gbanyan
e2a3dc2bc8
gnomAD v4.1 gene_id column is mixed: ~101K Ensembl IDs + ~111K NCBI numeric. Now falls back to gene_symbol → gene_universe lookup for non-ENSG entries. Coverage: 78.5% → 90.3% (17,875 → 20,555 genes with gnomAD scores). Sufficient evidence (≥4 layers): 19,946 → 20,683 genes. Validation median percentile: 79.9% → 81.1%. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
57 lines
1.2 KiB
JSON
57 lines
1.2 KiB
JSON
{
|
|
"run_id": "093b405b-5a20-4f35-b5b8-04f02451789d",
|
|
"timestamp": "2026-02-15T21:49:14.940206+00:00",
|
|
"pipeline_version": "0.1.0",
|
|
"parameters": {
|
|
"gnomad": 0.2,
|
|
"expression": 0.2,
|
|
"annotation": 0.15,
|
|
"localization": 0.15,
|
|
"animal_model": 0.15,
|
|
"literature": 0.15
|
|
},
|
|
"data_versions": {
|
|
"ensembl_release": 113,
|
|
"gnomad_version": "v4.1",
|
|
"gtex_version": "v8",
|
|
"hpa_version": "23.0"
|
|
},
|
|
"software_environment": {
|
|
"python": "3.14.3",
|
|
"polars": "1.38.1",
|
|
"duckdb": "1.4.4"
|
|
},
|
|
"filtering_steps": [
|
|
{
|
|
"step_name": "load_scored_genes",
|
|
"input_count": 0,
|
|
"output_count": 0,
|
|
"criteria": ""
|
|
},
|
|
{
|
|
"step_name": "apply_tier_classification",
|
|
"input_count": 0,
|
|
"output_count": 0,
|
|
"criteria": ""
|
|
},
|
|
{
|
|
"step_name": "write_candidate_output",
|
|
"input_count": 0,
|
|
"output_count": 0,
|
|
"criteria": ""
|
|
},
|
|
{
|
|
"step_name": "generate_visualizations",
|
|
"input_count": 0,
|
|
"output_count": 0,
|
|
"criteria": ""
|
|
}
|
|
],
|
|
"validation_metrics": {},
|
|
"tier_statistics": {
|
|
"total": 21177,
|
|
"high": 82,
|
|
"medium": 9626,
|
|
"low": 11469
|
|
}
|
|
} |