From 34ab5b48898619953e2185c4a0636998b1c66757 Mon Sep 17 00:00:00 2001 From: rpoplin Date: Sun, 19 Dec 2010 21:13:25 +0000 Subject: [PATCH] Turning on BAQ in Methods Development pipeline. A new dataset is added: 363 EUR samples from the November 1000G release. git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@4877 348d0f76-0448-11de-a6fe-93d51630548a --- .../MethodsDevelopmentCallingPipeline.scala | 30 ++++++++++++------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/scala/qscript/rpoplin/MethodsDevelopmentCallingPipeline.scala b/scala/qscript/rpoplin/MethodsDevelopmentCallingPipeline.scala index 3f38f457d..67e498335 100755 --- a/scala/qscript/rpoplin/MethodsDevelopmentCallingPipeline.scala +++ b/scala/qscript/rpoplin/MethodsDevelopmentCallingPipeline.scala @@ -18,7 +18,7 @@ class MethodsDevelopmentCallingPipeline extends QScript { trait UNIVERSAL_GATK_ARGS extends CommandLineGATK { logging_level = "INFO"; jarFile = gatkJarFile; memoryLimit = Some(4); } - class Target(val baseName: String, val reference: File, val rodName: String, val bamList: File, val goldStandard_VCF: File, val intervals: String, val titvTarget: Double) { + class Target(val baseName: String, val reference: File, val rodName: String, val bamList: File, val goldStandard_VCF: File, val intervals: String, val titvTarget: Double, val isLowpass: Boolean) { def name = qscript.outputDir + baseName def clusterFile = new File(name + ".clusters") def rawVCF = new File(name + ".raw.vcf") @@ -32,32 +32,37 @@ class MethodsDevelopmentCallingPipeline extends QScript { val b37 = new File("/humgen/1kg/reference/human_g1k_v37.fasta") // Define the target datasets here + def lowPass = true val HiSeq = new Target("NA12878.HiSeq", hg18, "hg18", new File("/humgen/gsa-hpprojects/NA12878Collection/bams/NA12878.GA2.WGS.bwa.cleaned.bam"), new File("/home/radon01/depristo/work/oneOffProjects/1000GenomesProcessingPaper/wgs.v13/HiSeq.WGS.cleaned.ug.snpfiltered.indelfiltered.vcf"), - "/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.hg18.intervals", 2.07) + "/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.hg18.intervals", 2.07, !lowPass) val WEx = new Target("NA12878.WEx", hg18, "hg18", new File("/humgen/gsa-hpprojects/NA12878Collection/bams/NA12878.WEx.cleaned.recal.bam"), new File("/home/radon01/depristo/work/oneOffProjects/1000GenomesProcessingPaper/wgs.v13/GA2.WEx.cleaned.ug.snpfiltered.indelfiltered.vcf"), - "/seq/references/HybSelOligos/whole_exome_agilent_1.1_refseq_plus_3_boosters/whole_exome_agilent_1.1_refseq_plus_3_boosters.targets.interval_list", 2.6) + "/seq/references/HybSelOligos/whole_exome_agilent_1.1_refseq_plus_3_boosters/whole_exome_agilent_1.1_refseq_plus_3_boosters.targets.interval_list", 2.6, !lowPass) val LowPassN60 = new Target("lowpass.N60", b36, "b36", // which reference the data is aligned to new File("/humgen/1kg/analysis/bamsForDataProcessingPapers/lowpass_b36/lowpass.chr20.cleaned.matefixed.bam"), // the bam list to call from new File("/home/radon01/depristo/work/oneOffProjects/VQSRCutByNRS/lowpass.N60.chr20.filtered.vcf"), // the gold standard VCF file to compare against - "/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.chr20.b36.intervals", 2.3) // chunked interval list to use with Queue's scatter/gather functionality + "/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.chr20.b36.intervals", 2.3, lowPass) // chunked interval list to use with Queue's scatter/gather functionality val LowPassAugust = new Target("ALL.august.v4", b37, "b37", new File("/humgen/1kg/processing/allPopulations_chr20_august_release.cleaned.merged.bams/ALL.cleaned.merged.list"), new File("/humgen/gsa-hpprojects/dev/data/AugChr20Calls_v4_3state/ALL.august.v4.chr20.filtered.vcf"), - "/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.chr20.hg19.intervals", 2.3) + "/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.chr20.hg19.intervals", 2.3, lowPass) + val LowPassEUR363Nov = new Target("EUR.nov2010", b37, "b37", + new File("/humgen/1kg/processing/pipeline_test_bams/EUR.363sample.Nov2010.chr20.bam"), + new File("/humgen/gsa-hpprojects/dev/data/AugChr20Calls_v4_3state/ALL.august.v4.chr20.filtered.vcf"), // ** THIS GOLD STANDARD NEEDS TO BE CORRECTED ** + "/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.chr20.hg19.intervals", 2.3, lowPass) val LowPassFIN79Nov = new Target("FIN.nov2010", b37, "b37", new File("/humgen/1kg/processing/pipeline_test_bams/FIN.79sample.Nov2010.chr20.bam"), new File("/humgen/gsa-hpprojects/dev/data/AugChr20Calls_v4_3state/ALL.august.v4.chr20.filtered.vcf"), // ** THIS GOLD STANDARD NEEDS TO BE CORRECTED ** - "/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.chr20.hg19.intervals", 2.3) + "/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.chr20.hg19.intervals", 2.3, lowPass) val TGPWExGdA = new Target("1000G.WEx.GdA", b37, "b37", new File("/humgen/1kg/processing/pipeline_test_bams/Barcoded_1000G_WEx_Reduced_Plate_1.cleaned.list"), new File("/humgen/gsa-scr1/delangel/NewUG/calls/AugustRelease.filtered_Q50_QD5.0_SB0.0.allSamples.SNPs_hg19.WEx_UG_newUG_MQC.vcf"), // ** THIS GOLD STANDARD NEEDS TO BE CORRECTED ** - "/seq/references/HybSelOligos/whole_exome_agilent_1.1_refseq_plus_3_boosters/whole_exome_agilent_1.1_refseq_plus_3_boosters.Homo_sapiens_assembly19.targets.interval_list", 2.6) + "/seq/references/HybSelOligos/whole_exome_agilent_1.1_refseq_plus_3_boosters/whole_exome_agilent_1.1_refseq_plus_3_boosters.Homo_sapiens_assembly19.targets.interval_list", 2.6, !lowPass) - val targets = List(HiSeq, WEx, LowPassN60, LowPassAugust, LowPassFIN79Nov, TGPWExGdA) + val targets = List(HiSeq, WEx, LowPassN60, LowPassAugust, LowPassEUR363Nov, LowPassFIN79Nov, TGPWExGdA) def script = { def goldStandard = true @@ -85,10 +90,15 @@ class MethodsDevelopmentCallingPipeline extends QScript { this.reference_sequence = t.reference this.DBSNP = new File("/humgen/gsa-hpprojects/GATK/data/dbsnp_129_" + t.rodName + ".rod") this.intervalsString ++= List(t.intervals) - this.scatterCount = 50 - this.dcov = Some(250) + this.scatterCount = 64 + if( t.isLowpass ) { + this.dcov = Some(50) + } else { + this.dcov = Some(250) + } this.input_file :+= t.bamList this.out = t.rawVCF + this.baq = Some(org.broadinstitute.sting.utils.baq.BAQ.CalculationMode.RECALCULATE) this.analysisName = t.name + "_UG" }