Predicts effective drug combinations. PDC-SGB is based on a stochastic gradient boosting algorithm. It integrates biological, chemical and pharmacological information. The method aims to help narrow the search space of possible drug combinations. It integrates six types of features to describe the drug combinations, which include the molecular two-dimensional (2D) structures, structural similarity, anatomical therapeutic similarity, protein-protein interaction (PPI), chemical-chemical interaction, and disease pathways.
State Key Laboratory of Microbial Metabolism, and College of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, China
PDC-SGB funding source(s)
Supported by the funding from National Key Research Program (Contract No. 2016YFA0501703), the grant from National Natural Science Foundation of China (NSFC, Grant No. 31371261), and the grants from NSFC for Young Scholars (Grant No. 31601074 and 31400704).