rewirebio.iobenchmarks
Contested result

REVEL and VEST4: Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) and An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers disagree

  • Low severity
  • Not yet reviewed
  • Two-study conflict
  • unknown

Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks REVEL above VEST4 in 6 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks VEST4 above REVEL in 3 of 4 comparisons. No other study gives a verdict, so neither is the outlier.

An automatic lead, not a finding of error. The results below are shown as published, everywhere on the site, until a reviewer decides otherwise.

Which studies agree

5 papers rank REVEL above VEST4 in 14 of their 30 comparisons and VEST4 higher in 12; 4 are ties. Of those papers, An openly licensed benchmark… ranks VEST4 higher on its own (3 of 6).

Papers grouped by which system they rank higher: REVEL or VEST4Rank REVEL higher: Livesey and Marsh 2025. Rank VEST4 higher: An openly licensed benchmark…. Mixed: Comprehensive assessment…, Clinical likelihood ratios and balanced…, ProteinGym.Rank REVEL higherMixedRank VEST4 higherLivesey and Marsh 2025Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)Comprehensiveassessment…Comprehensive assessment of computational algorithms in predicting cancer driver mutationsClinical likelihoodratios and balanced…Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genesProteinGymProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and DesignAn openly licensedbenchmark…An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers
  • Rank REVEL higher (1): Livesey and Marsh 2025
  • Rank VEST4 higher (1): An openly licensed benchmark…
  • Mixed (3): Comprehensive assessment…, Clinical likelihood ratios and balanced…, ProteinGym

Each paper sits where at least two thirds of its comparisons point; Mixed means neither model reaches two thirds. The larger, outlined dot is the paper that disagrees.

Comparisons in which each paper scores REVEL or VEST4 higherComprehensive assessment…: REVEL higher in 5, VEST4 higher in 5, 0 ties. Livesey and Marsh 2025: REVEL higher in 6, VEST4 higher in 1, 0 ties. An openly licensed benchmark…: REVEL higher in 1, VEST4 higher in 3, 2 ties. Clinical likelihood ratios and balanced…: REVEL higher in 2, VEST4 higher in 3, 1 tie. ProteinGym: REVEL higher in 0, VEST4 higher in 0, 1 tie.Comprehensive assessment…Comprehensive assessment of computational algorithms in predicting cancer driver mutations5 REVEL higher55 VEST4 higher5Livesey and Marsh 2025Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)6 REVEL higher61 VEST4 higher1An openly licensed benchmark…An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers1 REVEL higher12 tie23 VEST4 higher3Clinical likelihood ratios and balanced…Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes2 REVEL higher21 tie13 VEST4 higher3ProteinGymProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design1 tie1
REVEL higherTieVEST4 higherNumbers are counts of comparisons; the outlined bar is the paper that disagrees.
Comparisons in Comprehensive assessment… (10)
ProtocolDatasetMetricREVELVEST4Higher
OncoKB benchmark (positive set not stated), median-score threshold (Chen et al. 2020 Additional file 9)OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)Accuracy (OncoKB benchmark (positive set not stated), median-score threshold), fraction0.670.69VEST4
OncoKB benchmark (positive set not stated), median-score threshold (Chen et al. 2020 Additional file 9)OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)Negative predictive value (OncoKB benchmark (positive set not stated), median-score threshold), fraction0.670.69VEST4
OncoKB benchmark (positive set not stated), median-score threshold (Chen et al. 2020 Additional file 9)OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)Precision (OncoKB benchmark (positive set not stated), median-score threshold), fraction0.670.69VEST4
OncoKB benchmark (positive set not stated), median-score threshold (Chen et al. 2020 Additional file 9)OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)Recall (OncoKB benchmark (positive set not stated), median-score threshold), fraction0.670.69VEST4
OncoKB benchmark (positive set not stated), median-score threshold (Chen et al. 2020 Additional file 9)OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)Specificity (OncoKB benchmark (positive set not stated), median-score threshold), fraction0.670.69VEST4
Cell viability drivers versus neutral, median-score threshold (Chen et al. 2020 Additional file 21)Missense mutations with Ba/F3 and MCF10A cell viability calls (published and new)Accuracy (cell viability drivers versus neutral, median-score threshold), fraction0.640.62REVEL
Cell viability drivers versus neutral, median-score threshold (Chen et al. 2020 Additional file 21)Missense mutations with Ba/F3 and MCF10A cell viability calls (published and new)Negative predictive value (cell viability drivers versus neutral, median-score threshold), fraction0.640.62REVEL
Cell viability drivers versus neutral, median-score threshold (Chen et al. 2020 Additional file 21)Missense mutations with Ba/F3 and MCF10A cell viability calls (published and new)Precision (cell viability drivers versus neutral, median-score threshold), fraction0.640.62REVEL
Cell viability drivers versus neutral, median-score threshold (Chen et al. 2020 Additional file 21)Missense mutations with Ba/F3 and MCF10A cell viability calls (published and new)Recall (cell viability drivers versus neutral, median-score threshold), fraction0.650.62REVEL
Cell viability drivers versus neutral, median-score threshold (Chen et al. 2020 Additional file 21)Missense mutations with Ba/F3 and MCF10A cell viability calls (published and new)Specificity (cell viability drivers versus neutral, median-score threshold), fraction0.640.62REVEL
Comparisons in Livesey and Marsh 2025 (7)
ProtocolDatasetMetricREVELVEST4Higher
Livesey and Marsh 2025 clinical benchmark: pairwise AUROC win rate, ClinVar pathogenic versus gnomAD missenseLivesey and Marsh 2025 clinical set: ClinVar pathogenic versus gnomAD v4.1 missense (819 proteins)Pairwise win rate (average pairwise win rate against all other VEPs, per-protein AUROC on shared variants, ClinVar P/LP versus gnomAD v4.1 missense, proteins with at least 10 of each), percent7677.1VEST4
Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, all 36 DMS setsLivesey and Marsh 2025 human DMS benchmark set (36 proteins)Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS on shared variants, 36 human DMS sets), percent66.159REVEL
Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, all 36 DMS setsLivesey and Marsh 2025 human DMS benchmark set (36 proteins)Pairwise win rate (average pairwise win rate against the five top-ranked VEPs (column top_5_winrate; the five are not listed in the table), |Spearman| with DMS on shared variants, 36 human DMS sets), percent13.22.33REVEL
Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, direct assays onlyLivesey and Marsh 2025 human DMS benchmark set (36 proteins)Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS on shared variants, direct DMS assays only), percent65.659.9REVEL
Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, indirect assays onlyLivesey and Marsh 2025 human DMS benchmark set (36 proteins)Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS on shared variants, indirect DMS assays only), percent66.358.4REVEL
Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions onlyLivesey and Marsh 2025 human DMS benchmark set (36 proteins)Pairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS on shared variants, SNV-accessible substitutions only), percent66.159REVEL
Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filledLivesey and Marsh 2025 human DMS benchmark set (36 proteins)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), percent67.560.5REVEL
Comparisons in An openly licensed benchmark… (6)
ProtocolDatasetMetricREVELVEST4Higher
CGC missense oncogenicity, all genes (Lee 2026, OncoCal tool_performance.tsv)Missense variants in 768 Cancer Gene Census genes with open oncogenicity labelsAUROC (CGC missense, all genes), unitless0.8160.833VEST4
CGC missense oncogenicity, all genes (Lee 2026, OncoCal tool_performance.tsv)Missense variants in 768 Cancer Gene Census genes with open oncogenicity labelsAverage precision (CGC missense, all genes), unitless0.6520.648Tie
CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv)Missense variants in 768 Cancer Gene Census genes with open oncogenicity labelsAUROC (CGC missense, oncogenes (gain of function)), unitless0.8430.84Tie
CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv)Missense variants in 768 Cancer Gene Census genes with open oncogenicity labelsAverage precision (CGC missense, oncogenes (gain of function)), unitless0.7390.713REVEL
CGC missense oncogenicity, tumour suppressors (loss of function) (Lee 2026, OncoCal tool_performance.tsv)Missense variants in 768 Cancer Gene Census genes with open oncogenicity labelsAUROC (CGC missense, tumour suppressors (loss of function)), unitless0.8590.885VEST4
CGC missense oncogenicity, tumour suppressors (loss of function) (Lee 2026, OncoCal tool_performance.tsv)Missense variants in 768 Cancer Gene Census genes with open oncogenicity labelsAverage precision (CGC missense, tumour suppressors (loss of function)), unitless0.6180.626VEST4
Comparisons in Clinical likelihood ratios and balanced… (6)
ProtocolDatasetMetricREVELVEST4Higher
BRCA1 functional truth set, binary in silico calls (Cubuk et al. 2021)BRCA1 functional truth set: 1641 missense variants classed deleterious or tolerated by HAP1 cell survival after saturation genome editingBenignity likelihood ratio (Source 'negative likelihood ratio' (TNR/FNR): likelihood ratio for benignity of a tolerated call, BRCA1 functional truth set), unitless17.155.2VEST4
BRCA1 functional truth set, binary in silico calls (Cubuk et al. 2021)BRCA1 functional truth set: 1641 missense variants classed deleterious or tolerated by HAP1 cell survival after saturation genome editingFalse negatives (Functionally deleterious BRCA1 variants called tolerated), count21VEST4
BRCA1 functional truth set, binary in silico calls (Cubuk et al. 2021)BRCA1 functional truth set: 1641 missense variants classed deleterious or tolerated by HAP1 cell survival after saturation genome editingLikelihood ratio (Positive likelihood ratio of a deleterious call (TPR/FPR), BRCA1 functional truth set), unitless1.121.17VEST4
BRCA2 functional truth set, binary in silico calls (Cubuk et al. 2021)BRCA2 functional truth set: 188 missense variants classed deleterious or tolerated by Homology-directed repairBenignity likelihood ratio (Source 'negative likelihood ratio' (TNR/FNR): likelihood ratio for benignity of a tolerated call, BRCA2 functional truth set), unitless19.68.32REVEL
BRCA2 functional truth set, binary in silico calls (Cubuk et al. 2021)BRCA2 functional truth set: 188 missense variants classed deleterious or tolerated by Homology-directed repairFalse negatives (Functionally deleterious BRCA2 variants called tolerated), count11Tie
BRCA2 functional truth set, binary in silico calls (Cubuk et al. 2021)BRCA2 functional truth set: 188 missense variants classed deleterious or tolerated by Homology-directed repairLikelihood ratio (Positive likelihood ratio of a deleterious call (TPR/FPR), BRCA2 functional truth set), unitless1.451.13REVEL
Comparisons in ProteinGym (1)
ProtocolDatasetMetricREVELVEST4Higher
ProteinGym clinical substitutions, supervised predictors, average AUC (commit 144fe22)ProteinGym clinical substitution benchmark at commit 144fe22AUROC (ProteinGym clinical substitutions, supervised clinical predictors, Average_AUC over proteins), unitless0.9280.929Tie

What disagrees

studies
2
Compared
REVEL, VEST4
Study that disagrees
Other studies
Rule
Two-study conflict; unknown
Model identity
Matched across studies partly through links not yet reviewed

Follow-up

Current state: Not yet reviewed.

No one has reviewed this finding yet.

How to help resolve this

If you know why these studies disagree, for example a different population, metric or preprocessing step, or you have a corrected value, tell us through the contribution form. A reviewer checks every submission against its source before anything changes, and the step is added to the follow-up above.

Finding discrepancy-f979046b211fb6c6 · All contested results · How findings are made and followed up