rewirebio.iobenchmarks
Evidence and investigation

Contested results

Where one study disagrees with what other studies report for the same models, and what we are doing to resolve each case.

These are automatic leads, not findings of error. Each release, a check compares how every study ranks the models it shares with other studies. It flags a study that reverses the order the others agree on, or whose gap to a shared reference model lies well outside theirs. Different tasks, populations or metrics often explain a flag.

A flag never hides a result. Flagged results stay in every table, page and download, marked Contested. A result is withheld only when a reviewer marks it disputed.

How the check works, and how each follow-up is recorded: discrepancies between studies.

In this release

  • 192open
  • 6settled
  • 7resolved
  • 3medium severity
  • 202low severity

Release 2026-11-22-bbed7dce2323 · 205 findings in all · rules version 5

Findings

Status: All · Open · Settled · Resolved

Severity: All · Medium · Low

State: All · Not yet reviewed · Under investigation · Explained · Confirmed error · Not a real disagreement

192 findings match, most severe first.

LRT and phyloP: Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods and Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) disagree

  • Low severity
  • Not yet reviewed
  • Two-study conflict
  • Same task, different protocols

Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods ranks LRT above phyloP in 4 of 4 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks phyloP above LRT in 6 of 7 comparisons. No other study gives a verdict, so neither is the outlier.

3 papers rank LRT above phyloP in 7 of their 17 comparisons and phyloP higher in 10. Of those papers, Livesey and Marsh 2025, Clinical likelihood ratios and balanced… rank phyloP higher on their own (6 of 7, 4 of 6).

Comparisons in which each paper scores LRT or phyloP higher3 other papers: LRT higher in 7, phyloP higher in 10, 0 ties.3 other papers7 LRT higher710 phyloP higher10
LRT higherTiephyloP higher
Compared
LRT, phyloP

Not reviewed yet.

MutScore and VARITY: 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 VARITY above MutScore in 6 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks MutScore above VARITY in 4 of 4 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank MutScore above VARITY in 5 of their 13 comparisons and VARITY higher in 6; 2 are ties. Of those papers, Livesey and Marsh 2025 ranks VARITY higher on its own (6 of 7).

Comparisons in which each paper scores MutScore or VARITY higher2 other papers: MutScore higher in 5, VARITY higher in 6, 2 ties.2 other papers5 MutScore higher52 tie26 VARITY higher6
MutScore higherTieVARITY higher
Compared
MutScore, VARITY

Not reviewed yet.

RNA-FM and SpliceBERT: Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications and Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning disagree

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

Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications ranks SpliceBERT above RNA-FM in 3 of 3 comparisons; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning ranks RNA-FM above SpliceBERT in 31 of 36 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank RNA-FM above SpliceBERT in 31 of their 51 comparisons and SpliceBERT higher in 8; 12 are ties. Of those papers, Benchmarking pre-trained genomic… ranks SpliceBERT higher on its own (3 of 15).

Comparisons in which each paper scores RNA-FM or SpliceBERT higher2 other papers: RNA-FM higher in 31, SpliceBERT higher in 8, 12 ties.2 other papers31 RNA-FM higher3112 tie128 SpliceBERT higher8
RNA-FM higherTieSpliceBERT higher
Compared
RNA-FM, SpliceBERT

Not reviewed yet.

DeepSequence and VESPA: ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design and Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) disagree

  • Low severity
  • Not yet reviewed
  • Two-study conflict
  • different-task

ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design ranks VESPA above DeepSequence in 13 of 17 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks DeepSequence above VESPA in 5 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank DeepSequence above VESPA in 9 of their 26 comparisons and VESPA higher in 14; 3 are ties. Of those papers, ProteinGym ranks VESPA higher on its own (13 of 19).

Comparisons in which each paper scores DeepSequence or VESPA higher2 other papers: DeepSequence higher in 9, VESPA higher in 14, 3 ties.2 other papers9 DeepSequence higher93 tie314 VESPA higher14
DeepSequence higherTieVESPA higher
Compared
DeepSequence, VESPA

Not reviewed yet.

Evo 2 and Caduceus: GUANinE v1.1 reveals complementarity of supervised and genomic language models and GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models disagree

  • Low severity
  • Not yet reviewed
  • Two-study conflict
  • different-task

GUANinE v1.1 reveals complementarity of supervised and genomic language models ranks Caduceus above Evo 2 in 4 of 4 comparisons; GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models ranks Evo 2 above Caduceus in 35 of 46 comparisons. No other study gives a verdict, so neither is the outlier.

3 papers rank Evo 2 above Caduceus in 36 of their 58 comparisons and Caduceus higher in 15; 7 are ties. Of those papers, GUANinE v1.1 reveals complementarity… ranks Caduceus higher on its own (4 of 6).

Comparisons in which each paper scores Evo 2 or Caduceus higher3 other papers: Evo 2 higher in 36, Caduceus higher in 15, 7 ties.3 other papers36 Evo 2 higher367 tie715 Caduceus higher15
Evo 2 higherTieCaduceus higher
Compared
Evo 2, Caduceus

Not reviewed yet.

SuSPect and MetaSVM: 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 MetaSVM above SuSPect in 5 of 6 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks SuSPect above MetaSVM in 7 of 7 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank SuSPect above MetaSVM in 8 of their 13 comparisons and MetaSVM higher in 5. Of those papers, Clinical likelihood ratios and balanced… ranks MetaSVM higher on its own (5 of 6).

Comparisons in which each paper scores SuSPect or MetaSVM higher2 other papers: SuSPect higher in 8, MetaSVM higher in 5, 0 ties.2 other papers8 SuSPect higher85 MetaSVM higher5
SuSPect higherTieMetaSVM higher
Compared
SuSPect, MetaSVM

Not reviewed yet.

MPC and MutPred: Comprehensive assessment of computational algorithms in predicting cancer driver mutations 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

Comprehensive assessment of computational algorithms in predicting cancer driver mutations ranks MPC above MutPred in 4 of 5 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks MutPred above MPC in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

3 papers rank MPC above MutPred in 9 of their 23 comparisons and MutPred higher in 9; 5 are ties. Of those papers, An openly licensed benchmark… ranks MutPred higher on its own (6 of 6).

Comparisons in which each paper scores MPC or MutPred higher3 other papers: MPC higher in 9, MutPred higher in 9, 5 ties.3 other papers9 MPC higher95 tie59 MutPred higher9
MPC higherTieMutPred higher
Compared
MPC, MutPred

Not reviewed yet.

MutFormer and REVEL: 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 MutFormer above REVEL in 6 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks REVEL above MutFormer in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank MutFormer above REVEL in 6 of their 13 comparisons and REVEL higher in 7. Of those papers, An openly licensed benchmark… ranks REVEL higher on its own (6 of 6).

Comparisons in which each paper scores MutFormer or REVEL higher2 other papers: MutFormer higher in 6, REVEL higher in 7, 0 ties.2 other papers6 MutFormer higher67 REVEL higher7
MutFormer higherTieREVEL higher
Compared
MutFormer, REVEL

Not reviewed yet.

MutScore and PHACTboost: 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 PHACTboost above MutScore in 7 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks MutScore above PHACTboost in 5 of 5 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank MutScore above PHACTboost in 5 of their 13 comparisons and PHACTboost higher in 7; 1 is a tie. Of those papers, Livesey and Marsh 2025 ranks PHACTboost higher on its own (7 of 7).

Comparisons in which each paper scores MutScore or PHACTboost higher2 other papers: MutScore higher in 5, PHACTboost higher in 7, 1 tie.2 other papers5 MutScore higher51 tie7 PHACTboost higher7
MutScore higherTiePHACTboost higher
Compared
MutScore, PHACTboost

Not reviewed yet.

MutFormer and PROVEAN: 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 MutFormer above PROVEAN in 7 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks PROVEAN above MutFormer in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank MutFormer above PROVEAN in 7 of their 13 comparisons and PROVEAN higher in 6. Of those papers, An openly licensed benchmark… ranks PROVEAN higher on its own (6 of 6).

Comparisons in which each paper scores MutFormer or PROVEAN higher2 other papers: MutFormer higher in 7, PROVEAN higher in 6, 0 ties.2 other papers7 MutFormer higher76 PROVEAN higher6
MutFormer higherTiePROVEAN higher
Compared
MutFormer, PROVEAN

Not reviewed yet.

Borzoi and Sei: GUANinE v1.1 reveals complementarity of supervised and genomic language models and Comparative Analysis of Deep Learning Models for Predicting Causative Regulatory Variants disagree

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

GUANinE v1.1 reveals complementarity of supervised and genomic language models ranks Borzoi above Sei in 6 of 6 comparisons; Comparative Analysis of Deep Learning Models for Predicting Causative Regulatory Variants ranks Sei above Borzoi in 4 of 4 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank Borzoi above Sei in 6 of their 11 comparisons and Sei higher in 4; 1 is a tie. Of those papers, Comparative Analysis of Deep Learning… ranks Sei higher on its own (4 of 4).

Comparisons in which each paper scores Borzoi or Sei higher2 other papers: Borzoi higher in 6, Sei higher in 4, 1 tie.2 other papers6 Borzoi higher61 tie14 Sei higher4
Borzoi higherTieSei higher
Compared
Borzoi, Sei

Not reviewed yet.

ESM-2 and CADD: Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026) and Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) disagree

  • Low severity
  • Not yet reviewed
  • Two-study conflict
  • different-task

Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026) ranks CADD above ESM-2 in 14 of 14 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks ESM-2 above CADD in 6 of 7 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank ESM-2 above CADD in 6 of their 21 comparisons and CADD higher in 15. Of those papers, Genome modelling and design across all… ranks CADD higher on its own (14 of 14).

Comparisons in which each paper scores ESM-2 or CADD higher2 other papers: ESM-2 higher in 6, CADD higher in 15, 0 ties.2 other papers6 ESM-2 higher615 CADD higher15
ESM-2 higherTieCADD higher
Compared
ESM-2, CADD

Not reviewed yet.

MutFormer and ESM-1b: 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 MutFormer above ESM-1b in 7 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks ESM-1b above MutFormer in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank MutFormer above ESM-1b in 7 of their 13 comparisons and ESM-1b higher in 6. Of those papers, An openly licensed benchmark… ranks ESM-1b higher on its own (6 of 6).

Comparisons in which each paper scores MutFormer or ESM-1b higher2 other papers: MutFormer higher in 7, ESM-1b higher in 6, 0 ties.2 other papers7 MutFormer higher76 ESM-1b higher6
MutFormer higherTieESM-1b higher
Compared
MutFormer, ESM-1b

Not reviewed yet.

Eigen and PROVEAN: 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 PROVEAN in 6 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks PROVEAN above Eigen in 4 of 5 comparisons. No other study gives a verdict, so neither is the outlier.

4 papers rank Eigen above PROVEAN in 16 of their 29 comparisons and PROVEAN higher in 12; 1 is a tie. Of those papers, An openly licensed benchmark… ranks PROVEAN higher on its own (4 of 6).

Comparisons in which each paper scores Eigen or PROVEAN higher4 other papers: Eigen higher in 16, PROVEAN higher in 12, 1 tie.4 other papers16 Eigen higher161 tie12 PROVEAN higher12
Eigen higherTiePROVEAN higher
Compared
Eigen, PROVEAN

Not reviewed yet.

M-CAP and MutFormer: 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 MutFormer above M-CAP in 7 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks M-CAP above MutFormer in 4 of 5 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank M-CAP above MutFormer in 4 of their 13 comparisons and MutFormer higher in 8; 1 is a tie. Of those papers, Livesey and Marsh 2025 ranks MutFormer higher on its own (7 of 7).

Comparisons in which each paper scores M-CAP or MutFormer higher2 other papers: M-CAP higher in 4, MutFormer higher in 8, 1 tie.2 other papers4 M-CAP higher41 tie8 MutFormer higher8
M-CAP higherTieMutFormer higher
Compared
M-CAP, MutFormer

Not reviewed yet.

Condel and MVP: 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 MVP above Condel in 4 of 5 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks Condel above MVP in 6 of 7 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank Condel above MVP in 7 of their 12 comparisons and MVP higher in 5. Of those papers, Clinical likelihood ratios and balanced… ranks MVP higher on its own (4 of 5).

Comparisons in which each paper scores Condel or MVP higher2 other papers: Condel higher in 7, MVP higher in 5, 0 ties.2 other papers7 Condel higher75 MVP higher5
Condel higherTieMVP higher
Compared
Condel, MVP

Not reviewed yet.

FATHMM-XF and MutFormer: 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 MutFormer 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 MutFormer in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank FATHMM-XF above MutFormer in 6 of their 13 comparisons and MutFormer higher in 7. Of those papers, Livesey and Marsh 2025 ranks MutFormer higher on its own (7 of 7).

Comparisons in which each paper scores FATHMM-XF or MutFormer higher2 other papers: FATHMM-XF higher in 6, MutFormer higher in 7, 0 ties.2 other papers6 FATHMM-XF higher67 MutFormer higher7
FATHMM-XF higherTieMutFormer higher
Compared
FATHMM-XF, MutFormer

Not reviewed yet.

FATHMM and Integrated_fitCons: Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes and Comprehensive assessment of computational algorithms in predicting cancer driver mutations 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 FATHMM above Integrated_fitCons in 6 of 6 comparisons; Comprehensive assessment of computational algorithms in predicting cancer driver mutations ranks Integrated_fitCons above FATHMM in 8 of 9 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank FATHMM above Integrated_fitCons in 7 of their 16 comparisons and Integrated_fitCons higher in 8; 1 is a tie. Of those papers, Comprehensive assessment… ranks Integrated_fitCons higher on its own (8 of 10).

Comparisons in which each paper scores FATHMM or Integrated_fitCons higher2 other papers: FATHMM higher in 7, Integrated_fitCons higher in 8, 1 tie.2 other papers7 FATHMM higher71 tie8 Integrated_fitCons higher8
FATHMM higherTieIntegrated_fitCons higher
Compared
FATHMM, Integrated_fitCons

Not reviewed yet.

Evo 2 and CADD: Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026) and evo2-cloud-operations recorded run b75c67aa: run receipt, Google Cloud H100 (P2, attempt-1) disagree

  • Low severity
  • Not yet reviewed
  • Two-study conflict
  • different-task

Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026) ranks CADD above Evo 2 in 36 of 47 comparisons; evo2-cloud-operations recorded run b75c67aa: run receipt, Google Cloud H100 (P2, attempt-1) ranks Evo 2 above CADD in 3 of 3 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank Evo 2 above CADD in 14 of their 56 comparisons and CADD higher in 36; 6 are ties. Of those papers, Genome modelling and design across all… ranks CADD higher on its own (36 of 52).

Comparisons in which each paper scores Evo 2 or CADD higher2 other papers: Evo 2 higher in 14, CADD higher in 36, 6 ties.2 other papers14 Evo 2 higher146 tie636 CADD higher36
Evo 2 higherTieCADD higher
Compared
Evo 2, CADD

Not reviewed yet.

Evo and LucaOne: Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning and GENEB leaderboard (leaderboard.json, 13 task-type aggregates) disagree

  • Low severity
  • Not yet reviewed
  • Two-study conflict
  • different-task

Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning ranks Evo above LucaOne in 6 of 6 comparisons; GENEB leaderboard (leaderboard.json, 13 task-type aggregates) ranks LucaOne above Evo in 40 of 45 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank Evo above LucaOne in 11 of their 51 comparisons and LucaOne higher in 40. Of those papers, GENEB leaderboard ranks LucaOne higher on its own (40 of 45).

Comparisons in which each paper scores Evo or LucaOne higher2 other papers: Evo higher in 11, LucaOne higher in 40, 0 ties.2 other papers11 Evo higher1140 LucaOne higher40
Evo higherTieLucaOne higher
Compared
Evo, LucaOne

Not reviewed yet.

Condel and PolyPhen-2: 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 PolyPhen-2 above Condel in 4 of 5 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks Condel above PolyPhen-2 in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank Condel above PolyPhen-2 in 7 of their 12 comparisons and PolyPhen-2 higher in 4; 1 is a tie. Of those papers, Clinical likelihood ratios and balanced… ranks PolyPhen-2 higher on its own (4 of 6).

Comparisons in which each paper scores Condel or PolyPhen-2 higher2 other papers: Condel higher in 7, PolyPhen-2 higher in 4, 1 tie.2 other papers7 Condel higher71 tie4 PolyPhen-2 higher4
Condel higherTiePolyPhen-2 higher
Compared
Condel, PolyPhen-2

Not reviewed yet.

FATHMM and GenoCanyon: Comprehensive assessment of computational algorithms in predicting cancer driver mutations and Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) disagree

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

Comprehensive assessment of computational algorithms in predicting cancer driver mutations ranks GenoCanyon above FATHMM in 8 of 10 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks FATHMM above GenoCanyon in 7 of 7 comparisons. No other study gives a verdict, so neither is the outlier.

3 papers rank FATHMM above GenoCanyon in 12 of their 23 comparisons and GenoCanyon higher in 11. Of those papers, Comprehensive assessment… ranks GenoCanyon higher on its own (8 of 10).

Comparisons in which each paper scores FATHMM or GenoCanyon higher3 other papers: FATHMM higher in 12, GenoCanyon higher in 11, 0 ties.3 other papers12 FATHMM higher1211 GenoCanyon higher11
FATHMM higherTieGenoCanyon higher
Compared
FATHMM, GenoCanyon

Not reviewed yet.

MutFormer and BayesDel: 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 MutFormer above BayesDel in 6 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks BayesDel above MutFormer in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank MutFormer above BayesDel in 6 of their 13 comparisons and BayesDel higher in 7. Of those papers, An openly licensed benchmark… ranks BayesDel higher on its own (6 of 6).

Comparisons in which each paper scores MutFormer or BayesDel higher2 other papers: MutFormer higher in 6, BayesDel higher in 7, 0 ties.2 other papers6 MutFormer higher67 BayesDel higher7
MutFormer higherTieBayesDel higher
Compared
MutFormer, BayesDel

Not reviewed yet.

CADD and PROVEAN: 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 PROVEAN above CADD in 6 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks CADD above PROVEAN in 3 of 3 comparisons. No other study gives a verdict, so neither is the outlier.

4 papers rank CADD above PROVEAN in 9 of their 28 comparisons and PROVEAN higher in 13; 6 are ties. Of those papers, Comprehensive assessment…, Livesey and Marsh 2025 rank PROVEAN higher on their own (5 of 10, 6 of 7).

Comparisons in which each paper scores CADD or PROVEAN higher4 other papers: CADD higher in 9, PROVEAN higher in 13, 6 ties.4 other papers9 CADD higher96 tie613 PROVEAN higher13
CADD higherTiePROVEAN higher
Compared
CADD, PROVEAN

Not reviewed yet.

PHACTboost and BayesDel: 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 PHACTboost above BayesDel in 7 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks BayesDel above PHACTboost in 4 of 5 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank PHACTboost above BayesDel in 8 of their 13 comparisons and BayesDel higher in 4; 1 is a tie. Of those papers, An openly licensed benchmark… ranks BayesDel higher on its own (4 of 6).

Comparisons in which each paper scores PHACTboost or BayesDel higher2 other papers: PHACTboost higher in 8, BayesDel higher in 4, 1 tie.2 other papers8 PHACTboost higher81 tie4 BayesDel higher4
PHACTboost higherTieBayesDel higher
Compared
PHACTboost, BayesDel

Not reviewed yet.

Kraken2 and sourmash: Taxonomic classification of DNA sequences beyond sequence similarity using deep neural networks (PNAS PDF) and Evaluation of taxonomic classification and profiling methods for long-read shotgun metagenomic sequencing datasets disagree

  • Low severity
  • Not yet reviewed
  • Two-study conflict
  • different-task

Taxonomic classification of DNA sequences beyond sequence similarity using deep neural networks (PNAS PDF) ranks Kraken2 above sourmash in 2 of 2 comparisons; Evaluation of taxonomic classification and profiling methods for long-read shotgun metagenomic sequencing datasets ranks sourmash above Kraken2 in 24 of 29 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank Kraken2 above sourmash in 7 of their 52 comparisons and sourmash higher in 24; 21 are ties. Of those papers, Evaluation of taxonomic classification… ranks sourmash higher on its own (24 of 48).

Comparisons in which each paper scores Kraken2 or sourmash higher2 other papers: Kraken2 higher in 7, sourmash higher in 24, 21 ties.2 other papers7 Kraken2 higher721 tie2124 sourmash higher24
Kraken2 higherTiesourmash higher
Compared
Kraken2, sourmash

Not reviewed yet.

ClinPred and VARITY: 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 VARITY above ClinPred in 7 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks ClinPred above VARITY in 4 of 4 comparisons. No other study gives a verdict, so neither is the outlier.

3 papers rank ClinPred above VARITY in 5 of their 14 comparisons and VARITY higher in 7; 2 are ties. Of those papers, Livesey and Marsh 2025 ranks VARITY higher on its own (7 of 7).

Comparisons in which each paper scores ClinPred or VARITY higher3 other papers: ClinPred higher in 5, VARITY higher in 7, 2 ties.3 other papers5 ClinPred higher52 tie27 VARITY higher7
ClinPred higherTieVARITY higher
Compared
ClinPred, VARITY

Not reviewed yet.

FATHMM-MKL and M-CAP: Comprehensive assessment of computational algorithms in predicting cancer driver mutations and Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) disagree

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

Comprehensive assessment of computational algorithms in predicting cancer driver mutations ranks FATHMM-MKL above M-CAP in 16 of 20 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks M-CAP above FATHMM-MKL in 7 of 7 comparisons. No other study gives a verdict, so neither is the outlier.

3 papers rank FATHMM-MKL above M-CAP in 18 of their 31 comparisons and M-CAP higher in 12; 1 is a tie. Of those papers, Livesey and Marsh 2025 ranks M-CAP higher on its own (7 of 7).

Comparisons in which each paper scores FATHMM-MKL or M-CAP higher3 other papers: FATHMM-MKL higher in 18, M-CAP higher in 12, 1 tie.3 other papers18 FATHMM-MKL higher181 tie12 M-CAP higher12
FATHMM-MKL higherTieM-CAP higher
Compared
FATHMM-MKL, M-CAP

Not reviewed yet.

RNAErnie and SpliceBERT: Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications and Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning disagree

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

Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications ranks SpliceBERT above RNAErnie in 3 of 3 comparisons; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning ranks RNAErnie above SpliceBERT in 26 of 33 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank RNAErnie above SpliceBERT in 26 of their 51 comparisons and SpliceBERT higher in 10; 15 are ties. Of those papers, Benchmarking pre-trained genomic… ranks SpliceBERT higher on its own (3 of 15).

Comparisons in which each paper scores RNAErnie or SpliceBERT higher2 other papers: RNAErnie higher in 26, SpliceBERT higher in 10, 15 ties.2 other papers26 RNAErnie higher2615 tie1510 SpliceBERT higher10
RNAErnie higherTieSpliceBERT higher
Compared
RNAErnie, SpliceBERT

Not reviewed yet.

MutFormer and MVP: 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 MutFormer above MVP in 7 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks MVP above MutFormer in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank MutFormer above MVP in 7 of their 13 comparisons and MVP higher in 6. Of those papers, An openly licensed benchmark… ranks MVP higher on its own (6 of 6).

Comparisons in which each paper scores MutFormer or MVP higher2 other papers: MutFormer higher in 7, MVP higher in 6, 0 ties.2 other papers7 MutFormer higher76 MVP higher6
MutFormer higherTieMVP higher
Compared
MutFormer, MVP

Not reviewed yet.

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.

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).

Comparisons in which each paper scores Eigen or FATHMM-XF higher3 other papers: Eigen higher in 13, FATHMM-XF higher in 9, 1 tie.3 other papers13 Eigen higher131 tie9 FATHMM-XF higher9
Eigen higherTieFATHMM-XF higher
Compared
Eigen, FATHMM-XF

Not reviewed yet.

ClinPred and MutFormer: 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 MutFormer above ClinPred in 7 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks ClinPred above MutFormer in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank ClinPred above MutFormer in 6 of their 13 comparisons and MutFormer higher in 7. Of those papers, Livesey and Marsh 2025 ranks MutFormer higher on its own (7 of 7).

Comparisons in which each paper scores ClinPred or MutFormer higher2 other papers: ClinPred higher in 6, MutFormer higher in 7, 0 ties.2 other papers6 ClinPred higher67 MutFormer higher7
ClinPred higherTieMutFormer higher
Compared
ClinPred, MutFormer

Not reviewed yet.

Boltz-2 and AlphaFold 3: Shen et al. 2025, Chemical Science (Europe PMC full text) and Kim, Correy, Hall et al. 2026, eLife 15:RP110475 (Europe PMC full text) disagree

  • Low severity
  • Not yet reviewed
  • Two-study conflict
  • Same task, different protocols

Shen et al. 2025, Chemical Science (Europe PMC full text) ranks AlphaFold 3 above Boltz-2 in 9 of 9 comparisons; Kim, Correy, Hall et al. 2026, eLife 15:RP110475 (Europe PMC full text) ranks Boltz-2 above AlphaFold 3 in 2 of 2 comparisons. No other study gives a verdict, so neither is the outlier.

3 papers rank Boltz-2 above AlphaFold 3 in 4 of their 19 comparisons and AlphaFold 3 higher in 14; 1 is a tie. Of those papers, Shen et al. 2025, Structural Plausibility Without Binding… rank AlphaFold 3 higher on their own (9 of 10, 5 of 7).

Comparisons in which each paper scores Boltz-2 or AlphaFold 3 higher3 other papers: Boltz-2 higher in 4, AlphaFold 3 higher in 14, 1 tie.3 other papers4 Boltz-2 higher41 tie14 AlphaFold 3 higher14
Boltz-2 higherTieAlphaFold 3 higher
Compared
Boltz-2, AlphaFold 3

Not reviewed yet.

MutationTaster and ESM-1b: Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods 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

Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods ranks ESM-1b above MutationTaster in 4 of 4 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks MutationTaster above ESM-1b in 5 of 5 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank MutationTaster above ESM-1b in 5 of their 10 comparisons and ESM-1b higher in 4; 1 is a tie. Of those papers, Brandes et al. 2023 ranks ESM-1b higher on its own (4 of 4).

Comparisons in which each paper scores MutationTaster or ESM-1b higher2 other papers: MutationTaster higher in 5, ESM-1b higher in 4, 1 tie.2 other papers5 MutationTaster higher51 tie14 ESM-1b higher4
MutationTaster higherTieESM-1b higher
Compared
MutationTaster, ESM-1b

Not reviewed yet.

ClinPred and PHACTboost: 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 PHACTboost above ClinPred in 6 of 6 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks ClinPred above PHACTboost in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank ClinPred above PHACTboost in 6 of their 13 comparisons and PHACTboost higher in 6; 1 is a tie. Of those papers, Livesey and Marsh 2025 ranks PHACTboost higher on its own (6 of 7).

Comparisons in which each paper scores ClinPred or PHACTboost higher2 other papers: ClinPred higher in 6, PHACTboost higher in 6, 1 tie.2 other papers6 ClinPred higher61 tie6 PHACTboost higher6
ClinPred higherTiePHACTboost higher
Compared
ClinPred, PHACTboost

Not reviewed yet.

CADD and MutationAssessor: 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 MutationAssessor above CADD in 6 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks CADD above MutationAssessor in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

4 papers rank CADD above MutationAssessor in 15 of their 28 comparisons and MutationAssessor higher in 13. Of those papers, Livesey and Marsh 2025 ranks MutationAssessor higher on its own (6 of 7).

Comparisons in which each paper scores CADD or MutationAssessor higher4 other papers: CADD higher in 15, MutationAssessor higher in 13, 0 ties.4 other papers15 CADD higher1513 MutationAssessor higher13
CADD higherTieMutationAssessor higher
Compared
CADD, MutationAssessor

Not reviewed yet.

MutationAssessor and MutFormer: 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 MutFormer above MutationAssessor in 7 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks MutationAssessor above MutFormer in 5 of 5 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank MutationAssessor above MutFormer in 5 of their 13 comparisons and MutFormer higher in 7; 1 is a tie. Of those papers, Livesey and Marsh 2025 ranks MutFormer higher on its own (7 of 7).

Comparisons in which each paper scores MutationAssessor or MutFormer higher2 other papers: MutationAssessor higher in 5, MutFormer higher in 7, 1 tie.2 other papers5 MutationAssessor higher51 tie7 MutFormer higher7
MutationAssessor higherTieMutFormer higher
Compared
MutationAssessor, MutFormer

Not reviewed yet.

MuSE and NeuSomatic: A benchmarking study of individual somatic variant callers and voting-based ensembles for whole-exome sequencing and Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample disagree

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

A benchmarking study of individual somatic variant callers and voting-based ensembles for whole-exome sequencing ranks MuSE above NeuSomatic in 3 of 3 comparisons; Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample ranks NeuSomatic above MuSE in 67 of 74 comparisons. No other study gives a verdict, so neither is the outlier.

3 papers rank MuSE above NeuSomatic in 25 of their 107 comparisons and NeuSomatic higher in 75; 7 are ties. Of those papers, Achieving robust somatic mutation… ranks NeuSomatic higher on its own (67 of 77).

Comparisons in which each paper scores MuSE or NeuSomatic higher3 other papers: MuSE higher in 25, NeuSomatic higher in 75, 7 ties.3 other papers25 MuSE higher257 tie75 NeuSomatic higher75
MuSE higherTieNeuSomatic higher
Compared
MuSE, NeuSomatic

Not reviewed yet.

DEOGEN2 and MPC: Comprehensive assessment of computational algorithms in predicting cancer driver mutations and Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) disagree

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

Comprehensive assessment of computational algorithms in predicting cancer driver mutations ranks MPC above DEOGEN2 in 10 of 10 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks DEOGEN2 above MPC in 6 of 7 comparisons. No other study gives a verdict, so neither is the outlier.

4 papers rank DEOGEN2 above MPC in 10 of their 24 comparisons and MPC higher in 13; 1 is a tie. Of those papers, Comprehensive assessment… ranks MPC higher on its own (10 of 10).

Comparisons in which each paper scores DEOGEN2 or MPC higher4 other papers: DEOGEN2 higher in 10, MPC higher in 13, 1 tie.4 other papers10 DEOGEN2 higher101 tie13 MPC higher13
DEOGEN2 higherTieMPC higher
Compared
DEOGEN2, MPC

Not reviewed yet.

MUpro and ThermoNet: Transfer learning to leverage larger datasets for improved prediction of protein stability changes and Predicting protein stability changes upon single-point mutation: a thorough comparison of the available tools on a new dataset disagree

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

Transfer learning to leverage larger datasets for improved prediction of protein stability changes ranks MUpro above ThermoNet in 5 of 6 comparisons; Predicting protein stability changes upon single-point mutation: a thorough comparison of the available tools on a new dataset ranks ThermoNet above MUpro in 9 of 9 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank MUpro above ThermoNet in 5 of their 16 comparisons and ThermoNet higher in 10; 1 is a tie. Of those papers, Predicting protein stability changes… ranks ThermoNet higher on its own (9 of 10).

Comparisons in which each paper scores MUpro or ThermoNet higher2 other papers: MUpro higher in 5, ThermoNet higher in 10, 1 tie.2 other papers5 MUpro higher51 tie10 ThermoNet higher10
MUpro higherTieThermoNet higher
Compared
MUpro, ThermoNet

Not reviewed yet.

Condel and FATHMM-MKL: 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 FATHMM-MKL above Condel in 5 of 5 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks Condel above FATHMM-MKL in 7 of 7 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank Condel above FATHMM-MKL in 7 of their 12 comparisons and FATHMM-MKL higher in 5. Of those papers, Clinical likelihood ratios and balanced… ranks FATHMM-MKL higher on its own (5 of 5).

Comparisons in which each paper scores Condel or FATHMM-MKL higher2 other papers: Condel higher in 7, FATHMM-MKL higher in 5, 0 ties.2 other papers7 Condel higher75 FATHMM-MKL higher5
Condel higherTieFATHMM-MKL higher
Compared
Condel, FATHMM-MKL

Not reviewed yet.

MetaSVM and MutFormer: 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 MutFormer above MetaSVM in 7 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks MetaSVM above MutFormer in 4 of 5 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank MetaSVM above MutFormer in 4 of their 13 comparisons and MutFormer higher in 8; 1 is a tie. Of those papers, Livesey and Marsh 2025 ranks MutFormer higher on its own (7 of 7).

Comparisons in which each paper scores MetaSVM or MutFormer higher2 other papers: MetaSVM higher in 4, MutFormer higher in 8, 1 tie.2 other papers4 MetaSVM higher41 tie8 MutFormer higher8
MetaSVM higherTieMutFormer higher
Compared
MetaSVM, MutFormer

Not reviewed yet.

FATHMM and LRT: Comprehensive assessment of computational algorithms in predicting cancer driver mutations and Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) disagree

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

Comprehensive assessment of computational algorithms in predicting cancer driver mutations ranks LRT above FATHMM in 18 of 20 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks FATHMM above LRT in 6 of 7 comparisons. No other study gives a verdict, so neither is the outlier.

3 papers rank FATHMM above LRT in 10 of their 33 comparisons and LRT higher in 23. Of those papers, Comprehensive assessment…, Clinical likelihood ratios and balanced… rank LRT higher on their own (18 of 20, 4 of 6).

Comparisons in which each paper scores FATHMM or LRT higher3 other papers: FATHMM higher in 10, LRT higher in 23, 0 ties.3 other papers10 FATHMM higher1023 LRT higher23
FATHMM higherTieLRT higher
Compared
FATHMM, LRT

Not reviewed yet.

LRT and M-CAP: Comprehensive assessment of computational algorithms in predicting cancer driver mutations and Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) disagree

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

Comprehensive assessment of computational algorithms in predicting cancer driver mutations ranks LRT above M-CAP in 16 of 20 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks M-CAP above LRT in 7 of 7 comparisons. No other study gives a verdict, so neither is the outlier.

3 papers rank LRT above M-CAP in 18 of their 31 comparisons and M-CAP higher in 13. Of those papers, Livesey and Marsh 2025 ranks M-CAP higher on its own (7 of 7).

Comparisons in which each paper scores LRT or M-CAP higher3 other papers: LRT higher in 18, M-CAP higher in 13, 0 ties.3 other papers18 LRT higher1813 M-CAP higher13
LRT higherTieM-CAP higher
Compared
LRT, M-CAP

Not reviewed yet.

PhyloGPN and Caduceus: A Phylogenetic Approach to Genomic Language Modeling and GUANinE v1.1 reveals complementarity of supervised and genomic language models disagree

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

A Phylogenetic Approach to Genomic Language Modeling ranks PhyloGPN above Caduceus in 12 of 12 comparisons; GUANinE v1.1 reveals complementarity of supervised and genomic language models ranks Caduceus above PhyloGPN in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank PhyloGPN above Caduceus in 12 of their 18 comparisons and Caduceus higher in 6. Of those papers, GUANinE v1.1 reveals complementarity… ranks Caduceus higher on its own (6 of 6).

Comparisons in which each paper scores PhyloGPN or Caduceus higher2 other papers: PhyloGPN higher in 12, Caduceus higher in 6, 0 ties.2 other papers12 PhyloGPN higher126 Caduceus higher6
PhyloGPN higherTieCaduceus higher
Compared
PhyloGPN, Caduceus

Not reviewed yet.

MutFormer and MutPred: 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 MutFormer above MutPred in 6 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks MutPred above MutFormer in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank MutFormer above MutPred in 6 of their 13 comparisons and MutPred higher in 7. Of those papers, An openly licensed benchmark… ranks MutPred higher on its own (6 of 6).

Comparisons in which each paper scores MutFormer or MutPred higher2 other papers: MutFormer higher in 6, MutPred higher in 7, 0 ties.2 other papers6 MutFormer higher67 MutPred higher7
MutFormer higherTieMutPred higher
Compared
MutFormer, MutPred

Not reviewed yet.

FATHMM-XF and PrimateAI: Comprehensive assessment of computational algorithms in predicting cancer driver mutations and Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) disagree

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

Comprehensive assessment of computational algorithms in predicting cancer driver mutations ranks PrimateAI above FATHMM-XF in 15 of 19 comparisons; Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) ranks FATHMM-XF above PrimateAI in 7 of 7 comparisons. No other study gives a verdict, so neither is the outlier.

3 papers rank FATHMM-XF above PrimateAI in 14 of their 33 comparisons and PrimateAI higher in 17; 2 are ties. Of those papers, Comprehensive assessment… ranks PrimateAI higher on its own (15 of 20).

Comparisons in which each paper scores FATHMM-XF or PrimateAI higher3 other papers: FATHMM-XF higher in 14, PrimateAI higher in 17, 2 ties.3 other papers14 FATHMM-XF higher142 tie17 PrimateAI higher17
FATHMM-XF higherTiePrimateAI higher
Compared
FATHMM-XF, PrimateAI

Not reviewed yet.

MutPred 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 VEST4 above MutPred in 6 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks MutPred above VEST4 in 6 of 6 comparisons. No other study gives a verdict, so neither is the outlier.

4 papers rank MutPred above VEST4 in 14 of their 29 comparisons and VEST4 higher in 14; 1 is a tie. Of those papers, Livesey and Marsh 2025, Clinical likelihood ratios and balanced… rank VEST4 higher on their own (6 of 7, 4 of 6).

Comparisons in which each paper scores MutPred or VEST4 higher4 other papers: MutPred higher in 14, VEST4 higher in 14, 1 tie.4 other papers14 MutPred higher141 tie14 VEST4 higher14
MutPred higherTieVEST4 higher
Compared
MutPred, VEST4

Not reviewed yet.

MutFormer and phyloP: 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 MutFormer above phyloP in 7 of 7 comparisons; An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers ranks phyloP above MutFormer in 4 of 5 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank MutFormer above phyloP in 8 of their 13 comparisons and phyloP higher in 4; 1 is a tie. Of those papers, An openly licensed benchmark… ranks phyloP higher on its own (4 of 6).

Comparisons in which each paper scores MutFormer or phyloP higher2 other papers: MutFormer higher in 8, phyloP higher in 4, 1 tie.2 other papers8 MutFormer higher81 tie4 phyloP higher4
MutFormer higherTiephyloP higher
Compared
MutFormer, phyloP

Not reviewed yet.

DNABERT and RNABERT: Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications and Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning disagree

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

Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications ranks DNABERT above RNABERT in 12 of 12 comparisons; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning ranks RNABERT above DNABERT in 24 of 26 comparisons. No other study gives a verdict, so neither is the outlier.

2 papers rank DNABERT above RNABERT in 14 of their 42 comparisons and RNABERT higher in 24; 4 are ties. Of those papers, Zero-shot benchmarking of RNA language… ranks RNABERT higher on its own (24 of 30).

Comparisons in which each paper scores DNABERT or RNABERT higher2 other papers: DNABERT higher in 14, RNABERT higher in 24, 4 ties.2 other papers14 DNABERT higher144 tie424 RNABERT higher24
DNABERT higherTieRNABERT higher
Compared
DNABERT, RNABERT

Not reviewed yet.

First page · Next page