Dataset subset

ProteinGym clinical substitution benchmark at commit 144fe22

ProteinGym clinical substitution variants (benign or pathogenic labels per protein); the README at this commit gives 2,525 clinical proteins.

Evaluation results

30 evaluations · 30 results. Different protocols are not a single leaderboard.

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: BayesDel (addAF) [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.972 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 checked Methods, coverage and source BayesDel (addAF): 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 4, row 'BayesDel (addAF)', column 'Average_AUC'
Configuration: BayesDel (noAF) [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.925 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.003 (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 checked Methods, coverage and source BayesDel (noAF): 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 7, row 'BayesDel (noAF)', column 'Average_AUC'
Configuration: CADD [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.905 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.003 (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 checked Methods, coverage and source CADD: 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 11, row 'CADD', column 'Average_AUC'
Configuration: ClinPred [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.981 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.0 (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 checked Methods, coverage and source ClinPred: 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 2, row 'ClinPred', column 'Average_AUC'
Configuration: DANN [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.812 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.004 (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 checked Methods, coverage and source DANN: 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 17, row 'DANN', column 'Average_AUC'
Configuration: DEOGEN2 [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.894 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.004 (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 checked Methods, coverage and source DEOGEN2: 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 13, row 'DEOGEN2', column 'Average_AUC'
Configuration: FATHMM [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.723 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.006 (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 checked Methods, coverage and source FATHMM: 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 18, row 'FATHMM', column 'Average_AUC'
Configuration: gMVP [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.914 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.004 (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 checked Methods, coverage and source gMVP: 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 10, row 'gMVP', column 'Average_AUC'
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 checked Methods, coverage and source MetaRNN: 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'
Configuration: MPC [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.881 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.004 (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 checked Methods, coverage and source MPC: 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 14, row 'MPC', column 'Average_AUC'
Configuration: MutationTaster [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.816 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.004 (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 checked Methods, coverage and source MutationTaster: 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 16, row 'MutationTaster', column 'Average_AUC'
Configuration: PolyPhen2 (HDIV) [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.879 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.004 (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 checked Methods, coverage and source PolyPhen2 (HDIV): 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 15, row 'PolyPhen2 (HDIV)', column 'Average_AUC'
Configuration: PolyPhen2 (HVAR) [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.896 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.003 (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 checked Methods, coverage and source PolyPhen2 (HVAR): 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 12, row 'PolyPhen2 (HVAR)', column 'Average_AUC'
Configuration: REVEL [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.928 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.003 (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 checked Methods, coverage and source REVEL: 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 6, row 'REVEL', column 'Average_AUC'
Configuration: VARITY (ER) [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.918 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.003 (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 checked Methods, coverage and source VARITY (ER): 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 9, row 'VARITY (ER)', column 'Average_AUC'
Configuration: VARITY (R) [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.921 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.003 (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 checked Methods, coverage and source VARITY (R): 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 8, row 'VARITY (R)', column 'Average_AUC'
Configuration: VEST4 [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.929 AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.003 (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 checked Methods, coverage and source VEST4: 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 5, row 'VEST4', column 'Average_AUC'
Configuration: ESM-1b [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.892 AUROC (ProteinGym clinical substitutions, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.003 (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 checked Methods, coverage and source ESM-1b: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot substitutions AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/substitutions/AUC/Summary_performance_clinical_substitutions_AUC.csv line 6, row 'ESM-1b', column 'Average_AUC'
Configuration: GEMME [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.919 AUROC (ProteinGym clinical substitutions, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.003 (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 checked Methods, coverage and source GEMME: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot substitutions AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/substitutions/AUC/Summary_performance_clinical_substitutions_AUC.csv line 4, row 'GEMME', column 'Average_AUC'
Configuration: PoET (200M) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.92 AUROC (ProteinGym clinical substitutions, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.0 (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 checked Methods, coverage and source PoET (200M): ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot substitutions AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/substitutions/AUC/Summary_performance_clinical_substitutions_AUC.csv line 2, row 'PoET (200M)', column 'Average_AUC'
Configuration: EVE [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.914 AUROC (ProteinGym clinical substitutions, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.002 (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 checked Methods, coverage and source EVE: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot substitutions AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/substitutions/AUC/Summary_performance_clinical_substitutions_AUC.csv line 5, row 'EVE', column 'Average_AUC'
Configuration: LIST-S2 [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.842 AUROC (ProteinGym clinical substitutions, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.005 (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 checked Methods, coverage and source LIST-S2: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot substitutions AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/substitutions/AUC/Summary_performance_clinical_substitutions_AUC.csv line 13, row 'LIST-S2', column 'Average_AUC'
Configuration: LRT [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.805 AUROC (ProteinGym clinical substitutions, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.004 (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 checked Methods, coverage and source LRT: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot substitutions AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/substitutions/AUC/Summary_performance_clinical_substitutions_AUC.csv line 14, row 'LRT', column 'Average_AUC'
Configuration: MutationAssessor [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.877 AUROC (ProteinGym clinical substitutions, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.004 (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 checked Methods, coverage and source MutationAssessor: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot substitutions AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/substitutions/AUC/Summary_performance_clinical_substitutions_AUC.csv line 10, row 'MutationAssessor', column 'Average_AUC'
Configuration: MutPred [ProteinGym 144fe22 clinical summary]	Protocol: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical substitution benchmark at commit 144fe22	0.875 AUROC (ProteinGym clinical substitutions, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: ± 0.005 (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 checked Methods, coverage and source MutPred: ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot substitutions AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/substitutions/AUC/Summary_performance_clinical_substitutions_AUC.csv line 11, row 'MutPred', column 'Average_AUC'

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

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-10-22-1b7cf027e4f6 · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Metrics are recomputed from the saved predictions: not yet verified
Sample annotations are recorded: not yet verified
Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
A pinned run recipe exists: not yet verified
Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Independent validation data exist: not yet verified
Overlap with training data is checked: not yet verified

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Subset and evaluation context

This record describes a particular subset or cohort used in an evaluation. Its results do not describe the full dataset.

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.

5 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
Source location README.md lines 22 and 28 Context-only references	OATML-Markslab/ProteinGym / README.md Original source ↗ README.md lines 22 and 28 Version: Git commit 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-09-17T09:32:03.517591+00:00	not individually reviewed No individual claim review recorded Audit details Field: `attributes.source_locator` Source artifact SHA-256: `321487a8de52c6cfa647a658f61150dd72e0acb0125470524fb94d1f8b23321a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Subset scope 2,525 clinical proteins (README line 22); labels DMS_score_bin 1 pathogenic, 0 benign (README line 28). The README gives protein counts only, not variant counts. Context-only references	OATML-Markslab/ProteinGym / README.md Original source ↗ README.md lines 22 and 28 Version: Git commit 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-09-17T09:32:03.517591+00:00	not individually reviewed No individual claim review recorded Audit details Field: `attributes.subset_scope` Source artifact SHA-256: `321487a8de52c6cfa647a658f61150dd72e0acb0125470524fb94d1f8b23321a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Version 144fe22b07dfaeec2b366f2346203a9838a55b4c Context-only references	OATML-Markslab/ProteinGym / README.md Original source ↗ README.md lines 22 and 28 Version: Git commit 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-09-17T09:32:03.517591+00:00	not individually reviewed No individual claim review recorded Audit details Field: `attributes.version` Source artifact SHA-256: `321487a8de52c6cfa647a658f61150dd72e0acb0125470524fb94d1f8b23321a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Description ProteinGym clinical substitution variants (benign or pathogenic labels per protein); the README at this commit gives 2,525 clinical proteins. Context-only references	OATML-Markslab/ProteinGym / README.md Original source ↗ README.md lines 22 and 28 Version: Git commit 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-09-17T09:32:03.517591+00:00	not individually reviewed No individual claim review recorded Audit details Field: `description` Source artifact SHA-256: `321487a8de52c6cfa647a658f61150dd72e0acb0125470524fb94d1f8b23321a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Name ProteinGym clinical substitution benchmark at commit 144fe22 Context-only references	OATML-Markslab/ProteinGym / README.md Original source ↗ README.md lines 22 and 28 Version: Git commit 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-09-17T09:32:03.517591+00:00	not individually reviewed No individual claim review recorded Audit details Field: `name` Source artifact SHA-256: `321487a8de52c6cfa647a658f61150dd72e0acb0125470524fb94d1f8b23321a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

How to read the evidence

Sources and history

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

1 source record and release history

OATML-Markslab/ProteinGym / README.md · Original source · Git commit 144fe22b07dfaeec2b366f2346203a9838a55b4c

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: vep-lit-20261014-data-proteingym-clinical-substitutions-144fe22

areas: proteins-complexes; dna-genomes
contexts: clinical_research
version: 144fe22b07dfaeec2b366f2346203a9838a55b4c
subset scope: 2,525 clinical proteins (README line 22); labels DMS_score_bin 1 pathogenic, 0 benign (README line 28). The README gives protein counts only, not variant counts.
source locator: README.md lines 22 and 28
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: 321487a8de52c6cfa647a658f61150dd72e0acb0125470524fb94d1f8b23321a; retrieval url: https://raw.githubusercontent.com/OATML-Markslab/ProteinGym/144fe22b07dfaeec2b366f2346203a9838a55b4c/README.md; 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

Suggest a correction