rewirebio.iobenchmarks
Contested result

PrimateAI and PROVEAN: Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes reverses the order

  • Low severity
  • Not yet reviewed
  • Ordering reversal
  • unknown

Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes ranks PrimateAI above PROVEAN in 5 of 6 comparisons; 2 of 2 other studies rank PROVEAN above PrimateAI.

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

4 papers rank PROVEAN above PrimateAI in 20 of their 34 comparisons and PrimateAI higher in 12; 2 are ties. Clinical likelihood ratios and balanced… ranks PrimateAI above PROVEAN in 5 of its 6 comparisons and PROVEAN higher in 1.

Papers grouped by which system they rank higher: PROVEAN or PrimateAIRank PROVEAN higher: Livesey and Marsh 2025, An openly licensed benchmark…, ProteinGym. Rank PrimateAI higher: Clinical likelihood ratios and balanced… (disagrees). Mixed: Comprehensive assessment….Rank PROVEAN higherMixedRank PrimateAI higherLivesey and Marsh 2025Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)An openly licensedbenchmark…An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer driversProteinGymProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and DesignComprehensiveassessment…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 genes
  • Rank PROVEAN higher (3): Livesey and Marsh 2025, An openly licensed benchmark…, ProteinGym
  • Rank PrimateAI higher (1): Clinical likelihood ratios and balanced… (disagrees)
  • Mixed (1): Comprehensive assessment…

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 PROVEAN or PrimateAI higherClinical likelihood ratios and balanced… (disagrees): PROVEAN higher in 1, PrimateAI higher in 5, 0 ties. Comprehensive assessment…: PROVEAN higher in 8, PrimateAI higher in 11, 1 tie. Livesey and Marsh 2025: PROVEAN higher in 7, PrimateAI higher in 0, 0 ties. An openly licensed benchmark…: PROVEAN higher in 4, PrimateAI higher in 1, 1 tie. ProteinGym: PROVEAN higher in 1, PrimateAI higher in 0, 0 ties.Disagrees: Clinical likelihood ratios and balanced…Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes1 PROVEAN higher15 PrimateAI higher5Comprehensive assessment…Comprehensive assessment of computational algorithms in predicting cancer driver mutations8 PROVEAN higher81 tie11 PrimateAI higher11Livesey and Marsh 2025Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)7 PROVEAN higher7An openly licensed benchmark…An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers4 PROVEAN higher41 tie11 PrimateAI higher1ProteinGymProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design1 PROVEAN higher1
PROVEAN higherTiePrimateAI higherNumbers are counts of comparisons; the outlined bar is the paper that disagrees.
Comparisons in Clinical likelihood ratios and balanced… (6)
ProtocolDatasetMetricPROVEANPrimateAIHigher
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), unitless11.2PrimateAI
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), count366283PrimateAI
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), unitless6.82.92PROVEAN
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), unitless1.171.23PrimateAI
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), count5250PrimateAI
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), unitless3.846.78PrimateAI
Comparisons in Comprehensive assessment… (20)
ProtocolDatasetMetricPROVEANPrimateAIHigher
OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10)OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)Accuracy (OncoKB benchmark (positive set not stated), default categorical calls), fraction0.670.66PROVEAN
OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10)OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)Negative predictive value (OncoKB benchmark (positive set not stated), default categorical calls), fraction0.80.71PROVEAN
OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10)OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)Precision (OncoKB benchmark (positive set not stated), default categorical calls), fraction0.610.63PrimateAI
OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10)OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)Recall (OncoKB benchmark (positive set not stated), default categorical calls), fraction0.890.77PROVEAN
OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10)OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)Specificity (OncoKB benchmark (positive set not stated), default categorical calls), fraction0.450.55PrimateAI
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), fraction0.690.66PROVEAN
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), fraction0.70.66PROVEAN
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), fraction0.690.66PROVEAN
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), fraction0.70.66PROVEAN
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), fraction0.680.66PROVEAN
Cell viability drivers versus neutral, default categorical calls (Chen et al. 2020 Additional file 22)Missense mutations with Ba/F3 and MCF10A cell viability calls (published and new)Accuracy (cell viability drivers versus neutral, default categorical calls), fraction0.620.65PrimateAI
Cell viability drivers versus neutral, default categorical calls (Chen et al. 2020 Additional file 22)Missense mutations with Ba/F3 and MCF10A cell viability calls (published and new)Negative predictive value (cell viability drivers versus neutral, default categorical calls), fraction0.70.7Tie
Cell viability drivers versus neutral, default categorical calls (Chen et al. 2020 Additional file 22)Missense mutations with Ba/F3 and MCF10A cell viability calls (published and new)Precision (cell viability drivers versus neutral, default categorical calls), fraction0.570.63PrimateAI
Cell viability drivers versus neutral, default categorical calls (Chen et al. 2020 Additional file 22)Missense mutations with Ba/F3 and MCF10A cell viability calls (published and new)Recall (cell viability drivers versus neutral, default categorical calls), fraction0.780.79PrimateAI
Cell viability drivers versus neutral, default categorical calls (Chen et al. 2020 Additional file 22)Missense mutations with Ba/F3 and MCF10A cell viability calls (published and new)Specificity (cell viability drivers versus neutral, default categorical calls), fraction0.480.52PrimateAI
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), fraction0.590.7PrimateAI
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), fraction0.590.7PrimateAI
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), fraction0.580.7PrimateAI
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), fraction0.590.7PrimateAI
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), fraction0.580.7PrimateAI
Comparisons in Livesey and Marsh 2025 (7)
ProtocolDatasetMetricPROVEANPrimateAIHigher
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), percent48.631.6PROVEAN
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), percent48.119.9PROVEAN
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), percent5.471.22PROVEAN
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), percent5117.5PROVEAN
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), percent4621.7PROVEAN
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), percent48.319.9PROVEAN
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), percent5021PROVEAN
Comparisons in An openly licensed benchmark… (6)
ProtocolDatasetMetricPROVEANPrimateAIHigher
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), unitless0.8190.797PROVEAN
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), unitless0.5880.508PROVEAN
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)), unitless0.8130.817Tie
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)), unitless0.6460.618PROVEAN
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)), unitless0.8590.872PrimateAI
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)), unitless0.5480.505PROVEAN
Comparisons in ProteinGym (1)
ProtocolDatasetMetricPROVEANPrimateAIHigher
ProteinGym clinical substitutions, zero-shot, average AUC (commit 144fe22)ProteinGym clinical substitution benchmark at commit 144fe22AUROC (ProteinGym clinical substitutions, zero-shot, Average_AUC over proteins), unitless0.8860.855PROVEAN

What disagrees

Other studies
rank PROVEAN above PrimateAI in 11 of 12 comparisons
This study
ranks PrimateAI above PROVEAN in 5 of 6 comparisons
Compared
PrimateAI, PROVEAN
Study that disagrees
Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes, Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx)
Other studies
An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers, OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role), Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML), Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8)
Rule
Ordering reversal; unknown
Model identity
Matched across studies partly through links not yet reviewed

The compared numbers

Each value links to its result record and source. Compare values within one protocol; the rule compares rankings, not raw values across protocols.

In the study that disagrees (12)
StudyToolProtocol or benchmarkMetricValue
Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx)primateAI_b (Cubuk et al. 2021)BRCA1 functional truth set, binary in silico calls (Cubuk et al. 2021)Benignity likelihood ratio (Source 'negative likelihood ratio' (TNR/FNR): likelihood ratio for benignity of a tolerated call, BRCA1 functional truth set)1.2
Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx)primateAI_b (Cubuk et al. 2021)BRCA1 functional truth set, binary in silico calls (Cubuk et al. 2021)False negatives (Functionally deleterious BRCA1 variants called tolerated)283
Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx)primateAI_b (Cubuk et al. 2021)BRCA1 functional truth set, binary in silico calls (Cubuk et al. 2021)Likelihood ratio (Positive likelihood ratio of a deleterious call (TPR/FPR), BRCA1 functional truth set)2.92
Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx)primateAI_b (Cubuk et al. 2021)BRCA2 functional truth set, binary in silico calls (Cubuk et al. 2021)Benignity likelihood ratio (Source 'negative likelihood ratio' (TNR/FNR): likelihood ratio for benignity of a tolerated call, BRCA2 functional truth set)1.23
Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx)primateAI_b (Cubuk et al. 2021)BRCA2 functional truth set, binary in silico calls (Cubuk et al. 2021)False negatives (Functionally deleterious BRCA2 variants called tolerated)50
Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx)primateAI_b (Cubuk et al. 2021)BRCA2 functional truth set, binary in silico calls (Cubuk et al. 2021)Likelihood ratio (Positive likelihood ratio of a deleterious call (TPR/FPR), BRCA2 functional truth set)6.78
Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx)PROVEAN (Cubuk et al. 2021)BRCA1 functional truth set, binary in silico calls (Cubuk et al. 2021)Benignity likelihood ratio (Source 'negative likelihood ratio' (TNR/FNR): likelihood ratio for benignity of a tolerated call, BRCA1 functional truth set)1
Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx)PROVEAN (Cubuk et al. 2021)BRCA1 functional truth set, binary in silico calls (Cubuk et al. 2021)False negatives (Functionally deleterious BRCA1 variants called tolerated)366
Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx)PROVEAN (Cubuk et al. 2021)BRCA1 functional truth set, binary in silico calls (Cubuk et al. 2021)Likelihood ratio (Positive likelihood ratio of a deleterious call (TPR/FPR), BRCA1 functional truth set)6.8
Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx)PROVEAN (Cubuk et al. 2021)BRCA2 functional truth set, binary in silico calls (Cubuk et al. 2021)Benignity likelihood ratio (Source 'negative likelihood ratio' (TNR/FNR): likelihood ratio for benignity of a tolerated call, BRCA2 functional truth set)1.17
Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx)PROVEAN (Cubuk et al. 2021)BRCA2 functional truth set, binary in silico calls (Cubuk et al. 2021)False negatives (Functionally deleterious BRCA2 variants called tolerated)52
Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx)PROVEAN (Cubuk et al. 2021)BRCA2 functional truth set, binary in silico calls (Cubuk et al. 2021)Likelihood ratio (Positive likelihood ratio of a deleterious call (TPR/FPR), BRCA2 functional truth set)3.84
In the other studies (24)
StudyToolProtocol or benchmarkMetricValue
An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role)PrimateAI rank score, dbNSFP 5.3.1a (Lee 2026)CGC missense oncogenicity, all genes (Lee 2026, OncoCal tool_performance.tsv)Average precision (CGC missense, all genes)0.508
An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role)PrimateAI rank score, dbNSFP 5.3.1a (Lee 2026)CGC missense oncogenicity, all genes (Lee 2026, OncoCal tool_performance.tsv)AUROC (CGC missense, all genes)0.797
An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role)PrimateAI rank score, dbNSFP 5.3.1a (Lee 2026)CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv)Average precision (CGC missense, oncogenes (gain of function))0.618
An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role)PrimateAI rank score, dbNSFP 5.3.1a (Lee 2026)CGC missense oncogenicity, tumour suppressors (loss of function) (Lee 2026, OncoCal tool_performance.tsv)Average precision (CGC missense, tumour suppressors (loss of function))0.505
An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role)PrimateAI rank score, dbNSFP 5.3.1a (Lee 2026)CGC missense oncogenicity, tumour suppressors (loss of function) (Lee 2026, OncoCal tool_performance.tsv)AUROC (CGC missense, tumour suppressors (loss of function))0.872
An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role)PROVEAN rank score, dbNSFP 5.3.1a (Lee 2026)CGC missense oncogenicity, all genes (Lee 2026, OncoCal tool_performance.tsv)Average precision (CGC missense, all genes)0.588
An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role)PROVEAN rank score, dbNSFP 5.3.1a (Lee 2026)CGC missense oncogenicity, all genes (Lee 2026, OncoCal tool_performance.tsv)AUROC (CGC missense, all genes)0.819
An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role)PROVEAN rank score, dbNSFP 5.3.1a (Lee 2026)CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv)Average precision (CGC missense, oncogenes (gain of function))0.646
An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role)PROVEAN rank score, dbNSFP 5.3.1a (Lee 2026)CGC missense oncogenicity, tumour suppressors (loss of function) (Lee 2026, OncoCal tool_performance.tsv)Average precision (CGC missense, tumour suppressors (loss of function))0.548
An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role)PROVEAN rank score, dbNSFP 5.3.1a (Lee 2026)CGC missense oncogenicity, tumour suppressors (loss of function) (Lee 2026, OncoCal tool_performance.tsv)AUROC (CGC missense, tumour suppressors (loss of function))0.859
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PrimateAI (Livesey and Marsh 2025)Livesey and Marsh 2025 clinical benchmark: pairwise AUROC win rate, ClinVar pathogenic versus gnomAD missensePairwise 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)31.6
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PROVEAN (Livesey and Marsh 2025)Livesey and Marsh 2025 clinical benchmark: pairwise AUROC win rate, ClinVar pathogenic versus gnomAD missensePairwise 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)48.6
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PrimateAI (Livesey and Marsh 2025)Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, all 36 DMS setsPairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS on shared variants, 36 human DMS sets)19.9
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PrimateAI (Livesey and Marsh 2025)Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, all 36 DMS setsPairwise 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)1.22
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PROVEAN (Livesey and Marsh 2025)Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, all 36 DMS setsPairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS on shared variants, 36 human DMS sets)48.1
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PROVEAN (Livesey and Marsh 2025)Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, all 36 DMS setsPairwise 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)5.47
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PrimateAI (Livesey and Marsh 2025)Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, direct assays onlyPairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS on shared variants, direct DMS assays only)17.5
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PROVEAN (Livesey and Marsh 2025)Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, direct assays onlyPairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS on shared variants, direct DMS assays only)51
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PrimateAI (Livesey and Marsh 2025)Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, indirect assays onlyPairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS on shared variants, indirect DMS assays only)21.7
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PROVEAN (Livesey and Marsh 2025)Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, indirect assays onlyPairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS on shared variants, indirect DMS assays only)46
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PrimateAI (Livesey and Marsh 2025)Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filledPairwise 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)21
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PROVEAN (Livesey and Marsh 2025)Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions with gaps filledPairwise 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)50
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PrimateAI (Livesey and Marsh 2025)Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions onlyPairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS on shared variants, SNV-accessible substitutions only)19.9
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)PROVEAN (Livesey and Marsh 2025)Livesey and Marsh 2025 DMS benchmark: pairwise |Spearman| win rate, SNV-accessible substitutions onlyPairwise win rate (average pairwise win rate against all other VEPs, |Spearman| with DMS on shared variants, SNV-accessible substitutions only)48.3

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-fa2a9d7c2d2938a3 · All contested results · How findings are made and followed up