gbanyan
a228a56984
gene_universe contains 1,539 gene_symbols mapping to multiple Ensembl IDs (3,033 excess). Non-canonical IDs lack data in some evidence tables, causing weighted_sum/available_weight to inflate their composite scores. Fix: after scoring SQL, keep one row per gene_symbol with the most evidence_count (tiebreak by composite_score DESC). 22,604 → 19,555 genes. Results: HIGH 82→4, all top 20 now have 5-6 layers with expression data. Validation PASSED (CDH23 98.3rd percentile, median known gene 83.3%). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
57 lines
1.2 KiB
JSON
57 lines
1.2 KiB
JSON
{
|
|
"run_id": "f5587e39-163b-418c-8ac2-593b47323f34",
|
|
"timestamp": "2026-02-16T01:59:18.969516+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": 18243,
|
|
"high": 4,
|
|
"medium": 8051,
|
|
"low": 10188
|
|
}
|
|
} |