ESM-2 (35M) (Chu et al. 2024)

Overview

ESM-2 (35M) as evaluated in the cited comparison.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

7 evaluations · 7 results. Different protocols are not a single leaderboard.

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-2 (35M) (Chu et al. 2024)	Protocol: Acetyltransferase dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1) Dataset: Acetyltransferase dataset: Gentamicin 3-N-acetyltransferase, chemical stability	0.25 spearman-correlation 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-2 (35M) on Acetyltransferase dataset (Chu et al. 2024) protein-stability-20261009-protocol-chu2024-acetyltransferase Aggregation: Not reported Protein stability prediction by fine-tuning a protein language model on a mega-scale dataset · Table 1, row 'Acetyltransferase dataset', column 'ESM-2 (35M)' (unsupervised group)
Configuration: ESM-2 (35M) (Chu et al. 2024)	Protocol: Bgl3 dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1) Dataset: Bgl3 dataset: Beta-glucosidase (Bgl3), catalytic susceptibility to heat shock	0.43 spearman-correlation 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-2 (35M) on Bgl3 dataset (Chu et al. 2024) protein-stability-20261009-protocol-chu2024-bgl3 Aggregation: Not reported Protein stability prediction by fine-tuning a protein language model on a mega-scale dataset · Table 1, row 'Bgl3 dataset', column 'ESM-2 (35M)' (unsupervised group)
Configuration: ESM-2 (35M) (Chu et al. 2024)	Protocol: BglB dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1) Dataset: BglB dataset: Beta-glucosidase (BglB), melting temperature (Tm)	-0.12 spearman-correlation 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-2 (35M) on BglB dataset (Chu et al. 2024) protein-stability-20261009-protocol-chu2024-bglb Aggregation: Not reported Protein stability prediction by fine-tuning a protein language model on a mega-scale dataset · Table 1, row 'BglB dataset', column 'ESM-2 (35M)' (unsupervised group)
Configuration: ESM-2 (35M) (Chu et al. 2024)	Protocol: Lipase EstA dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1) Dataset: Lipase EstA dataset: Lipase EstA, melting temperature (T50)	0.26 spearman-correlation 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-2 (35M) on Lipase EstA dataset (Chu et al. 2024) protein-stability-20261009-protocol-chu2024-lipase-esta Aggregation: Not reported Protein stability prediction by fine-tuning a protein language model on a mega-scale dataset · Table 1, row 'Lipase EstA dataset', column 'ESM-2 (35M)' (unsupervised group)
Configuration: ESM-2 (35M) (Chu et al. 2024)	Protocol: Mega-scale dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1) Dataset: Mega-scale dataset: multiple, cDNA display proteolysis	0.36 spearman-correlation 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-2 (35M) on Mega-scale dataset (Chu et al. 2024) protein-stability-20261009-protocol-chu2024-mega-scale Aggregation: Not reported Protein stability prediction by fine-tuning a protein language model on a mega-scale dataset · Table 1, row 'Mega-scale dataset', column 'ESM-2 (35M)' (unsupervised group)
Configuration: ESM-2 (35M) (Chu et al. 2024)	Protocol: Methyltransferase dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1) Dataset: Methyltransferase dataset: Thiopurine S-methyltransferase, protein abundance	0.42 spearman-correlation 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-2 (35M) on Methyltransferase dataset (Chu et al. 2024) protein-stability-20261009-protocol-chu2024-methyltransferase Aggregation: Not reported Protein stability prediction by fine-tuning a protein language model on a mega-scale dataset · Table 1, row 'Methyltransferase dataset', column 'ESM-2 (35M)' (unsupervised group)
Configuration: ESM-2 (35M) (Chu et al. 2024)	Protocol: PTEN dataset stability ranking, Spearman correlation (Chu et al. 2024 Table 1) Dataset: PTEN dataset: PTEN, protein abundance	0.26 spearman-correlation 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-2 (35M) on PTEN dataset (Chu et al. 2024) protein-stability-20261009-protocol-chu2024-pten Aggregation: Not reported Protein stability prediction by fine-tuning a protein language model on a mega-scale dataset · Table 1, row 'PTEN dataset', column 'ESM-2 (35M)' (unsupervised group)

Source checking is not independent reproduction. Release 2026-10-10-6e93f504adfc.

Use this model

How it works, versions and access

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 2026-10-10-6e93f504adfc
Property and statement	Original source and location	Review and provenance

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

All evidence (JSONL) (gzip)How to read the evidence

Sources and history

Release 2026-10-10-6e93f504adfc · Record review: source checked

1 source records and release history

Protein stability prediction by fine-tuning a protein language model on a mega-scale dataset · Original source · PLOS Computational Biology 20(7):e1012248, published 2024-07-22; PMC11293664 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: protein-stability-20261009-config-chu2024-esm-2-35m

areas: proteins-complexes
contexts: research
method types: foundation_model
reported name: ESM-2 (35M)
foundation model eligible: true
source locator: Table 1 column header; Results 'Benchmarking on larger proteins'
protocol: Pretrained ESM-2 likelihood used without supervision
missing metadata: version: reason: unreported; note: No release number printed

Related records

configuration of: ESM-2
system: ESM-2 (35M) on Acetyltransferase dataset (Chu et al. 2024)
system: ESM-2 (35M) on Bgl3 dataset (Chu et al. 2024)
system: ESM-2 (35M) on BglB dataset (Chu et al. 2024)
system: ESM-2 (35M) on Lipase EstA dataset (Chu et al. 2024)
system: ESM-2 (35M) on Mega-scale dataset (Chu et al. 2024)
system: ESM-2 (35M) on Methyltransferase dataset (Chu et al. 2024)
system: ESM-2 (35M) on PTEN dataset (Chu et al. 2024)