ABTrans: A Transformer-based model for predicting interaction between anti-Aß antibodies and peptides
Bibliographic record
Abstract
Abstract Understanding the recognition of antibodies and Aβ peptide is crucial for the development of more effective therapeutic agents. Here we studied the interaction between anti-Aβ antibodies and different peptides by building a deep learning model, using the dodecapeptide sequences elucidated from phage display and known anti-Aβ antibody sequences collected from public sources. Our multi-classification model, ABTrans was trained to determine the four levels of binding ability between anti-Aβ antibody and dodecapeptide: not binding, weak binding, medium binding, and strong binding. The accuracy of our model reached 0.8278. Using the ABTrans, we examined the cross-reaction of anti-Aβ antibodies with other human amyloidogenic proteins, and we found that Aducanumab and Donanemab have the least cross-reactions with other human amyloidogenic proteins. We also systematically screened all human proteins interaction with eleven selected anti-Aβ antibodies to identify possible peptide fragments that could be an off-target candidate. Key Points ABTrans is a Transformer-based model that was developed for the first time to predict the interaction between anti-Aß antibodies and peptides. ABTrans was trained using a dataset with 1.5 million peptides and 110 anti-Aβ antibodies. ABTrans achieved an accuracy of 0.8278 and is capable of determining the four levels of binding ability between antibody and Aß: not binding, weak binding, medium binding, and strong binding. ABTrans has potential applications in predicting off-target and cross-reactivity effects of antibodies and in designing new anti-Aß antibodies.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".