DrugPredict: Online drug discovery service using polypharmacology-based interaction profiling
Most drugs exert their effects via multi-target interactions, as hypothesized by polypharmacology. While these multi-target interactions are responsible for the clinical effect profiles of drugs, current methods have failed to uncover the complex relationships between them. We introduce an approach which is able to relate complex drug-protein interaction profiles with effect profiles. Structural data and registered effect profiles of all small-molecule drugs were collected and interactions to a series of non-target protein sites of each drug were calculated. Statistical analyses confirmed a close relationship between the effect and interaction profiles. Based on this relationship, the effect profiles of drugs can be revealed in their entirety, and hitherto uncovered effects can be predicted in a systematic manner. In order to facilitate the use of this method, we present an online service at www.drugpredict.com , containing chemical information on 28 million small-molecule compounds (generated by JChem Base). From this set, 100 000 molecules, including the aforementioned 1200 FDA-approved drugs, were already examined and their pharmacological profiles have been generated. Users of DrugPredict are able to draw or upload further custom compounds in order to determine their possible physiological effects. Currently, our service is able to predict the quantitative probability of 181 therapeutic effect categories.