Protocol
ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)
Separate pathogenic from benign ClinVar SNVs within each variant type, scored by AUROC on the variants every compared model scores.
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
132 recorded evaluations, 132 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
132 evaluations · 132 results. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.
Methods and evaluation design
Procedure, tasks and evaluated configurations
Recorded evaluations
Each evaluation records what was tested and under which conditions.
- AlphaGenome on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- DNABERT2 on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- Evo2 on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- GPN-MSA on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- Nucleotide Transformer on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- PhyloGPN on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- PhyloP on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- Rule-based on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- AlphaGenome on ClinVar Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- DNABERT2 on ClinVar Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- Evo2 on ClinVar Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- GPN-MSA on ClinVar Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
Baseline coverage
Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.
0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.
No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.
- External evaluations
- 132
Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.
Null control
Proposed control: requires review
Select a task-valid null control after reviewing inputs and metric
Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.
This is a suggested selection rule, not a validated method or a measured score.
Conventional reference
Proposed control: requires review
Select an upstream conventional reference after reviewing the full protocol
Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.
This is a suggested selection rule, not a validated method or a measured score.
Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)
Coverage is derived from release 2026-11-02-a7f03c9e55a5. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.
Run instructions
No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
0 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
1 source record and release history
- Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2) · Original source · bioRxiv preprint version 2, posted 2025-09-10 (version 1 posted 2025-09-08); full-text PDF (21 pages)
Technical metadata and extraction receipts
Stable ID: lu-hetero-20261019-protocol-clinvar-variant-type-auroc
- areas
- dna-genomes
- contexts
- clinical_research
- metric
- auroc
- metric direction
- higher
- protocol
- AUROC per variant group; scores multiplied by -1 where lower means more pathogenic (Evo2, GPN-MSA, PhyloGPN, ESM models); within each group, variants missing a score from any compared model are excluded, except stop-gains for PrimateAI-3D (19,795 of 42,408 scored).
- source locator
- Methods 'Calculating and comparing AUROC scores' (pages 12 to 13); Figure 1 legend
- limitations
- Canonical splice site is defined as intronic within 1 to 2 nt of an exon boundary.; Groups such as 'Missense & 3'UTR' hold variants with different effects on different transcripts.; No confidence intervals.; Benign ClinVar labels can be informed by some of the evaluated predictors; the paper does not address label circularity.
- task link exemption
- No task or benchmark in the store covers ClinVar pathogenicity across all variant types; left unlinked on purpose so the discrepancy rules treat its scope as unknown rather than guess (#208). Reviewed 2026-11-01.
Related records
- uses data: Lu et al. 2025 ClinVar SNV variant-type benchmark (259,600 SNVs)
- assessment: AlphaGenome on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- assessment: Rule-based on ClinVar All variants SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaGenome on ClinVar Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaGenome on ClinVar Missense SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaMissense on ClinVar Missense SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaGenome on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaMissense on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM1b on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM1v on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM2 on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: PrimateAI-3D on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaGenome on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaMissense on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM1b on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM1v on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM2 on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: PrimateAI-3D on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar Missense SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM1b on ClinVar Missense SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM1v on ClinVar Missense SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM2 on ClinVar Missense SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar Missense SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar Missense SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar Missense SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar Missense SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar Missense SNVs (Lu et al. 2025 Figure 1)
- assessment: PrimateAI-3D on ClinVar Missense SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaGenome on ClinVar Noncoding SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar Noncoding SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar Noncoding SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar Noncoding SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar Noncoding SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar Noncoding SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar Noncoding SNVs (Lu et al. 2025 Figure 1)
- assessment: Rule-based on ClinVar Noncoding SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaGenome on ClinVar RNA gene SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar RNA gene SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar RNA gene SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar RNA gene SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar RNA gene SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar RNA gene SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar RNA gene SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaGenome on ClinVar Splice SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar Splice SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar Splice SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar Splice SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar Splice SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar Splice SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar Splice SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaGenome All outputs (quantile) on ClinVar splice variants (Lu et al. 2025 Supplementary Figure S2)
- assessment: AlphaGenome Splice junction (quantile) on ClinVar splice variants (Lu et al. 2025 Supplementary Figure S2)
- assessment: AlphaGenome Splice junction (raw) on ClinVar splice variants (Lu et al. 2025 Supplementary Figure S2)
- assessment: AlphaGenome All splice outputs (quantile) on ClinVar splice variants (Lu et al. 2025 Supplementary Figure S2)
- assessment: AlphaGenome All splice outputs (raw) on ClinVar splice variants (Lu et al. 2025 Supplementary Figure S2)
- assessment: AlphaGenome Splice site (quantile) on ClinVar splice variants (Lu et al. 2025 Supplementary Figure S2)
- assessment: AlphaGenome Splice site (raw) on ClinVar splice variants (Lu et al. 2025 Supplementary Figure S2)
- assessment: AlphaGenome Splice site usage (quantile) on ClinVar splice variants (Lu et al. 2025 Supplementary Figure S2)
- assessment: AlphaGenome Splice site usage (raw) on ClinVar splice variants (Lu et al. 2025 Supplementary Figure S2)
- assessment: AlphaGenome on ClinVar Start loss SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar Start loss SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM1b on ClinVar Start loss SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM1v on ClinVar Start loss SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM2 on ClinVar Start loss SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar Start loss SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar Start loss SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar Start loss SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar Start loss SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar Start loss SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaGenome on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaMissense on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM1b on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM1v on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1)
- assessment: ESM2 on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1)
- assessment: PrimateAI-3D* on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaGenome on ClinVar Stop loss SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar Stop loss SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar Stop loss SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar Stop loss SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar Stop loss SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar Stop loss SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar Stop loss SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaGenome on ClinVar Synonymous SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar Synonymous SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar Synonymous SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar Synonymous SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar Synonymous SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar Synonymous SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar Synonymous SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaGenome on ClinVar 3' UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar 3' UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar 3' UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar 3' UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar 3' UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar 3' UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar 3' UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: AlphaGenome on ClinVar 5' UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: DNABERT2 on ClinVar 5' UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: Evo2 on ClinVar 5' UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: GPN-MSA on ClinVar 5' UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: Nucleotide Transformer on ClinVar 5' UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloGPN on ClinVar 5' UTR SNVs (Lu et al. 2025 Figure 1)
- assessment: PhyloP on ClinVar 5' UTR SNVs (Lu et al. 2025 Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: All variants (Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: Intron (Non-splice) (Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: Missense (Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: Missense & Intron (Non-splice) (Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: Missense & 3'UTR (Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: Noncoding (Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: RNA gene (Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: Splice (Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: splice variants scored by AlphaGenome (Supplementary Figure S2)
- used in: Lu et al. 2025 ClinVar benchmark: Start loss (Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: Stop gain (Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: Stop loss (Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: Synonymous (Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: 3' UTR (Figure 1)
- used in: Lu et al. 2025 ClinVar benchmark: 5' UTR (Figure 1)