Merge branch 'develop' into rc-2489-removegenref

broadinstitute · Feb 21, 2024 · 51c44fa · 51c44fa
2 parents 97c2cf1 + 149e049
commit 51c44fa
Show file tree

Hide file tree

Showing 104 changed files with 641 additions and 628 deletions.
diff --git a/pipelines/broad/annotation_filtration/AnnotationFiltration.changelog.md b/pipelines/broad/annotation_filtration/AnnotationFiltration.changelog.md
@@ -1,3 +1,8 @@
+# 1.2.5
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0
+
 # 1.2.4
 2022-11-09 (Date of Last Commit)
 

diff --git a/pipelines/broad/annotation_filtration/AnnotationFiltration.wdl b/pipelines/broad/annotation_filtration/AnnotationFiltration.wdl
@@ -4,7 +4,7 @@ import "../../../tasks/broad/Funcotator.wdl" as Funcotator
 
 workflow AnnotationFiltration {
 
-  String pipeline_version = "1.2.4"
+  String pipeline_version = "1.2.5"
 
   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:4.3.0.0"
+    String gatk_docker = "us.gcr.io/broad-gatk/gatk:4.5.0.0"
     File? custom_data_source_tar_gz
   }
 

diff --git a/pipelines/broad/annotation_filtration/test_inputs/Plumbing/hg38.json b/pipelines/broad/annotation_filtration/test_inputs/Plumbing/hg38.json
@@ -10,6 +10,6 @@
   "AnnotationFiltration.ref_fasta_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai",
   "AnnotationFiltration.ref_dict": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict",
 
-  "AnnotationFiltration.gatk_docker": "us.gcr.io/broad-gatk/gatk:4.3.0.0",
+  "AnnotationFiltration.gatk_docker": "us.gcr.io/broad-gatk/gatk:4.5.0.0",
   "AnnotationFiltration.custom_data_source_tar_gz": "gs://broad-public-datasets/funcotator/funcotator_dataSources.v1.6.20190124g.tar.gz"
 }
diff --git a/pipelines/broad/annotation_filtration/test_inputs/Scientific/hg38.json b/pipelines/broad/annotation_filtration/test_inputs/Scientific/hg38.json
@@ -8,6 +8,6 @@
   "AnnotationFiltration.ref_fasta_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai",
   "AnnotationFiltration.ref_dict": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict",
 
-  "AnnotationFiltration.gatk_docker": "us.gcr.io/broad-gatk/gatk:4.3.0.0",
+  "AnnotationFiltration.gatk_docker": "us.gcr.io/broad-gatk/gatk:4.5.0.0",
   "AnnotationFiltration.custom_data_source_tar_gz": "gs://broad-public-datasets/funcotator/funcotator_dataSources.v1.6.20190124g.tar.gz"
 }
diff --git a/pipelines/broad/arrays/imputation/Imputation.changelog.md b/pipelines/broad/arrays/imputation/Imputation.changelog.md
@@ -1,3 +1,8 @@
+# 1.1.12
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0
+
 # 1.1.11
 2023-08-01 (Date of last Commit)
 

diff --git a/pipelines/broad/arrays/imputation/Imputation.wdl b/pipelines/broad/arrays/imputation/Imputation.wdl
@@ -6,7 +6,7 @@ import "../../../../tasks/broad/Utilities.wdl" as utils
 
 workflow Imputation {
 
-  String pipeline_version = "1.1.11"
+  String pipeline_version = "1.1.12"
 
   input {
     Int chunkLength = 25000000

diff --git a/pipelines/broad/arrays/single_sample/Arrays.changelog.md b/pipelines/broad/arrays/single_sample/Arrays.changelog.md
@@ -1,3 +1,8 @@
+# 2.6.22
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0
+
 # 2.6.21
 2023-12-08 (Date of Last Commit)
 

diff --git a/pipelines/broad/arrays/single_sample/Arrays.wdl b/pipelines/broad/arrays/single_sample/Arrays.wdl
@@ -23,7 +23,7 @@ import "../../../../tasks/broad/Utilities.wdl" as utils
 
 workflow Arrays {
 
-  String pipeline_version = "2.6.21"
+  String pipeline_version = "2.6.22"
 
   input {
     String chip_well_barcode

diff --git a/pipelines/broad/arrays/validate_chip/ValidateChip.changelog.md b/pipelines/broad/arrays/validate_chip/ValidateChip.changelog.md
@@ -1,3 +1,8 @@
+# 1.16.4
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0
+
 # 1.16.3
 2023-01-13 (Date of Last Commit)
 

diff --git a/pipelines/broad/arrays/validate_chip/ValidateChip.wdl b/pipelines/broad/arrays/validate_chip/ValidateChip.wdl
@@ -21,7 +21,7 @@ import "../../../../tasks/broad/InternalArraysTasks.wdl" as InternalTasks
 
 workflow ValidateChip {
 
-  String pipeline_version = "1.16.3"
+  String pipeline_version = "1.16.4"
 
   input {
     String sample_alias

diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/JointGenotyping.changelog.md b/pipelines/broad/dna_seq/germline/joint_genotyping/JointGenotyping.changelog.md
@@ -1,3 +1,8 @@
+# 1.6.10
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0
+
 # 1.6.9
 2023-09-08 (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
@@ -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 = "1.6.9"
+  String pipeline_version = "1.6.10"
 
   input {
     File unpadded_intervals_file

diff --git a/...line/joint_genotyping/UltimaGenomics/UltimaGenomicsJointGenotyping.changelog.md b/...line/joint_genotyping/UltimaGenomics/UltimaGenomicsJointGenotyping.changelog.md
@@ -1,3 +1,8 @@
+# 1.1.7
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0.
+
 # 1.1.6
 2023-02-06 (Date of Last Commit)
 

diff --git a/.../broad/dna_seq/germline/joint_genotyping/UltimaGenomics/UltimaGenomicsJointGenotyping.wdl b/.../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 = "1.1.6"
+  String pipeline_version = "1.1.7"
 
   input {
     File unpadded_intervals_file

diff --git a/.../joint_genotyping/by_chromosome/JointGenotypingByChromosomePartOne.changelog.md b/.../joint_genotyping/by_chromosome/JointGenotypingByChromosomePartOne.changelog.md
@@ -1,3 +1,8 @@
+# 1.4.12
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0
+
 # 1.4.11
 2023-09-08 (Date of Last Commit)
 

diff --git a/...ad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartOne.wdl b/...ad/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 = "1.4.11"
+  String pipeline_version = "1.4.12"
 
   input {
     File unpadded_intervals_file

diff --git a/.../joint_genotyping/by_chromosome/JointGenotypingByChromosomePartTwo.changelog.md b/.../joint_genotyping/by_chromosome/JointGenotypingByChromosomePartTwo.changelog.md
@@ -1,3 +1,8 @@
+# 1.4.11
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0
+
 # 1.4.10
 2023-09-08 (Date of Last Commit)
 

diff --git a/...ad/dna_seq/germline/joint_genotyping/by_chromosome/JointGenotypingByChromosomePartTwo.wdl b/...ad/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 = "1.4.10"
+  String pipeline_version = "1.4.11"
 
   input {
     String callset_name

diff --git a/...nes/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.changelog.md b/...nes/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.changelog.md
@@ -1,10 +1,14 @@
+# 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.
+
 # 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
@@ -5,7 +5,7 @@ import "../../../../../../tasks/broad/Qc.wdl" as QC
 
 workflow ReblockGVCF {
 
-  String pipeline_version = "2.1.10"
+  String pipeline_version = "2.1.11"
 
 
   input {
@@ -50,7 +50,7 @@ workflow ReblockGVCF {
         calling_interval_list_index = gvcf_index,
         is_gvcf = true,
         extra_args = "--no-overlaps",
-        gatk_docker = "us.gcr.io/broad-gatk/gatk:4.3.0.0"
+        gatk_docker = "us.gcr.io/broad-gatk/gatk:4.5.0.0"
     }
 
   output {

diff --git a/...oad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.changelog.md b/...oad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.changelog.md
@@ -1,10 +1,14 @@
+# 3.1.18
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0.
+
 # 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
@@ -44,7 +44,7 @@ import "../../../../../../structs/dna_seq/DNASeqStructs.wdl"
 # WORKFLOW DEFINITION
 workflow ExomeGermlineSingleSample {
 
-  String pipeline_version = "3.1.17"
+  String pipeline_version = "3.1.18"
 
 
   input {

diff --git a/...seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.changelog.md b/...seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.changelog.md
@@ -1,3 +1,8 @@
+# 1.0.15
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0.
+
 # 1.0.14
 2023-12-14 (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
@@ -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 = "1.0.14"
+  String pipeline_version = "1.0.15"
 
 
   References references = alignment_references.references

diff --git a/...dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.changelog.md b/...dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.changelog.md
@@ -1,3 +1,8 @@
+# 3.1.19
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0.
+
 # 3.1.18
 2023-12-14 (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
@@ -40,7 +40,7 @@ import "../../../../../../structs/dna_seq/DNASeqStructs.wdl"
 workflow WholeGenomeGermlineSingleSample {
 
 
-  String pipeline_version = "3.1.18"
+  String pipeline_version = "3.1.19"
 
 
   input {

diff --git a/...ine/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.dragen_mode_best_results.json b/...ine/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.dragen_mode_best_results.json
@@ -82,5 +82,6 @@
     "agg_preemptible_tries": 3
   },
 
-  "WholeGenomeGermlineSingleSample.dragen_maximum_quality_mode": true
+  "WholeGenomeGermlineSingleSample.dragen_maximum_quality_mode": true,
+  "WholeGenomeGermlineSingleSample.BamToGvcf.HaplotypeCallerGATK4.memory_multiplier":2
 }
diff --git a/..._sample/wgs/test_inputs/Scientific/G94982.NA12878.dragen_mode_functional_equivalence.json b/..._sample/wgs/test_inputs/Scientific/G94982.NA12878.dragen_mode_functional_equivalence.json
@@ -81,5 +81,6 @@
     "agg_preemptible_tries": 3
   },
 
-  "WholeGenomeGermlineSingleSample.dragen_functional_equivalence_mode": true
+  "WholeGenomeGermlineSingleSample.dragen_functional_equivalence_mode": true,
+  "WholeGenomeGermlineSingleSample.BamToGvcf.HaplotypeCallerGATK4.memory_multiplier":2
 }
diff --git a/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.changelog.md b/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.changelog.md
@@ -1,3 +1,8 @@
+# 2.1.17
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0. Header documentation change for RAW_GT_COUNT annotation.
+
 # 2.1.16
 2023-12-14 (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
@@ -9,7 +9,7 @@ import "../../../../../tasks/broad/DragenTasks.wdl" as DragenTasks
 workflow VariantCalling {
 
 
-  String pipeline_version = "2.1.16"
+  String pipeline_version = "2.1.17"
 
 
   input {
@@ -183,7 +183,7 @@ workflow VariantCalling {
       calling_interval_list = calling_interval_list,
       is_gvcf = make_gvcf,
       extra_args = if (skip_reblocking == false) then "--no-overlaps" else "",
-      gatk_docker = "us.gcr.io/broad-gatk/gatk:4.3.0.0",
+      gatk_docker = "us.gcr.io/broad-gatk/gatk:4.5.0.0",
       preemptible_tries = agg_preemptible_tries
   }
 

diff --git a/..._seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.changelog.md b/..._seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.changelog.md
@@ -1,3 +1,8 @@
+# 1.0.15
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0.
+
 # 1.0.14
 2023-12-14 (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
@@ -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 = "1.0.14"
+  String pipeline_version = "1.0.15"
 
   References references = alignment_references.references
 

diff --git a/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/test_inputs/Scientific/HCC1187.json b/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/test_inputs/Scientific/HCC1187.json
@@ -41,5 +41,6 @@
         "ref_dbsnp": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf",
         "ref_dbsnp_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf.idx",
         "wgs_coverage_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/wgs_coverage_regions.hg38.interval_list"
-    }
+    },
+    "UltimaGenomicsWholeGenomeCramOnly.AlignmentAndMarkDuplicates.MarkDuplicatesSpark.memory_mb":300000
 }
diff --git a/pipelines/broad/genotyping/illumina/IlluminaGenotypingArray.changelog.md b/pipelines/broad/genotyping/illumina/IlluminaGenotypingArray.changelog.md
@@ -1,3 +1,8 @@
+# 1.12.16
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0.
+
 # 1.12.15
 2023-12-08 (Date of Last Commit)
 

diff --git a/pipelines/broad/genotyping/illumina/IlluminaGenotypingArray.wdl b/pipelines/broad/genotyping/illumina/IlluminaGenotypingArray.wdl
@@ -21,7 +21,7 @@ import "../../../../tasks/broad/Qc.wdl" as Qc
 
 workflow IlluminaGenotypingArray {
 
-  String pipeline_version = "1.12.15"
+  String pipeline_version = "1.12.16"
 
   input {
     String sample_alias

diff --git a/pipelines/broad/internal/arrays/imputation/BroadInternalImputation.changelog.md b/pipelines/broad/internal/arrays/imputation/BroadInternalImputation.changelog.md
@@ -1,3 +1,8 @@
+# 1.1.10
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0.
+
 # 1.1.9
 2023-08-01 (Date of Last Commit)
 

diff --git a/pipelines/broad/internal/arrays/imputation/BroadInternalImputation.wdl b/pipelines/broad/internal/arrays/imputation/BroadInternalImputation.wdl
@@ -9,7 +9,7 @@ workflow BroadInternalImputation {
         description: "Push outputs of Imputation.wdl to TDR dataset table ImputationOutputsTable and split out Imputation arrays into ImputationWideOutputsTable."
         allowNestedInputs: true
     }
-    String pipeline_version = "1.1.9"
+    String pipeline_version = "1.1.10"
 
     input {
         # inputs to wrapper task 

diff --git a/pipelines/broad/internal/arrays/single_sample/BroadInternalArrays.changelog.md b/pipelines/broad/internal/arrays/single_sample/BroadInternalArrays.changelog.md
@@ -1,3 +1,8 @@
+# 1.1.6
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0.
+
 # 1.1.5
 2023-12-08 (Date of Last Commit)
 

diff --git a/pipelines/broad/internal/arrays/single_sample/BroadInternalArrays.wdl b/pipelines/broad/internal/arrays/single_sample/BroadInternalArrays.wdl
@@ -9,7 +9,7 @@ workflow BroadInternalArrays {
         description: "Push outputs of Arrays.wdl to TDR dataset table ArraysOutputsTable."
     }
 
-    String pipeline_version = "1.1.5"
+    String pipeline_version = "1.1.6"
 
     input {
         # inputs to wrapper task

diff --git a/.../germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.changelog.md b/.../germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.changelog.md
@@ -1,3 +1,8 @@
+# 1.0.16
+2023-12-18 (Date of Last Commit)
+
+* Updated to GATK version 4.5.0.0.
+* 
 # 1.0.15
 2023-12-14 (Date of Last Commit)
-Original file line number
+Diff line change
@@ Expand Up / @@ -40,7 +40,7 @@ import "../../../../../../structs/dna_seq/DNASeqStructs.wdl" @@
     workflow WholeGenomeGermlineSingleSample {
-      String pipeline_version = "3.1.18"
+      String pipeline_version = "3.1.19"
       input {
@@ Expand Down @@