Gromova, A. A. | bioRxiv Science

bioRxiv2025

ChemBERTaPolyPharm: Modeling polypharmacy side effects with ChemBERTa and PubMed Encoders

Polypharmacy side effects occur when drug combinations trigger unexpected interactions, altering therapeutic outcomes. During which the activity of one drug may change favorably or unfavorably if taken with the other drug. Drug interactions are rare and are only observed in clinical studies. Thus, the discovery and detection of polypharmacy side effects remains a challenge. Our approach achieves an impressive average F1 score of 0.93, demonstrating its efficacy in capturing drug interaction patterns. 1 Submission of papers to NeurIPS 2025Please read the instructions below carefully and follow them faithfully.

bioinformatics↗

bioRxiv2025

ChemBERTaDDI: Transforming Drug-Drug Interaction Prediction with Transformers and Clinical Insights

The problem of polypharmacy arises when two or more drugs taken in combination cause adverse side effects, even when the use of the drugs individually causes no harm. Drug-drug interactions (DDIs) are a major cause of these reactions, contributing to increased morbidity and mortality. As the potential for harmful DDI grows combinatorially, the prediction of drug-drug interactions is increasingly critical for patient safety and effective healthcare management. In this paper, we present the ChemBERTaDDI frame-work a robust approach that uses transformer self-attention to extract latent molecular representations. By employing ChemBERTa-77M-MLM--a transformer-based language model pretrained on SMILES sequences--our approach generates enriched chemical embeddings that capture detailed molecular structural information. These embeddings are integrated with clinical mono side effect data and processed through a DNN predictor, enabling the learning of complex pairwise interaction patterns with minimal architectural overhead. Experiments performed using this combined data on a benchmark data set show superior performance compared with five state-of-the-art methods: Decagon, DeepDDI, MDF-SA-DDI, DPSP and NNPS. ChemBER-TaDDI outperforms the baseline architectures, as measured by F1 and AUROC, and generalizes to new introduced drug compounds.

bioinformatics↗