Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
Rank score on SNV-accessible substitutions with each VEP's missing predictions filled with its most benign score (Table S7).
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.
97 recorded evaluations, 97 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
97 evaluations · 97 results. Different protocols are not a single leaderboard.
Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled · Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins)
Sorted by Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.
All 97 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: 3Cnet (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 6.65% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C98) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B98 (row '3Cnet', column 'rank_score') |
| Configuration: AlphaMissense (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 89.5% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C3) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B3 (row 'AlphaMissense', column 'rank_score') |
| Configuration: AlphScore (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 34.7% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C76) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B76 (row 'AlphScore', column 'rank_score') |
| Configuration: BayesDel_noAF (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 58.2% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C38) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B38 (row 'BayesDel_noAF', column 'rank_score') |
| Configuration: BayesDel (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 58.1% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C39) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B39 (row 'BayesDel', column 'rank_score') |
| Configuration: BLOSUM62 (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 15.6% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C87) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B87 (row 'BLOSUM62', column 'rank_score') |
| Configuration: CADD_1.6 (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 36.9% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C75) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B75 (row 'CADD_1.6', column 'rank_score') |
| Configuration: CADD_1.7 (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 42% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C68) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B68 (row 'CADD_1.7', column 'rank_score') |
| Configuration: CAPICE (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 30% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C77) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B77 (row 'CAPICE', column 'rank_score') |
| Configuration: CARP (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 71.2% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 28/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C19) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B19 (row 'CARP', column 'rank_score') |
| Configuration: ClinPred (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 64.5% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C29) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B29 (row 'ClinPred', column 'rank_score') |
| Configuration: CONDEL (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 47.8% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C57) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B57 (row 'CONDEL', column 'rank_score') |
| Configuration: CPT-1 (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 91.9% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 29/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C2) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B2 (row 'CPT-1', column 'rank_score') |
| Configuration: DANN (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 14.5% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C89) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B89 (row 'DANN', column 'rank_score') |
| Configuration: DeepSAV (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 55.5% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C44) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B44 (row 'DeepSAV', column 'rank_score') |
| Configuration: DeepSequence (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 77.5% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 29/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C13) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B13 (row 'DeepSequence', column 'rank_score') |
| Configuration: DeMaSk (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 49.8% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 31/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C54) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B54 (row 'DeMaSk', column 'rank_score') |
| Configuration: DEOGEN2 (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 61.1% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C33) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B33 (row 'DEOGEN2', column 'rank_score') |
| Configuration: Eigen (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 53.9% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C48) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B48 (row 'Eigen', column 'rank_score') |
| Configuration: Envision (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 46.8% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C60) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B60 (row 'Envision', column 'rank_score') |
| Configuration: ESCOTT (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 87.1% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C5) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B5 (row 'ESCOTT', column 'rank_score') |
| Configuration: ESM-1b (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 65.9% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C26) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B26 (row 'ESM-1b', column 'rank_score') |
| Configuration: ESM-1v (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 81.8% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C10) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B10 (row 'ESM-1v', column 'rank_score') |
| Configuration: ESM2 (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 71.1% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 36/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C20) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B20 (row 'ESM2', column 'rank_score') |
| Configuration: EVE (Livesey and Marsh 2025) | Protocol: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Dataset: Livesey and Marsh 2025 human DMS benchmark set (36 proteins) | 72.5% Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score) percent · higher Uncertainty: Not reported by the source: Bootstrap standard deviations appear only as Figure 2 error bars; not printed Coverage: 33/36 human DMS datasets (one per protein) with predictions for this VEP scored ('proteins' column, cell C17) | Independent external evaluation · Source checkedMethods, coverage and sourceLivesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled Aggregation: Not reported Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Supplementary Material 2, sheet 'Table S7', cell B17 (row 'EVE', column 'rank_score') |
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.
- 3Cnet: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- AlphaMissense: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- AlphScore: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- BayesDel: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- BayesDel_noAF: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- BLOSUM62: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- CADD_1.6: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- CADD_1.7: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- CAPICE: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- CARP: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- ClinPred: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- CONDEL: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
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.
- External evaluations
- 97
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
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-10-22-1b7cf027e4f6 · Record review: source checked
2 source records and release history
- Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) · Original source · PMC12016141 (published 2025-04-22; Genome Biol 26:104)
- Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8) · Original source · 13059_2025_3575_MOESM2_ESM.xlsx as published with PMC12016141
Technical metadata and extraction receipts
Stable ID: vep-lit-20261014-protocol-livesey2025-dms-snv-filled
- areas
- dna-genomes; proteins-complexes
- contexts
- research
- scope note
- Same pairwise procedure as the main DMS ranking, restricted to SNV-accessible substitutions, with every remaining missing prediction filled with the most benign score that VEP produces.
- task
- Missense variant effect prediction ranked against DMS
- metric
- pairwise-win-rate
- metric direction
- higher
- unit
- percent
- metric qualifier
- average pairwise win rate against all other VEPs, |Spearman| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score
- metric implementation
- scipy.stats.spearmanr (scipy 1.5.4, Python 3.6.8); absolute Spearman; the VEP with the higher |rho| on variants scored by the DMS and both VEPs earns the point
- aggregation
- Win rate of each VEP pair across proteins (wins divided by times the pair was tested), averaged over all other VEPs (Methods, 'Spearman's correlation and rank score')
- version
- Livesey and Marsh 2025, Supplementary Material 2 Table S7
- publication status
- peer_reviewed
- source locator
- Methods 'Spearman's correlation and rank score' and 'AUROC and AUPRC'; Supplementary Material 2 Legends (Table S7)
- limitations
- A rank score is relative to the other VEPs in the same table; values from different tables or editions are not comparable.; Per-pair, per-protein correlations and AUROCs behind the win rates are not printed; they are in the figshare deposit, which was not retrieved.; DMS assays measure a cellular or molecular phenotype chosen per protein, not pathogenicity.; Figure 2 error bars (standard deviation over 1000 bootstraps of the DMS sets) are not printed; Table S4 gives pairwise bootstrap counts, not extracted.; Five VEPs (Envision, CPT-1, DeMaSk, VARITY_R, VARITY_ER) have DMS sets they were trained on excluded, so they are compared on fewer proteins.
- 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: 1735ee461ef192d9de67c914e9ad73d72d8aa255ea0e3479eb68cd8631d99fa2; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12016141/fullTextXML; 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
- part of: Livesey and Marsh variant effect predictor benchmark (2025 edition)
- uses data: Livesey and Marsh 2025 human DMS benchmark set (36 proteins)
- assessed by: Use calibrated computational evidence for missense variants (PP3/BP4)
- assessed by: Predict missense variant effects in a protein of interest
- assessed by: Rank rare-disease variants for review
- assessment: 3Cnet: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: AlphaMissense: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: AlphScore: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: BayesDel: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: BayesDel_noAF: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: BLOSUM62: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: CADD_1.6: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: CADD_1.7: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: CAPICE: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: CARP: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: ClinPred: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: CONDEL: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: CPT-1: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: DANN: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: DeepSAV: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: DeepSequence: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: DeMaSk: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: DEOGEN2: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: Eigen: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: Envision: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: ESCOTT: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: ESM-1b: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: ESM-1v: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: ESM2: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: EVE: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: EVmutation_epistatic: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: EVmutation_independent: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: FATHMM: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: fathmm-MKL: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: FathmmXF: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: fitCons: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: GEMME: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: GenoCanyon: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: GERP++: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: gMVP: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: Grantham: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: iGEMME: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: InMeRF: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: LASSIE: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: LIST-S2: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: LRT: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: M-CAP: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: Maverick_benign: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: MetaLR: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: MetaRNN: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: MetaSVM: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: MISTIC: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: MOIpred_benign: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: MPC: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: MSA_Transformer: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: MutationAssessor: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: mutationTCN: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: MutFormer: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: MutPred: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: MutScore: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: MVP: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: mvPPT: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: PANTHER: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: PHACT: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: PHACTboost: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: phastCons: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: PhD_SNP: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: PhD-SNPg: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: phyloP: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: PolyPhen2_HumDiv: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: PolyPhen2_HumVar: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: PonP2: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: popEVE: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: PrimateAI: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: ProGen2: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: ProtGPT2: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: PROVEAN: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: REVEL: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: Rhapsody: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: RITA: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: SaProt: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: sequence_unet: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: SIFT: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: SIFT4G: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: SIGMA: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: SiPhy: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: SNAP2: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: SNPred: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: SNPs&GO: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: SNPs&GO3D: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: SPRI: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: SuSPect: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: TranceptEVE: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: Tranception: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: UNEECON: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: Unirep_evotune: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: VARITY_ER: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: VARITY_R: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: VESPA: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: VESPAl: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: VEST4: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled
- assessment: Wavenet: Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filled