Dataset

ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)

46,726 missense variants with ClinVar labels of at least one gold star across about 3,000 disease genes, downloaded from the EVE portal (includes variants not covered by EVE).

Evaluation results

19 evaluations · 38 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: bStatistic (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.543 AUPRC (balanced PRC-AUC: mean over 100 random downsamples to equal pathogenic and benign counts (80% of the minority class); zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source bStatistic on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell C19, row 'bStatistic', column 'AUC_Balanced_AUPRC'
Configuration: bStatistic (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.563 AUROC (global ROC-AUC over all variants; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source bStatistic on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell B19, row 'bStatistic', column 'AUC_AUROC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.884 AUPRC (balanced PRC-AUC: mean over 100 random downsamples to equal pathogenic and benign counts (80% of the minority class); zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM1b on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell C2, row 'ESM1b', column 'AUC_Balanced_AUPRC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.892 AUROC (global ROC-AUC over all variants; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM1b on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell B2, row 'ESM1b', column 'AUC_AUROC'
Configuration: EVE (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.875 AUPRC (balanced PRC-AUC: mean over 100 random downsamples to equal pathogenic and benign counts (80% of the minority class); zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source EVE on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell C3, row 'EVE', column 'AUC_Balanced_AUPRC'
Configuration: EVE (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.883 AUROC (global ROC-AUC over all variants; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source EVE on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell B3, row 'EVE', column 'AUC_AUROC'
Configuration: fitCons (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.512 AUPRC (balanced PRC-AUC: mean over 100 random downsamples to equal pathogenic and benign counts (80% of the minority class); zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source fitCons on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell C20, row 'fitCons', column 'AUC_Balanced_AUPRC'
Configuration: fitCons (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.529 AUROC (global ROC-AUC over all variants; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source fitCons on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell B20, row 'fitCons', column 'AUC_AUROC'
Configuration: GenoCanyon (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.682 AUPRC (balanced PRC-AUC: mean over 100 random downsamples to equal pathogenic and benign counts (80% of the minority class); zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GenoCanyon on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell C14, row 'GenoCanyon', column 'AUC_Balanced_AUPRC'
Configuration: GenoCanyon (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.685 AUROC (global ROC-AUC over all variants; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GenoCanyon on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell B14, row 'GenoCanyon', column 'AUC_AUROC'
Configuration: GERP++ (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.641 AUPRC (balanced PRC-AUC: mean over 100 random downsamples to equal pathogenic and benign counts (80% of the minority class); zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GERP++ on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell C12, row 'GERP++', column 'AUC_Balanced_AUPRC'
Configuration: GERP++ (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.704 AUROC (global ROC-AUC over all variants; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GERP++ on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell B12, row 'GERP++', column 'AUC_AUROC'
Configuration: LRT (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.779 AUPRC (balanced PRC-AUC: mean over 100 random downsamples to equal pathogenic and benign counts (80% of the minority class); zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LRT on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell C10, row 'LRT', column 'AUC_Balanced_AUPRC'
Configuration: LRT (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.753 AUROC (global ROC-AUC over all variants; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LRT on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell B10, row 'LRT', column 'AUC_AUROC'
Configuration: MTBAN (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.838 AUPRC (balanced PRC-AUC: mean over 100 random downsamples to equal pathogenic and benign counts (80% of the minority class); zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MTBAN on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell C8, row 'MTBAN', column 'AUC_Balanced_AUPRC'
Configuration: MTBAN (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.832 AUROC (global ROC-AUC over all variants; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MTBAN on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell B8, row 'MTBAN', column 'AUC_AUROC'
Configuration: MutationAssessor (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.857 AUPRC (balanced PRC-AUC: mean over 100 random downsamples to equal pathogenic and benign counts (80% of the minority class); zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MutationAssessor on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell C7, row 'MutationAssessor', column 'AUC_Balanced_AUPRC'
Configuration: MutationAssessor (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.86 AUROC (global ROC-AUC over all variants; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MutationAssessor on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell B7, row 'MutationAssessor', column 'AUC_AUROC'
Configuration: phastCons (mammalian) (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.668 AUPRC (balanced PRC-AUC: mean over 100 random downsamples to equal pathogenic and benign counts (80% of the minority class); zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source phastCons (mammalian) on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell C16, row 'phastCons (mammalian)', column 'AUC_Balanced_AUPRC'
Configuration: phastCons (mammalian) (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.648 AUROC (global ROC-AUC over all variants; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source phastCons (mammalian) on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell B16, row 'phastCons (mammalian)', column 'AUC_AUROC'
Configuration: phastCons (primate) (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.612 AUPRC (balanced PRC-AUC: mean over 100 random downsamples to equal pathogenic and benign counts (80% of the minority class); zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source phastCons (primate) on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell C17, row 'phastCons (primate)', column 'AUC_Balanced_AUPRC'
Configuration: phastCons (primate) (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.628 AUROC (global ROC-AUC over all variants; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source phastCons (primate) on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell B17, row 'phastCons (primate)', column 'AUC_AUROC'
Configuration: phastCons (vertebrate) (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.794 AUPRC (balanced PRC-AUC: mean over 100 random downsamples to equal pathogenic and benign counts (80% of the minority class); zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source phastCons (vertebrate) on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell C13, row 'phastCons (vertebrate)', column 'AUC_Balanced_AUPRC'
Configuration: phastCons (vertebrate) (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.699 AUROC (global ROC-AUC over all variants; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source phastCons (vertebrate) on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell B13, row 'phastCons (vertebrate)', column 'AUC_AUROC'
Configuration: phyloP (mammalian) (Brandes et al. 2023 clinical benchmarks)	Protocol: ClinVar missense pathogenicity, variants scored by all 19 eligible methods (Brandes et al. 2023 Fig. 2e-f, Supplementary Table 2) Dataset: ClinVar missense pathogenic vs benign, primary isoforms (Brandes et al. 2023, from the EVE portal)	0.633 AUPRC (balanced PRC-AUC: mean over 100 random downsamples to equal pathogenic and benign counts (80% of the minority class); zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source phyloP (mammalian) on ClinVar missense, variants scored by all 19 methods (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-all-19-methods Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_ClinVar' cell C15, row 'phyloP (mammalian)', column 'AUC_Balanced_AUPRC'

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.

Dataset and evaluation context

A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.

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.

12 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
Population Pathogenic versus benign ClinVar missense variants (at least one gold star) on primary UniProt isoforms Context-only references	Genome-wide prediction of disease variant effects with a deep protein language model (Brandes et al., Nature Genetics 2023) Original source ↗ Supplementary Methods 'Clinical benchmarks of missense variants (ClinVar and HGMD/gnomAD)' paragraph 1; Data availability Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Version of record, Nature Genetics 55, 1512-1522 (published 2023-08-10) Retrieved: 2026-10-14T12:03:14Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.population` Source artifact SHA-256: `919ca366369efbe7e0880565192de127375edddedb1aa43ad023dec612bb4a04` Hash scope: Hash scope not separately documented; inspect source record Archive member: artifacts/brandes2023-pmc10484790.xml.gz Inspected artifact
Population Pathogenic versus benign ClinVar missense variants (at least one gold star) on primary UniProt isoforms Context-only references	Brandes et al. 2023 Supplementary Information (Supplementary Table 1 and Methods) Original source ↗ Supplementary Methods 'Clinical benchmarks of missense variants (ClinVar and HGMD/gnomAD)' paragraph 1; Data availability Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Version of record, Nature Genetics 55, 1512-1522 (published 2023-08-10) Retrieved: 2026-10-14T12:03:21Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.population` Source artifact SHA-256: `30f1c2713875c7cec40f0beee19864840bc55326ddf68918841f93f8bb897c2a` Hash scope: Hash scope not separately documented; inspect source record Archive member: artifacts/brandes2023-supplementary-information.pdf.gz Inspected artifact
Source location Supplementary Methods 'Clinical benchmarks of missense variants (ClinVar and HGMD/gnomAD)' paragraph 1; Data availability Context-only references	Genome-wide prediction of disease variant effects with a deep protein language model (Brandes et al., Nature Genetics 2023) Original source ↗ Supplementary Methods 'Clinical benchmarks of missense variants (ClinVar and HGMD/gnomAD)' paragraph 1; Data availability Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Version of record, Nature Genetics 55, 1512-1522 (published 2023-08-10) Retrieved: 2026-10-14T12:03:14Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.source_locator` Source artifact SHA-256: `919ca366369efbe7e0880565192de127375edddedb1aa43ad023dec612bb4a04` Hash scope: Hash scope not separately documented; inspect source record Archive member: artifacts/brandes2023-pmc10484790.xml.gz Inspected artifact
Source location Supplementary Methods 'Clinical benchmarks of missense variants (ClinVar and HGMD/gnomAD)' paragraph 1; Data availability Context-only references	Brandes et al. 2023 Supplementary Information (Supplementary Table 1 and Methods) Original source ↗ Supplementary Methods 'Clinical benchmarks of missense variants (ClinVar and HGMD/gnomAD)' paragraph 1; Data availability Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Version of record, Nature Genetics 55, 1512-1522 (published 2023-08-10) Retrieved: 2026-10-14T12:03:21Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.source_locator` Source artifact SHA-256: `30f1c2713875c7cec40f0beee19864840bc55326ddf68918841f93f8bb897c2a` Hash scope: Hash scope not separately documented; inspect source record Archive member: artifacts/brandes2023-supplementary-information.pdf.gz Inspected artifact
Split Whole labelled set; ESM1b is unsupervised and comparator methods trained on clinical data are excluded Context-only references	Genome-wide prediction of disease variant effects with a deep protein language model (Brandes et al., Nature Genetics 2023) Original source ↗ Supplementary Methods 'Clinical benchmarks of missense variants (ClinVar and HGMD/gnomAD)' paragraph 1; Data availability Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Version of record, Nature Genetics 55, 1512-1522 (published 2023-08-10) Retrieved: 2026-10-14T12:03:14Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.split` Source artifact SHA-256: `919ca366369efbe7e0880565192de127375edddedb1aa43ad023dec612bb4a04` Hash scope: Hash scope not separately documented; inspect source record Archive member: artifacts/brandes2023-pmc10484790.xml.gz Inspected artifact
Split Whole labelled set; ESM1b is unsupervised and comparator methods trained on clinical data are excluded Context-only references	Brandes et al. 2023 Supplementary Information (Supplementary Table 1 and Methods) Original source ↗ Supplementary Methods 'Clinical benchmarks of missense variants (ClinVar and HGMD/gnomAD)' paragraph 1; Data availability Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Version of record, Nature Genetics 55, 1512-1522 (published 2023-08-10) Retrieved: 2026-10-14T12:03:21Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.split` Source artifact SHA-256: `30f1c2713875c7cec40f0beee19864840bc55326ddf68918841f93f8bb897c2a` Hash scope: Hash scope not separately documented; inspect source record Archive member: artifacts/brandes2023-supplementary-information.pdf.gz Inspected artifact
Version ClinVar benchmark file from the EVE portal (evemodel.org); download date not printed Context-only references	Genome-wide prediction of disease variant effects with a deep protein language model (Brandes et al., Nature Genetics 2023) Original source ↗ Supplementary Methods 'Clinical benchmarks of missense variants (ClinVar and HGMD/gnomAD)' paragraph 1; Data availability Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Version of record, Nature Genetics 55, 1512-1522 (published 2023-08-10) Retrieved: 2026-10-14T12:03:14Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.version` Source artifact SHA-256: `919ca366369efbe7e0880565192de127375edddedb1aa43ad023dec612bb4a04` Hash scope: Hash scope not separately documented; inspect source record Archive member: artifacts/brandes2023-pmc10484790.xml.gz Inspected artifact
Version ClinVar benchmark file from the EVE portal (evemodel.org); download date not printed Context-only references	Brandes et al. 2023 Supplementary Information (Supplementary Table 1 and Methods) Original source ↗ Supplementary Methods 'Clinical benchmarks of missense variants (ClinVar and HGMD/gnomAD)' paragraph 1; Data availability Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Version of record, Nature Genetics 55, 1512-1522 (published 2023-08-10) Retrieved: 2026-10-14T12:03:21Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.version` Source artifact SHA-256: `30f1c2713875c7cec40f0beee19864840bc55326ddf68918841f93f8bb897c2a` Hash scope: Hash scope not separately documented; inspect source record Archive member: artifacts/brandes2023-supplementary-information.pdf.gz Inspected artifact
Description 46,726 missense variants with ClinVar labels of at least one gold star across about 3,000 disease genes, downloaded from the EVE portal (includes variants not covered by EVE). Context-only references	Genome-wide prediction of disease variant effects with a deep protein language model (Brandes et al., Nature Genetics 2023) Original source ↗ Supplementary Methods 'Clinical benchmarks of missense variants (ClinVar and HGMD/gnomAD)' paragraph 1; Data availability Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Version of record, Nature Genetics 55, 1512-1522 (published 2023-08-10) Retrieved: 2026-10-14T12:03:14Z	not individually reviewed No individual claim review recorded Audit details Field: `description` Source artifact SHA-256: `919ca366369efbe7e0880565192de127375edddedb1aa43ad023dec612bb4a04` Hash scope: Hash scope not separately documented; inspect source record Archive member: artifacts/brandes2023-pmc10484790.xml.gz Inspected artifact
Description 46,726 missense variants with ClinVar labels of at least one gold star across about 3,000 disease genes, downloaded from the EVE portal (includes variants not covered by EVE). Context-only references	Brandes et al. 2023 Supplementary Information (Supplementary Table 1 and Methods) Original source ↗ Supplementary Methods 'Clinical benchmarks of missense variants (ClinVar and HGMD/gnomAD)' paragraph 1; Data availability Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Version of record, Nature Genetics 55, 1512-1522 (published 2023-08-10) Retrieved: 2026-10-14T12:03:21Z	not individually reviewed No individual claim review recorded Audit details Field: `description` Source artifact SHA-256: `30f1c2713875c7cec40f0beee19864840bc55326ddf68918841f93f8bb897c2a` Hash scope: Hash scope not separately documented; inspect source record Archive member: artifacts/brandes2023-supplementary-information.pdf.gz Inspected artifact

How to read the evidence

Sources and history

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

2 source records and release history

Brandes et al. 2023 Supplementary Information (Supplementary Table 1 and Methods) · Original source · Version of record, Nature Genetics 55, 1512-1522 (published 2023-08-10)
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)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm-guides-20261014-esm1b-data-clinvar-missense-eve-portal

areas: dna-genomes; protein-function
contexts: clinical_research
version: ClinVar benchmark file from the EVE portal (evemodel.org); download date not printed
split: Whole labelled set; ESM1b is unsupervised and comparator methods trained on clinical data are excluded
population: Pathogenic versus benign ClinVar missense variants (at least one gold star) on primary UniProt isoforms
source locator: Supplementary Methods 'Clinical benchmarks of missense variants (ClinVar and HGMD/gnomAD)' paragraph 1; Data availability

Related records

Suggest a correction