DTF: Deep Tensor Factorization for Predicting Anticancer Drug Synergy

Combination therapies have been widely used to treat cancers. However, it is cost- and time-consuming to experimentally screen synergistic drug pairs due to the enormous number of possible drug combinations. Thus, computational methods have become an important way to predict and prioritize synergistic drug pairs. We proposed a Deep Tensor Factorization (DTF) model, which integrated a tensor factorization method and a deep neural network (DNN), to predict drug synergy. The former extracts la-tent features from drug synergy information while the latter constructs a binary classifier to predict the drug synergy status. Compared to the tensor-based method, the DTF model performed better in predicting drug synergy. The area under the curve (AUC) of the receiver operating characteristic was 0.92 for DTF and 0.88 for the tensor method. We also compared the DTF model with random forest and logistic regression models and found that the DTF outperformed the two methods. A further look at the predictive performance of the DTF on the basis of individual cell lines found that the DTF showed an AUC greater than 0.90 for the majority of the cell lines. Applying the DTF model to predict missing entries in our drug-cell line tensor, we identified novel synergistic drug combinations for 27 cell lines from the six cancer types. A literature survey showed that some of these predicted drug synergies have been identified in vivo or in vitro. Thus, the DTF model could be valuable in silico tool for prioritizing novel synergistic drug combinations.