Prediction of viral protease inhibitors using proteochemometrics approach.

Being widely accepted tools in computational drug search, the (Q)SAR methods have limitations related to data incompleteness. The proteochemometrics (PCM) approach expands the applicability area by using description for both protein and ligand structures. The PCM algorithms are urgently required for the development of new antiviral agents. We suggest the PCM method using the TLMNA descriptors, combining the MNA descriptors of ligands and protein sequence N-grams. Our method was validated on the viral chymotrypsin-like proteases and their ligands. We have developed an original protocol allowing us to collect a comprehensive set of 15 protein sequences and more than 9000 ligands from the ChEMBL database. The N-grams were derived from the 3D-based alignment, accurately superposing ligand-binding regions. In testing the ligand set in SAR mode with MNA descriptors, an accuracy above 0.95 was determined that shows the perspective of the antiviral drug search in virtual chemical libraries. The effective PCM models were built with the TLMNA descriptor. The strong validation procedure with pair exclusion simulated the prediction of interactions between the new ligands and new targets, resulting in accuracy estimation up to 0.89. The PCM approach shows slightly lower accuracy caused by more uncertainty compared with SAR, but it overcomes the problem of data incompleteness.

MetaTox 2.0: Estimating the Biological Activity Spectra of Drug-like Compounds Taking into Account Probable Biotransformations.

After the biotransformation of xenobiotics in the human body, the biological activity of the metabolites may differ from the activity of parent compounds. Therefore, to assess the overall biological activity of a drug-like compound, it is important to take into account its metabolites and their biological activity. We developed MetaTox 2.0-an updated version of the MetaTox web application that was able to predict the metabolites of xenobiotics. Innovations include estimating the biological activity profile of a compound and taking into account its metabolites. The estimation is based on the PASS (prediction of activity spectra for substances) algorithm and on the latest version of the training set covering over 1900 biological activities predicted with an average accuracy exceeding 0.97. Also, MetaTox 2.0 allows the search for similar substances among more than 2000 drugs with known metabolic networks, which were extracted from the ChEMBL, MetXBIODB, and DrugBank databases. MetaTox 2.0 is freely available on the web at https://www.way2drug.com/metatox.

Web Service for HIV Drug Resistance Prediction Based on Analysis of Amino Acid Substitutions in Main Drug Targets.

Predicting viral drug resistance is a significant medical concern. The importance of this problem stimulates the continuous development of experimental and new computational approaches. The use of computational approaches allows researchers to increase therapy effectiveness and reduce the time and expenses involved when the prescribed antiretroviral therapy is ineffective in the treatment of infection caused by the human immunodeficiency virus type 1 (HIV-1). We propose two machine learning methods and the appropriate models for predicting HIV drug resistance related to amino acid substitutions in HIV targets: (i) k-mers utilizing the random forest and the support vector machine algorithms of the scikit-learn library, and (ii) multi-n-grams using the Bayesian approach implemented in MultiPASSR software. Both multi-n-grams and k-mers were computed based on the amino acid sequences of HIV enzymes: reverse transcriptase and protease. The performance of the models was estimated by five-fold cross-validation. The resulting classification models have a relatively high reliability (minimum accuracy for the drugs is 0.82, maximum: 0.94) and were used to create a web application, HVR (HIV drug Resistance), for the prediction of HIV drug resistance to protease inhibitors and nucleoside and non-nucleoside reverse transcriptase inhibitors based on the analysis of the amino acid sequences of the appropriate HIV proteins from clinical samples.

HGMMX: Host Gut Microbiota Metabolism Xenobiotics Database.

The metagenome of bacteria colonizing the human intestine is a set of genes that is almost 150 times greater than the set of host genes. Some of these genes encode enzymes whose functioning significantly expands the number of potential pathways for xenobiotic metabolism. The resulting metabolites can exhibit activity different from that of the parent compound. This can decrease the efficacy of pharmacotherapy as well as induce undesirable and potentially life-threatening side effects. Thus, analysis of the biotransformation of small drug-like compounds mediated by the gut microbiota is an important step in the development of new pharmaceutical agents and repurposing of the approved drugs. In vitro research, the interaction of drug-like compounds with the gut microbiota is a multistep and time-consuming process. Systematic testing of large sets of chemical structures is associated with a number of challenges, including the lack of standardized techniques and significant financial costs to identify the structure of the final metabolites. Estimation of the compounds' ability to be biotransformed by the gut microbiota and prediction of the structures of their metabolites are possible in silico. However, the development of computational approaches is limited by the lack of information about chemical structures metabolized by microbiota enzymes. The aim of this study is to create a database containing information on the metabolism of drug-like compounds by the gut microbiota. We created the data set containing information about 368 structures metabolized and 310 structures not metabolized by the human gut microbiota. The HGMMX database is freely available at https://www.way2drug.com/hgmmx. The information presented will be useful in the development of computational approaches for analyzing the impact of the human microbiota on metabolism of drug-like molecules.

TCR-Pred: A new web-application for prediction of epitope and MHC specificity for CDR3 TCR sequences using molecular fragment descriptors.

The search for the relationships between CDR3 TCR sequences and epitopes or MHC types is a challenging task in modern immunology. We propose a new approach to develop the classification models of structure-activity relationships (SAR) using molecular fragment descriptors MNA (Multilevel Neighbourhoods of Atoms) to represent CDR3 TCR sequences and the naïve Bayes classifier algorithm. We have created the freely available TCR-Pred web application (http://way2drug.com/TCR-pred/) to predict the interactions between α chain CDR3 TCR sequences and 116 epitopes or 25 MHC types, as well as the interactions between ß chain CDR3 TCR sequences and 202 epitopes or 28 MHC types. The TCR-Pred web application is based on the data (more 250 000 unique CDR3 TCR sequences) from VDJdb, McPAS-TCR, and IEDB databases and the proposed approach. The average AUC values of the prediction accuracy calculated using a 20-fold cross-validation procedure varies from 0.857 to 0.884. The created web application may be useful in studies related with T-cell profiling based on CDR3 TCR sequences.

SAV-Pred: A Freely Available Web Application for the Prediction of Pathogenic Amino Acid Substitutions for Monogenic Hereditary Diseases Studied in Newborn Screening.

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).

CLC-Pred 2.0: A Freely Available Web Application for In Silico Prediction of Human Cell Line Cytotoxicity and Molecular Mechanisms of Action for Druglike Compounds.

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.

The method predicting interaction between protein targets and small-molecular ligands with the wide applicability domain.

Prediction of protein-ligand interaction is necessary for drug design, gene regulatory networks investigation, and chemical probes detection. The existing methods commonly demonstrate high prediction accuracy for the particular groups of protein and their ligands. We developed an approach suited for the wider applicability and tested it on three dataset types significantly differing by protein homology. The study included three typical scenarios of assessing the target-ligand interaction: 1st - predicting protein targets by ligand structures' comparisons; 2nd - predicting ligands by target sequences' comparisons; 3rd - predicting both the uncharacterized targets and ligands with the fuzzy coefficients based on ligand comparisons. The 1st scenario implemented showed a high prediction accuracy of 0.96-0.99, providing fuzzy coefficients of target-ligand interactions in the 3rd scenario. Testing by 2nd scenario displayed the accuracy of 0.97-0.99 for predicting within the particular protein families, sets non-ordered by protein homology, and accuracy higher than 0.90 for most HIV sets, each presenting the close mutant proteins differing by point substitutions. The 3rd scenario displayed that fuzzy classification can reveal reasonable accuracy 0.86-0.94 at simulated data incompleteness. Thus, our approach provides high prediction accuracy with the wide applicability domain, including data differing in heterogeneity and completeness.

Relationships between the Structure and Severe Drug-Induced Liver Injury for Low, Medium, and High Doses of Drugs.

Assessment of structure-activity relationships (SARs) for predicting severe drug-induced liver injury (DILI) is essential since in vivo and in vitro preclinical methods cannot detect many druglike compounds disrupting liver functions. To date, plenty of SAR models for the prediction of DILI have been developed; however, none of them considered the route of drug administration and daily dose, which may introduce significant bias into prediction results. We have created a dataset of 617 drugs with parenteral and oral administration routes and consistent information on DILI severity. We have found a clear relationship between route, dose, and DILI severity. According to SAR, nearly 40% of moderate- and non-DILI-causing drugs would cause severe DILI if they were administered at high oral doses. We have proposed the following approach to predict severe DILI. New compounds recommended to be used at low oral doses (<∼10 mg daily), or parenterally, can be considered not causing severe DILI. DILI for compounds administered at medium oral doses (∼10-100 mg daily; 22.2% of drugs under consideration) can be considered unpredictable because reasonable SAR models were not obtained due to the small size and heterogeneity of the corresponding dataset. The DILI potential of the compounds recommended to be used at high oral doses (more than ∼100 mg daily) can be estimated using SAR modeling. The balanced accuracy of the approach calculated by a 10-fold cross-validation procedure is 0.803. The developed approach can be used to estimate severe DILI for druglike compounds proposed to use at low and high oral doses or parenterally at the early stages of drug development.

In Silico Prediction of Drug-Drug Interactions Mediated by Cytochrome P450 Isoforms.

Drug-drug interactions (DDIs) can cause drug toxicities, reduced pharmacological effects, and adverse drug reactions. Studies aiming to determine the possible DDIs for an investigational drug are part of the drug discovery and development process and include an assessment of the DDIs potential mediated by inhibition or induction of the most important drug-metabolizing cytochrome P450 isoforms. Our study was dedicated to creating a computer model for prediction of the DDIs mediated by the seven most important P450 cytochromes: CYP1A2, CYP2B6, CYP2C19, CYP2C8, CYP2C9, CYP2D6, and CYP3A4. For the creation of structure-activity relationship (SAR) models that predict metabolism-mediated DDIs for pairs of molecules, we applied the Prediction of Activity Spectra for Substances (PASS) software and Pairs of Substances Multilevel Neighborhoods of Atoms (PoSMNA) descriptors calculated based on structural formulas. About 2500 records on DDIs mediated by these cytochromes were used as a training set. Prediction can be carried out both for known drugs and for new, not-yet-synthesized substances. The average accuracy of the prediction of DDIs mediated by various isoforms of cytochrome P450 estimated by leave-one-out cross-validation (LOO CV) procedures was about 0.92. The SAR models created are publicly available as a web resource and provide predictions of DDIs mediated by the most important cytochromes P450.

Extraction of Data on Parent Compounds and Their Metabolites from Texts of Scientific Abstracts.

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).

Computer-Aided Estimation of Biological Activity Profiles of Drug-Like Compounds Taking into Account Their Metabolism in Human Body.

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' 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' 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.

Data and Text Mining Help Identify Key Proteins Involved in the Molecular Mechanisms Shared by SARS-CoV-2 and HIV-1.

Viruses can be spread from one person to another; therefore, they may cause disorders in many people, sometimes leading to epidemics and even pandemics. New, previously unstudied viruses and some specific mutant or recombinant variants of known viruses constantly appear. An example is a variant of coronaviruses (CoV) causing severe acute respiratory syndrome (SARS), named SARS-CoV-2. Some antiviral drugs, such as remdesivir as well as antiretroviral drugs including darunavir, lopinavir, and ritonavir are suggested to be effective in treating disorders caused by SARS-CoV-2. There are data on the utilization of antiretroviral drugs against SARS-CoV-2. Since there are many studies aimed at the identification of the molecular mechanisms of human immunodeficiency virus type 1 (HIV-1) infection and the development of novel therapeutic approaches against HIV-1, we used HIV-1 for our case study to identify possible molecular pathways shared by SARS-CoV-2 and HIV-1. We applied a text and data mining workflow and identified a list of 46 targets, which can be essential for the development of infections caused by SARS-CoV-2 and HIV-1. We show that SARS-CoV-2 and HIV-1 share some molecular pathways involved in inflammation, immune response, cell cycle regulation.

Combined network pharmacology and virtual reverse pharmacology approaches for identification of potential targets to treat vascular dementia.

Dementia is a major cause of disability and dependency among older people. If the lives of people with dementia are to be improved, research and its translation into druggable target are crucial. Ancient systems of healthcare (Ayurveda, Siddha, Unani and Sowa-Rigpa) have been used from centuries for the treatment vascular diseases and dementia. This traditional knowledge can be transformed into novel targets through robust interplay of network pharmacology (NetP) with reverse pharmacology (RevP), without ignoring cutting edge biomedical data. This work demonstrates interaction between recent and traditional data, and aimed at selection of most promising targets for guiding wet lab validations. PROTEOME, DisGeNE, DISEASES and DrugBank databases were used for selection of genes associated with pathogenesis and treatment of vascular dementia (VaD). The selection of new potential drug targets was made by methods of NetP (DIAMOnD algorithm, enrichment analysis of KEGG pathways and biological processes of Gene Ontology) and manual expert analysis. The structures of 1976 phytomolecules from the 573 Indian medicinal plants traditionally used for the treatment of dementia and vascular diseases were used for computational estimation of their interactions with new predicted VaD-related drug targets by RevP approach based on PASS (Prediction of Activity Spectra for Substances) software. We found 147 known genes associated with vascular dementia based on the analysis of the databases with gene-disease associations. Six hundred novel targets were selected by NetP methods based on 147 gene associations. The analysis of the predicted interactions between 1976 phytomolecules and 600 NetP predicted targets leaded to the selection of 10 potential drug targets for the treatment of VaD. The translational value of these targets is discussed herewith. Twenty four drugs interacting with 10 selected targets were identified from DrugBank. These drugs have not been yet studied for the treatment of VaD and may be investigated in this field for their repositioning. The relation between inhibition of two selected targets (GSK-3, PTP1B) and the treatment of VaD was confirmed by the experimental studies on animals and reported separately in our recent publications.

(Q)SAR Models of HIV-1 Protein Inhibition by Drug-Like Compounds.

Despite the achievements of antiretroviral therapy, discovery of new anti-HIV medicines remains an essential task because the existing drugs do not provide a complete cure for the infected patients, exhibit severe adverse effects, and lead to the appearance of resistant strains. To predict the interaction of drug-like compounds with multiple targets for HIV treatment, ligand-based drug design approach is widely applied. In this study, we evaluated the possibilities and limitations of (Q)SAR analysis aimed at the discovery of novel antiretroviral agents inhibiting the vital HIV enzymes. Local (Q)SAR models are based on the analysis of structure-activity relationships for molecules from the same chemical class, which significantly restrict their applicability domain. In contrast, global (Q)SAR models exploit data from heterogeneous sets of drug-like compounds, which allows their application to databases containing diverse structures. We compared the information for HIV-1 integrase, protease and reverse transcriptase inhibitors available in the EBI ChEMBL, NIAID HIV/OI/TB Therapeutics, and Clarivate Analytics Integrity databases as the sources for (Q)SAR training sets. Using the PASS and GUSAR software, we developed and validated a variety of (Q)SAR models, which can be further used for virtual screening of new antiretrovirals in the SAVI library. The developed models are implemented in the freely available web resource AntiHIV-Pred.

AntiBac-Pred: A Web Application for Predicting Antibacterial Activity of Chemical Compounds.

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.

Data Mining Approach for Extraction of Useful Information About Biologically Active Compounds from Publications.

A lot of high quality data on the biological activity of chemical compounds are required throughout the whole drug discovery process: from development of computational models of the structure-activity relationship to experimental testing of lead compounds and their validation in clinics. Currently, a large amount of such data is available from databases, scientific publications, and patents. Biological data are characterized by incompleteness, uncertainty, and low reproducibility. Despite the existence of free and commercially available databases of biological activities of compounds, they usually lack unambiguous information about peculiarities of biological assays. On the other hand, scientific papers are the primary source of new data disclosed to the scientific community for the first time. In this study, we have developed and validated a data-mining approach for extraction of text fragments containing description of bioassays. We have used this approach to evaluate compounds and their biological activity reported in scientific publications. We have found that categorization of papers into relevant and irrelevant may be performed based on the machine-learning analysis of the abstracts. Text fragments extracted from the full texts of publications allow their further partitioning into several classes according to the peculiarities of bioassays. We demonstrate the applicability of our approach to the comparison of the endpoint values of biological activity and cytotoxicity of reference compounds.

Prediction of Drug-Drug Interactions Related to Inhibition or Induction of Drug-Metabolizing Enzymes.

Drug-drug interaction (DDI) is the phenomenon of alteration of the pharmacological activity of a drug(s) when another drug(s) is co-administered in cases of so-called polypharmacy. There are three types of DDIs: pharmacokinetic (PK), pharmacodynamic, and pharmaceutical. PK is the most frequent type of DDI, which often appears as a result of the inhibition or induction of drug-metabolising enzymes (DME). In this review, we summarise in silico methods that may be applied for the prediction of the inhibition or induction of DMEs and describe appropriate computational methods for DDI prediction, showing the current situation and perspectives of these approaches in medicinal and pharmaceutical chemistry. We review sources of information on DDI, which can be used in pharmaceutical investigations and medicinal practice and/or for the creation of computational models. The problem of the inaccuracy and redundancy of these data are discussed. We provide information on the state-of-the-art physiologically- based pharmacokinetic modelling (PBPK) approaches and DME-based in silico methods. In the section on ligand-based methods, we describe pharmacophore models, molecular field analysis, quantitative structure-activity relationships (QSAR), and similarity analysis applied to the prediction of DDI related to the inhibition or induction of DME. In conclusion, we discuss the problems of DDI severity assessment, mention factors that influence severity, and highlight the issues, perspectives and practical using of in silico methods.

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 R 2 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.

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.