Open Peter-J-Freeman opened 2 years ago
seems OK when mane is selected
>>> import json
>>> import VariantValidator
>>> vval = VariantValidator.Validator()
>>> variant = 'NC_000002.12:g.73385903T>C'
>>> genome_build = 'GRCh38'
>>> select_transcripts = 'mane'
>>> validate = vval.validate(variant, genome_build, select_transcripts)
>>> validation = validate.format_as_dict(with_meta=True)
>>> print(json.dumps(validation, sort_keys=True, indent=4, separators=(',', ': ')))
{
"NM_001378454.1:c.35T>C": { # Looks good
"alt_genomic_loci": [],
"annotations": {
"chromosome": "2",
"db_xref": {
"CCDS": null,
"ensemblgene": null,
"hgnc": "HGNC:428",
"ncbigene": "7840",
"select": "MANE"
},
"ensembl_select": false,
"mane_plus_clinical": false,
"mane_select": true,
"map": "2p13.1",
"note": "ALMS1 centrosome and basal body associated protein",
"refseq_select": true,
"variant": "2"
},
"gene_ids": {
"ccds_ids": [
"CCDS42697"
],
"ensembl_gene_id": "ENSG00000116127",
"entrez_gene_id": "7840",
"hgnc_id": "HGNC:428",
"omim_id": [
"606844"
],
"ucsc_id": "uc032nrd.1"
},
"gene_symbol": "ALMS1",
"genome_context_intronic_sequence": "",
"hgvs_lrg_transcript_variant": "",
"hgvs_lrg_variant": "",
"hgvs_predicted_protein_consequence": {
"lrg_slr": "",
"lrg_tlr": "",
"slr": "NP_001365383.1:p.(L12P)",
"tlr": "NP_001365383.1:p.(Leu12Pro)"
},
"hgvs_refseqgene_variant": "",
"hgvs_transcript_variant": "NM_001378454.1:c.35T>C",
"primary_assembly_loci": {
"grch37": {
"hgvs_genomic_description": "NC_000002.11:g.73613031T>C",
"vcf": {
"alt": "C",
"chr": "2",
"pos": "73613031",
"ref": "T"
}
},
"grch38": {
"hgvs_genomic_description": "NC_000002.12:g.73385903T>C",
"vcf": {
"alt": "C",
"chr": "2",
"pos": "73385903",
"ref": "T"
}
},
"hg19": {
"hgvs_genomic_description": "NC_000002.11:g.73613031T>C",
"vcf": {
"alt": "C",
"chr": "chr2",
"pos": "73613031",
"ref": "T"
}
},
"hg38": {
"hgvs_genomic_description": "NC_000002.12:g.73385903T>C",
"vcf": {
"alt": "C",
"chr": "chr2",
"pos": "73385903",
"ref": "T"
}
}
},
"reference_sequence_records": {
"protein": "https://www.ncbi.nlm.nih.gov/nuccore/NP_001365383.1",
"transcript": "https://www.ncbi.nlm.nih.gov/nuccore/NM_001378454.1"
},
"refseqgene_context_intronic_sequence": "",
"selected_assembly": "GRCh38",
"submitted_variant": "NC_000002.12:g.73385903T>C",
"transcript_description": "Homo sapiens ALMS1 centrosome and basal body associated protein (ALMS1), transcript variant 2, mRNA",
"validation_warnings": [
"RefSeqGene record not available"
],
"variant_exonic_positions": {
"NC_000002.11": {
"end_exon": "1",
"start_exon": "1"
},
"NC_000002.12": {
"end_exon": "1",
"start_exon": "1"
}
}
},
"flag": "gene_variant",
"metadata": {
"variantvalidator_hgvs_version": "2.0.1.dev2+g58fc52a",
"variantvalidator_version": "1.0.5.dev272+gd30cbb9",
"vvdb_version": "vvdb_2022_04",
"vvseqrepo_db": "VV_SR_2022_02/master",
"vvta_version": "vvta_2022_02"
}
}
Correction, MANE is ok, the other transcript gives the delins!
Describe the bug When looking at variant 1 of the VariantValidator truth set, I tried updating to a MANE variant.
I got a strange delins in the MANE transcripts which is a simple substitution in the former RefSeq Select Transcript
To Reproduce
Expected behavior To be confirmed