Using the local symmetry in amino acids sequences of polypeptides to improve the predictive potential of models of their inhibitor activity.

The minimal inhibitory concentrations (pMIC) are a valuable measure of the biological activity of polypeptides. Numerical data on the pMIC are necessary to systematize knowledge on polypeptides' biochemical behaviour. The model of negative decimal logarithm of pMIC of polypeptides in the form of a mathematical function of a sequence of amino acids is suggested. The suggested model is based on the so-called correlation weights of amino acids together with the correlation weights of fragments of local symmetry (FLS). Three kinds of the FLS are considered: (i) three-symbol fragments '…xyx…', (ii) four-symbol fragments '…xyyx…', and (iii) five-symbol fragments '…xyzyx…'. The models built using the Monte Carlo technique improved by applying the index of ideality of correlation (IIC) and correlation intensity index (CII).

Development of Self-Consistency Models of Anticancer Activity of Nanoparticles under Different Experimental Conditions Using Quasi-SMILES Approach.

Algorithms of the simulation of the anticancer activity of nanoparticles under different experimental conditions toward cell lines A549 (lung cancer), THP-1 (leukemia), MCF-7 (breast cancer), Caco2 (cervical cancer), and hepG2 (hepatoma) have been developed using the quasi-SMILES approach. This approach is suggested as an efficient tool for the quantitative structure-property-activity relationships (QSPRs/QSARs) analysis of the above nanoparticles. The studied model is built up using the so-called vector of ideality of correlation. The components of this vector include the index of ideality of correlation (IIC) and the correlation intensity index (CII). The epistemological component of this study is the development of methods of registration, storage, and effective use of experimental situations that are comfortable for the researcher-experimentalist in order to be able to control the physicochemical and biochemical consequences of using nanomaterials. The proposed approach differs from the traditional models based on QSPR/QSAR in the following respects: (i) not molecules but experimental situations available in a database are considered; in other words, an answer is offered to the question of how to change the plot of the experiment in order to achieve the desired values of the endpoint being studied; and (ii) the user has the ability to select a list of controlled conditions available in the database that can affect the endpoint and evaluate how significant the influence of the selected controlled experimental conditions is.

Machine-learning technique, QSAR and molecular dynamics for hERG-drug interactions.

One of the most well-known anti-targets defining medication cardiotoxicity is the voltage-dependent hERG K + channel, which is well-known for its crucial involvement in cardiac action potential repolarization. Torsades de Pointes, QT prolongation, and sudden death are all caused by hERG (the human Ether-à-go-go-Related Gene) inhibition. There is great interest in creating predictive computational (in silico) tools to identify and weed out potential hERG blockers early in the drug discovery process because testing for hERG liability and the traditional experimental screening are complicated, expensive and time-consuming. This study used 2D descriptors of a large curated dataset of 6766 compounds and machine learning approaches to build robust descriptor-based QSAR and predictive classification models for KCNH2 liability. Decision Tree, Random Forest, Logistic Regression, Ada Boosting, kNN, SVM, Naïve Bayes, neural network and stochastic gradient classification classifier algorithms were used to build classification models. If a compound's IC50 value was between 10 µM and less, it was classified as a blocker (hERG-positive), and if it was more, it was classified as a non-blocker (hERG-negative). Matthew's correlation coefficient formula and F1score were applied to compare and track the developed models' performance. Molecular docking and dynamics studies were performed to understand the cardiotoxicity relating to the hERG-gene. The hERG residues interacting after 100 ns are LEU:697, THR:708, PHE:656, HIS:674, HIS:703, TRP:705 and ASN:709 and the hERG-ligand-16 complex trajectory showed stable behaviour with lesser fluctuations in the entire simulation of 200 ns.Communicated by Ramaswamy H. Sarma.

The system of self-consistent models based on quasi-SMILES as a tool to predict the potential of nano-inhibitors of human lung carcinoma cell line A549 for different experimental conditions.

The different features of the impact of nanoparticles on cells, such as the structure of the core, presence/absence of doping, quality of surface, diameter, and dose, were used to define quasi-SMILES, a line of symbols encoded the above physicochemical features of the impact of nanoparticles. The correlation weight for each code in the quasi-SMILES has been calculated by the Monte Carlo method. The descriptor, which is the sum of the correlation weights, is the basis for a one-variable model of the biological activity of nano-inhibitors of human lung carcinoma cell line A549. The system of models obtained by the above scheme was checked on the self-consistence, i.e., reproducing the statistical quality of these models observed for different distributions of available nanomaterials into the training and validation sets. The computational experiments confirm the excellent potential of the approach as a tool to predict the impact of nanomaterials under different experimental conditions. In conclusion, our model is a self-consistent model system that provides a user to assess the reliability of the statistical quality of the used approach.

Application of quasi-SMILES to the model of gold-nanoparticles uptake in A549 cells.

Cell death is critical to human health and is associated with a variety of medical conditions. Therefore, new controllers of cell death are needed for the treatment of diverse diseases. In particular, nanoparticles (NP) are now regularly used in various applications, including a variety of products and medicines. Gold nanoparticles (GNPs) are widely used in the medical field against A549 lung carcinoma cells. The present study is devoted to developing computational models of the cellular uptake potentials by A549 cells of gold nanoparticles (GNPs) under various conditions. Simplified molecular input-line entry system (SMILES) is an efficient tool to represent the molecular structure by a sequence of symbols. Quasi-SMILES represents an extended version of SMILES where symbols to denote physicochemical and/or biochemical conditions are added. In other words, the quasi-SMILES represents a biochemical (medical) phenomenon related to the whole matter (not only molecular structure). We developed models for the cellular utpake potential of gold nanoparticles (GNPs) in A549 [10-11 g Au/Cell] under various conditions based on quasi-SMILES using the Monte Carlo method. The statistical quality of these models is quite good.

The system of self-consistent models for the uptake of nanoparticles in PaCa2 cancer cells.

Quantitative structure-property/activity relationships (QSPRs/QSARs) are an important component of modern science. Validation of the QSPR/QSAR is the basis for applying. The system of self-consistent models is a new approach to validate QSPR/QSAR. The principle 'QSAR is a random event' means that an approach may be recognized as robust only if the statistical characteristics of models obtained by this approach for different splits (training/test) are reproduced. The above principle applies to the case of the nano-QSAR, also. Here, the cellular uptake of nanoparticles in pancreatic cancer cells examines as the endpoint. Groups of models for different splits (training/test) are compared. This comparison gives the possibility to formulate the system of self-consistent models as a way to assess the predictive potential for an arbitrary QSPR/QSAR and/or nano-QSPR/QSAR. The correlation intensity index (CII) has been tested as a tool to improve the quality of models for the cellular uptake of nanoparticles in pancreatic cancer cells (PaCa2). It has shown, that the CII can be useful, but only incorporating with the Index of ideality of correlation (IIC).

The index of ideality of correlation improves the predictive potential of models of the antioxidant activity of tripeptides from frog skin (Litoria rubella).

It is usually held that good-quality models for the biological activity of peptides must take into account their 3D architecture and descriptors of quantum mechanics. However, the present study shows that it is possible to build up models without these complex calculations. The structure of tripeptides represented by sequences of one-symbol abbreviations of the corresponding amino acids serves to build up quantitative structure-activity relationships for the antioxidant activity of tripeptides from frog skin. The statistical quality of the best model for the validation set is n = 27, r2 = 0.93, RMSE = 0.15.

Pesticides, cosmetics, drugs: identical and opposite influences of various molecular features as measures of endpoints similarity and dissimilarity.

The similarity is an important category in natural sciences. A measure of similarity for a group of various biochemical endpoints is suggested. The list of examined endpoints contains (1) toxicity of pesticides towards rainbow trout; (2) human skin sensitization; (3) mutagenicity; (4) toxicity of psychotropic drugs; and (5) anti HIV activity. Further applying and evolution of the suggested approach is discussed. In particular, the conception of the similarity (dissimilarity) of endpoints can play the role of a "useful bridge" between quantitative structure property/activity relationships (QSPRs/QSARs) and read-across technique.

How the CORAL software can be used to select compounds for efficient treatment of neurodegenerative diseases?

Recommendations on the efficient application of CORAL software (http://www.insilico.eu/coral) to establish quantitative structure-property/activity relationships (QSPRs/QSARs) are provided. The predictive potential of the approach has been demonstrated for QSAR models developed for inhibitor concentrations (negative decimal logarithm of IC50) of derivatives of N-methyl-d-aspartate (NMDA) receptor, leucine-rich repeat kinase 2 (LRRK2), and tropomyosin receptor kinase A (TrkA). The above three protein targets are related to various neurodegenerative diseases such as Alzheimer's and Parkinson's. Each model was checked using several splits of the data for the training and the validation sets. The index of ideality of correlation (IIC) represents a tool to improve the predictive potential for an arbitrary model. However, the use of the IIC should be carried out according to rules, described in this work.

Correlation intensity index: mathematical modeling of cytotoxicity of metal oxide nanoparticles.

Metal oxide nanoparticles (MO-NPs) have unique structural characteristics, exceptionally high surface area, strong mechanical stability, catalytic activities, and are biocompatible. Consequently, MO-NPs have recently attracted considerable interest in the field of imaging-guided therapeutic and biosensing applications. This study aims to develop Quantitative Structure-Activity Relationships (QSAR) for the prediction of cell viability of MO-NPs. The QSAR model based on the so-called optimal descriptors which calculated with a simplified molecular input-line entry system (SMILES). The Monte Carlo technique applied to calculate correlation weights for SMILES fragments. Factually, the optimal descriptor for SMILES is the summation of the correlation weights. The model of cytotoxicity is one variable correlation between cytotoxicity and the above optimal descriptor. The Correlation Intensity Index (CII) is a possible criterion of the predictive potential of the model. Applying the CII as a component of the target function in the Monte Carlo optimization routine, employed by the CORAL program, that is designed to find a predictive relationship between the optimal descriptor and cytotoxicity of MO-NPs, improves the statistical quality of the model. The significance of different eclectic features, in terms of whether they increase/decrease cell viability, i.e. decrease or increase cytotoxicity, is also discussed. Numerical data on 83 experimental samples of MO-NPs activity under different conditions taken from the literature are applied for the "nano-QSAR" analysis.

QSAR model for pesticides toxicity to Rainbow Trout based on "ideal correlations".

Pesticides have an impact on the aquatic environment, with ecological effects. The regulation of this impact is of key importance. One of the components of the planning of agricultural and industrial activities is the development of databases and models in order to identify substances that may cause damage. In this study, a quantitative structure-activity relationship (QSAR) approach was established for the prediction of acute toxicity toward rainbow trout of various pesticides. The so-called index of ideality of correlation is the main component of this approach. The validation of this approach has been carried out with three random splits into the training and validation sets. The range of statistical quality of models obtained here for the validation set is R2 = [0.81-0.86] and RMSE = [0.55-0.65].

Ecosystem ecology: Models for acute toxicity of pesticides towards Daphnia magna.

Quantitative structure - activity relationships (QSARs) which are obtained with a representation of the molecular architecture via simplified molecular input-line entry system (SMILES) are applied to build up predictive models of acute toxicity of pesticides towards Daphnia magna. The acute toxicity towards Daphnia magna is an adequate measure of the ecological impact of various substances. The Monte Carlo technique is the basis to build up the above QSAR models. The statistical quality of suggested models is good: the best model is characterized by n = 103, R2 = 0.76, RMSE = 0.91 (training set); n = 53, R2 = 0.82, RMSE = 0.87 (validation set). The approach provides the mechanistic interpretation (e.g. aromaticity and branching of carbon skeleton are promoters of increase for toxicity towards Daphnia magna in the case of the examined set of pesticides). The approach is attractive to build up predictive models since instead of a large number of different molecular descriptors the corresponding model is based on solely one optimal descriptor calculated with SMILES and all necessary calculations can be done using the CORAL software available on the Internet (http://ww.insilico.eu/coral).

QSPR/QSAR: State-of-Art, Weirdness, the Future.

Ability of quantitative structure-property/activity relationships (QSPRs/QSARs) to serve for epistemological processes in natural sciences is discussed. Some weirdness of QSPR/QSAR state-of-art is listed. There are some contradictions in the research results in this area. Sometimes, these should be classified as paradoxes or weirdness. These points are often ignored. Here, these are listed and briefly commented. In addition, hypotheses on the future evolution of the QSPR/QSAR theory and practice are suggested. In particular, the possibility of extending of the QSPR/QSAR problematic by searching for the "statistical similarity" of different endpoints is suggested and illustrated by an example for relatively "distanced each from other" endpoints, namely (i) mutagenicity, (ii) anticancer activity, and (iii) blood-brain barrier.

The using of the Index of Ideality of Correlation (IIC) to improve predictive potential of models of water solubility for pesticides.

Models for water solubility of pesticides suggested in this manuscript are important data from point of view of ecologic engineering. The Index of Ideality of Correlation (IIC) of groups of quantitative structure-property relationships (QSPRs) for water solubility of pesticides related to the calibration sets was used to identify good in silico models. This comparison confirmed the high IIC set provides better statistical quality of the model for the validation set. Though there are large databases on solubility, the reliable prediction of the endpoint for new substances which are potential pesticides is an important ecologic task. Unfortunately, predictive models for various endpoints suffer overtraining, and the IIC serves to avoid or at least reduce this. Thus, the approach suggested has both theoretical and economic effects for ecology.

CORAL: Building up QSAR models for the chromosome aberration test.

A high level of chromosomal aberrations in peripheral blood lymphocytes may be an early marker of cancer risk, but data on risk of specific cancers and types of chromosomal aberrations are limited. Consequently, the development of predictive models for chromosomal aberrations test is important task. Majority of models for chromosomal aberrations test are so-called knowledge-based rules system. The CORAL software (http://www.insilico.eu/coral, abbreviation of "CORrelation And Logic") is an alternative for knowledge-based rules system. In contrast to knowledge-based rules system, the CORAL software gives possibility to estimate the influence upon the predictive potential of a model of different molecular alerts as well as different splits into the training set and validation set. This possibility is not available for the approaches based on the knowledge-based rules system. Quantitative Structure-Activity Relationships (QSAR) for chromosome aberration test are established for five random splits into the training, calibration, and validation sets. The QSAR approach is based on representation of the molecular structure by simplified molecular input-line entry system (SMILES) without data on physicochemical and/or biochemical parameters. In spite of this limitation, the statistical quality of these models is quite good.

"Ideal correlations" for biological activity of peptides.

Sequences of one-symbol abbreviations of amino acids are applied as the basis to build up predictive model of Angiotensin converting enzyme (ACE) inhibitory activity of dipeptides and antibacterial activity of group of polypeptides. The developed models are one-variable correlations between biological activity and descriptors calculated with so-called correlation weights of amino acids. The numerical data on the correlation weights are obtained by the Monte Carlo method. The Index of Ideality of Correlation (IIC) is a mathematical function of (i) the determination coefficient; and (ii) sums of positive and negative values of "observed minus predicted" endpoints values. The obtained results confirm that IIC can be applied to improve predictive potential of models for ACE inhibitor activity of dipeptides and antibacterial activity of polypeptides.

Application of the Monte Carlo Method for the Prediction of Behavior of Peptides.

Prediction of physicochemical and biochemical behavior of peptides is an important and attractive task of the modern natural sciences, since these substances have a key role in life processes. The Monte Carlo technique is a possible way to solve the above task. The Monte Carlo method is a tool with different applications relative to the study of peptides: (i) analysis of the 3D configurations (conformers); (ii) establishment of quantitative structure - property / activity relationships (QSPRs/QSARs); and (iii) development of databases on the biopolymers. Current ideas related to application of the Monte Carlo technique for studying peptides and biopolymers have been discussed in this review.

Virtual Screening of Anti-Cancer Compounds: Application of Monte Carlo Technique.

Possibility and necessity of standardization of predictive models for anti-cancer activity are discussed. The hypothesis about rationality of common quantitative analysis of anti-cancer activity and carcinogenicity is developed. Potential of optimal descriptors to be used as a tool to build up predictive models for anti-cancer activity is examined from practical point of view. Various perspectives of application of optimal descriptors are reviewed. Stochastic nature of phenomena which are related to carcinogenic potential of various substances can be successfully detected and interpreted by the Monte Carlo technique. Hypothesises related to practical strategy and tactics of the searching for new anticancer agents are suggested.

Quasi-SMILES: quantitative structure-activity relationships to predict anticancer activity.

Reliable prediction of anticancer potential of different substances for different cells using unambiguous algorithms is attractive alternative of experimental investigation of impacts of various anticancer agents to various cells. Quasi-SMILES is a sequence of symbols, which represents all available eclectic data, i.e. not only molecular structure, but also different conditions, which can have influence on examined endpoint (e.g. kinds of cells: human breast; human colon; human liver; human lung). In this work, quasi-SMILES have been used to establish predictive models for anticancer activity isoquinoline quinones related to different cells. Descriptor calculated with optimal correlation weights of different fragments of quasi-SMILES defined by the Monte Carlo technique is used to predict pIC50 as a mathematical function of molecular structure and kinds of cells. The using of the so-called index of ideality of correlation for optimization by the Monte Carlo method improves predictive potential of the model. The statistical quality of the models based on correlation weights of fragments of quasi-SMILES is good. The range of correlation coefficient between experimental and calculated pIC50 for external validation set is 0.76-0.89. The statistical stable promoters for increase and for decrease in pIC50 are established. These models can be used to improve quality of pharmaceutical agents. These computational experiments can be reproduced with available on the Internet software ( http://www.insilico.eu/coral ).

Use of the index of ideality of correlation to improve predictive potential for biochemical endpoints.

The CORAL software is a tool to build up quantitative structure-property/activity relationships (QSPRs/QSARs). The project of updated version of the CORAL software is discussed in terms of practical applications for building up various models. The updating is the possibility to improve the predictive potential of models using the so-called Index of Ideality of Correlation (IIC) as a criterion of the predictive potential for QSPR/QSAR models. Efficacy of the IIC is examined with three examples of building up QSARs: (i) models for anticancer activity; (ii) models for mutagenicity; and (iii) models for toxicity of psychotropic drugs. The validation of these models has been carried out with several splits into the training, invisible training, calibration, and validation sets. The ability of IIC to be an indicator of predictive potential of QSAR models is confirmed. The updated version of the CORAL software (CORALSEA-2017, http://www.insilico.eu/coral ) is available on the Internet.