Protocol

ClinVar pathogenic versus benign SNVs by VEP consequence, AUPRC (AlphaGenome Atlas)

Separate ClinVar pathogenic from benign SNVs within each VEP consequence class, scored by AUPRC.

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.

10 recorded evaluations, 10 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

10 evaluations · 10 results. Different protocols are not a single leaderboard.

Protocol: ClinVar pathogenic versus benign SNVs by VEP consequence, AUPRC (AlphaGenome Atlas)

Sorted by AUPRC (ClinVar pathogenic vs benign SNVs, 3' UTR) (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	Protocol and dataset	AUPRC (ClinVar pathogenic vs benign SNVs, 3' UTR)	AUPRC (ClinVar pathogenic vs benign SNVs, 5' UTR)	AUPRC (ClinVar pathogenic vs benign SNVs, Intronic)	AUPRC (ClinVar pathogenic vs benign SNVs, Protein altering)	AUPRC (ClinVar pathogenic vs benign SNVs, Synonymous)
AVI six-model ensemble (AlphaGenome Atlas v1)Evaluation	ClinVar 2025-06-15 SNVs, 3' UTR (AlphaGenome Atlas test set)	0.5 (best in column)	Not reported	Not reported	Not reported	Not reported
GPN-Star (M), mammalian, mutation-rate calibrated (AlphaGenome Atlas v1)Evaluation	ClinVar 2025-06-15 SNVs, 3' UTR (AlphaGenome Atlas test set)	0.18	Not reported	Not reported	Not reported	Not reported
AVI six-model ensemble (AlphaGenome Atlas v1)Evaluation	ClinVar 2025-06-15 SNVs, Intronic (AlphaGenome Atlas test set)	Not reported	Not reported	0.76 (best in column)	Not reported	Not reported
GPN-Star (V), vertebrate, mutation-rate calibrated (AlphaGenome Atlas v1)Evaluation	ClinVar 2025-06-15 SNVs, Intronic (AlphaGenome Atlas test set)	Not reported	Not reported	0.44	Not reported	Not reported
AVI six-model ensemble (AlphaGenome Atlas v1)Evaluation	ClinVar 2025-06-15 SNVs, Protein altering (AlphaGenome Atlas test set)	Not reported	Not reported	Not reported	0.9 (best in column)	Not reported
GPN-Star (V), vertebrate, mutation-rate calibrated (AlphaGenome Atlas v1)Evaluation	ClinVar 2025-06-15 SNVs, Protein altering (AlphaGenome Atlas test set)	Not reported	Not reported	Not reported	0.86	Not reported
AVI six-model ensemble (AlphaGenome Atlas v1)Evaluation	ClinVar 2025-06-15 SNVs, Synonymous (AlphaGenome Atlas test set)	Not reported	Not reported	Not reported	Not reported	0.57 (best in column)
CADD v1.7 GRCh38, precomputed plus pipeline for missing indels (AlphaGenome Atlas v1)Evaluation	ClinVar 2025-06-15 SNVs, Synonymous (AlphaGenome Atlas test set)	Not reported	Not reported	Not reported	Not reported	0.35
AVI six-model ensemble (AlphaGenome Atlas v1)Evaluation	ClinVar 2025-06-15 SNVs, 5' UTR (AlphaGenome Atlas test set)	Not reported	0.26	Not reported	Not reported	Not reported
GPN-Star (V), vertebrate, mutation-rate calibrated (AlphaGenome Atlas v1)Evaluation	ClinVar 2025-06-15 SNVs, 5' UTR (AlphaGenome Atlas test set)	Not reported	0.27 (best in column)	Not reported	Not reported	Not reported

All 10 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: AVI six-model ensemble (AlphaGenome Atlas v1)	Protocol: ClinVar pathogenic versus benign SNVs by VEP consequence, AUPRC (AlphaGenome Atlas) Dataset subset: ClinVar 2025-06-15 SNVs, Intronic (AlphaGenome Atlas test set)	0.76 AUPRC (ClinVar pathogenic vs benign SNVs, Intronic) unitless · higher Uncertainty: Not reported by the source: Fig. 2A draws 95% bootstrap intervals (100 bootstraps) without printing them. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source avi on ClinVar Intronic SNVs (AlphaGenome Atlas Fig. 2A) ag-atlas-20261019-protocol-clinvar-snv-by-consequence-auprc Aggregation: Not reported AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) · Results 'State-of-the-art interpretable genome-wide variant prioritization with AVI' paragraph 1 (page 5), citing Fig. 2A: 'intronic (AUPRC 0.76 vs. GPN-Star-V’s 0.44)'
Configuration: GPN-Star (V), vertebrate, mutation-rate calibrated (AlphaGenome Atlas v1)	Protocol: ClinVar pathogenic versus benign SNVs by VEP consequence, AUPRC (AlphaGenome Atlas) Dataset subset: ClinVar 2025-06-15 SNVs, Intronic (AlphaGenome Atlas test set)	0.44 AUPRC (ClinVar pathogenic vs benign SNVs, Intronic) unitless · higher Uncertainty: Not reported by the source: Fig. 2A draws 95% bootstrap intervals (100 bootstraps) without printing them. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source gpn-star-v on ClinVar Intronic SNVs (AlphaGenome Atlas Fig. 2A) ag-atlas-20261019-protocol-clinvar-snv-by-consequence-auprc Aggregation: Not reported AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) · Results 'State-of-the-art interpretable genome-wide variant prioritization with AVI' paragraph 1 (page 5), citing Fig. 2A: 'intronic (AUPRC 0.76 vs. GPN-Star-V’s 0.44)'
Configuration: AVI six-model ensemble (AlphaGenome Atlas v1)	Protocol: ClinVar pathogenic versus benign SNVs by VEP consequence, AUPRC (AlphaGenome Atlas) Dataset subset: ClinVar 2025-06-15 SNVs, Protein altering (AlphaGenome Atlas test set)	0.9 AUPRC (ClinVar pathogenic vs benign SNVs, Protein altering) unitless · higher Uncertainty: Not reported by the source: Fig. 2A draws 95% bootstrap intervals (100 bootstraps) without printing them. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source avi on ClinVar Protein altering SNVs (AlphaGenome Atlas Fig. 2A) ag-atlas-20261019-protocol-clinvar-snv-by-consequence-auprc Aggregation: Not reported AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) · Results 'State-of-the-art interpretable genome-wide variant prioritization with AVI' paragraph 1 (page 5), citing Fig. 2A: 'protein-altering variants (0.90 vs. GPN-Star-V’s 0.86)'
Configuration: GPN-Star (V), vertebrate, mutation-rate calibrated (AlphaGenome Atlas v1)	Protocol: ClinVar pathogenic versus benign SNVs by VEP consequence, AUPRC (AlphaGenome Atlas) Dataset subset: ClinVar 2025-06-15 SNVs, Protein altering (AlphaGenome Atlas test set)	0.86 AUPRC (ClinVar pathogenic vs benign SNVs, Protein altering) unitless · higher Uncertainty: Not reported by the source: Fig. 2A draws 95% bootstrap intervals (100 bootstraps) without printing them. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source gpn-star-v on ClinVar Protein altering SNVs (AlphaGenome Atlas Fig. 2A) ag-atlas-20261019-protocol-clinvar-snv-by-consequence-auprc Aggregation: Not reported AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) · Results 'State-of-the-art interpretable genome-wide variant prioritization with AVI' paragraph 1 (page 5), citing Fig. 2A: 'protein-altering variants (0.90 vs. GPN-Star-V’s 0.86)'
Configuration: AVI six-model ensemble (AlphaGenome Atlas v1)	Protocol: ClinVar pathogenic versus benign SNVs by VEP consequence, AUPRC (AlphaGenome Atlas) Dataset subset: ClinVar 2025-06-15 SNVs, Synonymous (AlphaGenome Atlas test set)	0.57 AUPRC (ClinVar pathogenic vs benign SNVs, Synonymous) unitless · higher Uncertainty: Not reported by the source: Fig. 2A draws 95% bootstrap intervals (100 bootstraps) without printing them. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source avi on ClinVar Synonymous SNVs (AlphaGenome Atlas Fig. 2A) ag-atlas-20261019-protocol-clinvar-snv-by-consequence-auprc Aggregation: Not reported AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) · Results 'State-of-the-art interpretable genome-wide variant prioritization with AVI' paragraph 1 (page 5), citing Fig. 2A: 'synonymous (0.57 vs. CADD v1.7’s 0.35)'
Configuration: CADD v1.7 GRCh38, precomputed plus pipeline for missing indels (AlphaGenome Atlas v1)	Protocol: ClinVar pathogenic versus benign SNVs by VEP consequence, AUPRC (AlphaGenome Atlas) Dataset subset: ClinVar 2025-06-15 SNVs, Synonymous (AlphaGenome Atlas test set)	0.35 AUPRC (ClinVar pathogenic vs benign SNVs, Synonymous) unitless · higher Uncertainty: Not reported by the source: Fig. 2A draws 95% bootstrap intervals (100 bootstraps) without printing them. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source cadd-v1-7 on ClinVar Synonymous SNVs (AlphaGenome Atlas Fig. 2A) ag-atlas-20261019-protocol-clinvar-snv-by-consequence-auprc Aggregation: Not reported AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) · Results 'State-of-the-art interpretable genome-wide variant prioritization with AVI' paragraph 1 (page 5), citing Fig. 2A: 'synonymous (0.57 vs. CADD v1.7’s 0.35)'
Configuration: AVI six-model ensemble (AlphaGenome Atlas v1)	Protocol: ClinVar pathogenic versus benign SNVs by VEP consequence, AUPRC (AlphaGenome Atlas) Dataset subset: ClinVar 2025-06-15 SNVs, 3' UTR (AlphaGenome Atlas test set)	0.5 AUPRC (ClinVar pathogenic vs benign SNVs, 3' UTR) unitless · higher Uncertainty: Not reported by the source: Fig. 2A draws 95% bootstrap intervals (100 bootstraps) without printing them. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source avi on ClinVar 3' UTR SNVs (AlphaGenome Atlas Fig. 2A) ag-atlas-20261019-protocol-clinvar-snv-by-consequence-auprc Aggregation: Not reported AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) · Results 'State-of-the-art interpretable genome-wide variant prioritization with AVI' paragraph 1 (page 5), citing Fig. 2A: '3’ UTR categories (0.50 vs. GPN-Star-M’s 0.18)'
Configuration: GPN-Star (M), mammalian, mutation-rate calibrated (AlphaGenome Atlas v1)	Protocol: ClinVar pathogenic versus benign SNVs by VEP consequence, AUPRC (AlphaGenome Atlas) Dataset subset: ClinVar 2025-06-15 SNVs, 3' UTR (AlphaGenome Atlas test set)	0.18 AUPRC (ClinVar pathogenic vs benign SNVs, 3' UTR) unitless · higher Uncertainty: Not reported by the source: Fig. 2A draws 95% bootstrap intervals (100 bootstraps) without printing them. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source gpn-star-m on ClinVar 3' UTR SNVs (AlphaGenome Atlas Fig. 2A) ag-atlas-20261019-protocol-clinvar-snv-by-consequence-auprc Aggregation: Not reported AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) · Results 'State-of-the-art interpretable genome-wide variant prioritization with AVI' paragraph 1 (page 5), citing Fig. 2A: '3’ UTR categories (0.50 vs. GPN-Star-M’s 0.18)'
Configuration: AVI six-model ensemble (AlphaGenome Atlas v1)	Protocol: ClinVar pathogenic versus benign SNVs by VEP consequence, AUPRC (AlphaGenome Atlas) Dataset subset: ClinVar 2025-06-15 SNVs, 5' UTR (AlphaGenome Atlas test set)	0.26 AUPRC (ClinVar pathogenic vs benign SNVs, 5' UTR) unitless · higher Uncertainty: Not reported by the source: Fig. 2A draws 95% bootstrap intervals (100 bootstraps) without printing them. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source avi on ClinVar 5' UTR SNVs (AlphaGenome Atlas Fig. 2A) ag-atlas-20261019-protocol-clinvar-snv-by-consequence-auprc Aggregation: Not reported AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) · Results 'State-of-the-art interpretable genome-wide variant prioritization with AVI' paragraph 1 (page 5), citing Fig. 2A: 'GPN-Star-V outperformed AVI on 5’UTR ClinVar SNVs (0.27 vs. 0.26)'
Configuration: GPN-Star (V), vertebrate, mutation-rate calibrated (AlphaGenome Atlas v1)	Protocol: ClinVar pathogenic versus benign SNVs by VEP consequence, AUPRC (AlphaGenome Atlas) Dataset subset: ClinVar 2025-06-15 SNVs, 5' UTR (AlphaGenome Atlas test set)	0.27 AUPRC (ClinVar pathogenic vs benign SNVs, 5' UTR) unitless · higher Uncertainty: Not reported by the source: Fig. 2A draws 95% bootstrap intervals (100 bootstraps) without printing them. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source gpn-star-v on ClinVar 5' UTR SNVs (AlphaGenome Atlas Fig. 2A) ag-atlas-20261019-protocol-clinvar-snv-by-consequence-auprc Aggregation: Not reported AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) · Results 'State-of-the-art interpretable genome-wide variant prioritization with AVI' paragraph 1 (page 5), citing Fig. 2A: 'GPN-Star-V outperformed AVI on 5’UTR ClinVar SNVs (0.27 vs. 0.26)'

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.

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: 10

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

Claims, original sources and review scope · Release 2026-11-02-a7f03c9e55a5
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 2026-11-02-a7f03c9e55a5 · Record review: source checked

1 source record and release history

AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) · Original source · medRxiv preprint version 1, posted 2026-09-20; full-text PDF with supplementary figures and tables (83 pages)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: ag-atlas-20261019-protocol-clinvar-snv-by-consequence-auprc

areas: dna-genomes
contexts: research
protocol: Within each consequence class, AUPRC of each method's score for P/LP versus B/LB ClinVar SNVs after AVI positional overlap filtering.
metric: auprc
metric direction: higher
bootstrap replicates: 100
uncertainty reporting: printed: Error bars indicate 95% confidence intervals from 100 bootstraps; values printed: false
source locator: Fig. 2A and legend (page 6); Methods 'ClinVar Pathogenicity Classification' (page 27)
limitations: Developer study; comparators run by the AVI authors.; Positional filtering removes benchmark variants near AVI training variants for every method but comparator training data were not filtered.; ClinVar labels include no review-status filter.; Bar values in Fig. 2A identify methods by colour only; only values named in the text are extracted.
task link exemption: No task or benchmark in the store covers ClinVar pathogenicity of noncoding and all-consequence SNVs; 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: ClinVar 2025-06-15 pathogenic versus benign variants, AVI evaluation set
assessment: avi on ClinVar Intronic SNVs (AlphaGenome Atlas Fig. 2A)
assessment: gpn-star-v on ClinVar Intronic SNVs (AlphaGenome Atlas Fig. 2A)
assessment: avi on ClinVar Protein altering SNVs (AlphaGenome Atlas Fig. 2A)
assessment: gpn-star-v on ClinVar Protein altering SNVs (AlphaGenome Atlas Fig. 2A)
assessment: avi on ClinVar Synonymous SNVs (AlphaGenome Atlas Fig. 2A)
assessment: cadd-v1-7 on ClinVar Synonymous SNVs (AlphaGenome Atlas Fig. 2A)
assessment: avi on ClinVar 3' UTR SNVs (AlphaGenome Atlas Fig. 2A)
assessment: gpn-star-m on ClinVar 3' UTR SNVs (AlphaGenome Atlas Fig. 2A)
assessment: avi on ClinVar 5' UTR SNVs (AlphaGenome Atlas Fig. 2A)
assessment: gpn-star-v on ClinVar 5' UTR SNVs (AlphaGenome Atlas Fig. 2A)
used in: ClinVar 2025-06-15 SNVs, Intronic (AlphaGenome Atlas test set)
used in: ClinVar 2025-06-15 SNVs, Protein altering (AlphaGenome Atlas test set)
used in: ClinVar 2025-06-15 SNVs, Synonymous (AlphaGenome Atlas test set)
used in: ClinVar 2025-06-15 SNVs, 3' UTR (AlphaGenome Atlas test set)
used in: ClinVar 2025-06-15 SNVs, 5' UTR (AlphaGenome Atlas test set)

Suggest a correction