Codex · low
CleanResults by dataset
Raw metric, 95% CI where reported, and the normalized score against the dataset's SOTA (or reference).
| Dataset | Metric | Value | 95% CI | Normalized | Chance | Ref. | SOTA | n · coverage |
|---|---|---|---|---|---|---|---|---|
| traitgym complex Variant effect (DNA) | AUPRC | 0.348 | — | 0.95 | 0.100 | 0.284 | 0.362 | 11,400 · 100% |
| traitgym mendelian Variant effect (DNA) | AUPRC | 0.729 | — | 0.81 | 0.101 | 0.648 | 0.875 | 3,353 · 100% |
| clinvar Variant effect (DNA) | AUPRC | 0.992 | — | 1.00 | 0.494 | — | 0.990 | 29,953 · 100% |
| clinvar missensesupp. Variant effect (DNA) | AUROC | 0.955 | — | 0.97 | 0.500 | 0.966 | 0.972 | 7,861 · 100% |
| clinvar intronicsupp. Variant effect (DNA) | AUROC | 0.975 | — | 0.98 | 0.500 | — | 0.984 | 4,368 · 100% |
| clinvar synonymoussupp. Variant effect (DNA) | AUROC | 0.993 | — | 1.07 | 0.500 | — | 0.961 | 8,155 · 100% |
| clinvar stop gainedsupp. Variant effect (DNA) | AUROC | 0.823 | — | 0.81 | 0.500 | — | 0.900 | 5,762 · 100% |
All reported metrics
| Slice | AUPRC | AUROC | Brier |
|---|---|---|---|
| traitgym complex | 0.348 | 0.724 | 0.078 |
| traitgym mendelian | 0.729 | 0.886 | 0.048 |
| clinvar | 0.992 | 0.992 | 0.038 |
| clinvar missense | 0.982 | 0.955 | 0.076 |
| clinvar intronic | 0.880 | 0.975 | 0.041 |
| clinvar synonymous | 0.905 | 0.993 | 0.031 |
| clinvar stop gained | 1.000 | 0.823 | 0.003 |
Breakdown: clinvar by consequence
| Slice | n | AUPRC | AUROC | Brier |
|---|---|---|---|---|
| 3 prime utr | 445 | 0.038 | 0.944 | 0.023 |
| 5 prime utr | 170 | 0.556 | 0.834 | 0.106 |
| initiator codon | 163 | 0.997 | 0.868 | 0.066 |
| intronic | 4,368 | 0.880 | 0.975 | 0.041 |
| missense | 7,861 | 0.982 | 0.955 | 0.076 |
| other | 133 | 0.587 | 0.851 | 0.105 |
| splice acceptor | 1,231 | 1.000 | 0.939 | 0.010 |
| splice donor | 1,649 | 1.000 | 0.918 | 0.009 |
| stop gained | 5,762 | 1.000 | 0.823 | 0.003 |
| synonymous | 8,155 | 0.905 | 0.993 | 0.031 |
Breakdown: clinvar by review status
| Slice | n | AUPRC | AUROC | Brier |
|---|---|---|---|---|
| 2 star | 28,058 | 0.992 | 0.992 | 0.038 |
| 3 star expert panel | 1,764 | 0.997 | 0.986 | 0.037 |
| unknown | 124 | 0.993 | 0.995 | 0.029 |
Breakdown: clinvar by significance pair
| Slice | n | AUPRC | AUROC | Brier |
|---|---|---|---|---|
| strong only P vs B | 20,145 | 0.995 | 0.991 | 0.036 |
| hedged only LP vs LB | 9,790 | 0.982 | 0.991 | 0.042 |
| any P vs any B | 29,935 | 0.992 | 0.992 | 0.038 |
Integrity
Post-run checks (docs/INTEGRITY.md). Runs publish once checks pass.
- passleakage auditno test-label leakage (AUDIT_traitgym_mendelian.md, 2026-07-23)
- passtraining manifesttraining_manifest.json present
- passtraceagent_log.jsonl available for the trace judge
- pendingoverlapAutomated overlap audit not yet run
Run details
- Kind
- agent
- Suite
- vep_multieval v1
- Started
- Jul 22, 2026 06:54 UTC
- Finished
- —
- Sessions
- 11
- Tool calls
- 54
- Turns
- —
- Artifacts
- method.md, agent_log.jsonl, training_manifest.json
Method
method.md, written by the agent.
Method
I first checked normalization and uniqueness: the file contains 44,706 unique hg38 SNVs (22 autosomes plus X; no indels or duplicate tuples). No labeled training set was compiled, and no test labels were used.
Iterations were: (1) MyVariant batch lookup, rejected because CADD/dbNSFP coverage was poor; (2) sparse remote-tabix CADD v1.7 retrieval, confirmed exact allele scoring but rejected for full use because request latency was high; (3) exact joins to TraitGym's public matched and all-candidate files, extracting only coordinates, published predictions, CADD, and GPN-MSA columns; (4) sparse extraction of EVEE ClinVar predictions, rejected for the final model because its supervised ClinVar probe could overlap test variants; and (5) final Ensembl VEP batch annotation with CADD v1.7, AlphaMissense, SpliceAI, SIFT, PolyPhen, and consequence. The VEP parser intentionally discarded colocated ClinVar significance and all other label fields.
For tuples in TraitGym matched sets, I used its released chromosome-held-out CADD + GPN-MSA + Borzoi logistic-ensemble prediction. The 27 tuples shared by complex and Mendelian sets were averaged. Because TraitGym fit logistic regression with balanced class weights while matched_9 contains one positive per nine controls, I applied a prior-odds correction from 1:1 to 1:9; this preserves rankings.
All remaining rows received a consequence-aware clinical score. CADD PHRED was transformed by a fixed sigmoid centered at 15. Missense scores blend calibrated AlphaMissense (70%), CADD (20%), and available SIFT/PolyPhen (5% each). Core splice variants blend SpliceAI (65%) and CADD (35%); synonymous/intronic/splice-region variants take the stronger splice-aware signal. UTR variants use 80% CADD and 20% SpliceAI; other consequences use transformed CADD. Missing optional annotations are reweighted rather than imputed from labels. Scores are clipped to [0,1].
Validation selection used the published TraitGym chromosome-weighted AUPRCs supplied with the task (0.362 complex; 0.648 Mendelian); no local label-based validation was performed.
Training manifest
Declared data sources and filtering.
- TraitGym codeInspected scoring workflow and confirmed class_weight=balanced.
- TraitGym Hugging Face dataset
- Ensembl VEP REST
- CADD v1.7 GRCh38 prescored SNVsRemote-tabix feasibility pilot; final CADD values came through Ensembl VEP.
- MyVariant.infoCoverage pilot only; rejected and unused in final scoring.
- EVEE ClinVar prediction resource
- EVEE variant viewer codeRepository access attempted during schema discovery; no final dependency.
- AlphaMissense release documentationDocumentation consulted; scores were returned by Ensembl VEP.
Raw training_manifest.json
{
"schema_version": "1.0",
"test_set": {
"path": "/task/test.parquet",
"build": "GRCh38/hg38",
"rows": 44706,
"unique_exact_tuples": 44706,
"exact_duplicate_rows": 0
},
"labeled_training": {
"compiled": false,
"rows_before_test_exclusion": 0,
"exact_test_overlaps_excluded": 0,
"rows_after_test_exclusion": 0,
"note": "No labels were parsed or used for fitting/calibration. Released out-of-chromosome predictions and label-independent annotations were used as features/scores."
},
"sources": [
{
"name": "TraitGym code",
"url": "https://github.com/songlab-cal/TraitGym",
"use": "Inspected scoring workflow and confirmed class_weight=balanced."
},
{
"name": "TraitGym Hugging Face dataset",
"url": "https://huggingface.co/datasets/songlab/TraitGym",
"files_touched": [
"complex_traits_matched_9/test.parquet",
"complex_traits_matched_9/preds/all/CADD+GPN-MSA+Borzoi.LogisticRegression.chrom.parquet",
"complex_traits_matched_9/features/{CADD,GPN-MSA_absLLR,Borzoi_L2_L2}.parquet",
"mendelian_traits_matched_9/test.parquet",
"mendelian_traits_matched_9/preds/all/CADD+GPN-MSA+Borzoi.LogisticRegression.chrom.parquet",
"mendelian_traits_matched_9/features/{CADD,GPN-MSA_absLLR,Borzoi_L2_L2}.parquet",
"complex_traits_v22_matched_9/test.parquet",
"complex_traits_all/{test.parquet,features/CADDv1.7.RawScore.parquet,features/GPN-MSA_absLLR.parquet}",
"mendelian_traits_all/{test.parquet,features/CADDv1.7.RawScore.parquet,features/GPN-MSA_absLLR.parquet}"
],
"dedup": {
"matched_rows_before_cross_dataset_dedup": 14780,
"shared_exact_tuples": 27,
"unique_exact_test_tuples_used": 14753
},
"labels_used": false
},
{
"name": "Ensembl VEP REST",
"url": "https://rest.ensembl.org/vep/homo_sapiens/region",
"annotations": [
"CADD",
"AlphaMissense",
"SpliceAI",
"SIFT",
"PolyPhen",
"consequence"
],
"input_rows": 44706,
"unique_input_tuples": 44706,
"output_rows": 44706,
"cadd_coverage": 44706,
"alphamissense_coverage": 7308,
"spliceai_coverage": 34508,
"clinical_significance_fields_parsed": false
},
{
"name": "CADD v1.7 GRCh38 prescored SNVs",
"urls": [
"https://kircherlab.bihealth.org/download/CADD/v1.7/GRCh38/whole_genome_SNVs.tsv.gz",
"https://kircherlab.bihealth.org/download/CADD/v1.7/GRCh38/whole_genome_SNVs.tsv.gz.tbi",
"https://krishna.gs.washington.edu/download/CADD/v1.7/GRCh38/whole_genome_SNVs.tsv.gz",
"https://krishna.gs.washington.edu/download/CADD/v1.7/GRCh38/whole_genome_SNVs.tsv.gz.tbi"
],
"use": "Remote-tabix feasibility pilot; final CADD values came through Ensembl VEP."
},
{
"name": "MyVariant.info",
"urls": [
"https://myvariant.info/v1/variant",
"https://myvariant.info/v1/query"
],
"use": "Coverage pilot only; rejected and unused in final scoring."
},
{
"name": "EVEE ClinVar prediction resource",
"urls": [
"https://zenodo.org/records/19701997/files/manifest.json",
"https://zenodo.org/records/19701997/files/clean_shard_0.parquet",
"https://zenodo.org/records/19701997/files/clean_shard_1.parquet",
"https://zenodo.org/records/19701997/files/clean_shard_2.parquet",
"https://zenodo.org/records/19701997/files/clean_shard_3.parquet"
],
"rows_annotation_columns_touched": 3372596,
"exact_test_matches": 1604,
"labels_read": false,
"used_in_final": false,
"reason_rejected": "Conservative avoidance of possible overlap with the supervised ClinVar probe."
},
{
"name": "EVEE variant viewer code",
"url": "https://github.com/goodfire-ai/variant-viewer",
"use": "Repository access attempted during schema discovery; no final dependency."
},
{
"name": "AlphaMissense release documentation",
"urls": [
"https://storage.googleapis.com/dm_alphamissense/README.pdf",
"https://zenodo.org/records/8360242"
],
"use": "Documentation consulted; scores were returned by Ensembl VEP."
}
],
"iterations": [
{
"iteration": 1,
"method": "Input normalization/uniqueness audit",
"status": "completed",
"coverage": 1,
"validation_score": null
},
{
"iteration": 2,
"method": "MyVariant CADD/dbNSFP lookup",
"status": "rejected_low_coverage",
"coverage": null,
"validation_score": null
},
{
"iteration": 3,
"method": "Sparse remote-tabix CADD v1.7",
"status": "rejected_high_latency",
"coverage": null,
"validation_score": null
},
{
"iteration": 4,
"method": "TraitGym released chromosome-held-out ensemble exact join",
"status": "used",
"rows": 14753,
"validation_score": null,
"published_reference_auprc": {
"complex_traits": 0.362,
"mendelian_traits": 0.648
}
},
{
"iteration": 5,
"method": "TraitGym all-candidate CADD/GPN sparse extraction",
"status": "intermediate_fallback_only",
"unique_test_matches": 16981,
"validation_score": null
},
{
"iteration": 6,
"method": "EVEE sparse prediction lookup",
"status": "rejected_leakage_conservatism",
"exact_test_matches": 1604,
"validation_score": null
},
{
"iteration": 7,
"method": "Final TraitGym ensemble plus VEP consequence-aware clinical ensemble",
"status": "final",
"coverage": 1,
"validation_score": null
}
]
}