Multi-View Substructure Learning for Drug-Drug Interaction Prediction

TL;DR

This paper introduces MSN-DDI, a multi-view network that learns drug substructures from both individual drugs and drug pairs, significantly improving DDI prediction accuracy and generalization to unseen drugs.

Contribution

The paper proposes a novel multi-view drug substructure network that integrates intra-view and inter-view information for enhanced DDI prediction.

Findings

Achieved 19.32% accuracy improvement over existing methods.

Over 99% accuracy in transductive settings.

Improved generalization to unseen drugs by 7.07%.

Abstract

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.