Large-scale exploration and analysis of drug combinations

Motivation: Drug combinations are a promising strategy for combat- ing complex diseases by improving the efficacy and reducing corre- sponding side effects. Currently, a widely studied problem in phar- macology is to predict effective drug combinations, either through empirically screening in clinic or pure experimental trials. However, the large-scale prediction of drug combination by a systems method is rarely considered. Results: We report a systems pharmacology framework to predict drug combinations on a computational model, termed PEA (Proba- bility Ensemble Approach), for analysis of both the efficacy and ad- verse effects of drug combinations. Firstly, a Bayesian network inte- grating with a similarity algorithm is developed to model the combi- nations from drug molecular and pharmacological phenotypes, and the predictions are then assessed with both clinical efficacy and adverse effects. It is illustrated that PEA can predict the combination efficacy of drugs spanning different therapeutic classes with high specificity and sensitivity (AUC = 0.90), which was further validated by independent data or new experimental assays. PEA also evalu- ates the adverse effects (AUC = 0.95) quantitatively and detects the therapeutic indications for drug combinations. Finally, the PreDC (Predict Drug Combination) database includes 1571 known and 3269 predicted optimal combinations as well as their potential side effects and therapeutic indications. Availability and implementation: The PreDC database is available