An Optimized Drug Similarity Framework for Side-effect Prediction

Drug side-effects are crucial issues in both the pre-market drug developing process and post-market drug clinical applications. They contribute to one-third of drug failures and cause significant fatality and severe morbidity. Thus the early identification of potential drug side-effects is of great interests. Most existing methods essentially rely on leveraging few drug similarities directly for side-effect predictions, ignoring the performance improvement by drug similarity integration and optimization. In this study, we proposed an optimized drug similarity framework (ODSF) to improve the performance of side-effect predictions. First, this framework integrates four different drug similarities into a comprehensive similarity. Next, the comprehensive similarity is optimized via clustering and then enhanced by indirect drug similarity. Finally, the optimized drug similarity is employed for side-effect predictions. The performance of ODSF was evaluated on simulative side-effect predictions of 917 drugs from the DrugBank. Extensive comparison experiments demonstrate that ODSF is competent to capture drug features from diverse perspectives and the prediction performance is significantly improved owing to the optimized drug similarity.