rewirebio.iobenchmarks
Contested result

LRT and MutPred: Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes and Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) disagree

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

Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes ranks LRT above MutPred in 5 of 6 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks MutPred above LRT in 7 of 7 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

4 papers rank LRT above MutPred in 12 of their 24 comparisons and MutPred higher in 12. Of those papers, Livesey and Marsh 2025, ProteinGym rank MutPred higher on their own (7 of 7, 1 of 1).

Papers grouped by which system they rank higher: LRT or MutPredRank LRT higher: Comprehensive assessment…, Clinical likelihood ratios and balanced…. Rank MutPred higher: Livesey and Marsh 2025, ProteinGym. Mixed: none.Rank LRT higherMixedRank MutPred higherComprehensive assessment…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 genesLivesey and Marsh 2025Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)ProteinGymProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design
  • Rank LRT higher (2): Comprehensive assessment…, Clinical likelihood ratios and balanced…
  • Rank MutPred higher (2): Livesey and Marsh 2025, ProteinGym
  • Mixed (0): none

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 LRT or MutPred higherComprehensive assessment…: LRT higher in 7, MutPred higher in 3, 0 ties. Livesey and Marsh 2025: LRT higher in 0, MutPred higher in 7, 0 ties. Clinical likelihood ratios and balanced…: LRT higher in 5, MutPred higher in 1, 0 ties. ProteinGym: LRT higher in 0, MutPred higher in 1, 0 ties.Comprehensive assessment…Comprehensive assessment of computational algorithms in predicting cancer driver mutations7 LRT higher73 MutPred higher3Livesey and Marsh 2025Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)7 MutPred higher7Clinical likelihood ratios and balanced…Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes5 LRT higher51 MutPred higher1ProteinGymProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design1 MutPred higher1
LRT higherTieMutPred higherNumbers are counts of comparisons; the outlined bar is the paper that disagrees.
Comparisons in Comprehensive assessment… (10)
ProtocolDatasetMetricLRTMutPredHigher
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), fraction0.650.53LRT
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), fraction0.670.54LRT
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), fraction0.630.52LRT
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), fraction0.730.69LRT
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), fraction0.570.36LRT
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), fraction0.650.66MutPred
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), fraction0.680.66LRT
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), fraction0.630.66MutPred
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), fraction0.740.66LRT
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), fraction0.560.66MutPred
Comparisons in Livesey and Marsh 2025 (7)
ProtocolDatasetMetricLRTMutPredHigher
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), percent18.865.1MutPred
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), percent13.647.9MutPred
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), percent1.2214.4MutPred
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), percent15.446.5MutPred
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), percent12.349MutPred
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), percent13.647.9MutPred
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), percent14.349.2MutPred
Comparisons in Clinical likelihood ratios and balanced… (6)
ProtocolDatasetMetricLRTMutPredHigher
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), unitless2.991.17LRT
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), count85280LRT
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), unitless2.462.21LRT
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), unitless9.626.5LRT
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), count24LRT
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), unitless1.381.57MutPred
Comparisons in ProteinGym (1)
ProtocolDatasetMetricLRTMutPredHigher
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), unitless0.8050.875MutPred

What disagrees

studies
2
Compared
LRT, MutPred
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-b8029ae0331d3e9a · All contested results · How findings are made and followed up