ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22); 144fe22b07dfaeec2b366f2346203a9838a55b4c

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.

18 recorded evaluations, 18 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

18 evaluations · 18 results. Different protocols are not a single leaderboard.

Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) · Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22

Sorted by AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins)
PoET (200M) [ProteinGym 144fe22b snapshot]Evaluation	0.935 (best in column)
Provean [ProteinGym 144fe22 clinical summary]Evaluation	0.927
RITA L [ProteinGym 144fe22b snapshot]Evaluation	0.922
RITA XL [ProteinGym 144fe22b snapshot]Evaluation	0.916
RITA M [ProteinGym 144fe22b snapshot]Evaluation	0.892
Tranception L no retrieval [ProteinGym 144fe22b snapshot]Evaluation	0.852
Progen2 L [ProteinGym 144fe22b snapshot]Evaluation	0.851
Progen2 M [ProteinGym 144fe22b snapshot]Evaluation	0.846
Progen2 Base [ProteinGym 144fe22b snapshot]Evaluation	0.844
Tranception L [ProteinGym 144fe22b snapshot]Evaluation	0.843
Progen2 XL [ProteinGym 144fe22b snapshot]Evaluation	0.842
Tranception M no retrieval [ProteinGym 144fe22b snapshot]Evaluation	0.831
Tranception M [ProteinGym 144fe22b snapshot]Evaluation	0.828
RITA S [ProteinGym 144fe22b snapshot]Evaluation	0.784
Progen2 S [ProteinGym 144fe22b snapshot]Evaluation	0.763
Hidden Markov Model [ProteinGym 144fe22 clinical summary]Evaluation	0.663
ProtGPT2 [ProteinGym 144fe22b snapshot]Evaluation	0.649
Unirep [ProteinGym 144fe22b snapshot]Evaluation	0.599

All 18 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: PoET (200M) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.935 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source PoET (200M): ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 2, row 'PoET (200M)', column 'Average_AUC'
Configuration: Progen2 Base [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.844 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source Progen2 Base: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 10, row 'Progen2 Base', column 'Average_AUC'
Configuration: Progen2 L [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.851 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source Progen2 L: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 8, row 'Progen2 L', column 'Average_AUC'
Configuration: Progen2 M [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.846 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source Progen2 M: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 9, row 'Progen2 M', column 'Average_AUC'
Configuration: Progen2 S [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.763 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source Progen2 S: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 16, row 'Progen2 S', column 'Average_AUC'
Configuration: Progen2 XL [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.842 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source Progen2 XL: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 12, row 'Progen2 XL', column 'Average_AUC'
Configuration: Hidden Markov Model [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.663 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source Hidden Markov Model: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 17, row 'Hidden Markov Model', column 'Average_AUC'
Configuration: Provean [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.927 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source Provean: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 3, row 'Provean', column 'Average_AUC'
Configuration: ProtGPT2 [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.649 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtGPT2: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 18, row 'ProtGPT2', column 'Average_AUC'
Configuration: RITA L [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.922 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source RITA L: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 4, row 'RITA L', column 'Average_AUC'
Configuration: RITA M [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.892 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source RITA M: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 6, row 'RITA M', column 'Average_AUC'
Configuration: RITA S [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.784 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source RITA S: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 15, row 'RITA S', column 'Average_AUC'
Configuration: RITA XL [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.916 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source RITA XL: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 5, row 'RITA XL', column 'Average_AUC'
Configuration: Tranception L [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.843 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source Tranception L: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 11, row 'Tranception L', column 'Average_AUC'
Configuration: Tranception L no retrieval [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.852 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source Tranception L no retrieval: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 7, row 'Tranception L no retrieval', column 'Average_AUC'
Configuration: Tranception M [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.828 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source Tranception M: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 14, row 'Tranception M', column 'Average_AUC'
Configuration: Tranception M no retrieval [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.831 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source Tranception M no retrieval: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 13, row 'Tranception M no retrieval', column 'Average_AUC'
Configuration: Unirep [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22	0.599 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source Unirep: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 19, row 'Unirep', column 'Average_AUC'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

unreported: 18

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Protocol-valid seeded random ranking; no fitting on assay labels

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Established label-free reference with explicitly permitted sequence/MSA inputs

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-22-1b7cf027e4f6. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

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

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

3 source records and release history

ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · Original source · 144fe22b07dfaeec2b366f2346203a9838a55b4c
OATML-Markslab/ProteinGym / README.md · Original source · Git commit 144fe22b07dfaeec2b366f2346203a9838a55b4c
Protocol metadata evidence: proteingym-paper.xml · Original source · PMC10723403 retrieved 2026-09-23

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: vep-lit-20261014-protocol-proteingym-clinical-zero-shot-indels-auc-144fe22

areas: proteins-complexes; dna-genomes
contexts: clinical_research
task: Clinical indel pathogenicity classification, zero-shot
metric: auroc
metric direction: higher
unit: unitless
metric qualifier: Average_AUC column of the ProteinGym clinical summary file
version: 144fe22b07dfaeec2b366f2346203a9838a55b4c
upstream revision: 144fe22b07dfaeec2b366f2346203a9838a55b4c
publication status: official_project_source
source locator: benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv; README.md lines 39-52 and 106
limitations: The README says per-protein AUC is the clinical metric and gives dbNSFP 4.4a as the source of clinical baselines; the script that wrote this summary file was not read, so the averaging and the bootstrap standard error are not verified for this file.; The ProteinGym paper describes the clinical substitution set as ClinVar labels processed as in EVE (Frazer et al. 2021) and the indel set as short in-frame ClinVar indels (up to 3 amino acids, frameshifts filtered out) with common gnomAD indels as benign pseudocontrols, because 84% of ClinVar indel annotations are pathogenic. The paper describes the 2023 release; whether the sets behind the 144fe22 files are unchanged is not stated.; Not comparable with the DMS summaries or with Livesey and Marsh's rank scores.
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: 98a532c0e2c3d4720b73b7c05cf0dcf0419438c326761aaae3b788799f5aa836; retrieval url: https://raw.githubusercontent.com/OATML-Markslab/ProteinGym/144fe22b07dfaeec2b366f2346203a9838a55b4c/benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_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.

Related records