rewirebio.iobenchmarks
Task

antibody deamidation-site prediction

Antibody deamidation-site classification is assessed with class-sensitive metrics and an independent antibody dataset.

SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Results §§3.4–3.5; cached text lines 42–50

1 evaluation · 1 result

Overview

Datasets

Labeled active and inactive sites, including a separate six-antibody evaluation collection.

Metrics

Accuracy, precision, recall, specificity, F1, MCC and ROC-AUC; the source explicitly cautions that accuracy alone hides class imbalance.

Allowed inputs

Antibody sequences and candidate residue positions.

SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Results §§3.4–3.5; cached text lines 42–50
Evaluation procedure diagram
How it worksComputational evaluation flow
Computational evaluation flow1. Input: Antibody sequences and candidate residue positions.. Then: 2. Evaluation: Five-fold stratified cross-validation on training data, then evaluation on the independent collection.. Then: 3. Readout: Accuracy, precision, recall, specificity, F1, MCC and ROC-AUC; the source explicitly cautions that accuracy alone hides class imbalance.Computational evaluation flow1. Input: Antibody sequences and candidate residue positions.. Then: 2. Evaluation: Five-fold stratified cross-validation on training data, then evaluation on the independent collection.. Then: 3. Readout: Accuracy, precision, recall, specificity, F1, MCC and ROC-AUC; the source explicitly cautions that accuracy alone hides class imbalance.Computational evaluation flow1. Input: Antibody sequences and candidate residue positions.. Then: 2. Evaluation: Five-fold stratified cross-validation on training data, then evaluation on the independent collection.. Then: 3. Readout: Accuracy, precision, recall, specificity, F1, MCC and ROC-AUC; the source explicitly cautions that accuracy alone hides class imbalance.

Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.

SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Results §§3.4–3.5; cached text lines 42–50

Source reviewed · Automated source review, 2026-09-16. All specifications and missing details

1 recorded evaluation, 1 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

1 evaluation · 1 result. Different protocols are not a single leaderboard.

Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Pipeline: ESM-2 650M embeddings + classifierTask: antibody deamidation-site prediction
Dataset: antibody peptide-mapping training dataset
0.944 Accuracy
fraction · unknown

Uncertainty: ± 0.012 (type not stated)

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

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

global contextual embeddings only

Aggregation: Not reported

The 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. Release 2026-11-21-adc15377fab2.

Methods and evaluation design

Procedure, tasks and evaluated configurations

How it works

Evaluation methodology

Labeled active and inactive sites, including a separate six-antibody evaluation collection. Five-fold stratified cross-validation on training data, then evaluation on the independent collection. Accuracy, precision, recall, specificity, F1, MCC and ROC-AUC; the source explicitly cautions that accuracy alone hides class imbalance. Global-embedding and local-sequence ablations; published decision-tree/random-forest models and NGOME. Independent testing withholds complete antibodies from the training collection. The source does not establish whether within-training cross-validation also groups every site by antibody.

SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Results §§3.4–3.5; cached text lines 42–50

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Run instructions

No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths supported by sources

No source-reviewed explanatory claims are recorded here yet.

Profile review details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Stable record: reported-task-0647b0364def8f

Specifications

Inputs, training, access and other details

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

Data, procedure and scoring
PropertyDescription and evidence
DatasetsLabeled active and inactive sites, including a separate six-antibody evaluation collection.
SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Results §§3.4–3.5; cached text lines 42–50
SplitsFive-fold stratified cross-validation on training data, then evaluation on the independent collection.
SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Results §§3.4–3.5; cached text lines 42–50
MetricsAccuracy, precision, recall, specificity, F1, MCC and ROC-AUC; the source explicitly cautions that accuracy alone hides class imbalance.
SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Results §§3.4–3.5; cached text lines 42–50
BaselinesGlobal-embedding and local-sequence ablations; published decision-tree/random-forest models and NGOME.
SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Results §§3.4–3.5; cached text lines 42–50
Leakage controlsIndependent testing withholds complete antibodies from the training collection. The source does not establish whether within-training cross-validation also groups every site by antibody.
SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Results §§3.4–3.5; cached text lines 42–50
UncertaintyTable 1 gives values with ± terms for five-fold stratified cross-validation, whereas Table 2 gives point values for the independent test. The table caption does not define the ± terms as a standard deviation, standard error or confidence interval; that interpretation remains unreported.
SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Model-performance discussion and Tables 1–2
Entity typePaper-specific computational evaluation protocol.
SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Results §§3.4–3.5; cached text lines 42–50
OrganismsNISTmAb is a humanized IgG1 antibody. The other antibodies were produced in Chinese hamster ovary cells; this expression host should not be mistaken for their sequence species. The complete sequence-origin composition of the proprietary antibody panel is not reported in Methods 2.1–2.2.
SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Methods 2.1 Chemicals and Reagents; 2.2 Accelerated Thermal Stress
AssaysLabeled antibody deamidation sites.
SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Results §§3.4–3.5; cached text lines 42–50
Allowed inputsAntibody sequences and candidate residue positions.
SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Results §§3.4–3.5; cached text lines 42–50
AdaptationSupervised classifier with stratified cross-validation and an independent antibody evaluation.
SourcesThe Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning · Results §§3.4–3.5; cached text lines 42–50

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Papers and result coverage

Last literature check: 2026-09-17. Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.

Historical gaps recorded on 2026-09-17

The catalogue now holds 1 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.

  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Search and extraction details

primary comparison tables located

Searches

  • The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning 10.3390/antib13030074

Evidence locations

  • Table 2; XML table antibodies-13-00074-t002

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.

17 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-adc15377fab2
Property and statementOriginal source and locationReview and provenance
Diagram caption
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Individual claims
The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning

Original source ↗

Results §§3.4–3.5; cached text lines 42–50

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.478Z

source checked

automated source review · 2026-09-16

Audit details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Field: attributes.profile.diagram.caption

Source artifact SHA-256: aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Diagram steps
  • Input: Antibody sequences and candidate residue positions.
  • Evaluation: Five-fold stratified cross-validation on training data, then evaluation on the independent collection.
  • Readout: Accuracy, precision, recall, specificity, F1, MCC and ROC-AUC; the source explicitly cautions that accuracy alone hides class imbalance.
Individual claims
The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning

Original source ↗

Results §§3.4–3.5; cached text lines 42–50

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.478Z

source checked

automated source review · 2026-09-16

Audit details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Field: attributes.profile.diagram.steps

Source artifact SHA-256: aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Diagram title
Computational evaluation flow
Individual claims
The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning

Original source ↗

Results §§3.4–3.5; cached text lines 42–50

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.478Z

source checked

automated source review · 2026-09-16

Audit details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Field: attributes.profile.diagram.title

Source artifact SHA-256: aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Datasets
Labeled active and inactive sites, including a separate six-antibody evaluation collection.
Individual claims
The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning

Original source ↗

Results §§3.4–3.5; cached text lines 42–50

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.478Z

source checked

automated source review · 2026-09-16

Audit details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Field: attributes.profile.facts.0.value

Source artifact SHA-256: aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Splits
Five-fold stratified cross-validation on training data, then evaluation on the independent collection.
Individual claims
The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning

Original source ↗

Results §§3.4–3.5; cached text lines 42–50

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.478Z

source checked

automated source review · 2026-09-16

Audit details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Field: attributes.profile.facts.1.value

Source artifact SHA-256: aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Adaptation
Supervised classifier with stratified cross-validation and an independent antibody evaluation.
Individual claims
The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning

Original source ↗

Results §§3.4–3.5; cached text lines 42–50

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.478Z

source checked

automated source review · 2026-09-16

Audit details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Field: attributes.profile.facts.10.value

Source artifact SHA-256: aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Metrics
Accuracy, precision, recall, specificity, F1, MCC and ROC-AUC; the source explicitly cautions that accuracy alone hides class imbalance.
Individual claims
The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning

Original source ↗

Results §§3.4–3.5; cached text lines 42–50

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.478Z

source checked

automated source review · 2026-09-16

Audit details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Field: attributes.profile.facts.2.value

Source artifact SHA-256: aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Baselines
Global-embedding and local-sequence ablations; published decision-tree/random-forest models and NGOME.
Individual claims
The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning

Original source ↗

Results §§3.4–3.5; cached text lines 42–50

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.478Z

source checked

automated source review · 2026-09-16

Audit details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Field: attributes.profile.facts.3.value

Source artifact SHA-256: aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Leakage controls
Independent testing withholds complete antibodies from the training collection. The source does not establish whether within-training cross-validation also groups every site by antibody.
Individual claims
The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning

Original source ↗

Results §§3.4–3.5; cached text lines 42–50

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.478Z

source checked

automated source review · 2026-09-16

Audit details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Field: attributes.profile.facts.4.value

Source artifact SHA-256: aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Uncertainty
Table 1 gives values with ± terms for five-fold stratified cross-validation, whereas Table 2 gives point values for the independent test. The table caption does not define the ± terms as a standard deviation, standard error or confidence interval; that interpretation remains unreported.
Individual claims
The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning

Original source ↗

Model-performance discussion and Tables 1–2

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.478Z

source checked

automated source review · 2026-09-16

Audit details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Field: attributes.profile.facts.5.value

Source artifact SHA-256: aa049f6d78e29540ba902a0d3b7f53d49e9833e4dad9869f79ac27664e8c150b

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

How to read the evidence

Sources and history

Release 2026-11-21-adc15377fab2 · Record review: needs review

2 source records and release historyDownload this release (gzip)
Technical metadata and record identifiers

Technical metadata for this record is tracked under stable ID reported-task-0647b0364def8f.

Related records

Suggest a correction