Interpretable Multi-domain Awareness Scheme for Drug-target Interaction Prediction

Predicting drug-target interactions (DTI) is a fundamental step in drug discovery, where deep learning methods show promising performance. However, current approaches encounter challenges in interpretable generalizing the drug-target interactions and adapting to out-of-distribution data. To solve them, we propose a Multi-domain Awareness Drug-Target Interaction (MADTI) framework, which captures the overlooked shallow concrete features and intrinsic biological traits. Specifically, our design enhances the model’s understanding of shallow features in drug graphs and target sequences while retaining the advantages of existing methods that emphasize deep features. This multi-level domain comprehension, combined with the ability of the Category Awareness Domain Adaption(CADA) module to understand biological patterns in positive and negative samples, improves predictive accuracy in cross-domain scenarios. Additionally, by employing bilinear attention and gated attention to learn the multi-level interaction patterns of drug-target pairs explicitly, we further enhance the model’s biological interpretability. Through extensive experiments, MADTI demonstrates significant improvements over state-of-the-art methods, achieving higher AUC-ROC and PR-AUC in various tasks, including conventional prediction, missing data prediction, single-modality prediction, and clustering-based out-of-distribution prediction. The code are available at https://github.com/lian-xiao/MADTI.