Protocol

HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2)

Global ROC-AUC and balanced PRC-AUC of ESM1b and one other method, each on the HGMD/gnomAD variants that both methods score.

90 evaluations · 180 results

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.

90 recorded evaluations, 180 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

90 evaluations · 180 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: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and BayesDel (no AF) (Brandes et al. 2023)	0.905 AUPRC (balanced PRC-AUC over the variants both methods score: 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 HGMD/gnomAD missense, head to head against BayesDel (no AF) (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell H21, row 'BayesDel (no AF)', column 'head2head_ESM1b_auc_Balanced_AUPRC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and BayesDel (no AF) (Brandes et al. 2023)	0.894 AUROC (global ROC-AUC over the variants both methods score; 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 HGMD/gnomAD missense, head to head against BayesDel (no AF) (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell F21, row 'BayesDel (no AF)', column 'head2head_ESM1b_auc_AUROC'
Configuration: BayesDel (no AF) (Brandes et al. 2023 head-to-head comparison)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and BayesDel (no AF) (Brandes et al. 2023)	0.98 AUPRC (balanced PRC-AUC over the variants both methods score: 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 BayesDel (no AF) on HGMD/gnomAD missense, head to head against ESM1b (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell G21, row 'BayesDel (no AF)', column 'head2head_VEP_auc_Balanced_AUPRC'
Configuration: BayesDel (no AF) (Brandes et al. 2023 head-to-head comparison)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and BayesDel (no AF) (Brandes et al. 2023)	0.978 AUROC (global ROC-AUC over the variants both methods score; 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 BayesDel (no AF) on HGMD/gnomAD missense, head to head against ESM1b (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell E21, row 'BayesDel (no AF)', column 'head2head_VEP_auc_AUROC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and BayesDel (with AF) (Brandes et al. 2023)	0.905 AUPRC (balanced PRC-AUC over the variants both methods score: 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 HGMD/gnomAD missense, head to head against BayesDel (with AF) (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell H22, row 'BayesDel (with AF)', column 'head2head_ESM1b_auc_Balanced_AUPRC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and BayesDel (with AF) (Brandes et al. 2023)	0.894 AUROC (global ROC-AUC over the variants both methods score; 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 HGMD/gnomAD missense, head to head against BayesDel (with AF) (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell F22, row 'BayesDel (with AF)', column 'head2head_ESM1b_auc_AUROC'
Configuration: BayesDel (with AF) (Brandes et al. 2023 head-to-head comparison)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and BayesDel (with AF) (Brandes et al. 2023)	0.992 AUPRC (balanced PRC-AUC over the variants both methods score: 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 BayesDel (with AF) on HGMD/gnomAD missense, head to head against ESM1b (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell G22, row 'BayesDel (with AF)', column 'head2head_VEP_auc_Balanced_AUPRC'
Configuration: BayesDel (with AF) (Brandes et al. 2023 head-to-head comparison)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and BayesDel (with AF) (Brandes et al. 2023)	0.992 AUROC (global ROC-AUC over the variants both methods score; 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 BayesDel (with AF) on HGMD/gnomAD missense, head to head against ESM1b (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell E22, row 'BayesDel (with AF)', column 'head2head_VEP_auc_AUROC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and bStatistic (Brandes et al. 2023)	0.905 AUPRC (balanced PRC-AUC over the variants both methods score: 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 HGMD/gnomAD missense, head to head against bStatistic (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell H19, row 'bStatistic', column 'head2head_ESM1b_auc_Balanced_AUPRC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and bStatistic (Brandes et al. 2023)	0.894 AUROC (global ROC-AUC over the variants both methods score; 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 HGMD/gnomAD missense, head to head against bStatistic (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell F19, row 'bStatistic', column 'head2head_ESM1b_auc_AUROC'
Configuration: bStatistic (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and bStatistic (Brandes et al. 2023)	0.581 AUPRC (balanced PRC-AUC over the variants both methods score: 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 HGMD/gnomAD missense, head to head against ESM1b (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell G19, row 'bStatistic', column 'head2head_VEP_auc_Balanced_AUPRC'
Configuration: bStatistic (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and bStatistic (Brandes et al. 2023)	0.582 AUROC (global ROC-AUC over the variants both methods score; 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 HGMD/gnomAD missense, head to head against ESM1b (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell E19, row 'bStatistic', column 'head2head_VEP_auc_AUROC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and CADD (Brandes et al. 2023)	0.905 AUPRC (balanced PRC-AUC over the variants both methods score: 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 HGMD/gnomAD missense, head to head against CADD (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell H23, row 'CADD', column 'head2head_ESM1b_auc_Balanced_AUPRC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and CADD (Brandes et al. 2023)	0.894 AUROC (global ROC-AUC over the variants both methods score; 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 HGMD/gnomAD missense, head to head against CADD (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell F23, row 'CADD', column 'head2head_ESM1b_auc_AUROC'
Configuration: CADD (Brandes et al. 2023 head-to-head comparison)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and CADD (Brandes et al. 2023)	0.912 AUPRC (balanced PRC-AUC over the variants both methods score: 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 CADD on HGMD/gnomAD missense, head to head against ESM1b (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell G23, row 'CADD', column 'head2head_VEP_auc_Balanced_AUPRC'
Configuration: CADD (Brandes et al. 2023 head-to-head comparison)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and CADD (Brandes et al. 2023)	0.917 AUROC (global ROC-AUC over the variants both methods score; 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 CADD on HGMD/gnomAD missense, head to head against ESM1b (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell E23, row 'CADD', column 'head2head_VEP_auc_AUROC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and ClinPred (Brandes et al. 2023)	0.906 AUPRC (balanced PRC-AUC over the variants both methods score: 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 HGMD/gnomAD missense, head to head against ClinPred (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell H24, row 'ClinPred', column 'head2head_ESM1b_auc_Balanced_AUPRC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and ClinPred (Brandes et al. 2023)	0.894 AUROC (global ROC-AUC over the variants both methods score; 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 HGMD/gnomAD missense, head to head against ClinPred (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell F24, row 'ClinPred', column 'head2head_ESM1b_auc_AUROC'
Configuration: ClinPred (Brandes et al. 2023 head-to-head comparison)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and ClinPred (Brandes et al. 2023)	0.98 AUPRC (balanced PRC-AUC over the variants both methods score: 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 ClinPred on HGMD/gnomAD missense, head to head against ESM1b (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell G24, row 'ClinPred', column 'head2head_VEP_auc_Balanced_AUPRC'
Configuration: ClinPred (Brandes et al. 2023 head-to-head comparison)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and ClinPred (Brandes et al. 2023)	0.983 AUROC (global ROC-AUC over the variants both methods score; 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 ClinPred on HGMD/gnomAD missense, head to head against ESM1b (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell E24, row 'ClinPred', column 'head2head_VEP_auc_AUROC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and DANN (Brandes et al. 2023)	0.905 AUPRC (balanced PRC-AUC over the variants both methods score: 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 HGMD/gnomAD missense, head to head against DANN (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell H25, row 'DANN', column 'head2head_ESM1b_auc_Balanced_AUPRC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and DANN (Brandes et al. 2023)	0.894 AUROC (global ROC-AUC over the variants both methods score; 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 HGMD/gnomAD missense, head to head against DANN (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell F25, row 'DANN', column 'head2head_ESM1b_auc_AUROC'
Configuration: DANN (Brandes et al. 2023 head-to-head comparison)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and DANN (Brandes et al. 2023)	0.793 AUPRC (balanced PRC-AUC over the variants both methods score: 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 DANN on HGMD/gnomAD missense, head to head against ESM1b (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell G25, row 'DANN', column 'head2head_VEP_auc_Balanced_AUPRC'
Configuration: DANN (Brandes et al. 2023 head-to-head comparison)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and DANN (Brandes et al. 2023)	0.839 AUROC (global ROC-AUC over the variants both methods score; 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 DANN on HGMD/gnomAD missense, head to head against ESM1b (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell E25, row 'DANN', column 'head2head_VEP_auc_AUROC'
Configuration: ESM1b (Brandes et al. 2023 clinical benchmarks)	Protocol: HGMD/gnomAD missense pathogenicity, ESM1b head to head with one other method on the variants both score (Brandes et al. 2023 Fig. 2g,h, Supplementary Table 2) Dataset subset: HGMD/gnomAD missense variants scored by both ESM1b and DEOGEN2 (Brandes et al. 2023)	0.905 AUPRC (balanced PRC-AUC over the variants both methods score: 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 HGMD/gnomAD missense, head to head against DEOGEN2 (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-hgmd-head-to-head 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_HGMD' cell H26, row 'DEOGEN2', column 'head2head_ESM1b_auc_Balanced_AUPRC'

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.

Author-reported evaluations: 45
External evaluations: 45

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

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

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

Select an upstream conventional reference after reviewing the full protocol

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.

Strengths, limitations and unresolved questions

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

0 evidence rows matching the loaded filters

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

2 source records and release history

Genome-wide prediction of disease variant effects with a deep protein language model (Brandes et al., Nature Genetics 2023) · Original source · Version of record, Nature Genetics 55, 1512-1522 (published 2023-08-10)
Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · 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-protocol-hgmd-head-to-head

areas: dna-genomes; protein-function
contexts: clinical_research
protocol: Scores used directly (no training on these labels). For each comparator, restrict the labelled set to the variants with both an ESM1b and a comparator score; compute global ROC-AUC and balanced PRC-AUC (downsample to equal pathogenic and benign counts at 80% of the minority class, mean over 100 repeats) for both methods on that set.
version: Supplementary Table 2 sheet 'Table_of_results_HGMD', columns head2head_*
metric: auroc
metric direction: higher
unit: unitless
limitations: Benchmark built by the ESM1b workflow's authors (author-reported for ESM1b).; Each comparator has its own variant set, so comparator values are comparable only with the ESM1b value on the same set, not with each other.; 27 of the 45 comparators were excluded from the paper's main comparison because they were trained on clinical databases or use allele frequency ('data leakage concerns' in the Results); their head-to-head values may be inflated by that overlap and are not the paper's unbiased comparison. The reason is in each configuration's training_overlap.
source locator: Results 'ESM1b outperforms other VEP methods over clinical and experimental benchmarks', paragraph beginning 'In addition to EVE, we compared ESM1b to 44 other VEP methods'; Methods 'AUC metrics for pathogenicity classification'; Supplementary Table 2 'Contents' (header definitions)

Related records

Suggest a correction