dataset · needs review
variant-effects benchmark
Evaluation results
Release 2026-09-16-d74d282221a9 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| structure-informed pLM: protein variant-effect classification Model: structure-informed pLM · Benchmark: protein variant-effect classification · Dataset: variant-effects benchmark combined amino-acid, secondary structure, solvent accessibility and contact-map scoring Author-reported evaluation · Evaluation metadata: needs review | ||
| .803 AUROC Unit: fraction · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedStructure-Informed Protein Language Models are Robust Predictors for Variant Effects · PMC12068927 HTML, Table4, AA+SS+RSA+CM row, AUROC column Source checking is not independent reproduction. |
Sources and history
Release 2026-09-16-d74d282221a9 · Record review: needs review
- Structure-Informed Protein Language Models are Robust Predictors for Variant Effects · Original source · Human Genetics 2025 journal article (online 2024)
Technical metadata and extraction receipts
Stable ID: reported-dataset-2eaa2a051d45ee
- areas
- proteins-complexes
- version
- Not reported
- split
- paper evaluation
- missing metadata
- version: not_reported_in_legacy_extract; accession: not_reported_in_legacy_extract