MetaRNN [ProteinGym 144fe22 clinical summary]
Configuration of MetaRNN, from the ProteinGym clinical reference scores at commit 144fe22b (dbNSFP 4.4a scores).
Overview
MetaRNN: Recurrent neural network over other predictors' scores, conservation scores and population allele frequencies, with flanking-codon annotations read by bidirectional gated recurrent units, trained to separate rare pathogenic from rare benign nonsynonymous variants; a companion model covers non-frameshift indels.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Evaluations and results
1 evaluation · 1 result. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: MetaRNN [ProteinGym 144fe22 clinical summary] | Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22 | 0.977 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.001 (type not stated). Labelled a bootstrap standard error. The script that wrote the clinical summary was not read; in the DMS script the same column is the standard error of the difference from the top model, and the top row here prints 0.0, which suggests the same construction. Not verified for this file. Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceMetaRNN: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical supervised substitutions AUC summary at commit 144fe22 · benchmarks/clinical_supervised/substitutions/AUC/Summary_performance_clinical_substitutions_AUC.csv line 3, row 'MetaRNN', column 'Average_AUC' |
Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.
Use this configuration
How it works, versions and access
Strengths, limitations and unresolved questions
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 2026-10-22-1b7cf027e4f6 · Record review: source checked
4 source records and release history
- ProteinGym clinical zero-shot substitutions AUC summary at commit 144fe22 · Original source · 144fe22b07dfaeec2b366f2346203a9838a55b4c
- ProteinGym clinical supervised substitutions AUC summary at commit 144fe22 · Original source · 144fe22b07dfaeec2b366f2346203a9838a55b4c
- ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · Original source · 144fe22b07dfaeec2b366f2346203a9838a55b4c
- OATML-Markslab/ProteinGym / README.md · Original source · Git commit 144fe22b07dfaeec2b366f2346203a9838a55b4c
Technical metadata and extraction receipts
Stable ID: vep-lit-20261014-config-proteingym-clinical-metarnn
- areas
- proteins-complexes; dna-genomes
- contexts
- clinical_research
- method types
- supervised_machine_learning
- reported name
- MetaRNN
- foundation model eligible
- false
- configuration type
- reported_configuration
- version
- dbNSFP 4.4a scores (README line 106: clinical baselines from dbNSFP 4.4a); ProteinGym commit 144fe22b07dfaeec2b366f2346203a9838a55b4c
- access reuse
- Scores distributed by ProteinGym (README 'Clinical Model scores' downloads); original tool terms apply
- source locator
- ProteinGym clinical summary CSVs at 144fe22b07dfaeec2b366f2346203a9838a55b4c, Model_name 'MetaRNN', Model type 'Supervised'
- review
- reviewer: claude; reviewer note: Claude review agent; no human review claimed. Independent Claude (Opus 5.5) review agent, separate from the extraction agent that built this batch. Automated review only. Transcription, not reproduction.; reviewed at: 2026-10-14T15:30:00Z; artifact sha256: fbe453d1aaa6c30a1d0adf610f7fc23c36044a8e2548b178d316777383f8fe93; retrieval url: https://raw.githubusercontent.com/OATML-Markslab/ProteinGym/144fe22b07dfaeec2b366f2346203a9838a55b4c/benchmarks/clinical_zero_shot/substitutions/AUC/Summary_performance_clinical_substitutions_AUC.csv; method: ai-assisted-source-review; scope-review; method note: Descriptive fields, identity links and missing-metadata reasons checked against the cited sources.; note: Checked; see the dated review for rulings on identity and method type.
- provenance note
- MetaRNN as listed in the ProteinGym clinical benchmark summary at commit 144fe22.
Related records
- configuration of: MetaRNN
- system: MetaRNN: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22)