The problem of assessing the biological activity of organic xenobiotics using calculations like «structure – activity» is considered. This issue arises due to the fact that the number of anthropogenic and natural xenobiotics in environment exceed the maximum allowable concentrations. Examples of such calculations for xenobiotics detected in water bodies illustrate the practical solution of the problem.
Water: Chemistry and Ecology, 2012, No. 1, p.3-12.

In this paper, we associate an applicability domain (AD) of QSAR/QSPR models with the area in the input (descriptor) space in which the density of training data points exceeds a certain threshold. It could be proved that the predictive performance of the models (built on the training set) is larger for the test compounds inside the high density area, than for those outside this area. Instead of searching a decision surface separating high and low density areas in the input space, the one-class classification 1-SVM approach looks for a hyperplane in the associated feature space. Unlike other reported in the literature AD definitions, this approach: (i) is purely “data-based”, i.e. it assigns the same AD to all models built on the same training set, (ii) provides results that depend only on the initial descriptors pool generated for the training set, (iii) can be used for the huge number of descriptors, as well as in the framework of structured kernel-based approaches, e.g., chemical graph kernels. The developed approach has been applied to improve the performance of QSPR models for stability constants of the complexes of organic ligands with alkaline-earth metals in water.
Molecular Informatics, Volume 29, Issue 8-9, pages 581–587, September 17, 2010 (DOI: 0.1002/minf.201000063)

Computer aided prediction of biological activity spectra has been carried out for 50 new thiazolyl and benzothiazolyl derivatives. Predicted activity spectra for different compounds from the set include 1±8 activities with estimated probability to be found more than 50%, which cover both possible therapeutic and adverseyside effects. Experimental data coincide with the prediction for 25 of 39 compounds tested as NSAIDs (64.1%); for 4 of 6 compounds tested as local anaesthetics (66.7%); for 1 compound tested as antioxidants (100%). The concordance that describes the overall percentage of correct predictions equals to 65.2% that is sufficient to use this approach for optimization of biological testing. In particular, the compounds from studied data set will be further tested according to the additional predicted activities. Description of the current version of computer system PASS and feasibility for free testing is available via Internet on http://www.ibmh.msk.su/ PASS.
Quantitative Structure-Activity Relationships, 18 (1) 16-25.

Computer-aided prediction of rodent carcinogenicity for the external test set consisting of 293 chemicals was performed by PASS (Prediction of Activity Spectra for Substances) and by CISOC-PSCT. The set included 64 carcinogens from ISS Carcinogens Data Bank and 229 noncarcinogens from the Prestwick Chemical Library. We calculated the accuracy of carcinogenicity prediction by PASS and CISOC-PSCT in apart, and by the two programs together (the consensus model). Sensitivity, specificity and accuracy (concordance) were calculated for the external test set by PASS (0.81, 0.74, 0.76), by CISOC-PSCT (0.36, 0.89, 0.77) and by the consensus model (0.69, 0.86, 0.83). Thus, taking into account the prediction results of two computer programs for rodent carcinogenicity the consensus model increases the accuracy of prediction.
QSAR and Combinatorial Science, 2009, 28 (8) 806-810.