CDI-DTI: A Strong Cross-Domain Interpretable Drug-Target Interaction Prediction Framework Based on Multi-Strategy Fusion

Accurate prediction of drug-target interaction (DTI) is pivotal for drug discovery, yet existing methods often fail to address challenges like cross-domain generalization, cold-start prediction, and interpretability. In this work, we propose CDI-DTI, a novel cross-domain interpretable framework for DTI prediction, designed to overcome these limitations. By integrating multimodal features-textual, structural, and functional-through a multistrategy fusion approach, CDI-DTI ensures robust performance across different domains and in cold-start scenarios. A multisource cross-attention mechanism is introduced to align and fuse features early, while a bidirectional cross-attention layer captures fine-grained intramodal drug-target interaction. At the late fusion stage, we incorporate Gram Loss for feature alignment and a deep orthogonal fusion module to eliminate redundancy. Experimental results on several benchmark data sets demonstrate that CDI-DTI significantly outperforms existing methods, particularly in cross-domain and cold-start tasks, while maintaining high interpretability for practical applications in drug-target interaction prediction.