Online resources for the prediction of biological activity of organic compounds

Abstract

Online resources (PASS Online, SuperPred, SwissTargetPrediction and DRAR-CPI) for the prediction of biological activity of organic compounds from their structural formulas were considered. Based on a test set of drugs approved by 2014, the accuracies of predictions were compared. The four web resources can be arranged with respect to the quality of prediction (sensitivity, S) as follows: SwissTargetPrediction (S = 0.37) < DRAR-CPI (S = 0.41) < Super-Pred (S = 0.53) < PASS Online (S = 0.95). A conclusion was made that PASS Online employs superior machine learning algorithms based on MNA descriptors and Bayessian classifier in contrast to the similarity-based methods used in SuperPred and SwissTargetPrediction or the molecular docking methods used in DRAR-CPI. Possible reasons for the low prediction quality of SuperPred, SwissTargetPrediction, and DRAR-CPI are discussed and the development perspectives of this area of computational chemistry are given.