A network-based trans-omics approach for predicting synergistic drug combinations

Combination therapy can offer greater efficacy on medical treatments. However, the discovery of synergistic drug combinations is challenging. We propose a novel computational method, SyndrumNET, to predict synergistic drug combinations by network propagation with trans-omics analyses. The prediction is based on the topological relationship, network-based proximity, and transcriptional correlation between diseases and drugs. SyndrumNET was applied to analyzing six diseases including asthma, diabetes, hypertension, colorectal cancer, acute myeloid leukemia (AML), and chronic myeloid leukemia (CML). Here we show that SyndrumNET outperforms the previous methods in terms of high accuracy. We perform in vitro cell survival assays to validate our prediction for CML. Of the top 17 predicted drug pairs, 14 drug pairs successfully exhibits synergistic anticancer effects. Our mode-of-action analysis also reveals that the drug synergy of the top predicted combination of capsaicin and mitoxantrone is due to the complementary regulation of 12 pathways, including the Rap1 signaling pathway. The proposed method is expected to be useful for discovering synergistic drug combinations for various complex diseases. Adding drug treatments together can sometimes produce better results for patients. We introduced a new computer-based method called SyndrumNET, designed to identify effective drug combinations for treating diseases. The method uses data about how diseases and drugs interact at a molecular level to predict which drugs work well together. Tested on six different diseases, such as asthma and different types of cancer, SyndrumNET proved to be more accurate than previous approaches. For example, most of the drug combinations predicted by SyndrumNET to rank highly have shown better combination effects on leukemia cells. This method also helped understand why certain drug combinations work better by analyzing their effects on cellular pathways. The findings suggest that SyndrumNET could be a valuable tool in developing more effective treatment for various complex diseases. Iida et al. predict synergistic drug combinations using a computational method termed SyndrumNET. Validation of predictions in chronic myeloid leukemia using in vitro cell survival assays reveal synergistic anticancer effects in 14 of 17 top predicted drug pairings.