Protocol

ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4)

AUROC of zero-shot variant scores for ClinVar 'Pathogenic' versus gnomAD common missense variants.

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.

17 recorded evaluations, 34 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

17 evaluations · 34 results. Different protocols are not a single leaderboard.

Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) · Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)

Sorted by AUROC (maximum over three random seeds; zero-shot) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	AUROC (maximum over three random seeds; zero-shot)	AUROC (mean over three random seeds; zero-shot)
GPN-MSA ablation 'Default' (Supplementary Table 4)Evaluation	0.969 (best in column)	0.969 (best in column)
GPN-MSA ablation 'Window size = 256' (Supplementary Table 4)Evaluation	0.969 (best in column)	0.969 (best in column)
GPN-MSA ablation 'Window size = 64' (Supplementary Table 4)Evaluation	0.968	0.968
GPN-MSA ablation '51 vertebrates' (Supplementary Table 4)Evaluation	0.967	0.967
GPN-MSA ablation 'Don’t replace non-conserved' (Supplementary Table 4)Evaluation	0.967	0.966
GPN-MSA ablation 'Don’t upweight conserved' (Supplementary Table 4)Evaluation	0.967	0.967
GPN-MSA ablation 'Window size = 32' (Supplementary Table 4)Evaluation	0.967	0.967
GPN-MSA ablation '51 mammals' (Supplementary Table 4)Evaluation	0.965	0.964
GPN-MSA ablation 'Window size = 16' (Supplementary Table 4)Evaluation	0.965	0.964
GPN-MSA ablation 'Train on 50% most conserved' (Supplementary Table 4)Evaluation	0.963	0.963
GPN-MSA ablation 'Train on 100% of genome' (Supplementary Table 4)Evaluation	0.961	0.96
GPN-MSA ablation 'Window size = 8' (Supplementary Table 4)Evaluation	0.961	0.961
GPN-MSA ablation 'Include closest primates' (Supplementary Table 4)Evaluation	0.956	0.954
MSA frequencyEvaluation	0.95	0.95
GPN-MSA ablation 'Window size = 4' (Supplementary Table 4)Evaluation	0.943	0.942
Combined phyloP and phastConsEvaluation	0.928	0.928
GPN-MSA ablation 'w/o MSA' (Supplementary Table 4)Evaluation	0.585	0.584

All 34 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: GPN-MSA ablation '51 mammals' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.965 AUROC (maximum over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 51 mammals on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row '51 mammals', column 'ClinVar' / 'max'
Configuration: GPN-MSA ablation '51 mammals' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.964 AUROC (mean over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 51 mammals on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row '51 mammals', column 'ClinVar' / 'mean'
Configuration: GPN-MSA ablation '51 vertebrates' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.967 AUROC (maximum over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 51 vertebrates on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row '51 vertebrates', column 'ClinVar' / 'max'
Configuration: GPN-MSA ablation '51 vertebrates' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.967 AUROC (mean over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 51 vertebrates on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row '51 vertebrates', column 'ClinVar' / 'mean'
Configuration: GPN-MSA ablation 'Default' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.969 AUROC (maximum over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Default on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Default', column 'ClinVar' / 'max'
Configuration: GPN-MSA ablation 'Default' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.969 AUROC (mean over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Default on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Default', column 'ClinVar' / 'mean'
Configuration: GPN-MSA ablation 'Include closest primates' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.956 AUROC (maximum over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Include closest primates on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Include closest primates', column 'ClinVar' / 'max'
Configuration: GPN-MSA ablation 'Include closest primates' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.954 AUROC (mean over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Include closest primates on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Include closest primates', column 'ClinVar' / 'mean'
Method: MSA frequency	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.95 AUROC (maximum over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source MSA frequency (no neural net) on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'MSA frequency (no neural net)', column 'ClinVar' / 'max'
Method: MSA frequency	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.95 AUROC (mean over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source MSA frequency (no neural net) on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'MSA frequency (no neural net)', column 'ClinVar' / 'mean'
Configuration: GPN-MSA ablation 'Don’t replace non-conserved' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.967 AUROC (maximum over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Don’t replace non-conserved on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Don’t replace non-conserved', column 'ClinVar' / 'max'
Configuration: GPN-MSA ablation 'Don’t replace non-conserved' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.966 AUROC (mean over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Don’t replace non-conserved on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Don’t replace non-conserved', column 'ClinVar' / 'mean'
Configuration: GPN-MSA ablation 'Don’t upweight conserved' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.967 AUROC (maximum over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Don’t upweight conserved on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Don’t upweight conserved', column 'ClinVar' / 'max'
Configuration: GPN-MSA ablation 'Don’t upweight conserved' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.967 AUROC (mean over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Don’t upweight conserved on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Don’t upweight conserved', column 'ClinVar' / 'mean'
Method: Combined phyloP and phastCons	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.928 AUROC (maximum over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Combined phyloP and phastCons on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Combined phyloP and phastCons', column 'ClinVar' / 'max'
Method: Combined phyloP and phastCons	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.928 AUROC (mean over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Combined phyloP and phastCons on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Combined phyloP and phastCons', column 'ClinVar' / 'mean'
Configuration: GPN-MSA ablation 'Train on 100% of genome' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.961 AUROC (maximum over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Train on 100% of genome on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Train on 100% of genome', column 'ClinVar' / 'max'
Configuration: GPN-MSA ablation 'Train on 100% of genome' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.96 AUROC (mean over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Train on 100% of genome on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Train on 100% of genome', column 'ClinVar' / 'mean'
Configuration: GPN-MSA ablation 'Train on 50% most conserved' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.963 AUROC (maximum over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Train on 50% most conserved on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Train on 50% most conserved', column 'ClinVar' / 'max'
Configuration: GPN-MSA ablation 'Train on 50% most conserved' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.963 AUROC (mean over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Train on 50% most conserved on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Train on 50% most conserved', column 'ClinVar' / 'mean'
Configuration: GPN-MSA ablation 'Window size = 16' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.965 AUROC (maximum over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Window size = 16 on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Window size = 16', column 'ClinVar' / 'max'
Configuration: GPN-MSA ablation 'Window size = 16' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.964 AUROC (mean over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Window size = 16 on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Window size = 16', column 'ClinVar' / 'mean'
Configuration: GPN-MSA ablation 'Window size = 256' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.969 AUROC (maximum over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Window size = 256 on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Window size = 256', column 'ClinVar' / 'max'
Configuration: GPN-MSA ablation 'Window size = 256' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.969 AUROC (mean over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Window size = 256 on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Window size = 256', column 'ClinVar' / 'mean'
Configuration: GPN-MSA ablation 'Window size = 32' (Supplementary Table 4)	Protocol: ClinVar Pathogenic vs gnomAD common missense, AUROC (GPN-MSA Supplementary Table 4) Dataset: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)	0.967 AUROC (maximum over three random seeds; zero-shot) unitless · higher Uncertainty: Not reported by the source: Only mean and max over seeds are printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Window size = 32 on ClinVar (GPN-MSA Supplementary Table 4) gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Supplementary Table 4 (PDF page 23), row 'Window size = 32', column 'ClinVar' / 'max'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

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.

Author-reported evaluations: 16
External evaluations: 1

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Protocol-valid seeded random ranking; no fitting on assay labels

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

Established label-free reference with explicitly permitted sequence/MSA inputs

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 2026-10-22-1b7cf027e4f6. 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.

Strengths, limitations and unresolved questions

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

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Original source · bioRxiv v2, posted 2024-04-06

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm-guides-20261014-gpnmsa-protocol-ablation-clinvar-auroc

areas: dna-genomes
contexts: research
protocol: Each model or score is applied zero-shot (no training on these labels). GPN-MSA scores are the log-likelihood ratio of alternate versus reference allele averaged over both strands. For each ablation setting three replicate models with different seeds were trained where applicable; the table prints the mean and the maximum over seeds.
version: bioRxiv v2 Supplementary Table 4
metric: auroc
metric direction: higher
unit: unitless
limitations: Benchmark built and run by the GPN-MSA authors (author-reported).; Controls are gnomAD common variants rather than ClinVar benign variants; the authors report that with ClinVar benign controls GPN-MSA is slightly behind CADD and ESM-1b (Supplementary Figure 4, figure only).; Variant counts are not printed.
source locator: Methods 'Main VEP metrics' (ClinVar); Supplementary Table 4 column 'ClinVar'

Related records

part of: GPN-MSA variant effect prediction evaluation (Benegas et al.)
uses data: ClinVar Pathogenic vs gnomAD common missense variants (GPN-MSA paper)
assessment: 51 mammals on ClinVar (GPN-MSA Supplementary Table 4)
assessment: 51 vertebrates on ClinVar (GPN-MSA Supplementary Table 4)
assessment: Default on ClinVar (GPN-MSA Supplementary Table 4)
assessment: Include closest primates on ClinVar (GPN-MSA Supplementary Table 4)
assessment: MSA frequency (no neural net) on ClinVar (GPN-MSA Supplementary Table 4)
assessment: Don’t replace non-conserved on ClinVar (GPN-MSA Supplementary Table 4)
assessment: Don’t upweight conserved on ClinVar (GPN-MSA Supplementary Table 4)
assessment: Combined phyloP and phastCons on ClinVar (GPN-MSA Supplementary Table 4)
assessment: Train on 100% of genome on ClinVar (GPN-MSA Supplementary Table 4)
assessment: Train on 50% most conserved on ClinVar (GPN-MSA Supplementary Table 4)
assessment: Window size = 16 on ClinVar (GPN-MSA Supplementary Table 4)
assessment: Window size = 256 on ClinVar (GPN-MSA Supplementary Table 4)
assessment: Window size = 32 on ClinVar (GPN-MSA Supplementary Table 4)
assessment: Window size = 4 on ClinVar (GPN-MSA Supplementary Table 4)
assessment: Window size = 64 on ClinVar (GPN-MSA Supplementary Table 4)
assessment: Window size = 8 on ClinVar (GPN-MSA Supplementary Table 4)
assessment: w/o MSA on ClinVar (GPN-MSA Supplementary Table 4)

Suggest a correction