rewirebio.iobenchmarks
Contested result

GPN-MSA and phyloP: TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) reverses the order

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

TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym) ranks phyloP above GPN-MSA in 2 of 2 comparisons; 2 of 2 other studies rank GPN-MSA above phyloP.

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 GPN-MSA above phyloP in 59 of their 67 comparisons and phyloP higher in 2; 6 are ties. TraitGym official metrics ranks phyloP above GPN-MSA in all 2 of its comparisons.

Papers grouped by which system they rank higher: GPN-MSA or phyloPRank GPN-MSA higher: Genome modelling and design across all…, Genomic heterogeneity inflates…. Rank phyloP higher: TraitGym official metrics (disagrees). Mixed: GUANinE v1.1 reveals complementarity….Rank GPN-MSA higherMixedRank phyloP higherGenome modelling anddesign across all…Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026)Genomic heterogeneityinflates…Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GUANinE v1.1 revealscomplementarity…GUANinE v1.1 reveals complementarity of supervised and genomic language modelsTraitGym official metricsTraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym)
  • Rank GPN-MSA higher (2): Genome modelling and design across all…, Genomic heterogeneity inflates…
  • Rank phyloP higher (1): TraitGym official metrics (disagrees)
  • Mixed (1): GUANinE v1.1 reveals complementarity…

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 GPN-MSA or phyloP higherTraitGym official metrics (disagrees): GPN-MSA higher in 0, phyloP higher in 2, 0 ties. Genome modelling and design across all…: GPN-MSA higher in 46, phyloP higher in 2, 4 ties. Genomic heterogeneity inflates…: GPN-MSA higher in 13, phyloP higher in 0, 1 tie. GUANinE v1.1 reveals complementarity…: GPN-MSA higher in 0, phyloP higher in 0, 1 tie.Disagrees: TraitGym official metricsTraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym)2 phyloP higher2Genome modelling and design across all…Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026)46 GPN-MSA higher464 tie2 phyloP higherGenomic heterogeneity inflates…Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)13 GPN-MSA higher131 tieGUANinE v1.1 reveals complementarity…GUANinE v1.1 reveals complementarity of supervised and genomic language models1 tie1
GPN-MSA higherTiephyloP higherNumbers are counts of comparisons; the outlined bar is the paper that disagrees.
Comparisons in TraitGym official metrics (2)
ProtocolDatasetMetricGPN-MSAphyloPHigher
TraitGym Complex traits, zero-shot, AUPRC by chromosome weighted averageTraitGym Complex traits, matched 9 controlsAUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all'), unitless0.2240.227phyloP
TraitGym Mendelian traits, zero-shot, AUPRC by chromosome weighted averageTraitGym Mendelian traits, matched 9 controlsAUPRC (weighted average over chromosomes of per-chromosome AUPRC; subset 'all'), unitless0.6540.696phyloP
Comparisons in Genome modelling and design across all… (52)
ProtocolDatasetMetricGPN-MSAphyloPHigher
Zero-shot BRCA1 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUPRC (zero-shot; BRCA1 'Both' (coding and noncoding) SNVs), unitless0.650.495GPN-MSA
Zero-shot BRCA1 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUROC (zero-shot; BRCA1 'Both' (coding and noncoding) SNVs), unitless0.8630.811GPN-MSA
Zero-shot BRCA1 coding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUPRC (zero-shot; BRCA1 coding SNVs), unitless0.5790.454GPN-MSA
Zero-shot BRCA1 coding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUROC (zero-shot; BRCA1 coding SNVs), unitless0.8330.781GPN-MSA
Zero-shot BRCA1 intronic SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUPRC (zero-shot; BRCA1 intronic SNVs), unitless0.09730.084GPN-MSA
Zero-shot BRCA1 intronic SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUROC (zero-shot; BRCA1 intronic SNVs), unitless0.6530.637GPN-MSA
Zero-shot BRCA1 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUPRC (zero-shot; BRCA1 noncoding SNVs), unitless0.7750.709GPN-MSA
Zero-shot BRCA1 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUROC (zero-shot; BRCA1 noncoding SNVs), unitless0.9180.898GPN-MSA
Zero-shot BRCA1 splice region SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUPRC (zero-shot; BRCA1 splice region SNVs), unitless0.8320.784GPN-MSA
Zero-shot BRCA1 splice region SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA1 saturation genome editing SNVs, Findlay et al. 2018 classes (Brixi et al. 2026)AUROC (zero-shot; BRCA1 splice region SNVs), unitless0.8910.873GPN-MSA
Zero-shot BRCA2 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA2 SNVs with functional classifications, Huang et al. 2025 (Brixi et al. 2026)AUPRC (zero-shot; BRCA2 'Both' (coding and noncoding) SNVs), unitless0.570.397GPN-MSA
Zero-shot BRCA2 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA2 SNVs with functional classifications, Huang et al. 2025 (Brixi et al. 2026)AUROC (zero-shot; BRCA2 'Both' (coding and noncoding) SNVs), unitless0.8380.76GPN-MSA
Zero-shot BRCA2 coding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA2 SNVs with functional classifications, Huang et al. 2025 (Brixi et al. 2026)AUPRC (zero-shot; BRCA2 coding SNVs), unitless0.4460.325GPN-MSA
Zero-shot BRCA2 coding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA2 SNVs with functional classifications, Huang et al. 2025 (Brixi et al. 2026)AUROC (zero-shot; BRCA2 coding SNVs), unitless0.80.752GPN-MSA
Zero-shot BRCA2 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA2 SNVs with functional classifications, Huang et al. 2025 (Brixi et al. 2026)AUPRC (zero-shot; BRCA2 noncoding SNVs), unitless0.8350.828Tie
Zero-shot BRCA2 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)BRCA2 SNVs with functional classifications, Huang et al. 2025 (Brixi et al. 2026)AUROC (zero-shot; BRCA2 noncoding SNVs), unitless0.9050.888GPN-MSA
Zero-shot ClinVar 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar 'Both' (coding and noncoding) SNVs), unitless0.9440.886GPN-MSA
Zero-shot ClinVar 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar 'Both' (coding and noncoding) SNVs), unitless0.9590.919GPN-MSA
Zero-shot ClinVar coding SNVs classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar coding SNVs), unitless0.9320.906GPN-MSA
Zero-shot ClinVar coding SNVs classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar coding SNVs), unitless0.8960.857GPN-MSA
Zero-shot ClinVar coding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar coding SNVs, far from splice site), unitless0.9290.903GPN-MSA
Zero-shot ClinVar coding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar coding SNVs, far from splice site), unitless0.8960.857GPN-MSA
Zero-shot ClinVar coding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar coding SNVs, highly conserved), unitless0.9410.922GPN-MSA
Zero-shot ClinVar coding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar coding SNVs, highly conserved), unitless0.8240.783GPN-MSA
Zero-shot ClinVar coding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar coding SNVs, moderately conserved), unitless0.7480.374GPN-MSA
Zero-shot ClinVar coding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar coding SNVs, moderately conserved), unitless0.8660.579GPN-MSA
Zero-shot ClinVar coding SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar coding SNVs, near splice site), unitless0.9620.939GPN-MSA
Zero-shot ClinVar coding SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar coding SNVs, near splice site), unitless0.8960.846GPN-MSA
Zero-shot ClinVar coding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar coding SNVs, not conserved), unitless0.7620.155GPN-MSA
Zero-shot ClinVar coding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar coding SNVs, not conserved), unitless0.9160.571GPN-MSA
Zero-shot ClinVar coding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar coding SNVs, poorly conserved), unitless0.7080.224GPN-MSA
Zero-shot ClinVar coding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar coding SNVs, poorly conserved), unitless0.8820.531GPN-MSA
Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs), unitless0.360.341GPN-MSA
Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs), unitless0.9150.876GPN-MSA
Zero-shot ClinVar noncoding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, far from splice site), unitless0.1320.106GPN-MSA
Zero-shot ClinVar noncoding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, far from splice site), unitless0.7230.691GPN-MSA
Zero-shot ClinVar noncoding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, highly conserved), unitless0.9940.991Tie
Zero-shot ClinVar noncoding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, highly conserved), unitless0.9510.934GPN-MSA
Zero-shot ClinVar noncoding SNVs, intergenic classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, intergenic), unitless0.870.882phyloP
Zero-shot ClinVar noncoding SNVs, intergenic classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, intergenic), unitless0.8840.927phyloP
Zero-shot ClinVar noncoding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, moderately conserved), unitless0.4050.164GPN-MSA
Zero-shot ClinVar noncoding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, moderately conserved), unitless0.8280.697GPN-MSA
Zero-shot ClinVar noncoding SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, near splice site), unitless0.9940.994Tie
Zero-shot ClinVar noncoding SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, near splice site), unitless0.9770.978Tie
Zero-shot ClinVar noncoding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, not conserved), unitless0.05410.0159GPN-MSA
Zero-shot ClinVar noncoding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, not conserved), unitless0.6860.605GPN-MSA
Zero-shot ClinVar noncoding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUPRC (zero-shot; ClinVar noncoding SNVs, poorly conserved), unitless0.130.026GPN-MSA
Zero-shot ClinVar noncoding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)ClinVar October 2024 release, filtered (Brixi et al. 2026)AUROC (zero-shot; ClinVar noncoding SNVs, poorly conserved), unitless0.7060.547GPN-MSA
Zero-shot SpliceVarDB 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)SpliceVarDB experimentally validated splice variants (Brixi et al. 2026)AUPRC (zero-shot; SpliceVarDB 'Both' (coding and noncoding) SNVs), unitless0.8460.806GPN-MSA
Zero-shot SpliceVarDB 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)SpliceVarDB experimentally validated splice variants (Brixi et al. 2026)AUROC (zero-shot; SpliceVarDB 'Both' (coding and noncoding) SNVs), unitless0.790.76GPN-MSA
Zero-shot SpliceVarDB exonic SNVs classification (Evo 2 paper, Supplementary Data 1)SpliceVarDB experimentally validated splice variants (Brixi et al. 2026)AUPRC (zero-shot; SpliceVarDB exonic SNVs), unitless0.5480.498GPN-MSA
Zero-shot SpliceVarDB exonic SNVs classification (Evo 2 paper, Supplementary Data 1)SpliceVarDB experimentally validated splice variants (Brixi et al. 2026)AUROC (zero-shot; SpliceVarDB exonic SNVs), unitless0.6750.631GPN-MSA
Comparisons in Genomic heterogeneity inflates… (14)
ProtocolDatasetMetricGPN-MSAphyloPHigher
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: All variants (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, All variants), unitless0.960.908GPN-MSA
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: Intron (Non-splice) (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, Intron (Non-splice)), unitless0.8850.852GPN-MSA
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: Missense (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, Missense), unitless0.9060.856GPN-MSA
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: Missense & Intron (Non-splice) (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, Missense & Intron (Non-splice)), unitless0.8960.868GPN-MSA
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: Missense & 3'UTR (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, Missense & 3'UTR), unitless0.8870.853GPN-MSA
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: Noncoding (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, Noncoding), unitless0.9810.976Tie
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: RNA gene (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, RNA gene), unitless0.9380.882GPN-MSA
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: Splice (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, Splice), unitless0.7750.727GPN-MSA
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: Start loss (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, Start loss), unitless0.7690.675GPN-MSA
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: Stop gain (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, Stop gain), unitless0.7830.704GPN-MSA
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: Stop loss (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, Stop loss), unitless0.8880.796GPN-MSA
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: Synonymous (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, Synonymous), unitless0.8820.855GPN-MSA
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: 3' UTR (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, 3' UTR), unitless0.9080.862GPN-MSA
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)Lu et al. 2025 ClinVar benchmark: 5' UTR (Figure 1)AUROC (ClinVar pathogenic vs benign SNVs, 5' UTR), unitless0.7280.696GPN-MSA
Comparisons in GUANinE v1.1 reveals complementarity… (1)
ProtocolDatasetMetricGPN-MSAphyloPHigher
GUANinE v1.1 clinvar-snv, Spearman rho x100 (Table 4)GUANinE clinvar-snv test setSpearman (GUANinE v1.1 test set), unitless80.781.5Tie

What disagrees

Other studies
rank GPN-MSA above phyloP in 59 of 61 comparisons
This study
ranks phyloP above GPN-MSA in 2 of 2 comparisons
Compared
GPN-MSA, phyloP
Study that disagrees
TraitGym official metrics: AUPRC by chromosome, weighted average (Hugging Face dataset songlab/TraitGym)
Other studies
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026), Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026), Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)
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 other studies (122 results)
In the other studies
StudyToolProtocol or benchmarkMetricValue
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA1 'Both' (coding and noncoding) SNVs)0.65
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA1 'Both' (coding and noncoding) SNVs)0.863
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 coding SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA1 coding SNVs)0.579
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 coding SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA1 coding SNVs)0.833
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 intronic SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA1 intronic SNVs)0.097
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 intronic SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA1 intronic SNVs)0.653
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA1 noncoding SNVs)0.775
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA1 noncoding SNVs)0.918
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 splice region SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA1 splice region SNVs)0.832
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 splice region SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA1 splice region SNVs)0.891
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA2 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA2 'Both' (coding and noncoding) SNVs)0.57
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA2 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA2 'Both' (coding and noncoding) SNVs)0.838
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA2 coding SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA2 coding SNVs)0.446
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA2 coding SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA2 coding SNVs)0.8
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot BRCA2 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA2 noncoding SNVs)0.905
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar 'Both' (coding and noncoding) SNVs)0.944
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar 'Both' (coding and noncoding) SNVs)0.959
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs)0.932
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs)0.896
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs, far from splice site)0.929
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs, far from splice site)0.896
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs, highly conserved)0.941
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs, highly conserved)0.824
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs, moderately conserved)0.748
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs, moderately conserved)0.866
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs, near splice site)0.962
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs, near splice site)0.896
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs, not conserved)0.762
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs, not conserved)0.916
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs, poorly conserved)0.708
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs, poorly conserved)0.882
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs)0.36
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs)0.915
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar noncoding SNVs, far from splice site)0.132
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar noncoding SNVs, far from splice site)0.723
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar noncoding SNVs, highly conserved)0.951
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, intergenic classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar noncoding SNVs, intergenic)0.87
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, intergenic classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar noncoding SNVs, intergenic)0.884
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar noncoding SNVs, moderately conserved)0.405
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar noncoding SNVs, moderately conserved)0.828
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar noncoding SNVs, not conserved)0.054
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar noncoding SNVs, not conserved)0.686
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar noncoding SNVs, poorly conserved)0.13
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar noncoding SNVs, poorly conserved)0.706
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot SpliceVarDB 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; SpliceVarDB 'Both' (coding and noncoding) SNVs)0.846
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot SpliceVarDB 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; SpliceVarDB 'Both' (coding and noncoding) SNVs)0.79
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot SpliceVarDB exonic SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; SpliceVarDB exonic SNVs)0.548
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLGPN-MSA (Evo 2 paper variant effect evaluations)Zero-shot SpliceVarDB exonic SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; SpliceVarDB exonic SNVs)0.675
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA1 'Both' (coding and noncoding) SNVs)0.495
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA1 'Both' (coding and noncoding) SNVs)0.811
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 coding SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA1 coding SNVs)0.454
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 coding SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA1 coding SNVs)0.781
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 intronic SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA1 intronic SNVs)0.084
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 intronic SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA1 intronic SNVs)0.637
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA1 noncoding SNVs)0.709
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA1 noncoding SNVs)0.898
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 splice region SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA1 splice region SNVs)0.784
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA1 splice region SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA1 splice region SNVs)0.873
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA2 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA2 'Both' (coding and noncoding) SNVs)0.397
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA2 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA2 'Both' (coding and noncoding) SNVs)0.76
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA2 coding SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; BRCA2 coding SNVs)0.325
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA2 coding SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA2 coding SNVs)0.752
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot BRCA2 noncoding SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; BRCA2 noncoding SNVs)0.888
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar 'Both' (coding and noncoding) SNVs)0.886
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar 'Both' (coding and noncoding) SNVs)0.919
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs)0.906
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs)0.857
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs, far from splice site)0.903
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs, far from splice site)0.857
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs, highly conserved)0.922
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs, highly conserved)0.783
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs, moderately conserved)0.374
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs, moderately conserved)0.579
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs, near splice site)0.939
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, near splice site classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs, near splice site)0.846
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs, not conserved)0.155
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs, not conserved)0.571
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar coding SNVs, poorly conserved)0.224
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar coding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar coding SNVs, poorly conserved)0.531
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs)0.341
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs)0.876
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar noncoding SNVs, far from splice site)0.106
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, far from splice site classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar noncoding SNVs, far from splice site)0.691
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar noncoding SNVs, highly conserved)0.934
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, intergenic classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar noncoding SNVs, intergenic)0.882
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, intergenic classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar noncoding SNVs, intergenic)0.927
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar noncoding SNVs, moderately conserved)0.164
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, moderately conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar noncoding SNVs, moderately conserved)0.697
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar noncoding SNVs, not conserved)0.016
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, not conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar noncoding SNVs, not conserved)0.605
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; ClinVar noncoding SNVs, poorly conserved)0.026
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot ClinVar noncoding SNVs, poorly conserved classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; ClinVar noncoding SNVs, poorly conserved)0.547
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot SpliceVarDB 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; SpliceVarDB 'Both' (coding and noncoding) SNVs)0.806
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot SpliceVarDB 'Both' (coding and noncoding) SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; SpliceVarDB 'Both' (coding and noncoding) SNVs)0.76
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot SpliceVarDB exonic SNVs classification (Evo 2 paper, Supplementary Data 1)AUPRC (zero-shot; SpliceVarDB exonic SNVs)0.498
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026); evo2: Journal full-text XMLPhyloP 100 (Evo 2 paper variant effect evaluations)Zero-shot SpliceVarDB exonic SNVs classification (Evo 2 paper, Supplementary Data 1)AUROC (zero-shot; SpliceVarDB exonic SNVs)0.631
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GPN-MSA precomputed hg38 scores (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, All variants)0.96
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)PhyloP 100-way vertebrate (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, All variants)0.908
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GPN-MSA precomputed hg38 scores (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Intron (Non-splice))0.885
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)PhyloP 100-way vertebrate (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Intron (Non-splice))0.852
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GPN-MSA precomputed hg38 scores (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Missense & Intron (Non-splice))0.896
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)PhyloP 100-way vertebrate (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Missense & Intron (Non-splice))0.868
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GPN-MSA precomputed hg38 scores (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Missense & 3'UTR)0.887
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)PhyloP 100-way vertebrate (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Missense & 3'UTR)0.853
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GPN-MSA precomputed hg38 scores (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Missense)0.906
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)PhyloP 100-way vertebrate (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Missense)0.856
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GPN-MSA precomputed hg38 scores (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, RNA gene)0.938
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)PhyloP 100-way vertebrate (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, RNA gene)0.882
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GPN-MSA precomputed hg38 scores (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Splice)0.775
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)PhyloP 100-way vertebrate (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Splice)0.727
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GPN-MSA precomputed hg38 scores (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Start loss)0.769
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)PhyloP 100-way vertebrate (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Start loss)0.675
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GPN-MSA precomputed hg38 scores (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Stop gain)0.783
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)PhyloP 100-way vertebrate (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Stop gain)0.704
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GPN-MSA precomputed hg38 scores (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Stop loss)0.888
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)PhyloP 100-way vertebrate (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Stop loss)0.796
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GPN-MSA precomputed hg38 scores (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Synonymous)0.882
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)PhyloP 100-way vertebrate (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, Synonymous)0.855
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GPN-MSA precomputed hg38 scores (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, 3' UTR)0.908
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)PhyloP 100-way vertebrate (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, 3' UTR)0.862
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)GPN-MSA precomputed hg38 scores (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, 5' UTR)0.728
Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2)PhyloP 100-way vertebrate (Lu et al. 2025)ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)AUROC (ClinVar pathogenic vs benign SNVs, 5' UTR)0.696

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-8028d0bd151d6c00 · All contested results · How findings are made and followed up