- scoring/integration.py: Use CTEs with GROUP BY gene_id to deduplicate all evidence tables before LEFT JOIN (gnomAD had 211K rows for 18K genes due to per-transcript data; annotation/localization also had dupes) - literature/transform.py: Deduplicate gene_symbols before PubMed queries to avoid querying the same symbol multiple times - evidence_cmd.py: Fix Polars .alias() error in literature summary display - Updated report results with full 6-layer scoring (44 HIGH, 7268 MEDIUM) - Validation PASSED: known Usher genes median percentile 86.9% Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
57 lines
1.2 KiB
JSON
57 lines
1.2 KiB
JSON
{
|
|
"run_id": "0bcdae80-84c2-486b-809a-36040ce4821d",
|
|
"timestamp": "2026-02-15T20:47:54.482074+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": 19342,
|
|
"high": 44,
|
|
"medium": 7268,
|
|
"low": 12030
|
|
}
|
|
} |