Strengths supported by sources
No source-reviewed explanatory claims are recorded here yet.
Task
antibody deamidation-site prediction
Antibody deamidation-site classification is assessed with class-sensitive metrics and an independent antibody dataset.
Sources
The 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 42–50At a glance
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.
| Property | Description and evidence |
|---|---|
| Datasets | Labeled 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 |
| Splits | Five-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 |
| Metrics | Accuracy, 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 |
| Baselines | Global-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 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.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 |
| 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.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 type | Paper-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 |
| Organisms | NISTmAb 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 |
| Assays | Labeled 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 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 |
| Adaptation | Supervised 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 |
How it works
How it worksComputational evaluation flow
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Sources
The 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 42–50Evaluation 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.
Sources
The 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 42–50Recorded evaluations
Each evaluation records what was tested and under which conditions.
Tested entities and results
Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.
| 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. |
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.
| Paper or primary resource | Version | Reference |
|---|---|---|
| The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning | journal full text in PMC | Read source |
What is still missing
- 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
Strengths and limitations
Limitations and conditions
- Sites within one antibody may be correlated. Five-fold stratification alone does not establish antibody-disjoint evaluation, and expression host does not identify an antibody’s sequence species.
Sources
The 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; Methods 2.1 Chemicals and Reagents; 2.2 Accelerated Thermal Stress
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-0647b0364def8fEvidence 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
| Property and statement | Original source and location | Review 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 Results §§3.4–3.5; cached text lines 42–50 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| 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 Results §§3.4–3.5; cached text lines 42–50 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| 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 Results §§3.4–3.5; cached text lines 42–50 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| 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 Results §§3.4–3.5; cached text lines 42–50 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| 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 Results §§3.4–3.5; cached text lines 42–50 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| 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 Results §§3.4–3.5; cached text lines 42–50 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| 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 Results §§3.4–3.5; cached text lines 42–50 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| 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 Results §§3.4–3.5; cached text lines 42–50 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| 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 Results §§3.4–3.5; cached text lines 42–50 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| 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 Model-performance discussion and Tables 1–2 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-09-17-d277315f7d76 · Record review: needs review
2 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
- 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
Technical metadata and extraction receipts
Stable ID: reported-task-0647b0364def8f
- areas
- proteins-complexes
- tasks
- antibody deamidation-site prediction
- entity level
- task
- version
- Not reported
- task
- antibody deamidation-site prediction
- scope note
- Paper-specific evaluation task; protocol completeness requires further extraction.
- benchmark research
- review date: 2026-09-17; status: primary_comparison_tables_located; primary sources: evidence-expansion-antibody-deamidation-plm-2024-aa049f6d; inspected locators: Table 2; XML table antibodies-13-00074-t002; searched queries: The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning 10.3390/antib13030074; gaps: 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.; claim scope: 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 missing metadata
- protocol version: 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
- benchmark
- entity classification
- review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: antibody-deamidation-plm-2024; source locator: Results §§3.4–3.5; cached text lines 42–50; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.