Dev (#47)

* Updated to gatk4.1, Update VariantRecal syntax

* added samtools path variable

* Updated wording

* add a version of joint-discovery that takes in an array for gvcfs

* Update README.md

* increased mem for SNPsVariantRecalibrator for papiv2

* increased mem for SNPsVariantRecalibrator for papiv2

* increased memory to run on papiv2

* correction to variable names in json

* corrected parameter syntax for SNPsVariantRecalibrator task

* Updated haplotypecaller to WDL 1.0, removed comments from haplotypecaller #

* Added WDL 1.0 version of JointGenotyping to soon replace joint discovery wdl

* Update genotype2develop (#44)

* added updated joint-discovery wdl, needs testing

* Added place holder for terra verion of JointGenotyping wdl

* Replaced joint-discovery with JointGenotyping workflow, added place holders for terra version for JointGenotyping workflow

* updated the terra version of the JointGenotyping

* added urls for imports for JointGenotyping workflows

* Updated ReadMe

* Update genotype2develop (#45)

* added updated joint-discovery wdl, needs testing

* Added place holder for terra verion of JointGenotyping wdl

* Replaced joint-discovery with JointGenotyping workflow, added place holders for terra version for JointGenotyping workflow

* updated the terra version of the JointGenotyping

* added urls for imports for JointGenotyping workflows

* Updated ReadMe

* added missing runtime variables

* added missing runtime variable

* Update genotype2develop (#46)

* added updated joint-discovery wdl, needs testing

* Added place holder for terra verion of JointGenotyping wdl

* Replaced joint-discovery with JointGenotyping workflow, added place holders for terra version for JointGenotyping workflow

* updated the terra version of the JointGenotyping

* added urls for imports for JointGenotyping workflows

* Updated ReadMe

* added missing runtime variables

* added missing runtime variable

* Update genotype2develop (#48)

* added updated joint-discovery wdl, needs testing

* Added place holder for terra verion of JointGenotyping wdl

* Replaced joint-discovery with JointGenotyping workflow, added place holders for terra version for JointGenotyping workflow

* updated the terra version of the JointGenotyping

* added urls for imports for JointGenotyping workflows

* Updated ReadMe

* added missing runtime variables

* added missing runtime variable

* added recent updates from dsde-pipelines repo to terra version

* removed unnecessary optional override variables

* replaced '$' with '~'

* updated broad reference bucket path

* Add important notes regarding JointGenotype workflow to Readme

* minor update to Readme, renamed input file name in json

* minor spelling

* Added allele-specific annotations to HC command

* Updated import url to the next release tag

JointGenotyping.hg19.wgs.inputs.json

@@ -0,0 +1,41 @@
+{
+  "JointGenotyping.sample_name_map": "gs://gatk-test-data/1kgp/downsampled_gvcf_hg37/hg37.1kg_50.sample_map",
+  "JointGenotyping.callset_name": "NA12878",
+  "JointGenotyping.unbounded_scatter_count_scale_factor": 2.5,
+  "JointGenotyping.SplitIntervalList.scatter_mode": "INTERVAL_SUBDIVISION",
+
+  "JointGenotyping.unpadded_intervals_file": "gs://gatk-test-data/intervals/wgs_calling_regions.v1.list",
+  "JointGenotyping.ref_fasta": "gs://gcp-public-data--broad-references/hg19/v0/Homo_sapiens_assembly19.fasta",
+  "JointGenotyping.ref_fasta_index": "gs://gcp-public-data--broad-references/hg19/v0/Homo_sapiens_assembly19.fasta.fai",
+  "JointGenotyping.ref_dict": "gs://gcp-public-data--broad-references/hg19/v0/Homo_sapiens_assembly19.dict",
+  "JointGenotyping.eval_interval_list": "gs://gcp-public-data--broad-references/hg19/v0/wgs_evaluation_regions.v1.interval_list",
+  "JointGenotyping.haplotype_database": "gs://gcp-public-data--broad-references/hg19/v0/Homo_sapiens_assembly19.haplotype_database.txt",
+
+  "JointGenotyping.axiomPoly_resource_vcf": "gs://gcp-public-data--broad-references/hg19/v0/Axiom_Exome_Plus.genotypes.all_populations.poly.vcf.gz",
+  "JointGenotyping.axiomPoly_resource_vcf_index": "gs://gcp-public-data--broad-references/hg19/v0/Axiom_Exome_Plus.genotypes.all_populations.poly.vcf.gz.tbi",
+  "JointGenotyping.dbsnp_vcf": "gs://gcp-public-data--broad-references/hg19/v0/dbsnp_138.b37.vcf.gz",
+  "JointGenotyping.dbsnp_vcf_index": "gs://gcp-public-data--broad-references/hg19/v0/dbsnp_138.b37.vcf.gz.tbi",
+  "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg19/v0/hapmap_3.3.b37.vcf.gz",
+  "JointGenotyping.hapmap_resource_vcf_index": "gs://gcp-public-data--broad-references/hg19/v0/hapmap_3.3.b37.vcf.gz.tbi",
+  "JointGenotyping.mills_resource_vcf": "gs://gcp-public-data--broad-references/hg19/v0/Mills_and_1000G_gold_standard.indels.b37.sites.vcf",
+  "JointGenotyping.mills_resource_vcf_index": "gs://gcp-public-data--broad-references/hg19/v0/Mills_and_1000G_gold_standard.indels.b37.sites.vcf.idx",
+  "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg19/v0/1000G_omni2.5.b37.vcf.gz",
+  "JointGenotyping.omni_resource_vcf_index": "gs://gcp-public-data--broad-references/hg19/v0/1000G_omni2.5.b37.vcf.gz.tbi",
+  "JointGenotyping.one_thousand_genomes_resource_vcf": "gs://gcp-public-data--broad-references/hg19/v0/1000G_phase1.snps.high_confidence.b37.vcf.gz",
+  "JointGenotyping.one_thousand_genomes_resource_vcf_index": "gs://gcp-public-data--broad-references/hg19/v0/1000G_phase1.snps.high_confidence.b37.vcf.gz.tbi",
+
+  "JointGenotyping.SNP_VQSR_downsampleFactor": 10,
+  "JointGenotyping.snps_variant_recalibration_threshold": 20000,
+  "JointGenotyping.snp_filter_level": 99.7,
+  "JointGenotyping.snp_recalibration_annotation_values": ["QD", "MQRankSum", "ReadPosRankSum", "FS", "MQ", "SOR", "DP"],
+  "JointGenotyping.snp_recalibration_tranche_values": ["100.0", "99.95", "99.9", "99.8", "99.6", "99.5", "99.4", "99.3", "99.0", "98.0", "97.0", "90.0" ],
+
+  "JointGenotyping.indel_filter_level": 99.0,
+  "JointGenotyping.indel_recalibration_annotation_values": ["FS", "ReadPosRankSum", "MQRankSum", "QD", "SOR", "DP"],
+  "JointGenotyping.indel_recalibration_tranche_values": ["100.0", "99.95", "99.9", "99.5", "99.0", "97.0", "96.0", "95.0", "94.0", "93.5", "93.0", "92.0", "91.0", "90.0"],
+
+  "JointGenotyping.small_disk": 100,
+  "JointGenotyping.medium_disk": 200,
+  "JointGenotyping.large_disk": 1000,
+  "JointGenotyping.huge_disk": 2000
+}

JointGenotyping.hg38.terra.wgs.inputs.json

@@ -0,0 +1,35 @@
+{
+"JointGenotyping.large_disk":"1000",
+"JointGenotyping.medium_disk":"200",
+"JointGenotyping.indel_recalibration_annotation_values":["FS","ReadPosRankSum","MQRankSum","QD","SOR","DP"],
+"JointGenotyping.snp_recalibration_tranche_values":"[100.0,99.95,99.9,99.8,99.6,99.5,99.4,99.3,99.0,98.0,97.0,90.0]",
+"JointGenotyping.unbounded_scatter_count_scale_factor":"2.5",
+"JointGenotyping.omni_resource_vcf_index":"gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz.tbi",
+"JointGenotyping.eval_interval_list":"gs://gcp-public-data--broad-references/hg38/v0/wgs_evaluation_regions.hg38.interval_list",
+"JointGenotyping.one_thousand_genomes_resource_vcf_index":"gs://gcp-public-data--broad-references/hg38/v0/1000G_phase1.snps.high_confidence.hg38.vcf.gz.tbi",
+"JointGenotyping.one_thousand_genomes_resource_vcf":"gs://gcp-public-data--broad-references/hg38/v0/1000G_phase1.snps.high_confidence.hg38.vcf.gz",
+"JointGenotyping.small_disk":"100",
+"JointGenotyping.snp_recalibration_annotation_values":"[QD,MQRankSum,ReadPosRankSum,FS,MQ,SOR,DP]",
+"JointGenotyping.dbsnp_vcf":"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf",
+"JointGenotyping.callset_name":"hg38_1kg_50",
+"JointGenotyping.unpadded_intervals_file":"gs://gcp-public-data--broad-references/hg38/v0/hg38.even.handcurated.20k.intervals",
+"JointGenotyping.dbsnp_vcf_index":"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf.idx",
+"JointGenotyping.ref_fasta_index":"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai",
+"JointGenotyping.ref_dict":"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict",
+"JointGenotyping.mills_resource_vcf_index":"gs://gcp-public-data--broad-references/hg38/v0/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi",
+"JointGenotyping.sample_name_map":"gs://gatk-test-data/joint_discovery/1kg_50_hg38/gvcf/hg38_1kg_50.sample_map",
+"JointGenotyping.indel_recalibration_tranche_values":"[100.0,99.95,99.9,99.5,99.0,97.0,96.0,95.0,94.0,93.5,93.0,92.0,91.0,90.0]",
+"JointGenotyping.omni_resource_vcf":"gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz",
+"JointGenotyping.mills_resource_vcf":"gs://gcp-public-data--broad-references/hg38/v0/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz",
+"JointGenotyping.axiomPoly_resource_vcf":"gs://gcp-public-data--broad-references/hg38/v0/Axiom_Exome_Plus.genotypes.all_populations.poly.hg38.vcf.gz",
+"JointGenotyping.snp_filter_level":"99.7",
+"JointGenotyping.snps_variant_recalibration_threshold":"20000",
+"JointGenotyping.haplotype_database":"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt",
+"JointGenotyping.hapmap_resource_vcf":"gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz",
+"JointGenotyping.indel_filter_level":"99",
+"JointGenotyping.axiomPoly_resource_vcf_index":"gs://gcp-public-data--broad-references/hg38/v0/Axiom_Exome_Plus.genotypes.all_populations.poly.hg38.vcf.gz.tbi",
+"JointGenotyping.ref_fasta":"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta",
+"JointGenotyping.hapmap_resource_vcf_index":"gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz.tbi",
+"JointGenotyping.SNP_VQSR_downsampleFactor":"10",
+"JointGenotyping.huge_disk":"2000"
+}

JointGenotyping.hg38.wgs.inputs.json

@@ -0,0 +1,41 @@
+{
+  "JointGenotyping.sample_name_map": "gs://gatk-test-data/joint_discovery/1kg_50_hg38/gvcf/hg38_1kg_50.sample_map",
+  "JointGenotyping.callset_name": "hg38_1kg_50",
+  "JointGenotyping.unbounded_scatter_count_scale_factor": 2.5,
+  "JointGenotyping.SplitIntervalList.scatter_mode": "INTERVAL_SUBDIVISION",
+
+  "JointGenotyping.unpadded_intervals_file": "gs://gcp-public-data--broad-references/hg38/v0/hg38.even.handcurated.20k.intervals",
+  "JointGenotyping.ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta",
+  "JointGenotyping.ref_fasta_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai",
+  "JointGenotyping.ref_dict": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict",
+  "JointGenotyping.eval_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/wgs_evaluation_regions.hg38.interval_list",
+  "JointGenotyping.haplotype_database": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt",
+
+  "JointGenotyping.axiomPoly_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/Axiom_Exome_Plus.genotypes.all_populations.poly.hg38.vcf.gz",
+  "JointGenotyping.axiomPoly_resource_vcf_index": "gs://gcp-public-data--broad-references/hg38/v0/Axiom_Exome_Plus.genotypes.all_populations.poly.hg38.vcf.gz.tbi",
+  "JointGenotyping.dbsnp_vcf": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf",
+  "JointGenotyping.dbsnp_vcf_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf.idx",
+  "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz",
+  "JointGenotyping.hapmap_resource_vcf_index": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz.tbi",
+  "JointGenotyping.mills_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz",
+  "JointGenotyping.mills_resource_vcf_index": "gs://gcp-public-data--broad-references/hg38/v0/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi",
+  "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz",
+  "JointGenotyping.omni_resource_vcf_index": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz.tbi",
+  "JointGenotyping.one_thousand_genomes_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_phase1.snps.high_confidence.hg38.vcf.gz",
+  "JointGenotyping.one_thousand_genomes_resource_vcf_index": "gs://gcp-public-data--broad-references/hg38/v0/1000G_phase1.snps.high_confidence.hg38.vcf.gz.tbi",
+
+  "JointGenotyping.SNP_VQSR_downsampleFactor": 10,
+  "JointGenotyping.snps_variant_recalibration_threshold": 20000,
+  "JointGenotyping.snp_filter_level": 99.7,
+  "JointGenotyping.snp_recalibration_annotation_values": ["QD", "MQRankSum", "ReadPosRankSum", "FS", "MQ", "SOR", "DP"],
+  "JointGenotyping.snp_recalibration_tranche_values": ["100.0", "99.95", "99.9", "99.8", "99.6", "99.5", "99.4", "99.3", "99.0", "98.0", "97.0", "90.0" ],
+
+  "JointGenotyping.indel_filter_level": 99.0,
+  "JointGenotyping.indel_recalibration_annotation_values": ["FS", "ReadPosRankSum", "MQRankSum", "QD", "SOR", "DP"],
+  "JointGenotyping.indel_recalibration_tranche_values": ["100.0", "99.95", "99.9", "99.5", "99.0", "97.0", "96.0", "95.0", "94.0", "93.5", "93.0", "92.0", "91.0", "90.0"],
+
+  "JointGenotyping.small_disk": 100,
+  "JointGenotyping.medium_disk": 200,
+  "JointGenotyping.large_disk": 1000,
+  "JointGenotyping.huge_disk": 2000
+}