Structure-Aware Contrastive Learning with Fine-Grained Binding Representations for Drug Discovery
This work addresses the problem of scalable drug discovery for computational pharmacology, with incremental improvements in integrating structural information into sequence-based methods.
The paper tackled the challenge of accurately identifying drug-target interactions by introducing a sequence-based framework that integrates structural priors, achieving state-of-the-art performance on Human and BioSNAP datasets and substantial gains in AUROC and BEDROC on LIT-PCBA virtual screening tasks.
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.