A novel framework for drug synergy prediction using differential evolution based multinomial random forest

Abstract

An efficient prediction of drug synergy plays a significant role in the medical domain. Examination of different drug-drug interaction can be achieved by considering the drug synergy score. With an rapid increase in cancer disease, it becomes difficult for doctors to predict significant amount of drug synergy. Because each cancer patient's infection level varies. Therefore, less or more amount of drug may harm these patients. Machine learning techniques are extensively used to estimate drug synergy score. However, machine learning based drug synergy prediction approaches suffer from the parameter tuning problem. To overcome this issue, in this paper, an efficient Differential evolution based multinomial random forest (DERF) is designed and implemented. Extensive experiments by considering the existing and the proposed DERF based machine learning models. The comparative analysis of DERF reveals that it outperforms existing techniques in terms of coefficient of determination, root mean squared error and accuracy.