VS-623 exclude as yng from vcf (#8734)

* Remove AS_YNG from extracted VCFs
* Added the updated docker

Author: gbggrant

scripts/variantstore/wdl/GvsUtils.wdl

@@ -73,7 +73,7 @@ task GetToolVersions {
     # there are a handlful of tasks that require the larger GNU libc-based `slim`.
     String cloud_sdk_slim_docker = "gcr.io/google.com/cloudsdktool/cloud-sdk:435.0.0-slim"
     String variants_docker = "us.gcr.io/broad-dsde-methods/variantstore:2024-03-12-alpine-2beb1a005"
-    String gatk_docker = "us.gcr.io/broad-dsde-methods/broad-gatk-snapshots:varstore_2024_02_16_78c53a6"
+    String gatk_docker = "us.gcr.io/broad-dsde-methods/broad-gatk-snapshots:varstore_2024_03_15_ddc537dc8"
     String variants_nirvana_docker = "us.gcr.io/broad-dsde-methods/variantstore:nirvana_2022_10_19"
     String real_time_genomics_docker = "docker.io/realtimegenomics/rtg-tools:latest"
     String gotc_imputation_docker = "us.gcr.io/broad-gotc-prod/imputation-bcf-vcf:1.0.5-1.10.2-0.1.16-1649948623"

src/main/java/org/broadinstitute/hellbender/tools/gvs/extract/ExtractCohort.java

@@ -238,7 +238,6 @@ private static VCFHeader generateVcfHeader(Set<String> sampleNames,
                 VCFConstants.GENOTYPE_QUALITY_KEY
         );
         headerLines.add(GATKVCFHeaderLines.getFormatLine(GATKVCFConstants.REFERENCE_GENOTYPE_QUALITY));
-        headerLines.add(GATKVCFHeaderLines.getInfoLine(GATKVCFConstants.AS_YNG_STATUS_KEY));
 
         headerLines.addAll(extraHeaders);
 

src/main/java/org/broadinstitute/hellbender/tools/gvs/extract/ExtractCohortEngine.java

@@ -620,16 +620,13 @@ private VariantContext filterSiteByAlleleSpecificVQScore(VariantContext mergedVC
         mergedVC.getAlternateAlleles().forEach(key -> Optional.ofNullable(remappedScoreMap.get(key)).ifPresent(value -> relevantScoreMap.put(key, value)));
         final Map<Allele, Double> relevantVQScoreMap = new LinkedHashMap<>();
         mergedVC.getAlternateAlleles().forEach(key -> Optional.ofNullable(remappedVQScoreMap.get(key)).ifPresent(value -> relevantVQScoreMap.put(key, value)));
-        final Map<Allele, String> relevantYngMap = new LinkedHashMap<>();
-        mergedVC.getAlternateAlleles().forEach(key -> Optional.ofNullable(remappedYngMap.get(key)).ifPresent(value -> relevantYngMap.put(key, value)));
 
         final VariantContextBuilder builder = new VariantContextBuilder(mergedVC);
 
         if (getScoreFieldName() != null) {
             builder.attribute(getScoreKey(), relevantScoreMap.values().stream().map(val -> val.equals(Double.NaN) ? VCFConstants.EMPTY_INFO_FIELD : val.toString()).collect(Collectors.toList()));
         }
         builder.attribute(getAlleleSpecificVQSScoreKey(), relevantVQScoreMap.values().stream().map(val -> val.equals(Double.NaN) ? VCFConstants.EMPTY_INFO_FIELD : val.toString()).collect(Collectors.toList()));
-        builder.attribute(GATKVCFConstants.AS_YNG_STATUS_KEY, new ArrayList<>(relevantYngMap.values()));
 
         if (vqScoreFilteringType.equals(ExtractCohort.VQScoreFilteringType.SITES)) { // Note that these filters are not used with Genotype VQSLOD/Sensitivity Filtering
             int refLength = mergedVC.getReference().length();

src/test/resources/org/broadinstitute/hellbender/tools/gvs/extract/ExtractCohortToVcf/ranges_extract.expected_vqsr_classic.vcf

@@ -12,7 +12,6 @@
 ##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
 ##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
 ##INFO=<ID=AS_QUALapprox,Number=1,Type=String,Description="Allele-specific QUAL approximations">
-##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=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>

src/test/resources/org/broadinstitute/hellbender/tools/gvs/extract/ExtractCohortToVcf/ranges_extract.expected_vqsr_lite.vcf

@@ -12,7 +12,6 @@
 ##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
 ##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
 ##INFO=<ID=AS_QUALapprox,Number=1,Type=String,Description="Allele-specific QUAL approximations">
-##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=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>