Merge branch 'develop' into lk-PD-2736-doublets

pipeline_versions.txt

@@ -1,42 +1,42 @@
 Pipeline Name	Version	Date of Last Commit
-Optimus	 7.6.0	2024-08-06 
-Multiome	 5.5.0	2024-08-06 
-PairedTag	 1.5.0	2024-08-06 
-atac	 2.2.3	2024-08-02 
-SlideSeq	 3.4.0	2024-08-06 
-snm3C	 4.0.4	2024-08-06 
-MultiSampleSmartSeq2SingleNucleus	 1.4.2	2024-08-25-02 
+RNAWithUMIsPipeline	 1.0.17	2024-09-06 
+CheckFingerprint	 1.0.21	2024-09-06 
+CramToUnmappedBams	 1.1.3	2024-08-02 
+ExomeReprocessing	 3.3.1	2024-09-17 
+ExternalExomeReprocessing	 3.3.1	2024-09-17 
+ExternalWholeGenomeReprocessing	 2.3.1	2024-09-17 
+WholeGenomeReprocessing	 3.3.1	2024-09-17 
+AnnotationFiltration	 1.2.6	2024-09-06 
+IlluminaGenotypingArray	 1.12.22	2024-09-06 
+UltimaGenomicsWholeGenomeGermline	 1.1.0	2024-09-06 
+ExomeGermlineSingleSample	 3.2.1	2024-09-17 
+WholeGenomeGermlineSingleSample	 3.3.1	2024-09-17 
+JointGenotypingByChromosomePartTwo	 1.5.1	2024-09-10 
+JointGenotypingByChromosomePartOne	 1.5.1	2024-09-10 
+ReblockGVCF	 2.3.0	2024-09-06 
+JointGenotyping	 1.7.1	2024-09-10 
+UltimaGenomicsJointGenotyping	 1.2.1	2024-09-10 
+VariantCalling	 2.2.2	2024-09-06 
+UltimaGenomicsWholeGenomeCramOnly	 1.0.21	2024-09-06 
+GDCWholeGenomeSomaticSingleSample	 1.3.3	2024-09-06 
+Imputation	 1.1.14	2024-09-06 
+Arrays	 2.6.28	2024-09-06 
+MultiSampleArrays	 1.6.2	2024-08-02 
+ValidateChip	 1.16.6	2024-09-06 
+BroadInternalRNAWithUMIs	 1.0.34	2024-09-06 
+BroadInternalUltimaGenomics	 1.1.0	2024-09-06 
+BroadInternalImputation	 1.1.13	2024-09-06 
+BroadInternalArrays	 1.1.12	2024-09-06 
+MultiSampleSmartSeq2	 2.2.22	2024-09-11 
+MultiSampleSmartSeq2SingleNucleus	 2.0.0	2024-09-11 
+PairedTag	 1.6.1	2024-09-11 
+SmartSeq2SingleSample	 5.1.21	2024-09-11 
 scATAC	 1.3.2	2023-08-03 
-SmartSeq2SingleSample	 5.1.20	2023-04-19 
+Optimus	 7.6.1	2024-09-11 
+Multiome	 5.6.1	2024-09-11 
+snm3C	 4.0.4	2024-08-06 
 BuildIndices	 3.0.0	2023-12-06 
-MultiSampleSmartSeq2	 2.2.21	2023-04-19 
-CEMBA	 1.1.6	2023-12-18 
+atac	 2.3.1	2024-09-11 
+SlideSeq	 3.4.1	2024-09-11 
 BuildCembaReferences	 1.0.0	2020-11-15 
-UltimaGenomicsWholeGenomeCramOnly	 1.0.20	2024-08-02 
-GDCWholeGenomeSomaticSingleSample	 1.3.2	2024-08-02  
-ExomeGermlineSingleSample	 3.1.22	2024-06-12 
-UltimaGenomicsWholeGenomeGermline	 1.0.20	2024-08-02 
-WholeGenomeGermlineSingleSample	 3.2.1	2024-06-12 
-VariantCalling	 2.2.1	2024-06-12 
-UltimaGenomicsJointGenotyping	 1.1.7	2023-12-18 
-JointGenotyping	 1.6.10	2023-12-18 
-ReblockGVCF	 2.2.1	2024-06-12 
-JointGenotypingByChromosomePartTwo	 1.4.11	2023-12-18 
-JointGenotypingByChromosomePartOne	 1.4.12	2023-12-18 
-ExternalExomeReprocessing	 3.2.2	2024-08-02 
-ExternalWholeGenomeReprocessing	 2.2.2	2024-08-02 
-ExomeReprocessing	 3.2.2	2024-08-02 
-CramToUnmappedBams	 1.1.3	2024-08-02 
-WholeGenomeReprocessing	 3.2.2	2024-08-02 
-IlluminaGenotypingArray	 1.12.21	2024-08-02 
-Arrays	 2.6.27	2024-08-02 
-MultiSampleArrays	 1.6.2	2024-08-02 
-ValidateChip	 1.16.5	2024-08-02 
-Imputation	 1.1.13	2024-05-21 
-RNAWithUMIsPipeline	 1.0.16	2023-12-18 
-BroadInternalUltimaGenomics	 1.0.21	2024-08-02 
-BroadInternalArrays	 1.1.11	2024-08-02 
-BroadInternalImputation	 1.1.12	2024-08-02 
-BroadInternalRNAWithUMIs	 1.0.33	2024-08-02 
-CheckFingerprint	 1.0.20	2024-08-02 
-AnnotationFiltration	 1.2.5	2023-12-18 
+CEMBA	 1.1.7	2024-09-06 

pipelines/broad/annotation_filtration/AnnotationFiltration.changelog.md

@@ -1,3 +1,8 @@
+# 1.2.6
+2024-09-06 (Date of Last Commit)
+
+* Updated to GATK version 4.6.0.0
+
 # 1.2.5
 2023-12-18 (Date of Last Commit)
 

pipelines/broad/annotation_filtration/AnnotationFiltration.wdl

@@ -4,7 +4,7 @@ import "../../../tasks/broad/Funcotator.wdl" as Funcotator
 
 workflow AnnotationFiltration {
 
-  String pipeline_version = "1.2.5"
+  String pipeline_version = "1.2.6"
 
   input {
     Array[File] vcfs
@@ -15,7 +15,7 @@ workflow AnnotationFiltration {
     File ref_dict
     File? funcotator_interval_list
 
-    String gatk_docker = "us.gcr.io/broad-gatk/gatk:4.5.0.0"
+    String gatk_docker = "us.gcr.io/broad-gatk/gatk:4.6.0.0"
     File? custom_data_source_tar_gz
   }
 

pipelines/broad/arrays/imputation/Imputation.changelog.md

@@ -1,9 +1,13 @@
+# 1.1.14
+2024-09-06 (Date of Last Commit)
+
+* Updated to GATK version 4.6.0.0
+
 # 1.1.13
 2024-05-21 (Date of Last Commit)
 
 * Updated GermlineVariantDiscovery, BamProcessing, DragenTasks, Qc, and Utilities tasks to allow multi-cloud dockers. This change does not affect this pipeline.
 
-
 # 1.1.12
 2023-12-18 (Date of Last Commit)
 

pipelines/broad/arrays/imputation/Imputation.wdl

@@ -6,7 +6,7 @@ import "../../../../tasks/broad/Utilities.wdl" as utils
 
 workflow Imputation {
 
-  String pipeline_version = "1.1.13"
+  String pipeline_version = "1.1.14"
 
   input {
     Int chunkLength = 25000000

pipelines/broad/arrays/single_sample/Arrays.changelog.md

@@ -1,3 +1,8 @@
+# 2.6.28
+2024-09-06 (Date of Last Commit)
+
+* Updated to GATK version 4.6.0.0
+
 # 2.6.27
 2024-08-02 (Date of Last Commit)
 

pipelines/broad/arrays/single_sample/Arrays.wdl

@@ -23,7 +23,7 @@ import "../../../../tasks/broad/Utilities.wdl" as utils
 
 workflow Arrays {
 
-  String pipeline_version = "2.6.27"
+  String pipeline_version = "2.6.28"
 
   input {
     String chip_well_barcode

pipelines/broad/arrays/validate_chip/ValidateChip.changelog.md

@@ -1,3 +1,8 @@
+# 1.16.6
+2024-09-06 (Date of Last Commit)
+
+* Updated to GATK version 4.6.0.0
+
 # 1.16.5
 2024-08-02 (Date of Last Commit)
 

pipelines/broad/arrays/validate_chip/ValidateChip.wdl

@@ -21,7 +21,7 @@ import "../../../../tasks/broad/InternalArraysTasks.wdl" as InternalTasks
 
 workflow ValidateChip {
 
-  String pipeline_version = "1.16.5"
+  String pipeline_version = "1.16.6"
 
   input {
     String sample_alias

pipelines/broad/dna_seq/germline/joint_genotyping/JointGenotyping.changelog.md

@@ -1,3 +1,16 @@
+# 1.7.1
+2024-09-10 (Date of Last Commit)
+
+* Update to BGE filtering options in JointCalling 
+* If target interval list is provided for filtering, the documentation in the header will be clearer
+* If VETS is enabled, the SCORE annotation will be added to all output variants (even hard filtered sites)
+
+# 1.7.0
+2024-09-06 (Date of Last Commit)
+
+* Updated to GATK version 4.6.0.0
+* Updated how no-calls are represented in the output VCFs (0/0 -> ./.) which also changes some annotations in the VCF
+
 # 1.6.10
 2023-12-18 (Date of Last Commit)
 
@@ -105,4 +118,4 @@ The `"JointGenotyping.GenotypeGVCFs.allow_old_rms_mapping_quality_annotation_dat
 Converging WGS and Exome Joint Genotyping into one all-powerful workflow!
 
 # 1.0
-Initial release of the ExomeJointGenotyping pipeline
+Initial release of the ExomeJointGenotyping pipeline

pipelines/broad/dna_seq/germline/joint_genotyping/JointGenotyping.wdl

@@ -7,7 +7,7 @@ import "https://raw.githubusercontent.com/broadinstitute/gatk/4.5.0.0/scripts/vc
 # Joint Genotyping for hg38 Whole Genomes and Exomes (has not been tested on hg19)
 workflow JointGenotyping {
 
-  String pipeline_version = "1.6.10"
+  String pipeline_version = "1.7.1"
 
   input {
     File unpadded_intervals_file
@@ -214,7 +214,7 @@ workflow JointGenotyping {
         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"
+        gatk_docker = "us.gcr.io/broad-gatk/gatk:4.6.0.0"
     }
   } 
   if (!run_vets) {

pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/UltimaGenomicsJointGenotyping.changelog.md

@@ -1,3 +1,14 @@
+# 1.2.1
+2024-09-10 (Date of Last Commit)
+
+* Update to BGE filtering options in JointCalling; this has no effect on this pipeline
+
+# 1.2.0
+2024-09-06 (Date of Last Commit)
+
+* Updated to GATK version 4.6.0.0
+* Updated how no-calls are represented in the output VCFs (0/0 -> ./.) which also changes some annotations in the VCF
+
 # 1.1.7
 2023-12-18 (Date of Last Commit)
 

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 = "1.1.7"
+  String pipeline_version = "1.2.1"
 
   input {
     File unpadded_intervals_file
@@ -168,7 +168,7 @@ workflow UltimaGenomicsJointGenotyping {
       extract_extra_args = "--mode SNP",
       train_extra_args = "--mode SNP",
       score_extra_args = "--mode SNP",
-      gatk_docker = "us.gcr.io/broad-gatk/gatk:4.5.0.0"
+      gatk_docker = "us.gcr.io/broad-gatk/gatk:4.6.0.0"
   }
 
   call Filtering.JointVcfFiltering as TrainAndApplyFilteringModelINDELs {
@@ -184,7 +184,7 @@ workflow UltimaGenomicsJointGenotyping {
       extract_extra_args = "--mode INDEL",
       train_extra_args = "--mode INDEL",
       score_extra_args = "--mode INDEL",
-      gatk_docker = "us.gcr.io/broad-gatk/gatk:4.5.0.0"
+      gatk_docker = "us.gcr.io/broad-gatk/gatk:4.6.0.0"
   }
 
   call FilteringThreshold.ExtractOptimizeSingleSample as FindFilteringThresholdAndFilter {

pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartOne.changelog.md

@@ -1,3 +1,14 @@
+# 1.5.1
+2024-09-10 (Date of Last Commit)
+
+* Update to BGE filtering options in JointCalling; this has no effect on this pipeline
+
+# 1.5.0
+2024-09-06 (Date of Last Commit)
+
+* Updated to GATK version 4.6.0.0 
+* Updated how no-calls are represented in the output VCFs (0/0 -> ./.) which also changes some annotations in the VCF
+
 # 1.4.12
 2023-12-18 (Date of Last Commit)
 

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 = "1.4.12"
+  String pipeline_version = "1.5.1"
 
   input {
     File unpadded_intervals_file

pipelines/broad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartTwo.changelog.md

@@ -1,3 +1,14 @@
+# 1.5.1
+2024-09-10 (Date of Last Commit)
+
+* Update to BGE filtering options in JointCalling; this has no effect on this pipeline
+
+# 1.5.0
+2024-09-06 (Date of Last Commit)
+
+* Updated to GATK version 4.6.0.0
+* Updated how no-calls are represented in the output VCFs (0/0 -> ./.) which also changes some annotations in the VCF
+
 # 1.4.11
 2023-12-18 (Date of Last Commit)
 

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 = "1.4.11"
+  String pipeline_version = "1.5.1"
 
   input {
     String callset_name

pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.changelog.md

@@ -1,3 +1,8 @@
+# 2.3.0
+2024-09-06 (Date of Last Commit)
+
+* Updated to GATK version 4.6.0.0. Some expected minor differences around low quality sites (GQ0 genotypes or no-calls)
+
 # 2.2.1
 2024-06-12 (Date of Last Commit)
 
@@ -6,7 +11,7 @@
 # 2.2.0
 2024-07-09 (Date of Last Commit)
 
-* Updated ReblockGVCF.wdl to run in Azure. cloud_provider is a new, required input. 
+* Updated ReblockGVCF.wdl to run in Azure. cloud_provider is a new, required input 
 
 # 2.1.13
 2024-07-01 (Date of Last Commit)
@@ -16,12 +21,12 @@
 # 2.1.12
 2024-03-26 (Date of Last Commit)
 
-* ValidateVcfs requires less memory when run without interval list. This is useful for WGS samples that were previously running out of memory.
+* ValidateVcfs requires less memory when run without interval list. This is useful for WGS samples that were previously running out of memory
 
 # 2.1.11
 2023-12-18 (Date of Last Commit)
 
-* Updated to GATK version 4.5.0.0. Header documentation change for RAW_GT_COUNT annotation.
+* Updated to GATK version 4.5.0.0. Header documentation change for RAW_GT_COUNT annotation
 
 # 2.1.10
 2023-12-14 (Date of Last Commit)

pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.wdl

@@ -6,7 +6,7 @@ import "../../../../../../tasks/broad/Utilities.wdl" as utils
 
 workflow ReblockGVCF {
 
-  String pipeline_version = "2.2.1"
+  String pipeline_version = "2.3.0"
 
 
   input {
@@ -26,8 +26,8 @@ workflow ReblockGVCF {
 
   String gvcf_basename = basename(gvcf, gvcf_file_extension)
   # docker images
-  String gatk_docker_gcp = "us.gcr.io/broad-gatk/gatk:4.5.0.0"
-  String gatk_docker_azure = "dsppipelinedev.azurecr.io/gatk_reduced_layers:1.0.0"
+  String gatk_docker_gcp = "us.gcr.io/broad-gatk/gatk:4.6.0.0"
+  String gatk_docker_azure = "terrapublic.azurecr.io/gatk:4.6.0.0"
   String gatk_docker = if cloud_provider == "gcp" then gatk_docker_gcp else gatk_docker_azure
 
   # make sure either gcp or azr is supplied as cloud_provider input

pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/bge.json

@@ -24,7 +24,8 @@
   "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.snp_recalibration_annotation_values": ["QD", "MQRankSum", "ReadPosRankSum", "FS", "MQ", "SOR"],
+  "JointGenotyping.TrainAndApplyVETS.score_extra_args": " --ignore-all-filters ",
 
   "JointGenotyping.use_allele_specific_annotations": false,
 

pipelines/broad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.changelog.md

@@ -1,3 +1,14 @@
+# 3.2.1
+2024-09-17 (Date of Last Commit)
+
+* Updated DRAGEN aligner parameters to fix non-determinism; this does not affect the Exome workflow 
+
+# 3.2.0
+2024-09-06 (Date of Last Commit)
+
+* Updated to GATK version 4.6.0.0
+* Updated version drops some low quality sites from VCFs; if reblocking is enabled, the DP annotation in some ref blocks will change due to the change in HaplotypeCaller
+
 # 3.1.22
 2024-06-12 (Date of Last Commit)
 

pipelines/broad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.wdl

@@ -45,7 +45,7 @@ import "../../../../../../tasks/broad/Utilities.wdl" as utils
 # WORKFLOW DEFINITION
 workflow ExomeGermlineSingleSample {
 
-  String pipeline_version = "3.1.22"
+  String pipeline_version = "3.2.1"
 
 
   input {
@@ -68,8 +68,8 @@ workflow ExomeGermlineSingleSample {
   }
 
   # docker images
-  String gatk_docker_gcp = "us.gcr.io/broad-gatk/gatk:4.5.0.0"
-  String gatk_docker_azure = "dsppipelinedev.azurecr.io/gatk_reduced_layers:1.0.0"
+  String gatk_docker_gcp = "us.gcr.io/broad-gatk/gatk:4.6.0.0"
+  String gatk_docker_azure = "terrapublic.azurecr.io/gatk:4.6.0.0"
   String gatk_docker = if cloud_provider == "gcp" then gatk_docker_gcp else gatk_docker_azure
 
   # make sure either gcp or azr is supplied as cloud_provider input