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

TL;DR

CDI-DTI is a novel cross-domain, interpretable framework for drug-target interaction prediction that integrates multi-modal features and advanced attention mechanisms to improve robustness, interpretability, and performance in cold-start scenarios.

Contribution

It introduces a multi-strategy fusion approach with cross-attention and Gram Loss for enhanced interpretability and cross-domain generalization in DTI prediction.

Findings

Outperforms existing methods on benchmark datasets.

Demonstrates robustness in cross-domain and cold-start scenarios.

Maintains high interpretability for practical applications.

Abstract

Accurate prediction of drug-target interactions (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 multi-modal features-textual, structural, and functional-through a multi-strategy fusion approach, CDI-DTI ensures robust performance across different domains and in cold-start scenarios. A multi-source cross-attention mechanism is introduced to align and fuse features early, while a bidirectional cross-attention layer captures fine-grained intra-modal drug-target interactions. To enhance model interpretability, we incorporate Gram Loss for feature alignment and a deep orthogonal fusion module to eliminate redundancy. Experimental results on several benchmark datasets 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.