Predicting Drug–Drug Interaction via Dual-Drug Visual Representation

Drug-drug interaction (DDI) prediction is essential for ensuring medication safety and therapeutic efficacy. While existing models often rely on chemical descriptors or molecular graphs, they tend to overlook the rich spatial and structural cues embedded in visual molecules. To address this issue, we propose DDVR-DDI, a novel vision-based framework that predicts DDIs by encoding drug pairs as a single fused molecular image, enabling direct modeling of their potential interaction interface. To enhance representation learning of visual drug pairs, we introduce a two-stage self-supervised pretraining strategy: a position-invariant contrastive task improves understanding of certain drug pairs in different spatial variations, while a jigsaw puzzle task encourages fine-grained structural understanding. Additionally, we develop a multiexpert voting mechanism, where multiple models analyze distinct augmented views of each drug pair to boost prediction accuracy and stability through ensemble inference. Extensive experiments on benchmark DDI data sets show that our model achieves state-of-the-art performance. To further interpret its predictions, we employ Grad-CAM visualizations and conduct multiple experiments to validate the stability and interpretability of the model; furthermore, we conduct a case study on Ritonavir inhibition of CYP3A, revealing that our model consistently highlights chemically significant substructures. These findings underscore the potential of image-based modeling for both accurate prediction and mechanistic insight in drug interaction research.