Model type
Masked-token protein transformer encoder
ESM-2 is a family of protein sequence encoders that produce representations for downstream protein analyses.
Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.
Masked-token protein transformer encoder
Single amino-acid sequences.
Residue embeddings, sequence representations and masked-token predictions.
Official project documentation and implementation: https://github.com/facebookresearch/esm
limited source coverage · Automated source review, 2026-09-23. All specifications and missing details
3 evaluations · 11 results. Different protocols are not a single leaderboard.
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: ESM2 8M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 92.2% Prec. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 8M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 8M, column Prec.; XML row4 column4 |
| Configuration: ESM2 8M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 92.3% Recall percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 8M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 8M, column Recall; XML row4 column5 |
| Configuration: ESM2 8M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 98.1% AUROC percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 8M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 8M, column AUC (%); XML row4 column2 |
| Configuration: ESM2 8M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 94.7% Accur. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 8M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 8M, column Accur.; XML row4 column3 |
| Configuration: ESM-2 8M masked-marginal scoring (ProteinGym v1.3 AMFR substitution assay) | Protocol: ProteinGym v1.3 AMFR substitution assay Dataset subset: ProteinGym v1.3 AMFR substitution assay full assay | 0.394 AUC dimensionless · higher Uncertainty: Not reported Coverage: 2972/2972 | Rewire evaluation · Source checkedMethods, coverage and sourceESM-2 8M masked-marginal scoring on ProteinGym v1.3 AMFR substitution assay ProteinGym v1.3 AMFR substitution assay Aggregation: Not reported ESM-2 8M masked-marginal scoring: local execution report (20 September 2026); ESM-2 8M masked-marginal scoring: automated execution audit · protocol_results.per_assay.AMFR_HUMAN_Tsuboyama_2023_4G3O.metrics.AUC |
| Configuration: ESM-2 8M masked-marginal scoring (ProteinGym v1.3 AMFR substitution assay) | Protocol: ProteinGym v1.3 AMFR substitution assay Dataset subset: ProteinGym v1.3 AMFR substitution assay full assay | -0.139 MCC dimensionless · higher Uncertainty: Not reported Coverage: 2972/2972 | Rewire evaluation · Source checkedMethods, coverage and sourceESM-2 8M masked-marginal scoring on ProteinGym v1.3 AMFR substitution assay ProteinGym v1.3 AMFR substitution assay Aggregation: Not reported ESM-2 8M masked-marginal scoring: local execution report (20 September 2026); ESM-2 8M masked-marginal scoring: automated execution audit · protocol_results.per_assay.AMFR_HUMAN_Tsuboyama_2023_4G3O.metrics.MCC |
| Configuration: ESM-2 8M masked-marginal scoring (ProteinGym v1.3 AMFR substitution assay) | Protocol: ProteinGym v1.3 AMFR substitution assay Dataset subset: ProteinGym v1.3 AMFR substitution assay full assay | 0.44 NDCG dimensionless · higher Uncertainty: Not reported Coverage: 2972/2972 | Rewire evaluation · Source checkedMethods, coverage and sourceESM-2 8M masked-marginal scoring on ProteinGym v1.3 AMFR substitution assay ProteinGym v1.3 AMFR substitution assay Aggregation: Not reported ESM-2 8M masked-marginal scoring: local execution report (20 September 2026); ESM-2 8M masked-marginal scoring: automated execution audit · protocol_results.per_assay.AMFR_HUMAN_Tsuboyama_2023_4G3O.metrics.NDCG |
| Configuration: ESM-2 8M masked-marginal scoring (ProteinGym v1.3 AMFR substitution assay) | Protocol: ProteinGym v1.3 AMFR substitution assay Dataset subset: ProteinGym v1.3 AMFR substitution assay full assay | -0.209 Spearman dimensionless · higher Uncertainty: Not reported Coverage: 2972/2972 | Rewire evaluation · Source checkedMethods, coverage and sourceESM-2 8M masked-marginal scoring on ProteinGym v1.3 AMFR substitution assay ProteinGym v1.3 AMFR substitution assay Aggregation: Not reported ESM-2 8M masked-marginal scoring: local execution report (20 September 2026); ESM-2 8M masked-marginal scoring: automated execution audit · protocol_results.per_assay.AMFR_HUMAN_Tsuboyama_2023_4G3O.metrics.Spearman |
| Configuration: ESM-2 8M masked-marginal scoring (ProteinGym v1.3 AMFR substitution assay) | Protocol: ProteinGym v1.3 AMFR substitution assay Dataset subset: ProteinGym v1.3 AMFR substitution assay full assay | 0.057 Top_recall dimensionless · higher Uncertainty: Not reported Coverage: 2972/2972 | Rewire evaluation · Source checkedMethods, coverage and sourceESM-2 8M masked-marginal scoring on ProteinGym v1.3 AMFR substitution assay ProteinGym v1.3 AMFR substitution assay Aggregation: Not reported ESM-2 8M masked-marginal scoring: local execution report (20 September 2026); ESM-2 8M masked-marginal scoring: automated execution audit · protocol_results.per_assay.AMFR_HUMAN_Tsuboyama_2023_4G3O.metrics.Top_recall |
| Configuration: ESM-2 8M frozen residue-mean embeddings + fixed ridge (Rewire) (FLIP2 Rhomax by_wild_type) | Protocol: FLIP2 Rhomax by_wild_type Dataset subset: FLIP2 Rhomax by_wild_type test subset | 0.896 ndcg dimensionless · higher Uncertainty: Not reported Coverage: 184/184 | Rewire evaluation · Source checkedMethods, coverage and sourceESM-2 8M frozen residue-mean embeddings + fixed ridge (Rewire) on FLIP2 Rhomax by_wild_type FLIP2 Rhomax by_wild_type Aggregation: Not reported ESM-2 8M frozen residue-mean embeddings + fixed ridge (Rewire): report; ESM-2 8M frozen residue-mean embeddings + fixed ridge (Rewire): audit · metrics.ndcg |
| Configuration: ESM-2 8M frozen residue-mean embeddings + fixed ridge (Rewire) (FLIP2 Rhomax by_wild_type) | Protocol: FLIP2 Rhomax by_wild_type Dataset subset: FLIP2 Rhomax by_wild_type test subset | -0.146 spearman dimensionless · higher Uncertainty: Not reported Coverage: 184/184 | Rewire evaluation · Source checkedMethods, coverage and sourceESM-2 8M frozen residue-mean embeddings + fixed ridge (Rewire) on FLIP2 Rhomax by_wild_type FLIP2 Rhomax by_wild_type Aggregation: Not reported ESM-2 8M frozen residue-mean embeddings + fixed ridge (Rewire): report; ESM-2 8M frozen residue-mean embeddings + fixed ridge (Rewire): audit · metrics.spearman |
Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.
Related profile: ESM-2. This page retains the exact record and its evaluation context.
ESM-2 tokenizes an amino-acid sequence and uses a transformer encoder trained to recover masked residues. Self-attention lets each residue representation depend on its sequence context. The released model returns token probabilities and embeddings; a specified pooling rule, task head or complete folding pipeline is needed for a particular biological prediction.
ESM-2 checkpoint identifiers encode layer count, parameter scale and training-data tag. The checked esm2_t33_650M_UR50D configuration lists max_position_embeddings=1,026. This configuration field includes model positions and is not a claim of training or validated inference on 1,026 amino acids.
Follow-up review of Reference checkpoint, Context limits, Training data release, Training cutoff. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied.
Stable record: catalog-model-esm-2Explanatory profile: limited source coverage · Automated source review, 2026-09-23. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Model type | Masked-token protein transformer encoderSources (3)facebookresearch/esm: README.md; facebook/esm2_t33_650M_UR50D: README.md; facebook/esm2_t33_650M_UR50D: config.json · ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json |
| Architecture | Masked-token protein transformer encoder; the checked 650M checkpoint has 33 layers, hidden width 1,280, 20 attention heads and rotary positional encoding.Sources (3)facebookresearch/esm: README.md; facebook/esm2_t33_650M_UR50D: README.md; facebook/esm2_t33_650M_UR50D: config.json · ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json |
| Inputs | Single amino-acid sequences.Sources (3)facebookresearch/esm: README.md; facebook/esm2_t33_650M_UR50D: README.md; facebook/esm2_t33_650M_UR50D: config.json · ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json |
| Outputs | Residue embeddings, sequence representations and masked-token predictions.Sources (3)facebookresearch/esm: README.md; facebook/esm2_t33_650M_UR50D: README.md; facebook/esm2_t33_650M_UR50D: config.json · ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json |
| Parameters | Released scales: 8M, 35M, 150M, 650M, 3B and 15B.Sources (3)facebookresearch/esm: README.md; facebook/esm2_t33_650M_UR50D: README.md; facebook/esm2_t33_650M_UR50D: config.json · ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json |
| Known versions | ESM-2 checkpoint identifiers encode layer count, parameter scale and training-data tag.Sources (3)facebookresearch/esm: README.md; facebook/esm2_t33_650M_UR50D: README.md; facebook/esm2_t33_650M_UR50D: config.json · ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json |
| Training data | UniRef50 clusters with UniRef90 sampling; the pretrained-model table labels UR50/D 2021_04.Sources (3)facebookresearch/esm: README.md; facebook/esm2_t33_650M_UR50D: README.md; facebook/esm2_t33_650M_UR50D: config.json · ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json |
| Training cutoff | The inspected official table establishes an April 2021 UniRef release, but no separate latest-deposited-sequence date. Keep the corpus release distinct from a temporal leakage guarantee. · Not reported in inspected sourcesSourcesfacebookresearch/esm: README.md · README: Pre-trained Models and Pre-training Dataset Split |
| Context limits | The official extraction script truncates to 1,022 residues by default; --truncation_seq_length is configurable. This workflow default is not a universal architecture or validated biological-context limit.Sourcesesm2 extract: primary artifact · create_parser: --truncation_seq_length; run: get_batch_converter |
| Weights licence | The official facebook/esm2_t33_650M_UR50D model card declares MIT; this is the inspected checkpoint, not a licence inference from source code.Sources (3)facebookresearch/esm: README.md; facebook/esm2_t33_650M_UR50D: README.md; facebook/esm2_t33_650M_UR50D: config.json · ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json |
| Access | Official project documentation and implementation: https://github.com/facebookresearch/esmSources (3)facebookresearch/esm: README.md; facebook/esm2_t33_650M_UR50D: README.md; facebook/esm2_t33_650M_UR50D: config.json · ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json |
| Code licence | MITSourcesfacebookresearch/esm: LICENSE · LICENSE: licence text |
| Reference checkpoint | Example release: facebook/esm2_t33_650M_UR50D at 08e4846e537177426273712802403f7ba8261b6c. Its model.safetensors has registry-reported SHA-256 a08adabb949fa67ad3c14b509d04fd60368b35007b0095e3358f81200c4f4db0. This identifies a downloadable 650M checkpoint, not every ESM-2 evaluation.Sourcesesm2 release: primary artifact · sha; siblings[model.safetensors].lfs.sha256 |
| Training data release | The official pretrained-model table labels ESM-2 training data UR50/D 2021_04.Sourcesfacebookresearch/esm: README.md · README: Pre-trained Models table, ESM-2 rows |
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
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.
57 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims | facebook/esm2_t33_650M_UR50D: config.json ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 08e4846e537177426273712802403f7ba8261b6c | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Reference checkpoint, Context limits, Training data release, Training cutoff. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims | facebookresearch/esm: README.md ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Reference checkpoint, Context limits, Training data release, Training cutoff. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims | facebook/esm2_t33_650M_UR50D: README.md ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 08e4846e537177426273712802403f7ba8261b6c | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Reference checkpoint, Context limits, Training data release, Training cutoff. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
Diagram steps
| facebook/esm2_t33_650M_UR50D: config.json ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 08e4846e537177426273712802403f7ba8261b6c | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Reference checkpoint, Context limits, Training data release, Training cutoff. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
Diagram steps
| facebookresearch/esm: README.md ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Reference checkpoint, Context limits, Training data release, Training cutoff. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
Diagram steps
| facebook/esm2_t33_650M_UR50D: README.md ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 08e4846e537177426273712802403f7ba8261b6c | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Reference checkpoint, Context limits, Training data release, Training cutoff. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Diagram title ESM-2 workflow Individual claims | facebook/esm2_t33_650M_UR50D: config.json ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 08e4846e537177426273712802403f7ba8261b6c | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Reference checkpoint, Context limits, Training data release, Training cutoff. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Diagram title ESM-2 workflow Individual claims | facebookresearch/esm: README.md ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Reference checkpoint, Context limits, Training data release, Training cutoff. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Diagram title ESM-2 workflow Individual claims | facebook/esm2_t33_650M_UR50D: README.md ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 08e4846e537177426273712802403f7ba8261b6c | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Reference checkpoint, Context limits, Training data release, Training cutoff. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Model type Masked-token protein transformer encoder Individual claims | facebook/esm2_t33_650M_UR50D: config.json ESM README: Pre-trained Models and Main models; official facebook/esm2_t33_650M_UR50D README licence metadata and config.json Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 08e4846e537177426273712802403f7ba8261b6c | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Reference checkpoint, Context limits, Training data release, Training cutoff. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: discovered
Stable ID: catalog-model-esm-2