A Network Approach for Computational Drug Repositioning

Abstract

Computational drug repositioning offers promise for discovering new uses of existing drugs, as drug related molecular, chemical, and clinical information has increased over the past decade and become broadly accessible. In this study, we present a new computational approach for identifying potential new indications of an existing drug through its relation to similar drugs in disease-drug-target network. When measuring drug pairwise similarly, we used a bipartite-graph based method which combined similarity of drug compound structures, similarity of target protein profiles, and interaction between target proteins. In evaluation, our method compared favorably to the state of the art, achieving AUC of 0.888. The results indicated that our method is able to identify drug repositioning opportunities by exploring complex relationships in disease-drug-target network.