Pipeline

ESM-2 650M embeddings + classifier

This antibody-deamidation pipeline combines ESM-2 sequence embeddings with local sequence information to identify susceptible residues.

Sources

The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · 3. Results/3.4. Performance Evaluation of Models (paragraph 4); Abstract (paragraph 1)

1 evaluation · 1 metric row

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

The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Abstract (paragraph 1); 4. Discussion and Conclusions (paragraph 2)

At a glance

Model type

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

Sources

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

Biological inputs

Antibody amino-acid sequences and local residue context

Sources

The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · 1. Introduction (paragraph 5); 3. Results/3.2. The Use of ESM-2 Embedding for Deamidation Site Prediction (paragraph 4)

Outputs

Deamidation propensity and extent predictions

Sources

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

Evaluations and results

Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
ESM-2 650M embeddings + classifier: antibody deamidation-site prediction Pipeline: ESM-2 650M embeddings + classifierTask: antibody deamidation-site predictionDataset: antibody peptide-mapping training dataset global contextual embeddings only Author-reported evaluation · Evaluation metadata: needs review
0.944 accuracy Unit: fraction · Direction: unknown	Uncertainty: ± 0.012 Scored: Not reported · Eligible: Not reported	source checkedThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Table 1, Global embeddings only row, Accuracy column Source checking is not independent reproduction.

How it works

How the evaluated method works

A chimeric supervised predictor integrates pretrained protein-language-model embeddings and a local sequence branch. The score belongs to this complete antibody-specific predictor, not to ESM-2 alone.

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 650M embeddings + classifier: antibody deamidation-site prediction. Its dataset, split, adaptation and evidence origin remain attached to the reported results.

Sources

The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-b2-antibody-deamidation-plm-2024

Strengths and limitations

Strengths and considerations

Uses sequence inputs without requiring an experimentally solved antibody structure.
Sources
The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · 3. Results/3.5. Independent Dataset Predicting Deamidation Hot Spots (paragraph 1); 3. Results/3.3. Enhanced Prediction by Combining ESM-2 Embedding and Local Sequence Information (paragraph 1)

Limitations and conditions

Training labels reflect the study’s antibody modalities and peptide-mapping conditions; transfer to other assay conditions requires evidence.
Sources
The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · 2. Materials and Methods/2.2. Accelerated Thermal Stress (paragraph 1); Abstract (paragraph 1)

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-4921459942b45f

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	A chimeric supervised predictor integrates pretrained protein-language-model embeddings and a local sequence branch. The score belongs to this complete antibody-specific predictor, not to ESM-2 alone. Sources The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Abstract (paragraph 1); 4. Discussion and Conclusions (paragraph 2)
Biological inputs	Antibody amino-acid sequences and local residue context Sources The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · 1. Introduction (paragraph 5); 3. Results/3.2. The Use of ESM-2 Embedding for Deamidation Site Prediction (paragraph 4)
Outputs	Deamidation propensity and extent predictions Sources The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · 3. Results/3.4. Performance Evaluation of Models (paragraph 4); 3. Results/3.2. The Use of ESM-2 Embedding for Deamidation Site Prediction (paragraph 1)
Parameters	650-million-parameter ESM-2 backbone; the total trained pipeline parameter count is not established here. · Not reported in inspected sources Sources The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · 3. Results/3.2. The Use of ESM-2 Embedding for Deamidation Site Prediction (paragraph 2); 4. Discussion and Conclusions (paragraph 6)
Known versions / configuration	esm2_t33_650m_UR50D Sources The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · 3. Results/3.2. The Use of ESM-2 Embedding for Deamidation Site Prediction (paragraph 2); Table antibodies-13-00074-t002 (paragraph 1)
Training data / fitting	An antibody deamidation dataset of 2,285 observations assembled with automated peptide mapping. Sources The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · 3. Results/3.5. Independent Dataset Predicting Deamidation Hot Spots (paragraph 1); 3. Results/3.5. Independent Dataset Predicting Deamidation Hot Spots (paragraph 2)
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) The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning; facebookresearch/esm README.md · 2. Materials and Methods/2.1. Chemicals and Reagents; 2. Materials and Methods/2.2. Accelerated Thermal Stress ; 2. Materials and Methods/2.3. Automated Peptide Mapping; 2. Materials and Methods/2.4. LC-MS/MS Analysis ; 3. Results/3.7. Model Implementation for High-Throughput Screening Drug Candidates; 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 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.

21 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
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	The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning Original source ↗ Abstract (paragraph 1); 4. Discussion and Conclusions (paragraph 2) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:38.478Z	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: `aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps ["Antibody amino-acid sequences and local residue context","ESM-2 650M embeddings + classifier","Deamidation propensity and extent predictions"] Individual claims	The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning Original source ↗ Abstract (paragraph 1); 4. Discussion and Conclusions (paragraph 2) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:38.478Z	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: `aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Evaluated procedure (conceptual) Individual claims	The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning Original source ↗ Abstract (paragraph 1); 4. Discussion and Conclusions (paragraph 2) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:38.478Z	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: `aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b` 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 A chimeric supervised predictor integrates pretrained protein-language-model embeddings and a local sequence branch. The score belongs to this complete antibody-specific predictor, not to ESM-2 alone. Individual claims	The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning Original source ↗ Abstract (paragraph 1); 4. Discussion and Conclusions (paragraph 2) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:38.478Z	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: `aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b` 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 Antibody amino-acid sequences and local residue context Individual claims	The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning Original source ↗ 1. Introduction (paragraph 5); 3. Results/3.2. The Use of ESM-2 Embedding for Deamidation Site Prediction (paragraph 4) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:38.478Z	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: `aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Outputs Deamidation propensity and extent predictions Individual claims	The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning Original source ↗ 3. Results/3.4. Performance Evaluation of Models (paragraph 4); 3. Results/3.2. The Use of ESM-2 Embedding for Deamidation Site Prediction (paragraph 1) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:38.478Z	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: `aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Parameters 650-million-parameter ESM-2 backbone; the total trained pipeline parameter count is not established here. Individual claims	The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning Original source ↗ 3. Results/3.2. The Use of ESM-2 Embedding for Deamidation Site Prediction (paragraph 2); 4. Discussion and Conclusions (paragraph 6) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:38.478Z	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.4.value` Source artifact SHA-256: `aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Known versions / configuration esm2_t33_650m_UR50D Individual claims	The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning Original source ↗ 3. Results/3.2. The Use of ESM-2 Embedding for Deamidation Site Prediction (paragraph 2); Table antibodies-13-00074-t002 (paragraph 1) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:38.478Z	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: `aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b` 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

Release 2026-09-17-d277315f7d76 · Record review: needs review

3 source records and release history

The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Original source · journal full text in PMC
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-4921459942b45f

areas: proteins-complexes
entity level: method
version: esm2_t33_650m_UR50D
reported name: ESM-2 650M embeddings + classifier
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 record identifies a composed analysis workflow with separately identifiable upstream models, representations or tools and a downstream prediction/scoring procedure. Results belong to that complete composition rather than to an upstream model alone.; source ids: antibody-deamidation-plm-2024; evidence-reported-base-esm-readme-md; source locator: Abstract (paragraph 1); 4. Discussion and Conclusions (paragraph 2) | README.md model description | 3. Results/3.4. Performance Evaluation of Models (paragraph 4); Abstract (paragraph 1); ambiguities: This is the paper-specific pipeline identity; unspecified component checkpoints or implementation versions are not inferred from its name.

Related records

model: ESM-2 650M embeddings + classifier: antibody deamidation-site prediction

Suggest a correction