Structure-based prediction of drug side effects using a novel classification algorithm

In silico prediction of drug side-effects in early stage of drug development is becoming more popular now days, which reduces the time for drug design and drug development costs. In this paper, we propose an ensemble approach to predict drug side-effects of drug molecules based on their chemical structure. We applied our approach to 1385 side-effects in the SIDER database for 888 drugs. Results show that our approach outperformed previous approaches and standard classifiers. Furthermore, we apply our method to a number of uncharacterised drug molecules in DrugBank database and predict their side- effects for future usage. Results from various sources confirm that our method is able to predict the side-effects for uncharacterised drugs. Finally, we use our models to identify key chemical substructures that may cause different side- effects. Therefore this method can be useful to predict side-effects in drug design in an early stage to reduce experimental cost and time.