317 remove excess header values in VCF extract (#7786)

* remove unwanted header * missed the extra NAY * update dockstore * use new headers jar * remove header lines from test too
broadinstitute · Apr 15, 2022 · 1387d47 · 1387d47
1 parent 7a15427
commit 1387d47
Show file tree

Hide file tree

Showing 4 changed files with 3 additions and 10 deletions.
diff --git a/.dockstore.yml b/.dockstore.yml
@@ -117,6 +117,7 @@ workflows:
        branches:
          - master
          - ah_var_store
+         - rc-vs-317-remove-excess-headers
    - name: GvsImportGenomes
      subclass: WDL
      primaryDescriptorPath: /scripts/variantstore/wdl/GvsImportGenomes.wdl

diff --git a/scripts/variantstore/wdl/GvsExtractCallset.wdl b/scripts/variantstore/wdl/GvsExtractCallset.wdl
@@ -15,7 +15,7 @@ workflow GvsExtractCallset {
 
     File interval_list = "gs://gcp-public-data--broad-references/hg38/v0/wgs_calling_regions.hg38.noCentromeres.noTelomeres.interval_list"
     File interval_weights_bed = "gs://broad-public-datasets/gvs/weights/gvs_vet_weights_1kb.bed"
-    File gatk_override = "gs://broad-dsp-spec-ops/scratch/bigquery-jointcalling/jars/rc-add-AD-04112022/gatk-package-4.2.0.0-498-g1f53709-SNAPSHOT-local.jar"
+    File gatk_override = "gs://broad-dsp-spec-ops/scratch/bigquery-jointcalling/jars/rc-update-headers-04142022/gatk-package-4.2.0.0-497-gda8a97a-SNAPSHOT-local.jar"
 
     String output_file_base_name = filter_set_name
 

diff --git a/src/main/java/org/broadinstitute/hellbender/tools/gvs/extract/ExtractCohort.java b/src/main/java/org/broadinstitute/hellbender/tools/gvs/extract/ExtractCohort.java
@@ -211,17 +211,14 @@ protected static VCFHeader generateVcfHeader(Set<String> sampleNames,
 
         // Filter fields
         headerLines.add(GATKVCFHeaderLines.getFilterLine(GATKVCFConstants.LOW_QUAL_FILTER_NAME));
-        headerLines.add(GATKVCFHeaderLines.getFilterLine(GATKVCFConstants.NAY_FROM_YNG));
         headerLines.add(GATKVCFHeaderLines.getFilterLine(GATKVCFConstants.EXCESS_HET_KEY));
-        headerLines.add(GATKVCFHeaderLines.getFilterLine(GATKVCFConstants.EXCESS_ALLELES));
         headerLines.add(GATKVCFHeaderLines.getFilterLine(GATKVCFConstants.NO_HQ_GENOTYPES));
 
         // Info fields
         VCFStandardHeaderLines.addStandardInfoLines( headerLines, true,
                 VCFConstants.ALLELE_COUNT_KEY,
                 VCFConstants.ALLELE_FREQUENCY_KEY,
-                VCFConstants.ALLELE_NUMBER_KEY,
-                VCFConstants.END_KEY
+                VCFConstants.ALLELE_NUMBER_KEY
         );
         headerLines.add(GATKVCFHeaderLines.getInfoLine(GATKVCFConstants.AS_RAW_QUAL_APPROX_KEY));
         headerLines.add(GATKVCFHeaderLines.getInfoLine(GATKVCFConstants.RAW_QUAL_APPROX_KEY));
@@ -231,7 +228,6 @@ protected static VCFHeader generateVcfHeader(Set<String> sampleNames,
                 VCFConstants.GENOTYPE_QUALITY_KEY
         );
         headerLines.add(GATKVCFHeaderLines.getFormatLine(GATKVCFConstants.REFERENCE_GENOTYPE_QUALITY));
-        headerLines.add(GATKVCFHeaderLines.getInfoLine(GATKVCFConstants.EXCESS_HET_KEY));
         headerLines.add(GATKVCFHeaderLines.getInfoLine(GATKVCFConstants.AS_VQS_LOD_KEY));
         headerLines.add(GATKVCFHeaderLines.getInfoLine(GATKVCFConstants.AS_YNG_STATUS_KEY));
 

diff --git a/...org/broadinstitute/hellbender/tools/gvs/extract/ExtractCohort/ranges_extract.expected.vcf b/...org/broadinstitute/hellbender/tools/gvs/extract/ExtractCohort/ranges_extract.expected.vcf
@@ -1,8 +1,6 @@
 ##fileformat=VCFv4.2
-##FILTER=<ID=EXCESS_ALLELES,Description="Site has an excess of alternate alleles based on the input threshold (default is 6)">
 ##FILTER=<ID=ExcessHet,Description="Site has excess het value larger than the threshold">
 ##FILTER=<ID=LowQual,Description="Low quality">
-##FILTER=<ID=NAY,Description="Considered a NAY in the Yay, Nay, Grey table">
 ##FILTER=<ID=NO_HQ_GENOTYPES,Description="Site has no high quality variant genotypes">
 ##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
 ##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
@@ -13,8 +11,6 @@
 ##INFO=<ID=AS_QUALapprox,Number=1,Type=String,Description="Allele-specific QUAL approximations">
 ##INFO=<ID=AS_VQSLOD,Number=A,Type=String,Description="For each alt allele, the log odds of being a true variant versus being false under the trained gaussian mixture model">
 ##INFO=<ID=AS_YNG,Number=A,Type=String,Description="For each alt allele, the yay/nay/grey status (yay are known good alleles, nay are known false positives, grey are unknown)">
-##INFO=<ID=END,Number=1,Type=Integer,Description="Stop position of the interval">
-##INFO=<ID=ExcessHet,Number=1,Type=Float,Description="Phred-scaled p-value for exact test of excess heterozygosity">
 ##INFO=<ID=QUALapprox,Number=1,Type=Integer,Description="Sum of PL[0] values; used to approximate the QUAL score">
 ##contig=<ID=chr1,length=248956422,assembly=38>
 ##contig=<ID=chr2,length=242193529,assembly=38>