updates to BGE joint calling pipeline from GVS tieout (#1370)

* updates to BGE pipeline from GVS tieout fix string * changelogs * Updated pipeline_versions.txt with all pipeline version information * updated JointGenotyping changelog * Update changelog docs Co-authored-by: ekiernan <[email protected]> --------- Co-authored-by: GitHub Action <[email protected]> Co-authored-by: Nikelle Petrillo <[email protected]> Co-authored-by: ekiernan <[email protected]>
broadinstitute · Sep 16, 2024 · fe21c07 · fe21c07
1 parent e1891ab
commit fe21c07
Show file tree

Hide file tree

Showing 11 changed files with 34 additions and 11 deletions.
diff --git a/pipeline_versions.txt b/pipeline_versions.txt
@@ -14,10 +14,10 @@ BuildCembaReferences 1.0.0 2020-11-15
 CEMBA 1.1.7 2024-09-06 
 GDCWholeGenomeSomaticSingleSample 1.3.3 2024-09-06 
 UltimaGenomicsWholeGenomeCramOnly 1.0.21 2024-09-06 
-JointGenotypingByChromosomePartOne 1.5.0 2024-09-06 
-JointGenotypingByChromosomePartTwo 1.5.0 2024-09-06 
-UltimaGenomicsJointGenotyping 1.2.0 2024-09-06 
-JointGenotyping 1.7.0 2024-09-06 
+JointGenotypingByChromosomePartOne 1.5.1 2024-09-10 
+JointGenotypingByChromosomePartTwo 1.5.1 2024-09-10 
+UltimaGenomicsJointGenotyping 1.2.1 2024-09-10 
+JointGenotyping 1.7.1 2024-09-10 
 ReblockGVCF 2.3.0 2024-09-06 
 VariantCalling 2.2.2 2024-09-06 
 WholeGenomeGermlineSingleSample 3.3.0 2024-09-06 

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 +1,10 @@
+# 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)
 
@@ -111,4 +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
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 = "1.7.0"
+ String pipeline_version = "1.7.1"
 
  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 @@
+# 1.2.1
+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)
 

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 = "1.2.0"
+ String pipeline_version = "1.2.1"
 
  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 @@
+# 1.5.1
+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)
 

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 = "1.5.0"
+ String pipeline_version = "1.5.1"
 
  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 @@
+# 1.5.1
+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)
 

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 = "1.5.0"
+ String pipeline_version = "1.5.1"
 
  input {
  String callset_name

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
@@ -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,
 

diff --git a/tasks/broad/JointGenotypingTasks.wdl b/tasks/broad/JointGenotypingTasks.wdl
@@ -289,7 +289,7 @@ task HardFilterAndMakeSitesOnlyVcf {
  VariantFiltration \
  --filter-expression "ExcessHet > ~{excess_het_threshold}" \
  --filter-name ExcessHet \
- ~{"--filter-not-in-mask --mask-name OUTSIDE_OF_TARGETS --mask " + targets_interval_list} \
+ ~{"--filter-not-in-mask --mask-description \"Does not overlap the targets interval list.\" --mask-name OUTSIDE_OF_TARGETS --mask " + targets_interval_list} \
  -O ~{variant_filtered_vcf_filename} \
  -V ~{vcf}