Renaming datasets in the MDCP

Making dataset names and files generated by the MDCP more uniform.
This commit is contained in:
Mauricio Carneiro 2011-09-20 11:02:51 -04:00
parent 091c7197cd
commit 08ffb18b96
1 changed files with 26 additions and 14 deletions

View File

@ -98,40 +98,52 @@ class MethodsDevelopmentCallingPipeline extends QScript {
// BUGBUG: We no longer support b36/hg18 because several of the necessary files aren't available aligned to those references
val targetDataSets: Map[String, Target] = Map(
"HiSeq" -> new Target("NA12878.HiSeq", hg18, dbSNP_hg18_129, hapmap_hg18,
"NA12878_wgs_b37" -> new Target("NA12878.HiSeq.WGS.b37", hg19, dbSNP_b37, hapmap_b37, indelMask_b37,
new File("/humgen/gsa-hpprojects/NA12878Collection/bams/NA12878.HiSeq.WGS.bwa.cleaned.recal.hg19.bam"),
new File("/humgen/gsa-hpprojects/dev/carneiro/hiseq19/analysis/snps/NA12878.HiSeq19.filtered.vcf"),
"/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.noChrY.hg19.intervals", 2.14, 99.0, !lowPass, !exome, 1),
"NA12878_wgs_decoy" -> new Target("NA12878.HiSeq.WGS.b37_decoy", b37_decoy, dbSNP_b37, hapmap_b37, indelMask_b37,
new File("/humgen/gsa-hpprojects/NA12878Collection/bams/CEUTrio.HiSeq.WGS.b37_decoy.NA12878.clean.dedup.recal.bam"),
new File("/humgen/gsa-hpprojects/dev/carneiro/hiseq19/analysis/snps/NA12878.HiSeq19.filtered.vcf"), // ** THIS GOLD STANDARD NEEDS TO BE CORRECTED **
"/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.noChrY.hg19.intervals", 2.14, 99.0, !lowPass, !exome, 1),
"NA12878_wgs_hg18" -> new Target("NA12878.HiSeq.WGS.hg18", hg18, dbSNP_hg18_129, hapmap_hg18,
"/humgen/gsa-hpprojects/dev/depristo/oneOffProjects/1000GenomesProcessingPaper/wgs.v13/HiSeq.WGS.cleaned.indels.10.mask",
new File("/humgen/gsa-hpprojects/NA12878Collection/bams/NA12878.HiSeq.WGS.bwa.cleaned.recal.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", 2.14, 99.0, !lowPass, !exome, 1),
"HiSeq19" -> new Target("NA12878.HiSeq19", hg19, dbSNP_b37, hapmap_b37, indelMask_b37,
new File("/humgen/gsa-hpprojects/NA12878Collection/bams/NA12878.HiSeq.WGS.bwa.cleaned.recal.hg19.bam"),
new File("/humgen/gsa-hpprojects/dev/carneiro/hiseq19/analysis/snps/NA12878.HiSeq19.filtered.vcf"),
"/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.noChrY.hg19.intervals", 2.14, 99.0, !lowPass, !exome, 1),
"GA2hg19" -> new Target("NA12878.GA2.hg19", hg19, dbSNP_b37, hapmap_b37, indelMask_b37,
new File("/humgen/gsa-hpprojects/NA12878Collection/bams/NA12878.GA2.WGS.bwa.cleaned.hg19.bam"),
new File("/humgen/gsa-hpprojects/dev/carneiro/hiseq19/analysis/snps/NA12878.GA2.hg19.filtered.vcf"),
"/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.hg19.intervals", 2.14, 99.0, !lowPass, !exome, 1),
"WEx" -> new Target("NA12878.WEx", hg18, dbSNP_hg18_129, hapmap_hg18,
"NA12878_wex_b37" -> new Target("NA12878.HiSeq.WEx.b37", hg19, dbSNP_b37, hapmap_b37, indelMask_b37,
new File("/seq/picard_aggregation/C339/NA12878/v3/NA12878.bam"),
new File("/humgen/gsa-hpprojects/dev/carneiro/trio/analysis/snps/CEUTrio.WEx.filtered.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", 3.3, 98.0, !lowPass, exome, 1),
"NA12878_wex_hg18" -> new Target("NA12878.HiSeq.WEx.hg18", hg18, dbSNP_hg18_129, hapmap_hg18,
"/humgen/gsa-hpprojects/dev/depristo/oneOffProjects/1000GenomesProcessingPaper/wgs.v13/GA2.WEx.cleaned.indels.10.mask",
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", 3.3, 98.0, !lowPass, exome, 1),
"WExTrio" -> new Target("CEUTrio.WEx", hg19, dbSNP_b37, hapmap_b37, indelMask_b37,
"NA12878_wex_decoy" -> new Target("NA12878.HiSeq.WEx.b37_decoy", b37_decoy, dbSNP_b37, hapmap_b37, indelMask_b37,
new File("/humgen/gsa-hpprojects/NA12878Collection/bams/CEUTrio.HiSeq.WEx.b37_decoy.NA12878.clean.dedup.recal.bam"),
new File("/humgen/gsa-hpprojects/dev/carneiro/trio/analysis/snps/CEUTrio.WEx.filtered.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", 3.3, 98.0, !lowPass, exome, 1),
"CEUTrio_wex_b37" -> new Target("CEUTrio.HiSeq.WEx.b37", hg19, dbSNP_b37, hapmap_b37, indelMask_b37,
new File("/humgen/gsa-hpprojects/NA12878Collection/bams/CEUTrio.HiSeq.WEx.bwa.cleaned.recal.bam"),
new File("/humgen/gsa-hpprojects/dev/carneiro/trio/analysis/snps/CEUTrio.WEx.filtered.vcf"),
"/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", 3.3, 98.0, !lowPass, exome, 3),
"WGSTrio" -> new Target("CEUTrio.WGS", hg19, dbSNP_b37, hapmap_b37, indelMask_b37,
"CEUTrio_wgs_b37" -> new Target("CEUTrio.HiSeq.WGS.b37", hg19, dbSNP_b37, hapmap_b37, indelMask_b37,
new File("/humgen/gsa-hpprojects/NA12878Collection/bams/CEUTrio.HiSeq.WGS.bwa.cleaned.recal.bam"),
new File("/humgen/gsa-hpprojects/dev/carneiro/trio/analysis/snps/CEUTrio.WEx.filtered.vcf"), // ** THIS GOLD STANDARD NEEDS TO BE CORRECTED **
"/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.hg19.intervals", 2.3, 99.0, !lowPass, !exome, 3),
"WExTrioDecoy" -> new Target("CEUTrio.HiSeq.WEx.b37_decoy", b37_decoy, dbSNP_b37, hapmap_b37, indelMask_b37,
"CEUTrio_wex_decoy" -> new Target("CEUTrio.HiSeq.WEx.b37_decoy", b37_decoy, dbSNP_b37, hapmap_b37, indelMask_b37,
new File("/humgen/gsa-hpprojects/NA12878Collection/bams/CEUTrio.HiSeq.WEx.b37_decoy.list"),
new File("/humgen/gsa-hpprojects/dev/carneiro/trio/analysis/snps/CEUTrio.WEx.filtered.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", 3.3, 98.0, !lowPass, exome, 3),
"WGSTrioDecoy" -> new Target("CEUTrio.HiSeq.WGS.b37_decoy", b37_decoy, dbSNP_b37, hapmap_b37, indelMask_b37,
"CEUTrio_wgs_decoy" -> new Target("CEUTrio.HiSeq.WGS.b37_decoy", b37_decoy, dbSNP_b37, hapmap_b37, indelMask_b37,
new File("/humgen/gsa-hpprojects/NA12878Collection/bams/CEUTrio.HiSeq.WGS.b37_decoy.list"),
new File("/humgen/gsa-hpprojects/dev/carneiro/trio/analysis/snps/CEUTrio.WEx.filtered.vcf"), // ** THIS GOLD STANDARD NEEDS TO BE CORRECTED **
"/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.hg19.intervals", 2.3, 99.0, !lowPass, !exome, 3),
"GA2hg19" -> new Target("NA12878.GA2.hg19", hg19, dbSNP_b37, hapmap_b37, indelMask_b37,
new File("/humgen/gsa-hpprojects/NA12878Collection/bams/NA12878.GA2.WGS.bwa.cleaned.hg19.bam"),
new File("/humgen/gsa-hpprojects/dev/carneiro/hiseq19/analysis/snps/NA12878.GA2.hg19.filtered.vcf"),
"/humgen/1kg/processing/pipeline_test_bams/whole_genome_chunked.hg19.intervals", 2.14, 99.0, !lowPass, !exome, 1),
"FIN" -> new Target("FIN", b37, dbSNP_b37, hapmap_b37, indelMask_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 **