Deep learning based multi-drug synergy prediction model for individually optimized anti-cancer therapy

In this project, a novel computational method based on deep learning algorithm was successfully developed to predict synergistic multi-drug combinations (DeepMDS) for cancer treatment, which could predict IC50 values of drug combinations to quantify the synergistic anti-cancer effect, providing the most effective combinational therapy for a given cancer cell line from a number of drugs. Therefore, our model DeepMDS could be a very useful tool to enlarge the space of potential synergistic drug combinations by breaking through the limitation of only synergy prediction of two drugs, and provide valuable reference for determining more effective multi-drug combinational therapies for different types of cancer.