Search

The growing amount of experimental data on chemical objects includes properties of small molecules, results of studies of their interaction with human and animal proteins, and methods of synthesis of organic compounds (OCs). The data obtained can be used to identify the names of OCs automatically, including all possible synonyms and relevant data on the molecular properties and biological activity. Utilization of different synonymic names of chemical compounds allows researchers to increase the completeness of data on their properties available from publications. Enrichment of the data on the names of chemical compounds by information about their possible metabolites can help estimate the biological effects of parent compounds and their metabolites more thoroughly. Therefore, an attempt at automated extraction of the names of parent compounds and their metabolites from the texts is a rather important task. In our study, we aimed at developing a method that provides the extraction of the named entities (NEs) of parent compounds and their metabolites from abstracts of scientific publications. Based on the application of the conditional random fields' algorithm, we extracted the NEs of chemical compounds. We developed a set of rules allowing identification of parent compound NEs and their metabolites in the texts. We evaluated the possibility of extracting the names of potential metabolites based on cosine similarity between strings representing names of parent compounds and all other chemical NEs found in the text. Additionally, we used conditional random fields to fetch the names of parent compounds and their metabolites from the texts based on the corpus of texts labeled manually. Our computational experiments showed that usage of rules in combination with cosine similarity could increase the accuracy of recognition of the names of metabolites compared to the rule-based algorithm and application of a machine-learning algorithm (conditional random fields).

The huge space of experimental data on biological and chemical objects and their interactions contributes to the rapid growth of scientific publications containing their analysis. Such data may include characteristics of low-molecular-weight compounds, results of their biological activity evaluation, and their interaction with human and animal proteins, methods of synthesis of organic compounds, and their classification. The past decades saw the development of methods for automated extraction of data from texts of scientific publications, including those for retrieval of names of organic compounds. These data can be used for the automatic identification of the names of organic compounds, including all possible synonyms. Since the topics of scientific publications are diverse, the extracted data can be applied to obtain information about (1) classification of organic compounds (2) methods of synthesis of a given organic compound; (3) physicochemical properties of this compound; (4) its interaction with high-molecular-weight compounds (including proteins, mRNA of animals and humans); and (5) the therapeutic properties of organic compounds, the active substance of the drug, and data on clinical trials. This review considers the methods aimed at searching and extracting data on names of low-molecular-weight compounds and interactions between them and animal and human proteins (biological objects), as well as data on experimentally confirmed biological activity and the effects of organic compounds (including drugs) on pathological processes. Here, we discuss the methods developed and the results of their application published over the past 10 years.

Next Generation Sequencing (NGS) technologies are rapidly entering clinical practice. A promising area for their use lies in the field of newborn screening. The mass screening of newborns using NGS technology leads to the discovery of a large number of new missense variants that need to be assessed for association with the development of hereditary diseases. Currently, the primary analysis and identification of pathogenic variations is carried out using bioinformatic tools. Although extensive efforts have been made in the computational approach to variant interpretation, there is currently no generally accepted pathogenicity predictor. In this study, we used the sequence–structure–property relationships (SSPR) approach, based on the representation of protein fragments by molecular structural formula. The approach predicts the pathogenic effect of single amino acid substitutions in proteins related with twenty-five monogenic heritable diseases from the Uniform Screening Panel for Major Conditions recommended by the Advisory Committee on Hereditary Disorders in Newborns and Children. In order to create SSPR models of classification, we modified a piece of cheminformatics software, MultiPASS, that was originally developed for the prediction of activity spectra for drug-like substances. The created SSPR models were compared with traditional bioinformatic tools (SIFT 4G, Polyphen-2 HDIV, MutationAssessor, PROVEAN and FATHMM). The average AUC of our approach was 0.804 ± 0.040. Better quality scores were achieved for 15 from 25 proteins with a significantly higher accuracy for some proteins (IVD, HADHB, HBB). The best SSPR models of classification are freely available in the online resource SAV-Pred (Single Amino acid Variants Predictor).

In vitro cell-line cytotoxicity is widely used in the experimental studies of potential antineoplastic agents and evaluation of safety in drug discovery. In silico estimation of cytotoxicity against hundreds of tumor cell lines and dozens of normal cell lines considerably reduces the time and costs of drug development and the assessment of new pharmaceutical agent perspectives. In 2018, we developed the first freely available web application (CLC-Pred) for the qualitative prediction of cytotoxicity against 278 tumor and 27 normal cell lines based on structural formulas of 59,882 compounds. Here, we present a new version of this web application: CLC-Pred 2.0. It also employs the PASS (Prediction of Activity Spectra for Substance) approach based on substructural atom centric MNA descriptors and a Bayesian algorithm. CLC-Pred 2.0 provides three types of qualitative prediction: (1) cytotoxicity against 391 tumor and 47 normal human cell lines based on ChEMBL and PubChem data (128,545 structures) with a mean accuracy of prediction (AUC), calculated by the leave-one-out (LOO CV) and the 20-fold cross-validation (20F CV) procedures, of 0.925 and 0.923, respectively; (2) cytotoxicity against an NCI60 tumor cell-line panel based on the Developmental Therapeutics Program’s NCI60 data (22,726 structures) with different thresholds of IG50 data (100, 10 and 1 nM) and a mean accuracy of prediction from 0.870 to 0.945 (LOO CV) and from 0.869 to 0.942 (20F CV), respectively; (3) 2170 molecular mechanisms of actions based on ChEMBL and PubChem data (656,011 structures) with a mean accuracy of prediction 0.979 (LOO CV) and 0.978 (20F CV). Therefore, CLC-Pred 2.0 is a significant extension of the capabilities of the initial web application.

Discovery of new antibacterial agents is a never-ending task of medicinal chemistry. Every new drug brings significant improvement to patients with bacterial infections, but prolonged usage of antibacterials leads to the emergence of resistant strains. Therefore, novel active structures with new modes of action are required. We describe a web application called AntiBac-Pred aimed to help users in the rational selection of the chemical compounds for experimental studies of antibacterial activity. This application is developed using antibacterial activity data available in ChEMBL and PASS software. It allows users to classify chemical structures of interest into growth inhibitors or noninhibitors of 353 different bacteria strains, including both resistant and nonresistant ones.

Metabolite identification is an essential part of the drug discovery and development process. Experimental methods allow identifying metabolites and estimating their relative amount, but they require cost-intensive and time-consuming techniques. Computational methods for metabolite prediction are devoid of these shortcomings and may be applied at the early stage of drug discovery. In this study, we investigated the possibility of creating SAR models for the prediction of the qualitative metabolite yield ('major', 'minor', "trace" and "negligible") depending on species and biological experimental systems. In addition, we have created models for prediction of xenobiotic excretion depending on its administration route for different species. The prediction is based on an algorithm of naïve Bayes classifier implemented in PASS software. The average accuracy of prediction was 0.91 for qualitative metabolite yield prediction and 0.89 for prediction of xenobiotic excretion. The created models were included as a component of MetaTox web application, which allows predicting the xenobiotic metabolism pathways ( http://www.way2drug.com/mg ).

Simultaneous use of the drugs may lead to undesirable Drug-Drug Interactions (DDIs) in the human body. Many DDIs are associated with changes in drug metabolism that performed by Drug-Metabolizing Enzymes (DMEs). In this case, DDI manifests itself as a result of the effect of one drug on the biotransformation of other drug(s), its slowing down (in the case of inhibiting DME) or acceleration (in case of induction of DME), which leads to a change in the pharmacological effect of the drugs combination. We used OpeRational ClassificAtion (ORCA) system for categorizing DDIs. ORCA divides DDIs into five classes: contraindicated (class 1), provisionally contraindicated (class 2), conditional (class 3), minimal risk (class 4), no interaction (class 5). We collected a training set consisting of several thousands of drug pairs. Algorithm of PASS program was used for the first, second and third classes DDI prediction. Chemical descriptors called PoSMNA (Pairs of Substances Multilevel Neighbourhoods of Atoms) were developed and implemented in PASS software to describe in a machine-readable format drug substances pairs instead of the single molecules. The average accuracy of DDI class prediction is about 0.84. A freely available web resource for DDI prediction was developed (http://way2drug.com/ddi/).

Most xenobiotics undergo metabolic conversions in the human body. The biological activity, toxicity, and other properties of such metabolites may significantly differ from those of the parent compounds. Not only xenobiotics and their final metabolites produced in large quantities, but the intermediates and final metabolites formed in trace amounts, can cause undesirable effects. We have developed a freely available web application MetaTox ( http://www.way2drug.com/mg/ ) for integral assessment of xenobiotics toxicity taking into account their metabolism in humans. The generation of the metabolite structures is based on the reaction fragments. The probability estimation of the certain reaction and the probability estimation of the atoms, which are changed during biotransformation, are used for generation of the xenobiotic metabolism pathways. The MetaTox web application assesses metabolism of compounds in humans and evaluates their acute toxicity, specific (cardiotoxicity, hepatotoxicity, nephrotoxicity), and chronic toxicity (carcinogenicity, teratogenicity, mutagenicity, effects on the reproductive system).

Background: Phenazepam (bromdihydrochlorphenylbenzodiazepine) is the original Russian benzodiazepine tranquilizer belonging to 1,4-benzodiazepines. There is still limited knowledge about phenazepam’s metabolic liver pathways and other pharmacokinetic features. Methods: To determine phenazepam’s metabolic pathways, the study was divided into three stages: in silico modeling, in vitro experiment (cell culture study), and in vivo confirmation. In silico modeling was performed on the specialized software PASS and GUSAR to evaluate phenazepam molecule affinity to different cytochromes. The in vitro study was performed using a hepatocytes’ cell culture, cultivated in a microbioreactor to produce cytochrome P450 isoenzymes. The culture medium contained specific cytochrome P450 isoforms inhibitors and substrates (for CYP2C9, CYP3A4, CYP2C19, and CYP2B6) to determine the cytochrome that was responsible for phenazepam’s metabolism. We also measured CYP3A activity using the 6-betahydroxycortisol/cortisol ratio in patients. Results: According to in silico and in vitro analysis results, the most probable metabolizer of phenazepam is CYP3A4. By the in vivo study results, CYP3A activity decreased sufficiently (from 3.8 [95% CI: 2.94–4.65] to 2.79 [95% CI: 2.02–3.55], p=0.017) between the start and finish of treatment in patients who were prescribed just phenazepam. Conclusions: Experimental in silico and in vivo studies confirmed that the original Russian benzodiazepine phenazepam was the substrate of CYP3A4 isoenzyme.

The Way2Drug informational-computational platform (www.way2drug.com/dr) provides access to the data on drugs approved for medicinal use in the USA and Russian Federation, as well as computational possibilities for the prediction of biological activity of drug-like organic compounds. Currently realized computational tools of the platform, which allow one to predict several thousands of biological activity types, including the interaction with molecular targets, pharmacotherapeutic and side effects, metabolism, acute toxicity for rats, cytotoxicity, influence on gene expression, and other properties characterizing the evaluation how promising are particular drug-like compounds as potential pharmaceuticals, are reviewed. Using the Way2Drug platform, one can not only select the most promising "hits" for the synthesis and testing of biological activity but also reveal new indications for the launched drugs.

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.

Most pharmaceutical substances interact with several or even many molecular targets in the organism, determining the complex profiles of their biological activity. Moreover, due to biotransformation in the human body, they form one or several metabolites with different biological activity profiles. Therefore, the development and rational use of novel drugs requires the analysis of their biological activity profiles, taking into account metabolism in the human body. In silico methods are currently widely used for estimating new drug-like compounds&rsquo, interactions with pharmacological targets and predicting their metabolic transformations. In this study, we consider the estimation of the biological activity profiles of organic compounds, taking into account the action of both the parent molecule and its metabolites in the human body. We used an external dataset that consists of 864 parent compounds with known metabolites. It is shown that the complex assessment of active pharmaceutical ingredients&rsquo, interactions with the human organism increases the quality of computer-aided estimates. The toxic and adverse effects showed the most significant difference: reaching 0.16 for recall and 0.14 for precision.

Online resources (PASS Online, SuperPred, SwissTargetPrediction and DRAR-CPI) for the prediction of biological activity of organic compounds from their structural formulas were considered. Based on a test set of drugs approved by 2014, the accuracies of predictions were compared. The four web resources can be arranged with respect to the quality of prediction (sensitivity, S) as follows: SwissTargetPrediction (S = 0.37) < DRAR-CPI (S = 0.41) < Super-Pred (S = 0.53) < PASS Online (S = 0.95). A conclusion was made that PASS Online employs superior machine learning algorithms based on MNA descriptors and Bayessian classifier in contrast to the similarity-based methods used in SuperPred and SwissTargetPrediction or the molecular docking methods used in DRAR-CPI. Possible reasons for the low prediction quality of SuperPred, SwissTargetPrediction, and DRAR-CPI are discussed and the development perspectives of this area of computational chemistry are given.

Applicability of our computer programs PASS and PharmaExpert for prediction of biological activity spectra of rather complex and structurally diverse phytocomponents of medicinal plants, both separately and in combinations has been evaluated. For this purpose we have created the web-resource containing known information about structural formulas and biological activity of 1906 phytocomponents of 50 Ayurvedic medicinal plants used in Traditional Indian Medicine (TIM) (http://ayurveda.pharmaexpert.ru). The PASS training set was updated by addition of information about structure and biological activity of 946 natural compounds; then the training procedure and validation were performed, to estimate the quality of PASS prediction. It was shown that the differences between the average accuracy of prediction obtained in leave-5%-out cross-validation (94.467%) and in leave-one-out cross-validation (94.605%) are very small thus demonstrating high predictive ability of the program. Results of biological activity spectra prediction for all phytocomponents included in our database coincided in 83.5% of cases with known experimental data. Additional types of biological activity predicted with high probability indicate further promising directions for further studies of certain phytocomponents of some medicinal plants. The analysis of prediction results of sets of phytocomponents in each of 50 medicinal plants was made by the PharmaExpert software. Based on this analysis, we found that the combination of phytocomponents from Passiflora incarnata may exhibit nootropic, anticonvulsant, and antidepressant effects. Experiments carried out in mice models confirmed the predicted effects of P. incarnata extracts.

Biotransformation is a process of the chemical modifications which may lead to the reactive metabolites, in particular the epoxides. Epoxide reactive metabolites may cause the toxic effects. The prediction of such metabolites is important for drug development and ecotoxicology studies. Epoxides are formed by some oxidation reactions, usually catalysed by cytochromes P450, and represent a large class of three-membered cyclic ethers. Identification of molecules, which may be epoxidized, and indication of the specific location of epoxide functional group (which is called SOE - site of epoxidation) are important for prediction of epoxide metabolites. Datasets from 355 molecules and 615 reactions were created for training and validation. The prediction of SOE is based on a combination of LMNA (Labelled Multilevel Neighbourhood of Atom) descriptors and Bayesian-like algorithm implemented in PASS software and MetaTox web-service. The average invariant accuracy of prediction (AUC) calculated in leave-one-out and 20-fold cross-validation procedures is 0.9. Prediction of epoxide formation based on the created SAR model is included as the component of MetaTox web-service ( http://www.way2drug.com/mg ).

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.

Summary: A new freely available web server site of metabolism predictor to predict the sites of metabolism (SOM) based on the structural formula of chemicals has been developed. It is based on the analyses of ‘structure-SOM’ relationships using a Bayesian approach and labelled multilevel neighbourhoods of atoms descriptors to represent the structures of over 1000 metabolized xenobiotics. The server allows predicting SOMs that are catalysed by 1A2, 2C9, 2C19, 2D6 and 3A4 isoforms of cytochrome P450 and enzymes of the UDP-glucuronosyltransferase family. The average invariant accuracy of prediction that was calculated for the training sets (using leave-one-out cross-validation) and evaluation sets is 0.9 and 0.95, respectively. Availability and implementation: Freely available on the web at http://www.way2drug.com/SOMP. Contact: rudik_anastassia@mail.ru Supplementary information: Supplementary data are available at Bioinformatics online.

The phagocytic activity and production of proinflammatory cytokines by murine peritoneal macrophages was examined upon in vitro and in vivo exposure to low doses (up to 150 mJ/cm2) of red (650 nm) and infrared (850 nm) light generated by semiconductor lasers. Infrared irradiation proved stimulatory in a dose-dependent way for phagocytosis and killing of enteropathogenic Escherichia coli as well as for cytokine production. Red light markedly enhanced cytokine production but was detrimental to macrophage activity and at higher doses caused their destruction.

Metabolism of xenobiotics (Greek xenos: exogenous substances) plays an essential role in the prediction of biological activity and testing for the subsequent research and development of new drug candidates. Integration of various methods and techniques using different computational and experimental approaches is one of the keys to a successful metabolism prediction. While multiple structure-based and ligand-based approaches to metabolism prediction exist, the most important problem arises at the first stage of metabolism prediction: detection of the sites of metabolism (SOMs). In this paper, we describe the application of Quantitative Neighborhoods of Atoms (QNA) descriptors for prediction of the SOMs using potential function method, as well as several different machine learning techniques: naïve Bayes, random forest classifier, multilayer perceptron with back propagation and convolutional neural networks, and deep neural networks.

Background The knowledge of drug metabolite structures is essential at the early stage of drug discovery to understand the potential liabilities and risks connected with biotransformation. The determination of the site of a molecule at which a particular metabolic reaction occurs could be used as a starting point for metabolite identification. The prediction of the site of metabolism does not always correspond to the particular atom that is modified by the enzyme but rather is often associated with a group of atoms. To overcome this problem, we propose to operate with the term “reacting atom”, corresponding to a single atom in the substrate that is modified during the biotransformation reaction. The prediction of the reacting atom(s) in a molecule for the major classes of biotransformation reactions is necessary to generate drug metabolites. Results Substrates of the major human cytochromes P450 and UDP-glucuronosyltransferases from the Biovia Metabolite database were divided into nine groups according to their reaction classes, which are aliphatic and aromatic hydroxylation, N- and O-glucuronidation, N-, S- and C-oxidation, and N- and O-dealkylation. Each training set consists of positive and negative examples of structures with one labelled atom. In the positive examples, the labelled atom is the reacting atom of a particular reaction that changed adjacency. Negative examples represent non-reacting atoms of a particular reaction. We used Labelled Multilevel Neighbourhoods of Atoms descriptors for the designation of reacting atoms. A Bayesian-like algorithm was applied to estimate the structure–activity relationships. The average invariant accuracy of prediction obtained in leave-one-out and 20-fold cross-validation procedures for five human isoforms of cytochrome P450 and all isoforms of UDP-glucuronosyltransferase varies from 0.86 to 0.99 (0.96 on average). Conclusions We report that reacting atoms may be predicted with reasonable accuracy for the major classes of metabolic reactions—aliphatic and aromatic hydroxylation, N- and O-glucuronidation, N-, S- and C-oxidation, and N- and O-dealkylation. The proposed method is implemented as a freely available web service at http://www.way2drug.com/RA and may be used for the prediction of the most probable biotransformation reaction(s) and the appropriate reacting atoms in drug-like compounds.Graphical abstract. Electronic supplementary material The online version of this article (doi:10.1186/s13321-016-0183-x) contains supplementary material, which is available to authorized users.