Drug combinatorial therapy is a promising strategy for combating complex diseases due to\nits fewer side effects, lower toxicity and better efficacy. However, it is not feasible to determine all the\neffective drug combinations in the vast space of possible combinations given the increasing number\nof approved drugs in the market, since the experimental methods for identification of effective drug\ncombinations are both labor- and time-consuming. In this study, we conducted systematic analysis of\nvarious types of features to characterize pairs of drugs. These features included information about the\ntargets of the drugs, the pathway in which the target protein of a drug was involved in, side effects of\ndrugs, metabolic enzymes of the drugs, and drug transporters. The latter two features (metabolic\nenzymes and drug transporters) were related to the metabolism and transportation properties of\ndrugs, which were not analyzed or used in previous studies. Then, we devised a novel improved\nna�¯ve Bayesian algorithm to construct classification models to predict effective drug combinations by\nusing the individual types of features mentioned above. Our results indicated that the performance\nof our proposed method was indeed better than the na�¯ve Bayesian algorithm and other conventional\nclassification algorithms such as support vector machine and K-nearest neighbor.
Loading....