInt
- }
- case "INDEL" => {
- indelsOverlap += (sample1, sample2) -> overlap.toInt
- indelsTotal += sample1 -> all.toInt
- }
- case _ =>
- }
- }
- case _ =>
- }
- }
- reader.close()
- }
-
- val snpRelWritter = new PrintWriter(snpRelFile)
- val snpAbsWritter = new PrintWriter(snpAbsFile)
- val indelRelWritter = new PrintWriter(indelRelFile)
- val indelAbsWritter = new PrintWriter(indelAbsFile)
-
- val allWritters = List(snpRelWritter, snpAbsWritter, indelRelWritter, indelAbsWritter)
- for (writter <- allWritters) writter.println(samples.mkString("\t", "\t", ""))
- for (sample1 <- samples) {
- for (writter <- allWritters) writter.print(sample1)
- for (sample2 <- samples) {
- snpRelWritter.print("\t" + (round((snpsOverlap(sample1, sample2).toDouble / snpsTotal(sample1) * 10000.0)) / 10000.0))
- snpAbsWritter.print("\t" + snpsOverlap(sample1, sample2))
- indelRelWritter.print("\t" + (round((indelsOverlap(sample1, sample2).toDouble / indelsTotal(sample1) * 10000.0)) / 10000.0))
- indelAbsWritter.print("\t" + indelsOverlap(sample1, sample2))
- }
- for (writter <- allWritters) writter.println()
- }
- for (writter <- allWritters) writter.close()
-
- val totalWritter = new PrintWriter(totalFile)
- totalWritter.println("Sample\tSNPs\tIndels")
- for (sample <- samples)
- totalWritter.println(sample + "\t" + snpsTotal(sample) + "\t" + indelsTotal(sample))
- totalWritter.close()
-
- def plot(file: File) {
- val executor = new RScriptExecutor
- executor.addScript(new Resource("plotHeatmap.R", getClass))
- executor.addArgs(file, file.getAbsolutePath.stripSuffix(".tsv") + ".png", file.getAbsolutePath.stripSuffix(".tsv") + ".clustering.png")
- executor.exec()
- }
- plot(snpRelFile)
- plot(indelRelFile)
- }
-}
\ No newline at end of file
--
GitLab