ProteinGym DMS TADBP binary classification, AUROC (GPN-MSA paper); bioRxiv v2

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.

2 recorded evaluations, 2 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

2 evaluations · 2 results. Different protocols are not a single leaderboard.

Protocol: ProteinGym DMS TADBP binary classification, AUROC (GPN-MSA paper) · Dataset: ProteinGym v0.1 DMS TADBP_HUMAN Bolognesi 2019, binarised (GPN-MSA paper)

Sorted by AUROC (binary labels from absolute relative toxicity > 0.125; 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 (binary labels from absolute relative toxicity > 0.125; zero-shot)
GPN-MSA, main results model (bioRxiv v2)Evaluation	0.83 (best in column)
ESM-1b, precomputed log-likelihood ratios (GPN-MSA paper)Evaluation	0.75

All 2 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: ESM-1b, precomputed log-likelihood ratios (GPN-MSA paper)	Protocol: ProteinGym DMS TADBP binary classification, AUROC (GPN-MSA paper) Dataset: ProteinGym v0.1 DMS TADBP_HUMAN Bolognesi 2019, binarised (GPN-MSA paper)	0.75 AUROC (binary labels from absolute relative toxicity > 0.125; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM-1b on ProteinGym DMS TADBP binary classification (GPN-MSA paper) gfm-guides-20261014-gpnmsa-protocol-dms-tadbp-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Results paragraph beginning 'We also evaluate on deep mutational scanning', sentence 'Nevertheless, GPN-MSA performs better than ESM-1b on some proteins (e.g., TADBP, for which GPN-MSA AUROC is 0.83, while ESM-1b AUROC is 0.75)' (PDF page 6)
Configuration: GPN-MSA, main results model (bioRxiv v2)	Protocol: ProteinGym DMS TADBP binary classification, AUROC (GPN-MSA paper) Dataset: ProteinGym v0.1 DMS TADBP_HUMAN Bolognesi 2019, binarised (GPN-MSA paper)	0.83 AUROC (binary labels from absolute relative toxicity > 0.125; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source GPN-MSA on ProteinGym DMS TADBP binary classification (GPN-MSA paper) gfm-guides-20261014-gpnmsa-protocol-dms-tadbp-auroc Aggregation: Not reported GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction (bioRxiv v2) · Results paragraph beginning 'We also evaluate on deep mutational scanning', sentence 'Nevertheless, GPN-MSA performs better than ESM-1b on some proteins (e.g., TADBP, for which GPN-MSA AUROC is 0.83, while ESM-1b AUROC is 0.75)' (PDF page 6)

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.

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: 1
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.

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-dms-tadbp-auroc

areas: dna-genomes; protein-function
contexts: research
protocol: Labels: absolute value of relative toxicity binarised at 0.125 (TADBP only; other assays use the ProteinGym protein-specific cutoff). Genomic predictors take the most deleterious score among SNVs causing each substitution; ESM-1b uses precomputed log-likelihood ratios in protein coordinates, minimum over isoforms.
version: bioRxiv v2
metric: auroc
metric direction: higher
unit: unitless
limitations: Single assay, quoted in the Results text as an example where GPN-MSA beats ESM-1b; the 31-assay summary is figure-only (Supplementary Figure 5).; Values printed to two decimals.
source locator: Results paragraph beginning 'We also evaluate on deep mutational scanning' (PDF page 6); Methods 'Additional VEP metrics' (DMS) and 'VEP scores'

Related records