Configuration

ESM-2

This protein-language-model configuration is evaluated for viral RBD mutation properties under PRIME.

Sources

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Methods/Model architecture and scale (paragraph 1); Discussion (paragraph 1)

1 evaluation · 1 result

How it worksEvaluated procedure (conceptual)

Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings.

Sources

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Results/Optimization of neural architectures for real-time deployment (paragraph 1); Methods/Model architecture and scale (paragraph 1)

Overview

Model type

Protein sequence transformer; this record is the paper-specific evaluated configuration.

Sources

facebookresearch/esm README.md · README.md model description

Biological inputs

SARS-CoV-2 receptor-binding-domain sequences

Sources

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Results/Benchmark data collection for viral phenotype prediction (paragraph 3); Discussion (paragraph 7)

Outputs

Binding-affinity and expression predictions

Sources

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Methods/Computational resources and reproducibility (paragraph 2); Results/Optimization of neural architectures for real-time deployment (paragraph 2)

Access

Official upstream implementation and usage documentation: https://github.com/facebookresearch/esm/blob/2b369911bb5b4b0dda914521b9475cad1656b2ac/README.md. This pinned documentation revision is not automatically the evaluated weight revision.

Sources

facebookresearch/esm README.md · README.md; installation, model download and usage instructions

limited source coverage · Automated source review, 2026-09-16. All specifications and missing details

Evaluations and results

1 evaluation · 1 result. 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	Task: Mutated RBD binding prediction Dataset: PRIME mutated RBD	0.0248 R² unitless · unknown Uncertainty: ± 0.01 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM-2: Mutated RBD binding prediction Frozen mean-pooled representation with downstream regression; position-stratified split. Aggregation: Not reported PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, ESM-2 8M / Mean / not fine-tuned row, Position-Stratified Split Binding R² column

Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.

Use this model

How it works, versions and access

Underlying model: ESM-2. Results on this page belong to this configuration and its evaluated settings.

How it works

How the evaluated method works

Protein embeddings feed downstream prediction heads, with frozen and fine-tuned encoder conditions explicitly separated.

Sources

Underlying method and version boundaries

ESM-2 is a transformer protein language-model family. The official repository exposes residue embeddings, sequence-level pooling and models at several sizes; the study configuration determines which of these is evaluated.

Sources

facebookresearch/esm README.md · README.md; introduction, model description, pretrained-model and usage sections at pinned revision

What was evaluated

The linked evaluation record identifies ESM-2: Mutated RBD binding prediction. Its dataset, split, adaptation and evidence origin remain attached to the reported results.

Sources

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-021

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

Contrasts random splitting with a position-stratified protocol that exposes leakage from closely related variants.
Sources
PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Methods/Position-stratified validation protocol (paragraph 1); Methods/Position-stratified validation protocol/Leakage control (paragraph 1)

Limitations and conditions

Random-split performance is not evidence of generalisation to unseen mutation sites; the row’s model size and adaptation must stay attached to its score.
Sources
PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Background (paragraph 5); Discussion (paragraph 2)

Profile review details

Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction.

Stable record: reported-model-d0d5df2beb02b2

Specifications

Inputs, training, access and other details

Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

Inputs, outputs and configuration
Property	Description and evidence
Model type	Protein sequence transformer; this record is the paper-specific evaluated configuration. Sources facebookresearch/esm README.md · README.md model description
Architecture / procedure	Protein embeddings feed downstream prediction heads, with frozen and fine-tuned encoder conditions explicitly separated. Sources PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Results/Optimization of neural architectures for real-time deployment (paragraph 1); Methods/Model architecture and scale (paragraph 1)
Biological inputs	SARS-CoV-2 receptor-binding-domain sequences Sources PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Results/Benchmark data collection for viral phenotype prediction (paragraph 3); Discussion (paragraph 7)
Outputs	Binding-affinity and expression predictions Sources PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Methods/Computational resources and reproducibility (paragraph 2); Results/Optimization of neural architectures for real-time deployment (paragraph 2)
Parameters	8 million parameters, as identified for this row Sources PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Abstract (paragraph 1); Methods/Clustering and phylogenetic analysis/Clustering (paragraph 1)
Known versions / configuration	8M Sources PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table Tab1 (paragraph 1); Declarations/Consent for publication (paragraph 1)
Training data / fitting	347,432 RBD sequences in the study; position-stratified partitions test unseen mutational sites. Sources PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Methods/Position-stratified validation protocol/Leakage control (paragraph 1); Background (paragraph 5)
Context limits	A maximum input/context length for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sources Sources (2) PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space; facebookresearch/esm README.md · Results/Optimization of neural architectures for real-time deployment; Methods/Data collection and curation; Methods/Data collection and curation/Outbreak dataset; Methods/Data collection and curation/DMS dataset; Methods/Data collection and curation/BetaCov dataset; Methods/Model architecture and scale; Methods/Model architecture and scale/ESM-2 family; Methods/Model architecture and scale/ESM-C family; inspected for explicit maximum input length (dataset lengths and family-wide limits are not substituted); README.md at pinned repository revision
Access	Official upstream implementation and usage documentation: https://github.com/facebookresearch/esm/blob/2b369911bb5b4b0dda914521b9475cad1656b2ac/README.md. This pinned documentation revision is not automatically the evaluated weight revision. Sources facebookresearch/esm README.md · README.md; installation, model download and usage instructions
Code licence	MIT (upstream repository code at the cited revision; this does not establish every dependency or historical checkpoint licence). Sources facebookresearch/esm LICENSE · LICENSE; complete licence text
Weights licence	The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. · Not reported in inspected sources Sources facebookresearch/esm README.md · README.md; checkpoint/access documentation and licence scope

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.

22 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings. Individual claims	PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Original source ↗ Results/Optimization of neural architectures for real-time deployment (paragraph 1); Methods/Model architecture and scale (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:41:16.525183+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps SARS-CoV-2 receptor-binding-domain sequences ESM-2 Binding-affinity and expression predictions Individual claims	PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Original source ↗ Results/Optimization of neural architectures for real-time deployment (paragraph 1); Methods/Model architecture and scale (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:41:16.525183+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Evaluated procedure (conceptual) Individual claims	PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Original source ↗ Results/Optimization of neural architectures for real-time deployment (paragraph 1); Methods/Model architecture and scale (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:41:16.525183+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Model type Protein sequence transformer; this record is the paper-specific evaluated configuration. Individual claims	facebookresearch/esm README.md Original source ↗ README.md model description Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T20:00:00.816433+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `8b273c21a322fc9473d1b68d0dd40c8166ab2f89e4a190aa26ca87251b97cba9` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Architecture / procedure Protein embeddings feed downstream prediction heads, with frozen and fine-tuned encoder conditions explicitly separated. Individual claims	PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Original source ↗ Results/Optimization of neural architectures for real-time deployment (paragraph 1); Methods/Model architecture and scale (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:41:16.525183+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Weights licence The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. Individual claims	facebookresearch/esm README.md Original source ↗ README.md; checkpoint/access documentation and licence scope Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T20:00:00.816433+00:00	unreported automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `8b273c21a322fc9473d1b68d0dd40c8166ab2f89e4a190aa26ca87251b97cba9` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Biological inputs SARS-CoV-2 receptor-binding-domain sequences Individual claims	PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Original source ↗ Results/Benchmark data collection for viral phenotype prediction (paragraph 3); Discussion (paragraph 7) Version: version of record Retrieved: 2026-09-16T10:41:16.525183+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Outputs Binding-affinity and expression predictions Individual claims	PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Original source ↗ Methods/Computational resources and reproducibility (paragraph 2); Results/Optimization of neural architectures for real-time deployment (paragraph 2) Version: version of record Retrieved: 2026-09-16T10:41:16.525183+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Parameters 8 million parameters, as identified for this row Individual claims	PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Original source ↗ Abstract (paragraph 1); Methods/Clustering and phylogenetic analysis/Clustering (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:41:16.525183+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Known versions / configuration 8M Individual claims	PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Original source ↗ Table Tab1 (paragraph 1); Declarations/Consent for publication (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:41:16.525183+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.5.value` Source artifact SHA-256: `f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

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

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: needs review

3 source records and release history

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Original source · version of record
facebookresearch/esm README.md · Original source · 2b369911bb5b4b0dda914521b9475cad1656b2ac
facebookresearch/esm LICENSE · Original source · 2b369911bb5b4b0dda914521b9475cad1656b2ac

Download this release

Technical metadata and extraction receipts

Stable ID: reported-model-d0d5df2beb02b2

areas: proteins-complexes
entity level: method
version: 8M
reported name: ESM-2
historical missing metadata: checkpoint revision: not_reported_in_legacy_extract; training data: not_reported_in_legacy_extract; licence: not_reported_in_legacy_extract
metadata review scope: historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
legacy kinds: model
entity classification: review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: prime-2026; evidence-reported-base-esm-readme-md; source locator: Results/Optimization of neural architectures for real-time deployment (paragraph 1); Methods/Model architecture and scale (paragraph 1) | README.md model description | Methods/Model architecture and scale (paragraph 1); Discussion (paragraph 1); ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.

Related records

uses model: ESM-2
model: ESM-2: Mutated RBD binding prediction
subject: ESM-2: uses model ESM-2

Suggest a correction