Accurate identification of drug-target interactions (DTI) remains a central challenge in computational pharmacology, where sequence-based methods offer scalability. This work introduces a sequence-based drug-target interaction framework that integrates structural priors into protein representations while maintaining high-throughput screening capability. Evaluated across multiple benchmarks, the model achieves state-of-the-art performance on Human and BioSNAP datasets and remains competitive on BindingDB. In virtual screening tasks, it surpasses prior methods on LIT-PCBA, yielding substantial gains in AUROC and BEDROC. Ablation studies confirm the critical role of learned aggregation, bilinear attention, and contrastive alignment in enhancing predictive robustness. Embedding visualizations reveal improved spatial correspondence with known binding pockets and highlight interpretable attention patterns over ligand-residue contacts. These results validate the framework's utility for scalable and structure-aware DTI prediction.
@article{arxiv.2509.14788,
title = {Structure-Aware Contrastive Learning with Fine-Grained Binding Representations for Drug Discovery},
author = {Jing Lan and Hexiao Ding and Hongzhao Chen and Yufeng Jiang and Nga-Chun Ng and Gwing Kei Yip and Gerald W. Y. Cheng and Yunlin Mao and Jing Cai and Liang-ting Lin and Jung Sun Yoo},
journal= {arXiv preprint arXiv:2509.14788},
year = {2026}
}
Comments
Accepted by 2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026)