rewirebio.iobenchmarks
Contested result

Eigen and FATHMM-XF: 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 Eigen above FATHMM-XF in 7 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks FATHMM-XF above Eigen in 4 of 5 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

3 papers rank Eigen above FATHMM-XF in 13 of their 23 comparisons and FATHMM-XF higher in 9; 1 is a tie. Of those papers, An openly licensed benchmark… ranks FATHMM-XF higher on its own (4 of 6).

Papers grouped by which system they rank higher: Eigen or FATHMM-XFRank Eigen higher: Livesey and Marsh 2025. Rank FATHMM-XF higher: An openly licensed benchmark…. Mixed: Comprehensive assessment….Rank Eigen higherMixedRank FATHMM-XF 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 mutationsAn openly licensedbenchmark…An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers
  • Rank Eigen higher (1): Livesey and Marsh 2025
  • Rank FATHMM-XF higher (1): An openly licensed benchmark…
  • 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 Eigen or FATHMM-XF higherComprehensive assessment…: Eigen higher in 5, FATHMM-XF higher in 5, 0 ties. Livesey and Marsh 2025: Eigen higher in 7, FATHMM-XF higher in 0, 0 ties. An openly licensed benchmark…: Eigen higher in 1, FATHMM-XF higher in 4, 1 tie.Comprehensive assessment…Comprehensive assessment of computational algorithms in predicting cancer driver mutations5 Eigen higher55 FATHMM-XF higher5Livesey and Marsh 2025Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)7 Eigen higher7An openly licensed benchmark…An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers1 Eigen higher11 tie14 FATHMM-XF higher4
Eigen higherTieFATHMM-XF higherNumbers are counts of comparisons; the outlined bar is the paper that disagrees.
Comparisons in Comprehensive assessment… (10)
ProtocolDatasetMetricEigenFATHMM-XFHigher
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), fraction0.660.65Eigen
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), fraction0.660.65Eigen
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), fraction0.660.65Eigen
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), fraction0.660.65Eigen
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), fraction0.660.65Eigen
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), fraction0.620.63FATHMM-XF
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), fraction0.620.63FATHMM-XF
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), fraction0.620.63FATHMM-XF
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), fraction0.620.63FATHMM-XF
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), fraction0.620.63FATHMM-XF
Comparisons in Livesey and Marsh 2025 (7)
ProtocolDatasetMetricEigenFATHMM-XFHigher
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), percent54.632Eigen
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), percent52.424.5Eigen
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), percent4.831.83Eigen
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), percent53.727.1Eigen
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), percent51.322.6Eigen
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), percent52.424.5Eigen
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), percent53.925.5Eigen
Comparisons in An openly licensed benchmark… (6)
ProtocolDatasetMetricEigenFATHMM-XFHigher
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), unitless0.7990.813FATHMM-XF
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), unitless0.5570.568FATHMM-XF
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)), unitless0.7950.81FATHMM-XF
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)), unitless0.6070.644FATHMM-XF
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)), unitless0.8650.857Tie
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)), unitless0.5740.476Eigen

What disagrees

studies
2
Compared
Eigen, FATHMM-XF
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-90de3081fb83384a · All contested results · How findings are made and followed up