Virtual screening and design of new pharmaceutical agents using pass approach

Among the numerous tools currently used for virtual screening PASS occupies a special place because its development has been started over 20 years ago, and during the past time it is improved and extended permanently [1, 2]. Current version of PASS (Prediction of Activity Spectra for Substances) predicts 6,400 biological activities of drug-like compounds with a mean accuracy of about 95% based on analysis of structure-activity relationships for the training set consisted of 330,000 biologically active compounds.