Robustness of biological activity spectra predicting by computer program PASS for noncongeneric sets of chemical compounds

The computer system PASS provides simultaneous prediction of several hundre ds of biological activity types for any drug-like compound. The prediction is based on the analysis of structure-activity relationships of the trainin g set including more than 30000 known biologically active compounds. In thi s paper we investigate the influence on the accuracy of predicting the type s of activity with PASS by (a) reduction of the number of structures in the training set and (b) reduction of the number of known activities in the tr aining set. The compounds from the MDDR database are used to create heterog eneous training and evaluation sets. We demonstrate that predictions are ro bust despite the exclusion of up to 60%,of information.