Graph Distance Neural Networks for Predicting Multiple Drug Interactions

TL;DR

This paper introduces Graph Distance Neural Networks (GDNN), a novel approach that models drug interactions as a graph link prediction problem, effectively predicting multiple drug-drug interactions with high accuracy.

Contribution

The paper proposes GDNN, which incorporates distance information and an improved message passing framework for more accurate drug interaction prediction.

Findings

Achieved Test Hits@20=0.9037 on ogb-ddi dataset

Effectively models drug interactions as graph link prediction

Outperforms previous methods in DDI prediction accuracy

Abstract

Since multidrug combination is widely applied, the accurate prediction of drug-drug interaction (DDI) is becoming more and more critical. In our method, we use graph to represent drug-drug interaction: nodes represent drug; edges represent drug-drug interactions. Based on our assumption, we convert the prediction of DDI to link prediction problem, utilizing known drug node characteristics and DDI types to predict unknown DDI types. This work proposes a Graph Distance Neural Network (GDNN) to predict drug-drug interactions. Firstly, GDNN generates initial features for nodes via target point method, fully including the distance information in the graph. Secondly, GDNN adopts an improved message passing framework to better generate each drug node embedded expression, comprehensively considering the nodes and edges characteristics synchronously. Thirdly, GDNN aggregates the embedded expressions, undergoing MLP processing to generate the final predicted drug interaction type. GDNN achieved Test Hits@20=0.9037 on the ogb-ddi dataset, proving GDNN can predict DDI efficiently.