Experimentally found gene expression profiles are used to solve different problems in зharmaceutical studies, such as drug repositioning, resistance, toxicity and drug–drug interactions. A special web service, DIGEP-Pred, for prediction of drug-induced changes of gene expression profiles based on structural formulae of chemicals has been developed. Structure–activity relationships for prediction of drug-induced gene expression profiles were determined by Prediction of Activity Spectra for Substances (PASS) software. Comparative Toxicogenomics Database with data on the known drug-induced gene expression profiles of chemicals was used to create mRNA and protein-based training sets. An average prediction accuracy for the training sets (ROC AUC) calculated by leave-one-out cross-validation on the basis ofmRNA data (1385 compounds, 952 genes, 500 up and 475 down-regulations) and protein data (1451 compounds, 139 genes, 93 up- and 55 down-regulations) exceeded 0.85.
Bioinformatics, 2013, 29 (16): 2062-2063.

The evaluation of possible interactions between chemical compounds and antitarget proteins is an important task of the research and development process. Here, we describe the development and validation of QSAR models for the prediction of antitarget end-points, created on the basis of multilevel and quantitative neighborhoods of atom descriptors and selfconsistent regression. Data on 4000 chemical compounds interacting with 18 antitarget proteins (13 receptors, 2 enzymes, and 3 transporters) were used to model 32 sets of end-points (IC50, Ki, and Kact). Each set was randomly divided into training and test sets in a ratio of 80% to 20%, respectively. The test sets were used for external validation of QSAR models created on the basis of the training sets. The coverage of prediction for all test sets exceeded 95%, and for half of the test sets, it was 100%. The accuracy of prediction for 29 of the endpoints, based on the external test sets, was typically in the range of R2 test = 0.6− 0.9; three tests sets had lower R2 test values, specifically 0.55−0.6. The proposed approach showed a reasonable accuracy of prediction for 91% of the antitarget end-points and high coverage for all external test sets. On the basis of the created models, we have developed a freely available online service for in silico prediction of 32 antitarget end-points: http://www.pharmaexpert.ru/ GUSAR/antitargets.html.
Chemical Research in Toxicology, 2012, 25 (11) 2378-2385.

OpenTox provides an interoperable, standards-based Framework for the support of predictive toxicology data management, algorithms, modelling, validation and reporting. It is relevant to satisfying the chemical safety assessment requirements of the REACH legislation as it supports access to experimental data, (Quantitative) Structure-Activity Relationship models, and toxicological information through an integrating platform that adheres to regulatory requirements and OECD validation principles. Initial research defined the essential components of the Framework including the approach to data access, schema and management, use of controlled vocabularies and ontologies, architecture, web service and communications protocols, and selection and integration of algorithms for predictive modelling. OpenTox provides end-user oriented tools to non-computational specialists, risk assessors, and toxicological experts in addition to Application Programming Interfaces (APIs) for developers of new applications. OpenTox actively supports public standards for data representation, interfaces, vocabularies and ontologies, Open Source approaches to core platform components, and community-based collaboration approaches, so as to progress system interoperability goals. The OpenTox Framework includes APIs and services for compounds, datasets, features, algorithms, models, ontologies, tasks, validation, and reporting which may be combined into multiple applications satisfying a variety of different user needs. OpenTox applications are based on a set of distributed, interoperable OpenTox API-compliant REST web services. The OpenTox approach to ontology allows for efficient mapping of complementary data coming from different datasets into a unifying structure having a shared terminology and representation. Two initial OpenTox applications are presented as an illustration of the potential impact of OpenTox for high-quality and consistent structure-activity relationship modelling of REACH-relevant endpoints: ToxPredict which predicts and reports on toxicities for endpoints for an input chemical structure, and ToxCreate which builds and validates a predictive toxicity model based on an input toxicology dataset. Because of the extensible nature of the standardised Framework design, barriers of interoperability between applications and content are removed, as the user may combine data, models and validation from multiple sources in a dependable and time-effective way.
Journal of Cheminformatics, 2010, 2: 7.

During the XX century the dominant paradigm in creation of new drugs was based on suggestion about selectivity of action on a certain molecular target, which should lead to the normalization of pathological process. At the same time, the majority of known drugs interact with several or even many targets in the organism; however such action is mostly associated with unwanted adverse effects and toxicity. After the deciphering of human genome and first results achieved in postgenomic studies it became obvious that many diseases have a complex etiology, while drug action on a certain target often leads to activation/blockade of other elements in the appropriate regulatory network. As a consequence of negative feedbacks, expected pharmacotherapeutic action may be significantly decreased or even completely suppressed. The multitargeted drugs concept appears, according which such remedies due to the additive, synergistic or antagonistic action might have some advantages comparing to the monotargeted medicines. Discovery of new multitargeted drugs requires the solution of two tasks: (1) identification of targets which could be blocked or activated to achieve the desirable pharmacotherapeutic effect, and (2) finding of ligands that interact with the identified targets in a desirable mode. The first aim could be achieved by simulation of behavior in regulatory network blocking or activating certain nodes (targets) and their combinations. The second aim could be achieved either by prediction of biological activity spectra for molecules from different databases and selection of hits with the requested biological profiles, or by direct computer-aided design of multitargeted ligands. Possibilities and limitations of current bioinformatics and computer-aided drug design methods in discovery of particular molecular targets and their multiple ligands will be discussed.
Med. Chem. Res., 2010, 19 (S1), s30.

Finding and optimization of new HIV-1 integrase inhibitors is an important task due to the drawbacks of the existing antiretroviral therapy caused by the significant adverse effects, high cost of the treatment, and emerging resistance. In this study we used computer-assisted methods for finding and optimization of new HIV-1 integrase inhibitors blocking the 3’-processing reaction. Possibility of application of the specialized version of computer program PASS for searching original inhibitors of 3'-processing reaction among the commercially available samples of chemical compounds, belonging to a new chemical class, is shown. We compared the general pharmacological profiles calculated by PASS for the sets of original integrase inhibitors discovered in the study with those for known inhibitors published in literature. It was shown that the predicted average selectivity is close for the compounds from both sets, while the predicted adverse/toxic actions are less for the original compounds. Differences of pharmacological profiles of original compounds and known from literature inhibitors of 3 '-processing pointed out to the essential novelty of our substances. Significantly less deviations from the recommended values for QikProp parameters, which characterized the ADME properties, have been observed for the original compounds than for the integrase inhibitors published in literature. Thus, one may come to the conclusion that the original compounds look more prospective comparing to the earlier known inhibitors of 3’-processing.
Biochemistry (Moscow) Supplemental Series B. Biomedical Chemistry, 2010, 4 (1), 59-67.

The majority of biologically active compounds have both pharmacotherapeutic and side/toxic actions. To estimate general efficacy and safety of the molecules under study, their biological potential should be thoroughly evaluated. In an early stage of study, only information about structural formulae was available and was used as an input for computational prediction. Based on a structural formulae of compounds presented as SDF or MOL-files, computer program PASS predicts 900 pharmacological effects, mechanism of action, and specific toxicity. An average accuracy of prediction in leave-one-out cross-validation is about 85%. For evaluating new compounds, scientific community may use PASS via the Internet for free at URL: http://www.ibmh.msk.su/PASS. In the first 18 months of PASS Inet’s use, approximately 1000 researchers from 60 countries have obtained predicted biological activity spectra for about 23,000 different chemical compounds. More than 64 million PASS predictions for almost 250,000 compounds from Open NCI database are available on the web site http://cactus.nci.nih.gov/ncidb2/. These predictions are used for selecting compounds with desirable and without unwanted types of biological activities among the NCI samples available for screening.
SAR and QSAR in Environmental Research, 2003, 14 (5-6), 339-347.

Using the computer system PASS (prediction of activity spectra for substances), which predicts simultaneously several hundreds of biological activities, a training set for discriminating between drugs and nondrugs is created. For the training set, two subsets of databases of drugs and nondrugs (a subset of the World Drug Index, WDI, vs the Available Chemicals Directory, ACD) are used. The high value of prediction accuracy shows that the chemical descriptors and algorithms used in PASS provide highly robust structure-activity relationships and reliable predictions. Compared to other methods applied in this field, the direct benchmark undertaken with this paper showed that the results obtained with PASS are in good accordance with these approaches. In addition, it has been shown that the more specific drug information used in the training set of PASS, the more specific discrimination between drug and nondrug can be obtained.
Journal of Medicinal Chemistry, 2001, 44 (15), 2432-2437.