Motivation: Drug-target interaction (DTI) prediction is crucial for drug discovery, significantly reducing costs and time in experimental searches across vast drug compound spaces. While deep learning has advanced DTI prediction accuracy, challenges remain: (i) existing methods often lack generalizability, with performance dropping significantly on unseen proteins and cross-domain settings; (ii) current molecular relational learning often overlooks subpocket-level interactions, which are vital for a detailed understanding of binding sites.
Results: We introduce SP-DTI, a subpocket-informed transformer model designed to address these challenges through: (i) detailed subpocket analysis using the Cavity Identification and Analysis Routine (CAVIAR) for interaction modeling at both global and local levels, and (ii) integration of pre-trained language models into graph neural networks to encode drugs and proteins, enhancing generalizability to unlabeled data. Benchmark evaluations show that SP-DTI consistently outperforms state-of-the-art models, achieving a ROC-AUC of 0.873 in unseen protein settings, an 11% improvement over the best baseline.
Availability and implementation: The model scripts are available at https://github.com/Steven51516/SP-DTI.
Contact and supplementary information: For correspondence, please contact [email protected]. Supplementary data are available online at Bioinformatics.
© The Author(s) 2025. Published by Oxford University Press.