diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/JointGenotyping.changelog.md b/pipelines/broad/dna_seq/germline/joint_genotyping/JointGenotyping.changelog.md index e6488ba519..55378fdca6 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/JointGenotyping.changelog.md +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/JointGenotyping.changelog.md @@ -1,3 +1,9 @@ +# 1.6.9 +2023-09-08 (Date of Last Commit) + +* Added option to run VETS instead of VQSR for filtering +* Added option to hard filter sites outside of provided interval list + # 1.6.8 2023-06-29 (Date of Last Commit) diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/JointGenotyping.wdl b/pipelines/broad/dna_seq/germline/joint_genotyping/JointGenotyping.wdl index 75c46efe4e..87832c4c12 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/JointGenotyping.wdl +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/JointGenotyping.wdl @@ -1,12 +1,13 @@ version 1.0 import "../../../../../tasks/broad/JointGenotypingTasks.wdl" as Tasks +import "https://raw.githubusercontent.com/broadinstitute/gatk/4.5.0.0/scripts/vcf_site_level_filtering_wdl/JointVcfFiltering.wdl" as Filtering # Joint Genotyping for hg38 Whole Genomes and Exomes (has not been tested on hg19) workflow JointGenotyping { - String pipeline_version = "1.6.8" + String pipeline_version = "1.6.9" input { File unpadded_intervals_file @@ -26,10 +27,10 @@ workflow JointGenotyping { Int large_disk Int huge_disk - Array[String] snp_recalibration_tranche_values + Array[String]? snp_recalibration_tranche_values Array[String] snp_recalibration_annotation_values - Array[String] indel_recalibration_tranche_values - Array[String] indel_recalibration_annotation_values + Array[String]? indel_recalibration_tranche_values + Array[String]? indel_recalibration_annotation_values File haplotype_database @@ -50,9 +51,10 @@ workflow JointGenotyping { # ExcessHet is a phred-scaled p-value. We want a cutoff of anything more extreme # than a z-score of -4.5 which is a p-value of 3.4e-06, which phred-scaled is 54.69 Float excess_het_threshold = 54.69 - Float snp_filter_level - Float indel_filter_level - Int snp_vqsr_downsampleFactor + Float? vqsr_snp_filter_level + Float? vqsr_indel_filter_level + Int? snp_vqsr_downsampleFactor + File? targets_interval_list Int? top_level_scatter_count Boolean? gather_vcfs @@ -61,9 +63,10 @@ workflow JointGenotyping { Float unbounded_scatter_count_scale_factor = 0.15 Int gnarly_scatter_count = 10 Boolean use_gnarly_genotyper = false - Boolean use_allele_specific_annotations = true + Boolean use_allele_specific_annotations = true # only applicabale to VQSR Boolean cross_check_fingerprints = true Boolean scatter_cross_check_fingerprints = false + Boolean run_vets = false } Boolean allele_specific_annotations = !use_gnarly_genotyper && use_allele_specific_annotations @@ -182,6 +185,7 @@ workflow JointGenotyping { excess_het_threshold = excess_het_threshold, variant_filtered_vcf_filename = callset_name + "." + idx + ".variant_filtered.vcf.gz", sites_only_vcf_filename = callset_name + "." + idx + ".sites_only.variant_filtered.vcf.gz", + targets_interval_list = targets_interval_list, disk_size_gb = medium_disk } } @@ -192,58 +196,57 @@ workflow JointGenotyping { output_vcf_name = callset_name + ".sites_only.vcf.gz", disk_size_gb = medium_disk } - - call Tasks.IndelsVariantRecalibrator { - input: - sites_only_variant_filtered_vcf = SitesOnlyGatherVcf.output_vcf, - sites_only_variant_filtered_vcf_index = SitesOnlyGatherVcf.output_vcf_index, - recalibration_filename = callset_name + ".indels.recal", - tranches_filename = callset_name + ".indels.tranches", - recalibration_tranche_values = indel_recalibration_tranche_values, - recalibration_annotation_values = indel_recalibration_annotation_values, - mills_resource_vcf = mills_resource_vcf, - mills_resource_vcf_index = mills_resource_vcf_index, - axiomPoly_resource_vcf = axiomPoly_resource_vcf, - axiomPoly_resource_vcf_index = axiomPoly_resource_vcf_index, - dbsnp_resource_vcf = dbsnp_resource_vcf, - dbsnp_resource_vcf_index = dbsnp_resource_vcf_index, - use_allele_specific_annotations = allele_specific_annotations, - disk_size_gb = small_disk - } - - if (num_gvcfs > snps_variant_recalibration_threshold) { - call Tasks.SNPsVariantRecalibratorCreateModel { + + if (run_vets) { + String resource_args = " --resource:hapmap,training=true,calibration=true " + hapmap_resource_vcf + + " --resource:omni,training=true,calibration=true " + omni_resource_vcf + + " --resource:1000G,training=true " + one_thousand_genomes_resource_vcf + + " --resource:mills,training=true,calibration=true " + mills_resource_vcf + " " + String extract_extra_args = if defined(targets_interval_list) then " -L " + targets_interval_list + " " else "" #only train the model over the targets, apply the model to everything + + call Filtering.JointVcfFiltering as TrainAndApplyVETS { + input: + input_vcfs = HardFilterAndMakeSitesOnlyVcf.variant_filtered_vcf, + input_vcf_idxs = HardFilterAndMakeSitesOnlyVcf.variant_filtered_vcf_index, + sites_only_vcf = SitesOnlyGatherVcf.output_vcf, + sites_only_vcf_idx = SitesOnlyGatherVcf.output_vcf_index, + annotations = snp_recalibration_annotation_values, #the snp list here is a superset of the indel list + extract_extra_args = extract_extra_args, + resource_args = resource_args, + output_prefix = callset_name, + gatk_docker = "us.gcr.io/broad-gatk/gatk:4.5.0.0" + } + } + if (!run_vets) { + call Tasks.IndelsVariantRecalibrator { input: sites_only_variant_filtered_vcf = SitesOnlyGatherVcf.output_vcf, sites_only_variant_filtered_vcf_index = SitesOnlyGatherVcf.output_vcf_index, - recalibration_filename = callset_name + ".snps.recal", - tranches_filename = callset_name + ".snps.tranches", - recalibration_tranche_values = snp_recalibration_tranche_values, - recalibration_annotation_values = snp_recalibration_annotation_values, - downsampleFactor = snp_vqsr_downsampleFactor, - model_report_filename = callset_name + ".snps.model.report", - hapmap_resource_vcf = hapmap_resource_vcf, - hapmap_resource_vcf_index = hapmap_resource_vcf_index, - omni_resource_vcf = omni_resource_vcf, - omni_resource_vcf_index = omni_resource_vcf_index, - one_thousand_genomes_resource_vcf = one_thousand_genomes_resource_vcf, - one_thousand_genomes_resource_vcf_index = one_thousand_genomes_resource_vcf_index, + recalibration_filename = callset_name + ".indels.recal", + tranches_filename = callset_name + ".indels.tranches", + recalibration_tranche_values = select_first([indel_recalibration_tranche_values]), + recalibration_annotation_values = select_first([indel_recalibration_annotation_values]), + mills_resource_vcf = mills_resource_vcf, + mills_resource_vcf_index = mills_resource_vcf_index, + axiomPoly_resource_vcf = axiomPoly_resource_vcf, + axiomPoly_resource_vcf_index = axiomPoly_resource_vcf_index, dbsnp_resource_vcf = dbsnp_resource_vcf, dbsnp_resource_vcf_index = dbsnp_resource_vcf_index, use_allele_specific_annotations = allele_specific_annotations, disk_size_gb = small_disk } - scatter (idx in range(length(HardFilterAndMakeSitesOnlyVcf.sites_only_vcf))) { - call Tasks.SNPsVariantRecalibrator as SNPsVariantRecalibratorScattered { + if (num_gvcfs > snps_variant_recalibration_threshold) { + call Tasks.SNPsVariantRecalibratorCreateModel { input: - sites_only_variant_filtered_vcf = HardFilterAndMakeSitesOnlyVcf.sites_only_vcf[idx], - sites_only_variant_filtered_vcf_index = HardFilterAndMakeSitesOnlyVcf.sites_only_vcf_index[idx], - recalibration_filename = callset_name + ".snps." + idx + ".recal", - tranches_filename = callset_name + ".snps." + idx + ".tranches", - recalibration_tranche_values = snp_recalibration_tranche_values, + sites_only_variant_filtered_vcf = SitesOnlyGatherVcf.output_vcf, + sites_only_variant_filtered_vcf_index = SitesOnlyGatherVcf.output_vcf_index, + recalibration_filename = callset_name + ".snps.recal", + tranches_filename = callset_name + ".snps.tranches", + recalibration_tranche_values = select_first([snp_recalibration_tranche_values]), recalibration_annotation_values = snp_recalibration_annotation_values, - model_report = SNPsVariantRecalibratorCreateModel.model_report, + downsampleFactor = select_first([snp_vqsr_downsampleFactor]), + model_report_filename = callset_name + ".snps.model.report", hapmap_resource_vcf = hapmap_resource_vcf, hapmap_resource_vcf_index = hapmap_resource_vcf_index, omni_resource_vcf = omni_resource_vcf, @@ -254,65 +257,93 @@ workflow JointGenotyping { dbsnp_resource_vcf_index = dbsnp_resource_vcf_index, use_allele_specific_annotations = allele_specific_annotations, disk_size_gb = small_disk - } + } + + scatter (idx in range(length(HardFilterAndMakeSitesOnlyVcf.sites_only_vcf))) { + call Tasks.SNPsVariantRecalibrator as SNPsVariantRecalibratorScattered { + input: + sites_only_variant_filtered_vcf = HardFilterAndMakeSitesOnlyVcf.sites_only_vcf[idx], + sites_only_variant_filtered_vcf_index = HardFilterAndMakeSitesOnlyVcf.sites_only_vcf_index[idx], + recalibration_filename = callset_name + ".snps." + idx + ".recal", + tranches_filename = callset_name + ".snps." + idx + ".tranches", + recalibration_tranche_values = select_first([snp_recalibration_tranche_values]), + recalibration_annotation_values = snp_recalibration_annotation_values, + model_report = SNPsVariantRecalibratorCreateModel.model_report, + hapmap_resource_vcf = hapmap_resource_vcf, + hapmap_resource_vcf_index = hapmap_resource_vcf_index, + omni_resource_vcf = omni_resource_vcf, + omni_resource_vcf_index = omni_resource_vcf_index, + one_thousand_genomes_resource_vcf = one_thousand_genomes_resource_vcf, + one_thousand_genomes_resource_vcf_index = one_thousand_genomes_resource_vcf_index, + dbsnp_resource_vcf = dbsnp_resource_vcf, + dbsnp_resource_vcf_index = dbsnp_resource_vcf_index, + use_allele_specific_annotations = allele_specific_annotations, + disk_size_gb = small_disk + } + } + + call Tasks.GatherTranches as SNPGatherTranches { + input: + tranches = SNPsVariantRecalibratorScattered.tranches, + output_filename = callset_name + ".snps.gathered.tranches", + mode = "SNP", + disk_size_gb = small_disk + } } - call Tasks.GatherTranches as SNPGatherTranches { - input: - tranches = SNPsVariantRecalibratorScattered.tranches, - output_filename = callset_name + ".snps.gathered.tranches", - mode = "SNP", - disk_size_gb = small_disk + if (num_gvcfs <= snps_variant_recalibration_threshold) { + call Tasks.SNPsVariantRecalibrator as SNPsVariantRecalibratorClassic { + input: + sites_only_variant_filtered_vcf = SitesOnlyGatherVcf.output_vcf, + sites_only_variant_filtered_vcf_index = SitesOnlyGatherVcf.output_vcf_index, + recalibration_filename = callset_name + ".snps.recal", + tranches_filename = callset_name + ".snps.tranches", + recalibration_tranche_values = select_first([snp_recalibration_tranche_values]), + recalibration_annotation_values = snp_recalibration_annotation_values, + hapmap_resource_vcf = hapmap_resource_vcf, + hapmap_resource_vcf_index = hapmap_resource_vcf_index, + omni_resource_vcf = omni_resource_vcf, + omni_resource_vcf_index = omni_resource_vcf_index, + one_thousand_genomes_resource_vcf = one_thousand_genomes_resource_vcf, + one_thousand_genomes_resource_vcf_index = one_thousand_genomes_resource_vcf_index, + dbsnp_resource_vcf = dbsnp_resource_vcf, + dbsnp_resource_vcf_index = dbsnp_resource_vcf_index, + use_allele_specific_annotations = allele_specific_annotations, + disk_size_gb = small_disk + } } - } - if (num_gvcfs <= snps_variant_recalibration_threshold) { - call Tasks.SNPsVariantRecalibrator as SNPsVariantRecalibratorClassic { - input: - sites_only_variant_filtered_vcf = SitesOnlyGatherVcf.output_vcf, - sites_only_variant_filtered_vcf_index = SitesOnlyGatherVcf.output_vcf_index, - recalibration_filename = callset_name + ".snps.recal", - tranches_filename = callset_name + ".snps.tranches", - recalibration_tranche_values = snp_recalibration_tranche_values, - recalibration_annotation_values = snp_recalibration_annotation_values, - hapmap_resource_vcf = hapmap_resource_vcf, - hapmap_resource_vcf_index = hapmap_resource_vcf_index, - omni_resource_vcf = omni_resource_vcf, - omni_resource_vcf_index = omni_resource_vcf_index, - one_thousand_genomes_resource_vcf = one_thousand_genomes_resource_vcf, - one_thousand_genomes_resource_vcf_index = one_thousand_genomes_resource_vcf_index, - dbsnp_resource_vcf = dbsnp_resource_vcf, - dbsnp_resource_vcf_index = dbsnp_resource_vcf_index, - use_allele_specific_annotations = allele_specific_annotations, - disk_size_gb = small_disk + scatter (idx in range(length(HardFilterAndMakeSitesOnlyVcf.variant_filtered_vcf))) { + #for really large callsets we give to friends, just apply filters to the sites-only + call Tasks.ApplyRecalibration { + input: + recalibrated_vcf_filename = callset_name + ".filtered." + idx + ".vcf.gz", + input_vcf = HardFilterAndMakeSitesOnlyVcf.variant_filtered_vcf[idx], + input_vcf_index = HardFilterAndMakeSitesOnlyVcf.variant_filtered_vcf_index[idx], + indels_recalibration = IndelsVariantRecalibrator.recalibration, + indels_recalibration_index = IndelsVariantRecalibrator.recalibration_index, + indels_tranches = IndelsVariantRecalibrator.tranches, + snps_recalibration = if defined(SNPsVariantRecalibratorScattered.recalibration) then select_first([SNPsVariantRecalibratorScattered.recalibration])[idx] else select_first([SNPsVariantRecalibratorClassic.recalibration]), + snps_recalibration_index = if defined(SNPsVariantRecalibratorScattered.recalibration_index) then select_first([SNPsVariantRecalibratorScattered.recalibration_index])[idx] else select_first([SNPsVariantRecalibratorClassic.recalibration_index]), + snps_tranches = select_first([SNPGatherTranches.tranches_file, SNPsVariantRecalibratorClassic.tranches]), + indel_filter_level = select_first([vqsr_indel_filter_level]), + snp_filter_level = select_first([vqsr_snp_filter_level]), + use_allele_specific_annotations = allele_specific_annotations, + disk_size_gb = medium_disk + } } } - scatter (idx in range(length(HardFilterAndMakeSitesOnlyVcf.variant_filtered_vcf))) { - #for really large callsets we give to friends, just apply filters to the sites-only - call Tasks.ApplyRecalibration { - input: - recalibrated_vcf_filename = callset_name + ".filtered." + idx + ".vcf.gz", - input_vcf = HardFilterAndMakeSitesOnlyVcf.variant_filtered_vcf[idx], - input_vcf_index = HardFilterAndMakeSitesOnlyVcf.variant_filtered_vcf_index[idx], - indels_recalibration = IndelsVariantRecalibrator.recalibration, - indels_recalibration_index = IndelsVariantRecalibrator.recalibration_index, - indels_tranches = IndelsVariantRecalibrator.tranches, - snps_recalibration = if defined(SNPsVariantRecalibratorScattered.recalibration) then select_first([SNPsVariantRecalibratorScattered.recalibration])[idx] else select_first([SNPsVariantRecalibratorClassic.recalibration]), - snps_recalibration_index = if defined(SNPsVariantRecalibratorScattered.recalibration_index) then select_first([SNPsVariantRecalibratorScattered.recalibration_index])[idx] else select_first([SNPsVariantRecalibratorClassic.recalibration_index]), - snps_tranches = select_first([SNPGatherTranches.tranches_file, SNPsVariantRecalibratorClassic.tranches]), - indel_filter_level = indel_filter_level, - snp_filter_level = snp_filter_level, - use_allele_specific_annotations = allele_specific_annotations, - disk_size_gb = medium_disk - } + Array[File] filtered_vcfs = select_first([ApplyRecalibration.recalibrated_vcf, TrainAndApplyVETS.scored_vcfs]) + Array[File] filtered_vcf_idxs = select_first([ApplyRecalibration.recalibrated_vcf_index, TrainAndApplyVETS.scored_vcf_idxs]) + if (!is_small_callset) { + scatter (idx in range(length(filtered_vcfs))) { # For large callsets we need to collect metrics from the shards and gather them later. - if (!is_small_callset) { call Tasks.CollectVariantCallingMetrics as CollectMetricsSharded { input: - input_vcf = ApplyRecalibration.recalibrated_vcf, - input_vcf_index = ApplyRecalibration.recalibrated_vcf_index, + input_vcf = filtered_vcfs[idx], + input_vcf_index = filtered_vcf_idxs[idx], metrics_filename_prefix = callset_name + "." + idx, dbsnp_vcf = dbsnp_vcf, dbsnp_vcf_index = dbsnp_vcf_index, @@ -321,13 +352,21 @@ workflow JointGenotyping { disk_size_gb = medium_disk } } + + call Tasks.GatherVariantCallingMetrics { + input: + input_details = CollectMetricsSharded.detail_metrics_file, + input_summaries = CollectMetricsSharded.summary_metrics_file, + output_prefix = callset_name, + disk_size_gb = medium_disk + } } # For small callsets we can gather the VCF shards and then collect metrics on it. if (is_small_callset) { call Tasks.GatherVcfs as FinalGatherVcf { input: - input_vcfs = ApplyRecalibration.recalibrated_vcf, + input_vcfs = filtered_vcfs, output_vcf_name = callset_name + ".vcf.gz", disk_size_gb = huge_disk } @@ -345,17 +384,6 @@ workflow JointGenotyping { } } - if (!is_small_callset) { - # For large callsets we still need to gather the sharded metrics. - call Tasks.GatherVariantCallingMetrics { - input: - input_details = select_all(CollectMetricsSharded.detail_metrics_file), - input_summaries = select_all(CollectMetricsSharded.summary_metrics_file), - output_prefix = callset_name, - disk_size_gb = medium_disk - } - } - # CrossCheckFingerprints takes forever on large callsets. # We scatter over the input GVCFs to make things faster. if (cross_check_fingerprints) { @@ -425,7 +453,7 @@ if (cross_check_fingerprints) { call Tasks.CrossCheckFingerprint as CrossCheckFingerprintSolo { input: gvcf_paths = gvcf_paths, - vcf_paths = ApplyRecalibration.recalibrated_vcf, + vcf_paths = filtered_vcfs, sample_name_map = sample_name_map, haplotype_database = haplotype_database, output_base_name = callset_name @@ -439,8 +467,8 @@ if (cross_check_fingerprints) { File output_summary_metrics_file = select_first([CollectMetricsOnFullVcf.summary_metrics_file, GatherVariantCallingMetrics.summary_metrics_file]) # Get the VCFs from either code path - Array[File?] output_vcf_files = if defined(FinalGatherVcf.output_vcf) then [FinalGatherVcf.output_vcf] else ApplyRecalibration.recalibrated_vcf - Array[File?] output_vcf_index_files = if defined(FinalGatherVcf.output_vcf_index) then [FinalGatherVcf.output_vcf_index] else ApplyRecalibration.recalibrated_vcf_index + Array[File?] output_vcf_files = if defined(FinalGatherVcf.output_vcf) then [FinalGatherVcf.output_vcf] else filtered_vcfs + Array[File?] output_vcf_index_files = if defined(FinalGatherVcf.output_vcf_index) then [FinalGatherVcf.output_vcf_index] else filtered_vcf_idxs output { # Metrics from either the small or large callset diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/UltimaGenomicsJointGenotyping.changelog.md b/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/UltimaGenomicsJointGenotyping.changelog.md index f2eac3e4a8..a6c388e712 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/UltimaGenomicsJointGenotyping.changelog.md +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/UltimaGenomicsJointGenotyping.changelog.md @@ -1,3 +1,8 @@ +# 1.1.5 +2023-09-08 (Date of Last Commit) + +* Added option to hard filter sites outside of provided interval list to HardFilterAndMakeSitesOnlyVcf task + # 1.1.4 2023-06-29 (Date of Last Commit) diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/UltimaGenomicsJointGenotyping.wdl b/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/UltimaGenomicsJointGenotyping.wdl index f008d3ade8..48e5da0d28 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/UltimaGenomicsJointGenotyping.wdl +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/UltimaGenomicsJointGenotyping.wdl @@ -11,7 +11,7 @@ import "../../../../../../tasks/broad/UltimaGenomicsGermlineFilteringThreshold.w # For choosing a filtering threshold (where on the ROC curve to filter) a sample with truth data is required. workflow UltimaGenomicsJointGenotyping { - String pipeline_version = "1.1.4" + String pipeline_version = "1.1.5" input { File unpadded_intervals_file diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartOne.changelog.md b/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartOne.changelog.md index 48adc5353a..61a0a0daed 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartOne.changelog.md +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartOne.changelog.md @@ -1,3 +1,8 @@ +# 1.4.11 +2023-09-08 (Date of Last Commit) + +* Added option to hard filter sites outside of provided interval list to HardFilterAndMakeSitesOnlyVcf task + # 1.4.10 2023-06-29 (Date of Last Commit) diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartOne.wdl b/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartOne.wdl index 853eadb3e2..a067eb2882 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartOne.wdl +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartOne.wdl @@ -5,7 +5,7 @@ import "../../../../../../tasks/broad/JointGenotypingTasks.wdl" as Tasks # Joint Genotyping for hg38 Exomes and Whole Genomes (has not been tested on hg19) workflow JointGenotypingByChromosomePartOne { - String pipeline_version = "1.4.10" + String pipeline_version = "1.4.11" input { File unpadded_intervals_file diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartTwo.changelog.md b/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartTwo.changelog.md index a64cb8e356..4d158220e9 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartTwo.changelog.md +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartTwo.changelog.md @@ -1,3 +1,8 @@ +# 1.4.10 +2023-09-08 (Date of Last Commit) + +* Added option to hard filter sites outside of provided interval list to HardFilterAndMakeSitesOnlyVcf task + # 1.4.9 2023-06-29 (Date of Last Commit) diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartTwo.wdl b/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartTwo.wdl index 8094c9dbf1..ccb36af7d0 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartTwo.wdl +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartTwo.wdl @@ -5,7 +5,7 @@ import "../../../../../../tasks/broad/JointGenotypingTasks.wdl" as Tasks # Joint Genotyping for hg38 Exomes and Whole Genomes (has not been tested on hg19) workflow JointGenotypingByChromosomePartTwo { - String pipeline_version = "1.4.9" + String pipeline_version = "1.4.10" input { String callset_name diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/JointGenotyping.inputs.json b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/JointGenotyping.inputs.json index 940af50c4a..57ab178ef3 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/JointGenotyping.inputs.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/JointGenotyping.inputs.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/gather_vcfs_high_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/gather_vcfs_high_memory.json index 41f26297c4..be9aae05ed 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/gather_vcfs_high_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/gather_vcfs_high_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 1, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/gather_vcfs_low_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/gather_vcfs_low_memory.json index ab197c3bc0..a81631a23d 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/gather_vcfs_low_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/gather_vcfs_low_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/gnarly.json b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/gnarly.json index ac7088764e..1825ba3822 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/gnarly.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/gnarly.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["QD", "MQRankSum", "ReadPosRankSum", "FS", "SOR"], "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.indel_recalibration_annotation_values": ["FS", "ReadPosRankSum", "MQRankSum", "QD", "SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/shard_vcfs_high_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/shard_vcfs_high_memory.json index ea2204087c..350afb4ea1 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/shard_vcfs_high_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/shard_vcfs_high_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 1, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/shard_vcfs_low_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/shard_vcfs_low_memory.json index d03e24df2a..06eeda58ca 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/shard_vcfs_low_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Plumbing/shard_vcfs_low_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/gather_vcfs_high_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/gather_vcfs_high_memory.json index 5a785a76a8..1dfd205112 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/gather_vcfs_high_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/gather_vcfs_high_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 1, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/gather_vcfs_low_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/gather_vcfs_low_memory.json index 4dd6be52e3..efb4a7510e 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/gather_vcfs_low_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/gather_vcfs_low_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/shard_vcfs_high_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/shard_vcfs_high_memory.json index 7e16ac733b..0c4b17b3b2 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/shard_vcfs_high_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/shard_vcfs_high_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 1, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/shard_vcfs_low_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/shard_vcfs_low_memory.json index bbb48acc76..af2d0ab568 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/shard_vcfs_low_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/exome/test_inputs/Scientific/shard_vcfs_low_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.changelog.md b/pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.changelog.md index b67a277f04..7f3d1abfc6 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.changelog.md +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.changelog.md @@ -1,3 +1,10 @@ +# 2.1.10 +2023-12-14 (Date of Last Commit) + +* Updated GATK for Reblock task to version 4.5.0.0 +* Added options to Reblock task to remove annotations and move filters to genotype level + + # 2.1.9 2023-12-08 (Date of Last Commit) diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.wdl b/pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.wdl index 2e9585b825..69c0e37591 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.wdl +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.wdl @@ -5,7 +5,7 @@ import "../../../../../../tasks/broad/Qc.wdl" as QC workflow ReblockGVCF { - String pipeline_version = "2.1.9" + String pipeline_version = "2.1.10" input { @@ -17,9 +17,12 @@ workflow ReblockGVCF { File ref_fasta_index Float? tree_score_cutoff String? annotations_to_keep_command + String? annotations_to_remove_command + Boolean? move_filters_to_genotypes + String gvcf_file_extension = ".g.vcf.gz" } - String gvcf_basename = basename(gvcf, ".g.vcf.gz") + String gvcf_basename = basename(gvcf, gvcf_file_extension) call Calling.Reblock as Reblock { input: @@ -30,6 +33,8 @@ workflow ReblockGVCF { ref_dict = ref_dict, tree_score_cutoff = tree_score_cutoff, annotations_to_keep_command = annotations_to_keep_command, + annotations_to_remove_command = annotations_to_remove_command, + move_filters_to_genotypes = move_filters_to_genotypes, output_vcf_filename = gvcf_basename + ".rb.g.vcf.gz" } diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/test_inputs/Scientific/NA12878.bge.json b/pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/test_inputs/Scientific/NA12878.bge.json new file mode 100644 index 0000000000..5e99cbce58 --- /dev/null +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/test_inputs/Scientific/NA12878.bge.json @@ -0,0 +1,11 @@ +{ + "ReblockGVCF.gvcf": "gs://broad-gotc-test-storage/ReblockGVCF/input/scientific/NA12878.bge/NA12878.hard-filtered.gvcf.gz", + "ReblockGVCF.gvcf_index": "gs://broad-gotc-test-storage/ReblockGVCF/input/scientific/NA12878.bge/NA12878.hard-filtered.gvcf.gz.tbi", + "ReblockGVCF.calling_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/bge_exome_calling_regions.v1.1.interval_list", + "ReblockGVCF.ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta", + "ReblockGVCF.ref_fasta_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai", + "ReblockGVCF.ref_dict": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict", + "ReblockGVCF.annotations_to_remove_command": "--format-annotations-to-remove PRI", + "ReblockGVCF.move_filters_to_genotypes": true, + "ReblockGVCF.gvcf_file_extension": ".gvcf.gz" +} diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_high_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_high_memory.json index 41f26297c4..be9aae05ed 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_high_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_high_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 1, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_low_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_low_memory.json index ab197c3bc0..a81631a23d 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_low_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_low_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gnarly.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gnarly.json index ac7088764e..1825ba3822 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gnarly.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gnarly.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["QD", "MQRankSum", "ReadPosRankSum", "FS", "SOR"], "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.indel_recalibration_annotation_values": ["FS", "ReadPosRankSum", "MQRankSum", "QD", "SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/plumbing.input.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/plumbing.input.json index 37299dc1ff..4827117051 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/plumbing.input.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/plumbing.input.json @@ -26,11 +26,11 @@ "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.snps_variant_recalibration_threshold": 20000, - "JointGenotyping.snp_filter_level": 99.7, + "JointGenotyping.vqsr_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.vqsr_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"], diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_high_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_high_memory.json index ea2204087c..350afb4ea1 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_high_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_high_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 1, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_low_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_low_memory.json index d03e24df2a..06eeda58ca 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_low_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_low_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/bge.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/bge.json new file mode 100644 index 0000000000..985fedd66f --- /dev/null +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/bge.json @@ -0,0 +1,36 @@ +{ + "JointGenotyping.sample_name_map": "gs://broad-gotc-test-storage/JointGenotyping/inputs/scientific/bge/BGE_JG_test_sample_map.txt", + "JointGenotyping.callset_name": "bge_joint_genotyping", + "JointGenotyping.run_vets": true, + + "JointGenotyping.unpadded_intervals_file": "gs://gcp-public-data--broad-references/hg38/v0/bge_exome_calling_regions.v1.1.interval_list", + "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://broad-gotc-test-storage/JointGenotyping/inputs/scientific/bge/TwistAllianceClinicalResearchExome_Covered_Targets_hg38.interval_list", + "JointGenotyping.targets_interval_list": "gs://broad-gotc-test-storage/JointGenotyping/inputs/scientific/bge/TwistAllianceClinicalResearchExome_Covered_Targets_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_recalibration_annotation_values": ["QD", "MQRankSum", "ReadPosRankSum", "FS", "MQ", "SOR", "DP"], + + "JointGenotyping.use_allele_specific_annotations": false, + + + "JointGenotyping.small_disk": 100, + "JointGenotyping.medium_disk": 200, + "JointGenotyping.large_disk": 1000, + "JointGenotyping.huge_disk": 2000 +} diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_high_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_high_memory.json index 5a785a76a8..1dfd205112 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_high_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_high_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 1, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_low_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_low_memory.json index 4dd6be52e3..efb4a7510e 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_low_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_low_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gnarly.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gnarly.json index b19de495c1..799e8868a8 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gnarly.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gnarly.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["QD", "MQRankSum", "ReadPosRankSum", "FS", "SOR"], "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.indel_recalibration_annotation_values": ["FS", "ReadPosRankSum", "MQRankSum", "QD", "SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_high_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_high_memory.json index 7e16ac733b..0c4b17b3b2 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_high_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_high_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 1, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_low_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_low_memory.json index bbb48acc76..af2d0ab568 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_low_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_low_memory.json @@ -9,8 +9,8 @@ "JointGenotyping.snp_recalibration_annotation_values": ["AS_QD", "AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_MQ", "AS_SOR"], "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.indel_recalibration_annotation_values": ["AS_FS", "AS_ReadPosRankSum", "AS_MQRankSum", "AS_QD", "AS_SOR"], - "JointGenotyping.snp_filter_level": 99.7, - "JointGenotyping.indel_filter_level": 95.0, + "JointGenotyping.vqsr_snp_filter_level": 99.7, + "JointGenotyping.vqsr_indel_filter_level": 95.0, "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.hapmap_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/hapmap_3.3.hg38.vcf.gz", "JointGenotyping.omni_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/1000G_omni2.5.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/wgs/JointGenotyping.inputs.json b/pipelines/broad/dna_seq/germline/joint_genotyping/wgs/JointGenotyping.inputs.json index 3c2cfd16e4..189ea660be 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/wgs/JointGenotyping.inputs.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/wgs/JointGenotyping.inputs.json @@ -27,11 +27,11 @@ "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.snps_variant_recalibration_threshold": 20000, - "JointGenotyping.snp_filter_level": 99.7, + "JointGenotyping.vqsr_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.vqsr_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"], diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/wgs/test_inputs/Plumbing/plumbing.input.json b/pipelines/broad/dna_seq/germline/joint_genotyping/wgs/test_inputs/Plumbing/plumbing.input.json index e6a182236f..acc20a72d8 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/wgs/test_inputs/Plumbing/plumbing.input.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/wgs/test_inputs/Plumbing/plumbing.input.json @@ -26,11 +26,11 @@ "JointGenotyping.snp_vqsr_downsampleFactor": 10, "JointGenotyping.snps_variant_recalibration_threshold": 20000, - "JointGenotyping.snp_filter_level": 99.7, + "JointGenotyping.vqsr_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.vqsr_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"], diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/wgs/test_inputs/wgs_sample_name_map b/pipelines/broad/dna_seq/germline/joint_genotyping/wgs/test_inputs/wgs_sample_name_map index 31bbb61e4b..d9b8e8781f 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/wgs/test_inputs/wgs_sample_name_map +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/wgs/test_inputs/wgs_sample_name_map @@ -1,4 +1,4 @@ -CHM1_CHM13_WGS2 gs://broad-gotc-test-storage/germline_single_sample/wgs/load/truth/develop/CHM1_CHM13_WGS2/CHM1_CHM13_WGS2.g.vcf.gz +CHM1_CHM13_WGS2 gs://broad-gotc-test-storage/WholeGenomeGermlineSingleSample/truth/scientific/master/G94794.CHMI_CHMI3_WGS2/CHMI_CHMI3_WGS2.f6c39eb5-0716-4f02-9be8-47b343c5830e.rb.g.vcf.gz HG00623 gs://broad-gotc-test-storage/germline_single_sample/wgs/load/truth/develop/HG00623/HG00623.g.vcf.gz HG01967 gs://broad-gotc-test-storage/germline_single_sample/wgs/load/truth/develop/HG01967/HG01967.g.vcf.gz NA12877 gs://broad-gotc-test-storage/germline_single_sample/wgs/load/truth/develop/NA12877/NA12877.g.vcf.gz diff --git a/pipelines/broad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.changelog.md b/pipelines/broad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.changelog.md index 4cab7e0b06..14369eee0e 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.changelog.md +++ b/pipelines/broad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.changelog.md @@ -1,3 +1,10 @@ +# 3.1.17 +2023-12-14 (Date of Last Commit) + +* Updated GATK for Reblock task to version 4.5.0.0 +* Added options to Reblock task to remove annotations and move filters to genotype level + + # 3.1.16 2023-12-08 (Date of Last Commit) diff --git a/pipelines/broad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.wdl b/pipelines/broad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.wdl index f87f7f8a4f..8be4e1a5fc 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.wdl +++ b/pipelines/broad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.wdl @@ -44,7 +44,7 @@ import "../../../../../../structs/dna_seq/DNASeqStructs.wdl" # WORKFLOW DEFINITION workflow ExomeGermlineSingleSample { - String pipeline_version = "3.1.16" + String pipeline_version = "3.1.17" input { diff --git a/pipelines/broad/dna_seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.changelog.md b/pipelines/broad/dna_seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.changelog.md index b1d38a4c45..c011691d1f 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.changelog.md +++ b/pipelines/broad/dna_seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.changelog.md @@ -1,3 +1,9 @@ +# 1.0.14 +2023-12-14 (Date of Last Commit) + +* Updated GATK for Reblock task to version 4.5.0.0 +* Added options to Reblock task to remove annotations and move filters to genotype level + # 1.0.13 2023-12-08 (Date of Last Commit) diff --git a/pipelines/broad/dna_seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.wdl b/pipelines/broad/dna_seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.wdl index e09bcf3a05..479e6b914a 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.wdl +++ b/pipelines/broad/dna_seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.wdl @@ -50,7 +50,7 @@ workflow UltimaGenomicsWholeGenomeGermline { filtering_model_no_gt_name: "String describing the optional filtering model; default set to rf_model_ignore_gt_incl_hpol_runs" } - String pipeline_version = "1.0.13" + String pipeline_version = "1.0.14" References references = alignment_references.references diff --git a/pipelines/broad/dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.changelog.md b/pipelines/broad/dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.changelog.md index 81cd464c07..052c66c391 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.changelog.md +++ b/pipelines/broad/dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.changelog.md @@ -1,3 +1,9 @@ +# 3.1.18 +2023-12-14 (Date of Last Commit) + +* Updated GATK for Reblock task to version 4.5.0.0 +* Added options to Reblock task to remove annotations and move filters to genotype level + # 3.1.17 2023-12-08 (Date of Last Commit) diff --git a/pipelines/broad/dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.wdl b/pipelines/broad/dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.wdl index e1a08e1315..2b1fad60a3 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.wdl +++ b/pipelines/broad/dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.wdl @@ -40,7 +40,7 @@ import "../../../../../../structs/dna_seq/DNASeqStructs.wdl" workflow WholeGenomeGermlineSingleSample { - String pipeline_version = "3.1.17" + String pipeline_version = "3.1.18" input { diff --git a/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.changelog.md b/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.changelog.md index 1216d5ff7d..676deb72b6 100644 --- a/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.changelog.md +++ b/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.changelog.md @@ -1,3 +1,9 @@ +# 2.1.16 +2023-12-14 (Date of Last Commit) + +* Updated GATK for Reblock task to version 4.5.0.0 +* Added options to Reblock task to remove annotations and move filters to genotype level + # 2.1.15 2023-12-08 (Date of Last Commit) diff --git a/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.wdl b/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.wdl index 8741308fab..90dff51c08 100644 --- a/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.wdl +++ b/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.wdl @@ -9,7 +9,7 @@ import "../../../../../tasks/broad/DragenTasks.wdl" as DragenTasks workflow VariantCalling { - String pipeline_version = "2.1.15" + String pipeline_version = "2.1.16" input { diff --git a/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.changelog.md b/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.changelog.md index 1883574518..53166ccfe6 100644 --- a/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.changelog.md +++ b/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.changelog.md @@ -1,3 +1,8 @@ +# 1.0.14 +2023-12-14 (Date of Last Commit) + +* Updates to Reblock task. This update has no effect on this pipeline. + # 1.0.13 2023-12-08 (Date of Last Commit) diff --git a/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.wdl b/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.wdl index af1c5551ea..3946c87545 100644 --- a/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.wdl +++ b/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.wdl @@ -43,7 +43,7 @@ workflow UltimaGenomicsWholeGenomeCramOnly { save_bam_file: "If true, then save intermeidate ouputs used by germline pipeline (such as the output BAM) otherwise they won't be kept as outputs." } - String pipeline_version = "1.0.13" + String pipeline_version = "1.0.14" References references = alignment_references.references diff --git a/pipelines/broad/internal/dna_seq/germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.changelog.md b/pipelines/broad/internal/dna_seq/germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.changelog.md index e6d3ee8655..69de3d250d 100644 --- a/pipelines/broad/internal/dna_seq/germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.changelog.md +++ b/pipelines/broad/internal/dna_seq/germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.changelog.md @@ -1,3 +1,9 @@ +# 1.0.15 +2023-12-14 (Date of Last Commit) + +* Updated GATK for Reblock task to version 4.5.0.0 +* Added options to Reblock task to remove annotations and move filters to genotype level + # 1.0.14 2023-12-08 (Date of Last Commit) diff --git a/pipelines/broad/internal/dna_seq/germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.wdl b/pipelines/broad/internal/dna_seq/germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.wdl index 2656884f84..fe1761415a 100644 --- a/pipelines/broad/internal/dna_seq/germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.wdl +++ b/pipelines/broad/internal/dna_seq/germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.wdl @@ -6,7 +6,7 @@ import "../../../../../../../pipelines/broad/qc/CheckFingerprint.wdl" as FP workflow BroadInternalUltimaGenomics { - String pipeline_version = "1.0.14" + String pipeline_version = "1.0.15" input { diff --git a/pipelines/broad/reprocessing/exome/ExomeReprocessing.changelog.md b/pipelines/broad/reprocessing/exome/ExomeReprocessing.changelog.md index 2776f63f89..7a0b8b9a7d 100644 --- a/pipelines/broad/reprocessing/exome/ExomeReprocessing.changelog.md +++ b/pipelines/broad/reprocessing/exome/ExomeReprocessing.changelog.md @@ -1,3 +1,10 @@ +# 3.1.17 +2023-12-14 (Date of Last Commit) + +* Updated GATK for Reblock task to version 4.5.0.0 +* Added options to Reblock task to remove annotations and move filters to genotype level + + # 3.1.16 2023-12-08 (Date of Last Commit) diff --git a/pipelines/broad/reprocessing/exome/ExomeReprocessing.wdl b/pipelines/broad/reprocessing/exome/ExomeReprocessing.wdl index 40880130d7..46607e6499 100644 --- a/pipelines/broad/reprocessing/exome/ExomeReprocessing.wdl +++ b/pipelines/broad/reprocessing/exome/ExomeReprocessing.wdl @@ -7,7 +7,7 @@ import "../../../../structs/dna_seq/DNASeqStructs.wdl" workflow ExomeReprocessing { - String pipeline_version = "3.1.16" + String pipeline_version = "3.1.17" input { File? input_cram diff --git a/pipelines/broad/reprocessing/external/exome/ExternalExomeReprocessing.changelog.md b/pipelines/broad/reprocessing/external/exome/ExternalExomeReprocessing.changelog.md index de9e3ad232..af5579f916 100644 --- a/pipelines/broad/reprocessing/external/exome/ExternalExomeReprocessing.changelog.md +++ b/pipelines/broad/reprocessing/external/exome/ExternalExomeReprocessing.changelog.md @@ -1,3 +1,10 @@ +# 3.1.19 +2023-12-14 (Date of Last Commit) + +* Updated GATK for Reblock task to version 4.5.0.0 +* Added options to Reblock task to remove annotations and move filters to genotype level + + # 3.1.18 2023-12-08 (Date of Last Commit) diff --git a/pipelines/broad/reprocessing/external/exome/ExternalExomeReprocessing.wdl b/pipelines/broad/reprocessing/external/exome/ExternalExomeReprocessing.wdl index 807f0cc1f2..be94c054af 100644 --- a/pipelines/broad/reprocessing/external/exome/ExternalExomeReprocessing.wdl +++ b/pipelines/broad/reprocessing/external/exome/ExternalExomeReprocessing.wdl @@ -5,7 +5,7 @@ import "../../../../../tasks/broad/CopyFilesFromCloudToCloud.wdl" as Copy workflow ExternalExomeReprocessing { - String pipeline_version = "3.1.18" + String pipeline_version = "3.1.19" input { diff --git a/pipelines/broad/reprocessing/external/wgs/ExternalWholeGenomeReprocessing.changelog.md b/pipelines/broad/reprocessing/external/wgs/ExternalWholeGenomeReprocessing.changelog.md index 12844d6afb..152a5ce375 100644 --- a/pipelines/broad/reprocessing/external/wgs/ExternalWholeGenomeReprocessing.changelog.md +++ b/pipelines/broad/reprocessing/external/wgs/ExternalWholeGenomeReprocessing.changelog.md @@ -1,3 +1,10 @@ +# 2.1.19 +2023-12-14 (Date of Last Commit) + +* Updated GATK for Reblock task to version 4.5.0.0 +* Added options to Reblock task to remove annotations and move filters to genotype level + + # 2.1.18 2023-12-08 (Date of Last Commit) diff --git a/pipelines/broad/reprocessing/external/wgs/ExternalWholeGenomeReprocessing.wdl b/pipelines/broad/reprocessing/external/wgs/ExternalWholeGenomeReprocessing.wdl index 5814c8b253..a80fde6b94 100644 --- a/pipelines/broad/reprocessing/external/wgs/ExternalWholeGenomeReprocessing.wdl +++ b/pipelines/broad/reprocessing/external/wgs/ExternalWholeGenomeReprocessing.wdl @@ -6,7 +6,7 @@ import "../../../../../tasks/broad/CopyFilesFromCloudToCloud.wdl" as Copy workflow ExternalWholeGenomeReprocessing { - String pipeline_version = "2.1.18" + String pipeline_version = "2.1.19" input { File? input_cram diff --git a/pipelines/broad/reprocessing/wgs/WholeGenomeReprocessing.changelog.md b/pipelines/broad/reprocessing/wgs/WholeGenomeReprocessing.changelog.md index 7627d84fec..83d465aae4 100644 --- a/pipelines/broad/reprocessing/wgs/WholeGenomeReprocessing.changelog.md +++ b/pipelines/broad/reprocessing/wgs/WholeGenomeReprocessing.changelog.md @@ -1,3 +1,9 @@ +# 3.1.18 +2023-12-14 (Date of Last Commit) + +* Updated GATK for Reblock task to version 4.5.0.0 +* Added options to Reblock task to remove annotations and move filters to genotype level + # 3.1.17 2023-12-08 (Date of Last Commit) diff --git a/pipelines/broad/reprocessing/wgs/WholeGenomeReprocessing.wdl b/pipelines/broad/reprocessing/wgs/WholeGenomeReprocessing.wdl index 78c54cd078..f60603e7bd 100644 --- a/pipelines/broad/reprocessing/wgs/WholeGenomeReprocessing.wdl +++ b/pipelines/broad/reprocessing/wgs/WholeGenomeReprocessing.wdl @@ -6,7 +6,7 @@ import "../../../../structs/dna_seq/DNASeqStructs.wdl" workflow WholeGenomeReprocessing { - String pipeline_version = "3.1.17" + String pipeline_version = "3.1.18" input { File? input_cram diff --git a/tasks/broad/GermlineVariantDiscovery.wdl b/tasks/broad/GermlineVariantDiscovery.wdl index 7139404ec7..0e446a1993 100644 --- a/tasks/broad/GermlineVariantDiscovery.wdl +++ b/tasks/broad/GermlineVariantDiscovery.wdl @@ -203,10 +203,12 @@ task Reblock { File ref_fasta File ref_fasta_index String output_vcf_filename - String docker_image = "us.gcr.io/broad-gatk/gatk:4.3.0.0" + String docker_image = "us.gcr.io/broad-gatk/gatk:4.5.0.0" Int additional_disk = 20 String? annotations_to_keep_command + String? annotations_to_remove_command Float? tree_score_cutoff + Boolean move_filters_to_genotypes = false } Int disk_size = ceil((size(gvcf, "GiB")) * 4) + additional_disk @@ -227,7 +229,9 @@ task Reblock { -do-qual-approx \ --floor-blocks -GQB 20 -GQB 30 -GQB 40 \ ~{annotations_to_keep_command} \ + ~{annotations_to_remove_command} \ ~{"--tree-score-threshold-to-no-call " + tree_score_cutoff} \ + ~{if move_filters_to_genotypes then "--add-site-filters-to-genotype" else ""} \ -O ~{output_vcf_filename} } diff --git a/tasks/broad/JointGenotypingTasks.wdl b/tasks/broad/JointGenotypingTasks.wdl index 0ae5d835e9..41918ed50b 100644 --- a/tasks/broad/JointGenotypingTasks.wdl +++ b/tasks/broad/JointGenotypingTasks.wdl @@ -273,6 +273,7 @@ task HardFilterAndMakeSitesOnlyVcf { String variant_filtered_vcf_filename String sites_only_vcf_filename + File? targets_interval_list # filters out all variants outside of the targets interval list for targeted sequencing Int disk_size_gb Int machine_mem_mb = 3750 @@ -282,10 +283,13 @@ task HardFilterAndMakeSitesOnlyVcf { command <<< set -euo pipefail + ~{"gatk IndexFeatureFile -I " + targets_interval_list} + gatk --java-options "-Xms3000m -Xmx3250m" \ VariantFiltration \ --filter-expression "ExcessHet > ~{excess_het_threshold}" \ --filter-name ExcessHet \ + ~{"--filter-not-in-mask --mask-name OUTSIDE_OF_TARGETS --mask " + targets_interval_list} \ -O ~{variant_filtered_vcf_filename} \ -V ~{vcf} diff --git a/verification/test-wdls/TestJointGenotyping.wdl b/verification/test-wdls/TestJointGenotyping.wdl index d0bdc640ab..389d7307b6 100644 --- a/verification/test-wdls/TestJointGenotyping.wdl +++ b/verification/test-wdls/TestJointGenotyping.wdl @@ -21,10 +21,10 @@ workflow TestJointGenotyping { Int medium_disk Int large_disk Int huge_disk - Array[String] snp_recalibration_tranche_values + Array[String]? snp_recalibration_tranche_values Array[String] snp_recalibration_annotation_values - Array[String] indel_recalibration_tranche_values - Array[String] indel_recalibration_annotation_values + Array[String]? indel_recalibration_tranche_values + Array[String]? indel_recalibration_annotation_values File haplotype_database File eval_interval_list File hapmap_resource_vcf @@ -40,11 +40,13 @@ workflow TestJointGenotyping { File dbsnp_resource_vcf = dbsnp_vcf File dbsnp_resource_vcf_index = dbsnp_vcf_index Float excess_het_threshold = 54.69 - Float snp_filter_level - Float indel_filter_level - Int snp_vqsr_downsampleFactor + Float? vqsr_snp_filter_level + Float? vqsr_indel_filter_level + File? targets_interval_list + Int? snp_vqsr_downsampleFactor Int? top_level_scatter_count Boolean? gather_vcfs + Boolean? run_vets Int snps_variant_recalibration_threshold = 500000 Boolean rename_gvcf_samples = true Float unbounded_scatter_count_scale_factor = 0.15 @@ -99,11 +101,13 @@ workflow TestJointGenotyping { dbsnp_resource_vcf = dbsnp_resource_vcf, dbsnp_resource_vcf_index = dbsnp_resource_vcf_index, excess_het_threshold = excess_het_threshold, - snp_filter_level = snp_filter_level, - indel_filter_level = indel_filter_level, + vqsr_snp_filter_level = vqsr_snp_filter_level, + vqsr_indel_filter_level = vqsr_indel_filter_level, snp_vqsr_downsampleFactor = snp_vqsr_downsampleFactor, + targets_interval_list = targets_interval_list, top_level_scatter_count = top_level_scatter_count, gather_vcfs = gather_vcfs, + run_vets = run_vets, snps_variant_recalibration_threshold = snps_variant_recalibration_threshold, rename_gvcf_samples = rename_gvcf_samples, unbounded_scatter_count_scale_factor = unbounded_scatter_count_scale_factor, diff --git a/verification/test-wdls/TestReblockGVCF.wdl b/verification/test-wdls/TestReblockGVCF.wdl index 6f5c386892..f34e22f1b7 100644 --- a/verification/test-wdls/TestReblockGVCF.wdl +++ b/verification/test-wdls/TestReblockGVCF.wdl @@ -17,6 +17,9 @@ workflow TestReblockGVCF { File ref_fasta_index Float? tree_score_cutoff String? annotations_to_keep_command + String? annotations_to_remove_command + Boolean? move_filters_to_genotypes + String? gvcf_file_extension # These values will be determined and injected into the inputs by the scala test framework String truth_path @@ -39,8 +42,10 @@ workflow TestReblockGVCF { ref_fasta = ref_fasta, ref_fasta_index = ref_fasta_index, tree_score_cutoff = tree_score_cutoff, - annotations_to_keep_command = annotations_to_keep_command - + annotations_to_keep_command = annotations_to_keep_command, + annotations_to_remove_command = annotations_to_remove_command, + move_filters_to_genotypes = move_filters_to_genotypes, + gvcf_file_extension = gvcf_file_extension }