Updated header writing

broadinstitute · Dec 13, 2024 · 170ec7c · 170ec7c
1 parent d403387
commit 170ec7c
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 4 deletions.
diff --git a/inputs/values/dockers.json b/inputs/values/dockers.json
@@ -12,8 +12,8 @@
   "samtools_cloud_docker": "us.gcr.io/broad-dsde-methods/gatk-sv/samtools-cloud:2024-10-25-v0.29-beta-5ea22a52",
   "sv_base_docker": "us.gcr.io/broad-dsde-methods/gatk-sv/sv-base:2024-10-25-v0.29-beta-5ea22a52",
   "sv_base_mini_docker": "us.gcr.io/broad-dsde-methods/gatk-sv/sv-base-mini:2024-10-25-v0.29-beta-5ea22a52",
-  "sv_pipeline_docker": "us-central1-docker.pkg.dev/talkowski-training/kj-development/sv-pipeline:kj-clean-vcf-766acf63d47b59191cfd2362c5acb8311202a904",
-  "sv_pipeline_qc_docker": "us-central1-docker.pkg.dev/talkowski-training/kj-development/sv-pipeline:kj-clean-vcf-766acf63d47b59191cfd2362c5acb8311202a904",
+  "sv_pipeline_docker": "us-central1-docker.pkg.dev/talkowski-training/kj-development/sv-pipeline:kj-clean-vcf-d4033870e659b59c96980ba834241a3e68a5865e",
+  "sv_pipeline_qc_docker": "us-central1-docker.pkg.dev/talkowski-training/kj-development/sv-pipeline:kj-clean-vcf-d4033870e659b59c96980ba834241a3e68a5865e",
   "wham_docker": "us.gcr.io/broad-dsde-methods/gatk-sv/wham:2024-10-25-v0.29-beta-5ea22a52",
   "igv_docker": "us.gcr.io/broad-dsde-methods/gatk-sv/igv:mw-xz-fixes-2-b1be6a9",
   "duphold_docker": "us.gcr.io/broad-dsde-methods/gatk-sv/duphold:mw-xz-fixes-2-b1be6a9",
@@ -28,5 +28,5 @@
   "sv_utils_docker": "us.gcr.io/broad-dsde-methods/gatk-sv/sv-utils:2024-10-25-v0.29-beta-5ea22a52",
   "gq_recalibrator_docker": "us.gcr.io/broad-dsde-methods/markw/gatk:mw-tb-form-sv-filter-training-data-899360a",
   "str": "us.gcr.io/broad-dsde-methods/gatk-sv/str:2023-05-23-v0.27.3-beta-e537bdd6",
-  "denovo": "us-central1-docker.pkg.dev/talkowski-training/kj-development/denovo:kj-clean-vcf-766acf63d47b59191cfd2362c5acb8311202a904"
+  "denovo": "us-central1-docker.pkg.dev/talkowski-training/kj-development/denovo:kj-clean-vcf-d4033870e659b59c96980ba834241a3e68a5865e"
 }
diff --git a/src/sv-pipeline/04_variant_resolution/scripts/cleanvcf_postprocess.py b/src/sv-pipeline/04_variant_resolution/scripts/cleanvcf_postprocess.py
@@ -11,12 +11,15 @@
 UNR = 'UNR'
 FILTER_VCF_INFO_LINES = {
     'BND_DEPTH', 'BND_MATEID', 'SPLIT_READS', 'PAIRED_END_READS', 
-    'CLUSTER_MEMBER_IDS', 'MULTIALLELIC', 'UNRESOLVED'
+    'CLUSTER_MEMBER_IDS', 'MULTIALLELIC', 'UNRESOLVED', 'VARGQ', 
+    'EVENT', 'REVISED_EVENT', 'MULTI_CNV'
 }
 FILTER_VCF_TEXT_LINES = {
     'CIPOS', 'CIEND', 'RMSSTD', 'source', 'bcftools', 'GATKCommandLine', 'fileformat'
 }
 
+# TODO: Remove INFO fields in advance of script: 'MULTI_CNV', 'VARGQ', 'REVISED_EVENT'
+
 def cleanse_header(header):
     new_header = pysam.VariantHeader()