Pavel V. Pogodin

PREDICTION OF THE BIOLOGICAL ACTIVITY SPECTRA OF ORGANIC COMPOUNDS USING THE PASS ONLINE WEB RESOURCE

The freely accessible web resource PASS Online is presented. This resource is designed for the prediction of the biological activity spectra of organic compounds based on their structural formulas for more than 4000 types of biological activity with average accuracy above 95% (http://www.way2drug.com/passonline). The prediction is based on an analysis of the structure-activity relationships in the training set containing information on the structure and biological activity of more than 300000 organic compounds. The possibilities and limitations of this approach are described. Recommendations are given for interpreting the prediction results. Examples are given for the practical use of the PASS Online web resource in order to establish priorities for chemical synthesis and biological testing of substances on the basis of prediction results. The further trends are considered for the using PASS Online as an Internet platform for joint projects of academic researchers for the search and development of new pharmaceutical agents.

PASS Targets: Ligand-based multi-target computational system based on a public data and naïve Bayes approach

Estimation of interactions between drug-like compounds and drug targets is very important for drug discovery and toxicity assessment. Using data extracted from the 19th version of the ChEMBL database (https://www.ebi.ac.uk/chembl) as a training set and a Bayesian-like method realized in PASS software (http://www.way2drug.com/PASSOnline), we developed a computational tool for the prediction of interactions between protein targets and drug-like compounds. After training, PASS Targets became able to predict interactions of drug-like compounds with 2507 protein targets from different organisms based on analysis of structure–activity relationships for 589,107 different chemical compounds. The prediction accuracy, estimated as AUC ROC calculated by the leave-one-out cross-validation and 20-fold cross-validation procedures, was about 96%. Average AUC ROC value was about 90% for the external test set from approximately 700 known drugs interacting with 206 protein targets.

Identification of Drug-Induced Myocardial Infarction-Related Protein Targets through the Prediction of Drug–Target Interactions and Analysis of Biological Processes

Drug-induced myocardial infarction (DIMI) is one of the most serious adverse drug effects that often lead to death. Therefore, the identification of DIMI at the early stages of drug development is essential. For this purpose, the in vitro testing and in silico prediction of interactions between drug-like substances and various off-target proteins associated with serious adverse drug reactions are performed. However, only a few DIMI-related protein targets are currently known. We developed a novel in silico approach for the identification of DIMI-related protein targets. This approach is based on the computational prediction of drug-target interaction profiles based on information from approximately 1738 human targets and 828 drugs, including 254 drugs that cause myocardial infarction. Through a statistical analysis, we revealed the 155 most significant associations between protein targets and DIMI. Because not all of the identified associations may lead to DIMI, an analysis of the biological functions of these proteins was performed. The Random Walk with Restart algorithm based on a functional linkage gene network was used to prioritize the revealed DIMI-related protein targets according to the functional similarity between their genes and known genes associated with myocardial infarction. The biological processes associated with the 155 selected protein targets were determined by gene ontology and pathway enrichment analysis. This analysis indicated that most of the processes leading to DIMI are associated with atherosclerosis. The revealed proteins were manually annotated with biological processes using functional and disease-related data extracted from the literature. Finally, the 155 protein targets were classified into three categories of confidence: (1) high (the protein targets are known to be involved in DIMI via atherosclerotic progression; 50 targets), (2) medium (the proteins are known to participate in biological processes related with DIMI; 65 targets), and (3) low (the proteins are indirectly involved in DIMI pathogenesis; 40 proteins).

Molecular imprinting coupled with electrochemical analysis for plasma samples classification in acute myocardial infarction diagnostic

Electroanalysis of myoglobin (Mb) in 10 plasma samples of healthy donors (HDs) and 14 plasma samples of patients with acute myocardial infarction (AMI) was carried out with screen-printed electrodes modified first with multi-walled carbon nanotubes (MWCNT) and then with a molecularly imprinted polymer film (MIP), viz., myoglobin-imprinted electropolymerized poly(o-phenylenediamine). The differential pulse voltammetry (DPV) parameters, such as a maximum amplitude of reduction peak current (A, nA), a reduction peak area (S, nA × V), and a peak potential (P, V), were measured for the MWCNT/MIP-sensors after their incubation with non-diluted plasma. The relevance of the multi-parameter electrochemical data for accurate discrimination between HDs and patients with AMI was assessed on the basis of electrochemical threshold values (this requires the reference standard method (RAMP® immunoassay)) or alternatively on the basis of the computational cluster assay (this does not require any reference standard method). The multi-parameter electrochemical analysis of biosamples combined with computational cluster assay was found to provide better accuracy in classification of plasma samples to the groups of HDs or AMI patients.

Identification of Drug Targets Related to the Induction of Ventricular Tachyarrhythmia Through a Systems Chemical Biology Approach

Ventricular tachyarrhythmia (VT) is one of the most serious adverse drug reactions leading to death. The in vitro assessment of the interaction of lead compounds with HERG potassium channels, which is one of the primary known causes of VT induction, is an obligatory test during drug development. However, experimental and clinical data support the hypothesis that the inhibition of ion channels is not the only mechanism of VT induction. Therefore, the identification of other drug targets contributing to the induction of VT is crucial. We developed a systems chemical biology approach for searching for such targets. This approach involves the following steps: (1) creation of special sets of VT-causing and non-VT-causing drugs, (2) statistical analysis of in silico predicted drug-target interaction profiles of studied drugs with 1738 human protein targets for the identification of potential VT-related targets, (3) gene ontology and pathway enrichment analysis of the revealed targets for the identification of biological processes underlying drug-induced VT etiology, (4) creation of a cardiomyocyte regulatory network (CRN) based on general and heart-specific signaling and regulatory pathways, and (5) simulation of changes in the behavior of the CRN caused by the inhibition of each node for the identification of potential VT-related targets. As a result, we revealed 312 potential VT-related targets and classified them into 3 confidence categories: high (36 proteins), medium (111 proteins), and low (165 proteins) classes. The most probable targets may serve as a basis for experimental confirmation and may be used for in vitro or in silico assessments of the relationships between drug candidates and drug-induced VT, the understanding of contraindications of drug application and dangerous drug combinations.

CLC-Pred: A freely available web-service for in silico prediction of human cell line cytotoxicity for drug-like compounds

In silico methods of phenotypic screening are necessary to reduce the time and cost of the experimental in vivo screening of anticancer agents through dozens of millions of natural and synthetic chemical compounds. We used the previously developed PASS (Prediction of Activity Spectra for Substances) algorithm to create and validate the classification SAR models for predicting the cytotoxicity of chemicals against different types of human cell lines using ChEMBL experimental data. A training set from 59,882 structures of compounds was created based on the experimental data (IG50, IC50, and % inhibition values) from ChEMBL. The average accuracy of prediction (AUC) calculated by leave-one-out and a 20-fold cross-validation procedure during the training was 0.930 and 0.927 for 278 cancer cell lines, respectively, and 0.948 and 0.947 for cytotoxicity prediction for 27 normal cell lines, respectively. Using the given SAR models, we developed a freely available web-service for cell-line cytotoxicity profile prediction (CLC-Pred: Cell-Line Cytotoxicity Predictor) based on the following structural formula: http://way2drug.com/Cell-line/.

How to Achieve Better Results Using Pass-Based Virtual Screening: Case Study for Kinase Inhibitors

Discovery of new pharmaceutical substances is currently boosted by the possibility of utilization of the Synthetically Accessible Virtual Inventory (SAVI) library, which includes about 283 million molecules, each annotated with a proposed synthetic one-step route from commercially available starting materials. The SAVI database is well-suited for ligand-based methods of virtual screening to select molecules for experimental testing. In this study, we compare the performance of three approaches for the analysis of structure-activity relationships that differ in their criteria for selecting of “active” and “inactive” compounds included in the training sets. PASS (Prediction of Activity Spectra for Substances), which is based on a modified Naïve Bayes algorithm, was applied since it had been shown to be robust and to provide good predictions of many biological activities based on just the structural formula of a compound even if the information in the training set is incomplete. We used different subsets of kinase inhibitors for this case study because many data are currently available on this important class of drug-like molecules. Based on the subsets of kinase inhibitors extracted from the ChEMBL 20 database we performed the PASS training, and then applied the model to ChEMBL 23 compounds not yet present in ChEMBL 20 to identify novel kinase inhibitors. As one may expect, the best prediction accuracy was obtained if only the experimentally confirmed active and inactive compounds for distinct kinases in the training procedure were used. However, for some kinases, reasonable results were obtained even if we used merged training sets, in which we designated as inactives the compounds not tested against the particular kinase. Thus, depending on the availability of data for a particular biological activity, one may choose the first or the second approach for creating ligand-based computational tools to achieve the best possible results in virtual screening.

Comparison of quantitative and qualitative (Q)SAR models created for the prediction of Ki and IC50 values of antitarget inhibitors

Estimation of interaction of drug-like compounds with antitargets is important for the assessment of possible toxic effects during drug development. Publicly available online databases provide data on the experimental results of chemical interactions with antitargets, which can be used for the creation of (Q)SAR models. The structures and experimental Ki and IC50 values for compounds tested on the inhibition of 30 antitargets from the ChEMBL 20 database were used. Data sets with Ki and IC50 values including more than 100 compounds were created for each antitarget. The (Q)SAR models were created by GUSAR software using quantitative neighborhoods of atoms (QNA), multilevel neighborhoods of atoms (MNA) descriptors, and self-consistent regression. The accuracy of (Q)SAR models was validated by the fivefold cross-validation procedure. The balanced accuracy was higher for qualitative SAR models (0.80 and 0.81 for Ki and IC50 values, respectively) than for quantitative QSAR models (0.73 and 0.76 for Ki and IC50 values, respectively). In most cases, sensitivity was higher for SAR models than for QSAR models, but specificity was higher for QSAR models. The mean R2 and RMSE were 0.64 and 0.77 for Ki values and 0.59 and 0.73 for IC50 values, respectively. The number of compounds falling within the applicability domain was higher for SAR models than for the test sets.

Integral estimation of xenobiotics’ toxicity with regard to their metabolism in human organism

Abstract Toxicity and severe adverse effects are the primary cause of drug-candidate failures at the late stages of preclinical and clinical trials. Since most xenobiotics undergo biotransformations, their interaction with human organism reveals the effects produced by parent compounds and all metabolites. To increase the chances of successful drug development, estimation of the entire toxicity for drug substance and its metabolites is necessary for filtering out the potentially toxic compounds. We proposed the computational approach to the integral evaluation of xenobiotics’ toxicity based on the structural formula of the drug-like compound. In the framework of this study, the consensus QSAR model was developed based on the analysis of over 3000 compounds with information about their rat acute toxicity for intravenous route of administration. Four different numerical methods, estimating the integral toxicity, were proposed, and their comparative performance was studied using the external evaluation set consisting of 37 structures of drugs and 200 their metabolites. It was shown that, on the average, the best correspondence between the predicted and published data is obtained using the method that takes into account the estimated characteristics for both the parent compound and its most toxic metabolite.