Configuration

ESM2 650M log-likelihood ratio, Brandes et al. pipeline (Lu et al. 2025)

ESM2 esm2_t33_650M_UR50D scoring missense variants by the logit difference between alternative and reference residues.

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.

Evaluations and results

5 evaluations · 5 results. Different protocols are not a single leaderboard.

Protocol: ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)

Sorted by AUROC (ClinVar pathogenic vs benign SNVs, Missense & 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	AUROC (ClinVar pathogenic vs benign SNVs, Missense & 3'UTR)	AUROC (ClinVar pathogenic vs benign SNVs, Missense & Intron (Non-splice))	AUROC (ClinVar pathogenic vs benign SNVs, Missense)	AUROC (ClinVar pathogenic vs benign SNVs, Start loss)	AUROC (ClinVar pathogenic vs benign SNVs, Stop gain)
ESM2 650M log-likelihood ratio, Brandes et al. pipeline (Lu et al. 2025)Evaluation	Lu et al. 2025 ClinVar benchmark: Missense & 3'UTR (Figure 1)	0.878	Not reported	Not reported	Not reported	Not reported
ESM2 650M log-likelihood ratio, Brandes et al. pipeline (Lu et al. 2025)Evaluation	Lu et al. 2025 ClinVar benchmark: Missense & Intron (Non-splice) (Figure 1)	Not reported	0.818	Not reported	Not reported	Not reported
ESM2 650M log-likelihood ratio, Brandes et al. pipeline (Lu et al. 2025)Evaluation	Lu et al. 2025 ClinVar benchmark: Missense (Figure 1)	Not reported	Not reported	0.886	Not reported	Not reported
ESM2 650M log-likelihood ratio, Brandes et al. pipeline (Lu et al. 2025)Evaluation	Lu et al. 2025 ClinVar benchmark: Start loss (Figure 1)	Not reported	Not reported	Not reported	0.709	Not reported
ESM2 650M log-likelihood ratio, Brandes et al. pipeline (Lu et al. 2025)Evaluation	Lu et al. 2025 ClinVar benchmark: Stop gain (Figure 1)	Not reported	Not reported	Not reported	Not reported	0.684

All 5 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: ESM2 650M log-likelihood ratio, Brandes et al. pipeline (Lu et al. 2025)	Protocol: ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025) Dataset subset: Lu et al. 2025 ClinVar benchmark: Missense & Intron (Non-splice) (Figure 1)	0.818 AUROC (ClinVar pathogenic vs benign SNVs, Missense & Intron (Non-splice)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM2 on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1) lu-hetero-20261019-protocol-clinvar-variant-type-auroc Aggregation: Not reported Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2) · Figure 1 (page 8), column 3, panel 2 'Missense & Intron (Non-splice) (N=255, %P=17.91%)', row 'ESM2', bar label
Configuration: ESM2 650M log-likelihood ratio, Brandes et al. pipeline (Lu et al. 2025)	Protocol: ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025) Dataset subset: Lu et al. 2025 ClinVar benchmark: Missense & 3'UTR (Figure 1)	0.878 AUROC (ClinVar pathogenic vs benign SNVs, Missense & 3'UTR) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM2 on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1) lu-hetero-20261019-protocol-clinvar-variant-type-auroc Aggregation: Not reported Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2) · Figure 1 (page 8), column 3, panel 3 'Missense & 3'UTR (N=117, %P=40.97%)', row 'ESM2', bar label
Configuration: ESM2 650M log-likelihood ratio, Brandes et al. pipeline (Lu et al. 2025)	Protocol: ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025) Dataset subset: Lu et al. 2025 ClinVar benchmark: Missense (Figure 1)	0.886 AUROC (ClinVar pathogenic vs benign SNVs, Missense) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM2 on ClinVar Missense SNVs (Lu et al. 2025 Figure 1) lu-hetero-20261019-protocol-clinvar-variant-type-auroc Aggregation: Not reported Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2) · Figure 1 (page 8), column 3, panel 1 'Missense (N=50,820, %P=40.09%)', row 'ESM2', bar label
Configuration: ESM2 650M log-likelihood ratio, Brandes et al. pipeline (Lu et al. 2025)	Protocol: ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025) Dataset subset: Lu et al. 2025 ClinVar benchmark: Start loss (Figure 1)	0.709 AUROC (ClinVar pathogenic vs benign SNVs, Start loss) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM2 on ClinVar Start loss SNVs (Lu et al. 2025 Figure 1) lu-hetero-20261019-protocol-clinvar-variant-type-auroc Aggregation: Not reported Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2) · Figure 1 (page 8), column 2, panel 5 'Start loss (N=847, %P=97.53%)', row 'ESM2', bar label
Configuration: ESM2 650M log-likelihood ratio, Brandes et al. pipeline (Lu et al. 2025)	Protocol: ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025) Dataset subset: Lu et al. 2025 ClinVar benchmark: Stop gain (Figure 1)	0.684 AUROC (ClinVar pathogenic vs benign SNVs, Stop gain) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM2 on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1) lu-hetero-20261019-protocol-clinvar-variant-type-auroc Aggregation: Not reported Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2) · Figure 1 (page 8), column 3, panel 4 'Stop gain (N=42,408, %P=98.13%)', row 'ESM2', bar label

Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

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

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)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lu-hetero-20261019-config-esm2-650m-llr

areas: dna-genomes
contexts: clinical_research
method types: foundation_model
reported name: ESM2
parameters: esm2_t33_650M_UR50D; 1,022 aa context; same stop-gain and start-loss handling as ESM1b.
source locator: Methods 'ESM models' (page 15)

Related records

configuration of: ESM-2
system: ESM2 on ClinVar Missense & Intron (Non-splice) SNVs (Lu et al. 2025 Figure 1)
system: ESM2 on ClinVar Missense & 3'UTR SNVs (Lu et al. 2025 Figure 1)
system: ESM2 on ClinVar Missense SNVs (Lu et al. 2025 Figure 1)
system: ESM2 on ClinVar Start loss SNVs (Lu et al. 2025 Figure 1)
system: ESM2 on ClinVar Stop gain SNVs (Lu et al. 2025 Figure 1)

Suggest a correction