Write out SV callers as array (#81)

Closes: #81
Related-Issue: #81
Projected-Results-Impact: none

CHANGES.md

@@ -2,10 +2,15 @@
 
 ## v0.27 (work in progress)
 
+**IMPORTANT COMPATIBILITY NOTE:**
+For annotating SVs, the output of this version is not compatible with `varfish-server` v1.2 (Anthenea) and early versions of the v2 (Bollonaster) development branch.
+You can generate compatible files by adding the `--opt-out=chrom2-columns,dbcounts-columns,callers-array` as arguments to `annotate-svs`.
+
 - Writing out proper SV type for Dragen CNV (#76)
 - Adding support for depth of coverage annotation (#73)
 - Ensure output files are sorted by chromosomes (#79)
 - Merge multiple input VCFs in annotate-svs with clustering (#75)
+- Write out SV callers as array (#81)
 
 ## v0.26
 

tests/hg19-chr22/Case_1_index.delly2.gts.tsv-expected

@@ -1,2 +1,2 @@
-release	chromosome	chromosome_no	bin	chromosome2	chromosome_no2	bin2	pe_orientation	start	end	start_ci_left	start_ci_right	end_ci_left	end_ci_right	case_id	set_id	sv_uuid	caller	sv_type	sv_sub_type	info	num_hom_alt	num_hom_ref	num_het	num_hemi_alt	num_hemi_ref	genotype
-GRCh37	22	22	89	22	22	89	3to5	17400000	17700000	-29	29	-29	29	.	.	UUID	EMBL.DELLYv1.1.3	DEL	DEL	{"""affectedCarriers""":0,"""backgroundCarriers""":0,"""unaffectedCarriers""":0}	0	2	1	0	0	{"""Case_1_father-N1-DNA1-WGS1""":{"""cn""":2,"""ft""":["""LowQual"""],"""gq""":14,"""gt""":"""0/1""","""pec""":0,"""pev""":0,"""src""":34,"""srv""":4},"""Case_1_index-N1-DNA1-WGS1""":{"""cn""":2,"""gq""":35,"""gt""":"""0/0""","""pec""":0,"""pev""":0,"""src""":29,"""srv""":2},"""Case_1_mother-N1-DNA1-WGS1""":{"""cn""":2,"""gq""":67,"""gt""":"""0/0""","""pec""":0,"""pev""":0,"""src""":32,"""srv""":1}}
+release	chromosome	chromosome_no	bin	chromosome2	chromosome_no2	bin2	pe_orientation	start	end	start_ci_left	start_ci_right	end_ci_left	end_ci_right	case_id	set_id	sv_uuid	callers	sv_type	sv_sub_type	info	num_hom_alt	num_hom_ref	num_het	num_hemi_alt	num_hemi_ref	genotype
+GRCh37	22	22	89	22	22	89	3to5	17400000	17700000	-29	29	-29	29	.	.	UUID	{"EMBL.DELLYv1.1.3"}	DEL	DEL	{"""affectedCarriers""":0,"""backgroundCarriers""":0,"""unaffectedCarriers""":0}	0	2	1	0	0	{"""Case_1_father-N1-DNA1-WGS1""":{"""cn""":2,"""ft""":["""LowQual"""],"""gq""":14,"""gt""":"""0/1""","""pec""":0,"""pev""":0,"""src""":34,"""srv""":4},"""Case_1_index-N1-DNA1-WGS1""":{"""cn""":2,"""gq""":35,"""gt""":"""0/0""","""pec""":0,"""pev""":0,"""src""":29,"""srv""":2},"""Case_1_mother-N1-DNA1-WGS1""":{"""cn""":2,"""gq""":67,"""gt""":"""0/0""","""pec""":0,"""pev""":0,"""src""":32,"""srv""":1}}

varfish-annotator-cli/src/main/java/com/github/bihealth/varfish_annotator/annotate_svs/AnnotateSvsVcf.java

@@ -500,7 +500,8 @@ private void writeRecords(List<GenotypeRecord> chromRecords, Writer writer) thro
       writer.write(
           record.toTsv(
               !args.getOptOutFeatures().contains(GtRecordBuilder.FEATURE_CHROM2_COLUMNS),
-              !args.getOptOutFeatures().contains(GtRecordBuilder.FEATURE_DBCOUNTS_COLUMNS)));
+              !args.getOptOutFeatures().contains(GtRecordBuilder.FEATURE_DBCOUNTS_COLUMNS),
+              !args.getOptOutFeatures().contains(GtRecordBuilder.FEATURE_CALLERS_ARRAY)));
       writer.write('\n');
     }
   }
@@ -587,7 +588,8 @@ private void checkOptOutFeatures() {
         ImmutableList.of(
             GtRecordBuilder.FEATURE_CHROM2_COLUMNS,
             GtRecordBuilder.FEATURE_DBCOUNTS_COLUMNS,
-            GtRecordBuilder.FEATURE_SUPPRESS_CARRIER_COUNTS);
+            GtRecordBuilder.FEATURE_SUPPRESS_CARRIER_COUNTS,
+            GtRecordBuilder.FEATURE_CALLERS_ARRAY);
     final String features[] = args.getOptOutFeatures().split(",");
     boolean allGood = true;
     for (String feature : features) {
@@ -651,7 +653,8 @@ private void annotateSvVcf(
         gtWriter.append(
             GenotypeRecord.tsvHeader(
                     !args.getOptOutFeatures().contains(GtRecordBuilder.FEATURE_CHROM2_COLUMNS),
-                    !args.getOptOutFeatures().contains(GtRecordBuilder.FEATURE_DBCOUNTS_COLUMNS))
+                    !args.getOptOutFeatures().contains(GtRecordBuilder.FEATURE_DBCOUNTS_COLUMNS),
+                    !args.getOptOutFeatures().contains(GtRecordBuilder.FEATURE_CALLERS_ARRAY))
                 + "\n");
         // Write feature-effects header.
         featureEffectsWriter.append(Joiner.on("\t").join(HEADERS_FEATURE_EFFECTS) + "\n");
@@ -893,7 +896,8 @@ private void annotateVariantContext(
         gtWriter.append(
             gtOutRec.toTsv(
                     !args.getOptOutFeatures().contains(GtRecordBuilder.FEATURE_CHROM2_COLUMNS),
-                    !args.getOptOutFeatures().contains(GtRecordBuilder.FEATURE_DBCOUNTS_COLUMNS))
+                    !args.getOptOutFeatures().contains(GtRecordBuilder.FEATURE_DBCOUNTS_COLUMNS),
+                    !args.getOptOutFeatures().contains(GtRecordBuilder.FEATURE_CALLERS_ARRAY))
                 + "\n");
       } catch (IOException e) {
         throw new VarfishAnnotatorException("Problem writing to genotypes call file.", e);

varfish-annotator-cli/src/test/java/com/github/bihealth/varfish_annotator/annotate_svs/AnnotateDellyVcf37Chr22Test.java

@@ -141,8 +141,8 @@ void testWithTrio(boolean gzipOutput) throws IOException {
             + "GRCh37\tvarfish-annotator\tnull\n"
             + "GRCh37\tvarfish-annotator-db\tfor-testing\n";
     final String expectedGts =
-        "release\tchromosome\tchromosome_no\tbin\tchromosome2\tchromosome_no2\tbin2\tpe_orientation\tstart\tend\tstart_ci_left\tstart_ci_right\tend_ci_left\tend_ci_right\tcase_id\tset_id\tsv_uuid\tcaller\tsv_type\tsv_sub_type\tinfo\tnum_hom_alt\tnum_hom_ref\tnum_het\tnum_hemi_alt\tnum_hemi_ref\tgenotype\n"
-            + "GRCh37\t22\t22\t89\t22\t22\t89\t3to5\t17400000\t17700000\t-29\t29\t-29\t29\t.\t.\t00000000-0000-0000-0000-000000000000\tEMBL.DELLYv1.1.3\tDEL\tDEL\t{\"\"\"affectedCarriers\"\"\":0,\"\"\"backgroundCarriers\"\"\":0,\"\"\"unaffectedCarriers\"\"\":0}\t0\t2\t1\t0\t0\t{\"\"\"Case_1_father-N1-DNA1-WGS1\"\"\":{\"\"\"cn\"\"\":2,\"\"\"ft\"\"\":[\"\"\"LowQual\"\"\"],\"\"\"gq\"\"\":14,\"\"\"gt\"\"\":\"\"\"0/1\"\"\",\"\"\"pec\"\"\":0,\"\"\"pev\"\"\":0,\"\"\"src\"\"\":34,\"\"\"srv\"\"\":4},\"\"\"Case_1_index-N1-DNA1-WGS1\"\"\":{\"\"\"cn\"\"\":2,\"\"\"gq\"\"\":35,\"\"\"gt\"\"\":\"\"\"0/0\"\"\",\"\"\"pec\"\"\":0,\"\"\"pev\"\"\":0,\"\"\"src\"\"\":29,\"\"\"srv\"\"\":2},\"\"\"Case_1_mother-N1-DNA1-WGS1\"\"\":{\"\"\"cn\"\"\":2,\"\"\"gq\"\"\":67,\"\"\"gt\"\"\":\"\"\"0/0\"\"\",\"\"\"pec\"\"\":0,\"\"\"pev\"\"\":0,\"\"\"src\"\"\":32,\"\"\"srv\"\"\":1}}\n";
+        "release\tchromosome\tchromosome_no\tbin\tchromosome2\tchromosome_no2\tbin2\tpe_orientation\tstart\tend\tstart_ci_left\tstart_ci_right\tend_ci_left\tend_ci_right\tcase_id\tset_id\tsv_uuid\tcallers\tsv_type\tsv_sub_type\tinfo\tnum_hom_alt\tnum_hom_ref\tnum_het\tnum_hemi_alt\tnum_hemi_ref\tgenotype\n"
+            + "GRCh37\t22\t22\t89\t22\t22\t89\t3to5\t17400000\t17700000\t-29\t29\t-29\t29\t.\t.\t00000000-0000-0000-0000-000000000000\t{\"EMBL.DELLYv1.1.3\"}\tDEL\tDEL\t{\"\"\"affectedCarriers\"\"\":0,\"\"\"backgroundCarriers\"\"\":0,\"\"\"unaffectedCarriers\"\"\":0}\t0\t2\t1\t0\t0\t{\"\"\"Case_1_father-N1-DNA1-WGS1\"\"\":{\"\"\"cn\"\"\":2,\"\"\"ft\"\"\":[\"\"\"LowQual\"\"\"],\"\"\"gq\"\"\":14,\"\"\"gt\"\"\":\"\"\"0/1\"\"\",\"\"\"pec\"\"\":0,\"\"\"pev\"\"\":0,\"\"\"src\"\"\":34,\"\"\"srv\"\"\":4},\"\"\"Case_1_index-N1-DNA1-WGS1\"\"\":{\"\"\"cn\"\"\":2,\"\"\"gq\"\"\":35,\"\"\"gt\"\"\":\"\"\"0/0\"\"\",\"\"\"pec\"\"\":0,\"\"\"pev\"\"\":0,\"\"\"src\"\"\":29,\"\"\"srv\"\"\":2},\"\"\"Case_1_mother-N1-DNA1-WGS1\"\"\":{\"\"\"cn\"\"\":2,\"\"\"gq\"\"\":67,\"\"\"gt\"\"\":\"\"\"0/0\"\"\",\"\"\"pec\"\"\":0,\"\"\"pev\"\"\":0,\"\"\"src\"\"\":32,\"\"\"srv\"\"\":1}}\n";
     final String expectedFeatureEffects =
         "case_id\tset_id\tsv_uuid\trefseq_gene_id\trefseq_transcript_id\trefseq_transcript_coding\trefseq_effect\tensembl_gene_id\tensembl_transcript_id\tensembl_transcript_coding\tensembl_effect\n"
             + ".\t.\t00000000-0000-0000-0000-000000000000\t51816\tNM_017424.2\tTRUE\t{\"transcript_ablation\",\"coding_transcript_variant\"}\tENSG00000093072\tENST00000262607.3\tTRUE\t{\"transcript_ablation\",\"coding_transcript_variant\"}\n"