fix: handle AN=0

src/anyvlm/functions/ingest_vcf.py

@@ -62,6 +62,14 @@ def _yield_expression_af_batches(
                 msg = f"One or more required INFO column is missing: {'AC' in info}, {'AN' in info}, {'AC_Het' in info}, {'AC_Hom' in info}, {'AC_Hemi' in info}"
                 _logger.exception(msg)
                 raise VcfAfColumnsError(msg) from e
+            if af.an == 0:
+                _logger.debug(
+                    "Encountered AN=0 in VCF at %s-%s-%s-%s; this will be skipped during ingest.",
+                    record.chrom,
+                    record.pos,
+                    record.ref,
+                    alt,
+                )
             batch.append((expression, af))
             if len(batch) >= batch_size:
                 _logger.debug("Yielding next batch")
@@ -106,11 +114,15 @@ def ingest_vcf(
         for variant_id, af in zip(variant_ids, afs, strict=True):
             if variant_id is None:
                 continue
+            try:
+                allele_frequency = af.ac / af.an
+            except ZeroDivisionError:
+                continue
             caf = AnyVlmCohortAlleleFrequencyResult(
                 focusAllele=iriReference(variant_id),
                 focusAlleleCount=af.ac,
                 locusAlleleCount=af.an,
-                focusAlleleFrequency=af.ac / af.an,
+                focusAlleleFrequency=allele_frequency,
                 qualityMeasures=QualityMeasures(qcFilters=af.filters),
                 ancillaryResults=AncillaryResults(
                     heterozygotes=af.ac_het,

tests/data/vcf/vcf_an_0.vcf

@@ -0,0 +1,15 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=LowQual,Description="Low quality">
+##FILTER=<ID=NO_HQ_GENOTYPES,Description="Site has no high quality variant genotypes">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AC_Hemi,Number=A,Type=Integer,Description="Allele counts in hemizygous genotypes">
+##INFO=<ID=AC_Het,Number=A,Type=Integer,Description="Allele counts in heterozygous genotypes">
+##INFO=<ID=AC_Hom,Number=A,Type=Integer,Description="Allele counts in homozygous genotypes">
+##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">
+##contig=<ID=chr14,length=107043718>
+##source=SelectVariants
+##INFO=<ID=VRS_Allele_IDs,Number=R,Type=String,Description="The computed identifiers for the GA4GH VRS Alleles corresponding to the GT indexes of the REF and ALT alleles">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO
+chr14	18223529	.	C	A	.	LowQual;NO_HQ_GENOTYPES	AC=0;AC_Hemi=0;AC_Het=0;AC_Hom=0;AF=0.00;AN=0;AS_QUALapprox=0|55;VRS_Allele_IDs=ga4gh:VA.8OSPHYmhyg9hJTpFQ8aNcmLgYMR77ZyJ,ga4gh:VA.slgr2fnRKaUnQrJZvYNDGMrfZHw6QCr6

tests/unit/functions/test_ingest_vcf.py

@@ -115,3 +115,14 @@ def test_ingest_vcf_infocol_missing(
             stub_anyvar_client,
             postgres_storage,
         )
+
+
+def test_ingest_vcf_an_zero(
+    stub_anyvar_client: BaseAnyVarClient, test_data_dir: Path, postgres_storage: Storage
+):
+    """Test smooth handling of VCF row where AN=0"""
+    ingest_vcf(
+        test_data_dir / "vcf" / "vcf_an_0.vcf",
+        stub_anyvar_client,
+        postgres_storage,
+    )