Metraipolis › archive › dc_103bd2561868
BERT4DTI : BERT-based Model for Predicting Drug-Protein Interactions — arXiv:2609.33254
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33254
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:01:12.404Z
- SHA-256 of the archived text
2b8989bbb314ae48acee03fc091a4bbf0c92ca9ca126e2647208af6f4f4b5ad8- Stable URL of this page
https://metraipolis.com/documento/dc_103bd2561868
How to cite
BERT4DTI : BERT-based Model for Predicting Drug-Protein Interactions — arXiv:2609.33254 — arXiv (en), https://arxiv.org/abs/2609.33254 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_103bd2561868 (Metraipolis archive dc_103bd2561868, sha256 2b8989bbb314ae48acee03fc091a4bbf0c92ca9ca126e2647208af6f4f4b5ad8)
BibTeX
@misc{dc103bd2561868,
title = {BERT4DTI : BERT-based Model for Predicting Drug-Protein Interactions — arXiv:2609.33254},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33254},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_103bd2561868; sha256 2b8989bbb314ae48acee03fc091a4bbf0c92ca9ca126e2647208af6f4f4b5ad8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33254. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Understanding how drugs interact with protein targets is fundamental to drug discovery, drug repurposing and the early identification of promising therapeutic candidates before costly experimental testing. Sequence-based DTI models face three practical limitations: labelled interactions are scarce and unevenly distributed, large pretrained chemical and protein encoders are expensive to fine-tune end-to-end, and independently encoded sequences do not capture pair-specific dependencies. We present BERT4DTI, which encodes SMILES strings with ChemBERTa and amino-acid sequences with ProtBERT, applies bidirectional mutual attention between token-level representations, and classifies the resulting interaction features using convolutional layers and a multilayer perceptron. To reduce trainable size, ProtBERT is truncated to 18 retained layers and only the last two layers of each encoder are fine-tuned. On BIOSNAP, DAVIS and BindingDB, BERT4DTI is competitive, achieving the best ROC-AUC and PR-AUC on BIOSNAP and the highest sensitivity on all three benchmarks. An ablation on DAVIS shows that mutual attention improves PR-AUC and specificity. With 125M trainable parameters compared with 353M for full BERT fine-tuning, BERT4DTI provides a favourable performance-parameter trade-off for sequence-based DTI screening, while leaving runtime profiling, calibration and leakage-audited validation for future work. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.33254 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:02.592Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).