Clinical missense variant pathogenicity classification
Separate pathogenic from benign human missense variants using clinical labels such as ClinVar, scored by AUROC or a similar ranking metric.
Results are recorded on the linked protocols, tasks or configurations listed below. Their settings and evaluations are kept separate.
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Results on linked records
This task has no results of its own in this release. 2 linked records have results. They are not assigned to the underlying task: each record keeps its own settings and evaluations, and its scores are on its own page.
- Livesey and Marsh 2025 clinical benchmark: pairwise AUROC win rate, ClinVar pathogenic versus gnomAD missense Protocol · evaluates this task · 85 evaluations · 85 results
- ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Protocol · evaluates this task · 13 evaluations · 13 results
Methods and evaluation design
Procedure, tasks and evaluated configurations
Additional methodological details, tasks and evaluated configurations have not yet been extracted into a structured profile for this task. Consult the linked sources and evaluation records below.
Run instructions
No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
0 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: needs review
3 source records and release history
- Genome-wide prediction of disease variant effects with a deep protein language model (Brandes et al., Nature Genetics 2023) · Original source · Version of record, Nature Genetics 55, 1512-1522 (published 2023-08-10)
- Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Original source · PMC12016141 (published 2025-04-22; Genome Biol 26:104)
- ProteinGym clinical zero-shot substitutions AUC summary at commit 144fe22 · Original source · 144fe22b07dfaeec2b366f2346203a9838a55b4c
Technical metadata and extraction receipts
Stable ID: discrepancy-v4-20261023-task-clinical-missense-pathogenicity
- areas
- dna-genomes; proteins-complexes
- contexts
- clinical_research
- task
- Clinical missense variant pathogenicity classification
- scope note
- Evaluated by Brandes et al. 2023 (ClinVar and HGMD/gnomAD missense benchmarks), the ProteinGym clinical substitutions track and the Livesey and Marsh 2025 clinical benchmark. The label sets, variant filters and metrics differ between them; they share the prediction question, not a protocol.
Related records
- evaluates task: Brandes et al. 2023 clinical missense pathogenicity benchmarks (ClinVar and HGMD/gnomAD)
- evaluates task: Livesey and Marsh 2025 clinical benchmark: pairwise AUROC win rate, ClinVar pathogenic versus gnomAD missense
- evaluates task: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22)