Statistical Learning for Predicting Probable Drug-Drug Interactions using Machine Learning Classifiers

Abstract: Drug-Drug Interaction (DDI) is a change in the effect of a drug when patient takes another drug. Characterizing DDIs is extremely important to avoid potential adverse drug reactions. DDIs are representing as a complex network in which nodes refer to drugs and links refer to their potential interactions. Recently, the problem of link prediction has attracted much consideration in scientific community. The process of link prediction as a binary classification task on networks of potential DDIs are presented. By using link prediction techniques for predicting unknown interactions between drugs in arbitrary chosen large-scale DDI databases namely Two-Sides and Drug bank. The performance of link prediction is estimated using a series of experiments on DDI networks. The link prediction is performed using some of the machine learning classifiers such as random forest; Gradient Boosting .The applied methodology can be used as a tool to help researchers to identify potential DDIs.

Keywords: Random Forest, DNN, Gradient boosting. Pharmacology, Pharmacokinetics