Multi-View Substructure Learning for Drug-Drug Interaction Prediction
This addresses incomplete and noisy information in DDI prediction for drug development, offering incremental improvements in accuracy and generalization.
The paper tackles drug-drug interaction (DDI) prediction by proposing a multi-view substructure learning method, achieving a 19.32% relative accuracy improvement and over 99% accuracy in transductive settings, with better generalization to unseen drugs.
Drug-drug interaction (DDI) prediction provides a drug combination strategy for systemically effective treatment. Previous studies usually model drug information constrained on a single view such as the drug itself, leading to incomplete and noisy information, which limits the accuracy of DDI prediction. In this work, we propose a novel multi- view drug substructure network for DDI prediction (MSN-DDI), which learns chemical substructures from both the representations of the single drug (intra-view) and the drug pair (inter-view) simultaneously and utilizes the substructures to update the drug representation iteratively. Comprehensive evaluations demonstrate that MSN-DDI has almost solved DDI prediction for existing drugs by achieving a relatively improved accuracy of 19.32% and an over 99% accuracy under the transductive setting. More importantly, MSN-DDI exhibits better generalization ability to unseen drugs with a relatively improved accuracy of 7.07% under more challenging inductive scenarios. Finally, MSN-DDI improves prediction performance for real-world DDI applications to new drugs.