Drug repurposing improvement using a novel data integration framework based on the drug side effect

Abstract

The most significant drawback of experimental methods in drug development and discovery is that they are time-consuming and costly. Researches have indicated that designing a new drug from primary stages to its delivery to the consumer market lasts between 10 and 15 years. Moreover, this process costs about 0.8–1.5 billion dollars. Drug repurposing refers to seeking new indications for approved drugs. Recently, some methods have attempted to repurpose drugs based on incorporating computational approaches. In the present research, a method has been proposed for drug repurposing with the aim of integrating diverse and heterogeneous data sources, called DRSE. The proposed method can predict drug-disease associations based on the integration of multiple data sources through a matrix factorization algorithm considering side effect features of the drugs. The experimental results confirmed that the proposed method can improve accuracy of the drug repurposing task. In addition, the AUC and AUPR criteria have been improved by 1.13 and 14.23%, respectively, compared to the state-of-the-art methods. • A framework for drug repurposing by integration of diverse and heterogeneous data sources is proposed. • It predicts drug-disease associations by a matrix factorization algorithm based on side-effect features of drugs. • It uses a Random Walk with Restart (RWR) and feature compacting technique.