Manjit Kaur, Dilbag Singh* and Vijay Kumar Pages 1 - 9 ( 9 )
Purpose: In cancer therapies, drug combinations have shown significance accuracy and minimal side effects than the single drug administration. Therefore, the drug synergy has drawn great interest from pharmaceutical companies and researchers. Unfortunately, the prediction of drug synergy score by purely investigational means is only possible on small groups of drugs.
Methods: With an advancement in high-throughput screening (HTS), the size of drug synergy datasets has grown enormously in recent years. Therefore, recently, many machine learning models have been utilized to predict the drug synergy score. However, the majority of these machine learning models suffer from over-fitting and hyper-parameters tuning issues.
Results: Therefore, a novel deep bidirectional mixture density network (BMDN) model is proposed. To optimize the hyperparameters of BMDN, a dynamic mutation based multi-objective differential evolution is used. Extensive experiments are drawn by using the NCI-ALMANAC drug synergy dataset with over 290,000 synergy determinations.
Conclusions: Experimental results shows that BMDN outperforms the exisitng drug synergy models in terms of various performance metrics.
Drug synergy, deep learning, machine learning, neural networks, BMDN, HTS
Computer Science Engineering, School of Engineering and Applied Sciences, Bennett University, Greater Noida, Computer Science Engineering, School of Engineering and Applied Sciences, Bennett University, Greater Noida, Computer Science and Engineering Department, NIT Hamirpur