Application ofab initio theory to QSAR study of 1,4-dihydropyridine-based calcium channel blockers using GA-MLR and PC-GA-ANN procedures

Interpretation of ANN-based QSAR models for prediction of antioxidant activity of flavonoids

Quantitative structure-activity relationships (QSARs) built using machine learning methods, such as artificial neural networks (ANNs) are powerful in prediction of (antioxidant) activity from quantum mechanical (QM) parameters describing the molecular structure, but are usually not interpretable. This obvious difficulty is one of the most common obstacles in application of ANN-based QSAR models for design of potent antioxidants or elucidating the underlying mechanism. Interpreting the resulting models is often omitted or performed erroneously altogether. In this work, a comprehensive comparative study of six methods (PaD, PaD₂ , weights, stepwise, perturbation and profile) for exploration and interpretation of ANN models built for prediction of Trolox-equivalent antioxidant capacity (TEAC) QM descriptors, is presented. Sum of ranking differences (SRD) was used for ranking of the six methods with respect to the contributions of the calculated QM molecular descriptors toward TEAC. The results show that the PaD, PaD₂ and profile methods are the most stable and give rise to realistic interpretation of the observed correlations. Therefore, they are safely applicable for future interpretations without the opinion of an experienced chemist or bio-analyst. © 2018 Wiley Periodicals, Inc.

Computational approaches to understand the adverse drug effect on potassium, sodium and calcium channels for predicting TdP cardiac arrhythmias

Ion channels play a crucial role in the cardiovascular system. Our understanding of cardiac ion channel function has improved since their first discoveries. The flow of potassium, sodium and calcium ions across cardiomyocytes is vital for regular cardiac rhythm. Blockage of these channels, delays cardiac repolarization or tend to shorten repolarization and may induce arrhythmia. Detection of drug risk by channel blockade is considered essential for drug regulators. Advanced computational models can be used as an early screen for torsadogenic potential in drug candidates. New drug candidates that are determined to not cause blockage are more likely to pass successfully through preclinical trials and not be withdrawn later from the marketplace by manufacturer. Several different approved drugs, however, can cause a distinctive polymorphic ventricular arrhythmia known as torsade de pointes (TdP), which may lead to sudden death. The objective of the present study is to review the mechanisms and computational models used to assess the risk that a drug may TdP.

KEY POINTS

There is strong evidence from multiple studies that blockage of the L-type calcium current reduces risk of TdP. Blockage of sodium channels slows cardiac action potential conduction, however, not all sodium channel blocking antiarrhythmic drugs produce a significant effect, while late sodium channel block reduces TdP. Interestingly, there are some drugs that block the hERG potassium channel and therefore cause QT prolongation, but they are not associated with TdP. Recent studies confirmed the necessity of studying multiple distinctionic ion channels which are responsible for cardiac related diseases or TdP, to obtain an improved clinical TdP risk prediction of compound interactions and also for designing drugs.

QSAR study of the acute toxicity to fathead minnow based on a large dataset

Acute fathead minnow toxicity is an important basis of hazard and risk assessment for compounds in the aquatic environment. In this paper, a large dataset consisting of 963 organic compounds with acute toxicity towards fathead minnow was studied with a QSAR approach. All molecular structures of compounds were optimized by the hybrid density functional theory method. Dragon molecular descriptors and log Kow were selected to describe molecular information. Genetic algorithm and multiple linear regression analysis were combined to develop models. A global prediction model for compounds without known mode of action and two local models for organic compounds that exhibit narcosis toxicity and excess toxicity were developed, respectively. For all developed models, internal validations were performed by cross-validation and external validations were implemented by the setting of validation set. In addition, applicability domains of models were evaluated using a leverage method and outliers were listed and checked using toxicological knowledge.

Predicting carcinogenicity of organic compounds based on CPDB

Cancer is a major killer of human health and predictions for the carcinogenicity of chemicals are of great importance. In this article, predictive models for the carcinogenicity of organic compounds using QSAR methods for rats and mice were developed based on the data from CPDB. The models was developed based on the data of specific target site liver and classified according to sex of rats and mice. Meanwhile, models were also classified according to whether there is a ring in the molecular structure in order to reduce the diversity of molecular structure. Therefore, eight local models were developed in the final. Taking into account the complexity of carcinogenesis and in order to obtain as much information, DRAGON descriptors were selected as the variables used to develop models. Fitting ability, robustness and predictive power of the models were assessed according to the OECD principles. The external predictive coefficients for validation sets of each model were in the range of 0.711-0.906, and for the whole data in each model were all greater than 0.8, which represents that all models have good predictivity. In order to study the mechanism of carcinogenesis, standardized regression coefficients were calculated for all predictor variables. In addition, the effect of animal sex on carcinogenesis was compared and a trend that female showed stronger tolerance for cancerogen than male in both species was appeared.

1,4-Dihydropyridine Calcium Channel Blockers: Homology Modeling of the Receptor and Assessment of Structure Activity Relationship

1,4-Dihydropyridine (DHP), an important class of calcium antagonist, inhibits the influx of extracellular Ca+2 through L-type voltage-dependent calcium channels. Three-dimensional (3D) structure of calcium channel as a receptor for 1,4-dihydropyridine is a step in understanding its mode of action. Protein structure prediction and modeling tools are becoming integral parts of the standard toolkit in biological and biomedical research. So, homology modeling (HM) of calcium channel alpha-1C subunit as DHP receptor model was achieved. The 3D structure of potassium channel was used as template for HM process. The resulted dihydropyridine receptor model was checked by different means to assure stereochemical quality and structural integrity of the model. This model was achieved in an attempt to understand the mode of action of DHP calcium channel antagonist and in further computer-aided drug design (CADD) analysis. Also the structure-activity relationship (SAR) of DHPs as antihypertensive and antianginal agents was reviewed, summarized, and discussed.

Asymmetrical 2,6-bis(benzylidene)cyclohexanones: Synthesis, cytotoxic activity and QSAR study

In order to develop novel anti-cancer agents, a series of asymmetrical 2,6-bis (benzylidene)cyclohexanone derivatives containing nitrobenzylidene moiety were synthesized and their cytotoxic activity were determined in vitro against MDA-MB 231, MCF-7 and SK-N-MC cell lines using MTT assay. Among the tested compounds, the highest activity against MDA-MB 231 cells was achieved by 2-(3-bromo-5-methoxy-4-propoxybenzylidene)-6-(2-nitrobenzylidene)cyclohexanone (compound 5d). Whereas, compound 5j (the 3-nitro analog of compound 5d) was the most potent compound against MCF-7 and SK-N-MC cell lines. The results indicated that the cytotoxic activity profile against different tumor cells can be optimized by desired 4-alkoxy-3-bromo-5-methoxybenzylidene scaffold.

Fragment-based quantitative structure-activity relationship (FB-QSAR) for fragment-based drug design

In cooperation with the fragment-based design a new drug design method, the so-called "fragment-based quantitative structure-activity relationship" (FB-QSAR) is proposed. The essence of the new method is that the molecular framework in a family of drug candidates are divided into several fragments according to their substitutes being investigated. The bioactivities of molecules are correlated with the physicochemical properties of the molecular fragments through two sets of coefficients in the linear free energy equations. One coefficient set is for the physicochemical properties and the other for the weight factors of the molecular fragments. Meanwhile, an iterative double least square (IDLS) technique is developed to solve the two sets of coefficients in a training data set alternately and iteratively. The IDLS technique is a feedback procedure with machine learning ability. The standard Two-dimensional quantitative structure-activity relationship (2D-QSAR) is a special case, in the FB-QSAR, when the whole molecule is treated as one entity. The FB-QSAR approach can remarkably enhance the predictive power and provide more structural insights into rational drug design. As an example, the FB-QSAR is applied to build a predictive model of neuraminidase inhibitors for drug development against H5N1 influenza virus.

Synthesis, QSAR and Calcium Channel Antagonist Activity of New 1,4-Dihydropyridine Derivatives Containing 1-Methyl-4,5-dichloroimidazolyl Substituents

A group of dialkyl and diarylester analogues of nifedipine, in which the ortho-nitrophenyl group at position 4 was replaced by a 1-methyl-4,5-dichloroimidazolyl substituent, were synthesized and evaluated as calcium-channel antagonists using the high K(+)concentration of guinea-pig ileum longitudinal smooth muscle. The structure of all compounds was confirmed by IR,(1)H-NMR, and mass spectra. The calcium-channel antagonist activity of compounds 10a-f demonstrated that compound 10b was the most active and 10f the least active one. With unsymmetrical diesters 12a-k, the most active compound was the ethyl, phenethyl derivative. Structural parameters on the calcium-channel antagonist activity were evaluated by QSAR analysis and a linear correlation was found between the -log IC(50) values of these compounds and their constitutional and topological properties.

QSAR modeling of matrix metalloproteinase inhibition by N-hydroxy-alpha-phenylsulfonylacetamide derivatives

The main molecular features which determine the selectivity of a set of 80 N-hydroxy-alpha-phenylsulfonylacetamide derivatives (HPSAs) in the inhibition of three matrix metalloproteinases (MMP-1, MMP-9, and MMP-13) have been identified by using linear and nonlinear predictive models. The molecular information has been encoded in 2D autocorrelation descriptors, obtained from different weighting schemes. The linear models were built by multiple linear regression (MLR) combined with genetic algorithm (GA), and a robust QSAR mapping paradigm. The Bayesian-regularized genetic neural network (BRGNN) was employed for nonlinear modeling. In such approaches each model could have its own set of input variables. All models were predictive according to internal and external validation experiments; but the best results correspond to nonlinear ones. The 2D autocorrelation space brings different descriptors for each MMP inhibition, and suggests the atomic properties relevant for the inhibitors to interact with each MMP active site. On the basis of the current results, the reported models have the potential to discover new potent and selective inhibitors and bring useful molecular information about the ligand specificity for MMP S(1)(') and S(2)(') subsites.

Application of quantum topological molecular similarity descriptors in QSPR study of the O-methylation of substituted phenols

The usefulness of a novel type of electronic descriptors called quantum topological molecular similarity (QTMS) indices for describing the quantitative effects of molecular electronic environments on the O-methylation kinetic of substituted phenols has been investigated. QTMS theory produces for each molecule a matrix of descriptors, containing bond (or structure) information in one dimension and electronic effects in another dimension, instead of other methods producing a vector of descriptors for each molecule. A collection of chemometrics tools including principal component analysis (PCA), partial least squares (PLS), and genetic algorithms (GA) were used to model the structure-kinetic data. PCA separated the bond and descriptor effects, and PLS modeled the effects of these parameters on the rate constant data, and GA selected the most relevant subset of variables. The model performances were validated by both cross-validation and external validation. The results indicated that the proposed models could explain about 95% of variances in the rate constant data. The significant effects of variables on the reaction kinetic were identified by calculating variable important in projection (VIP). It was found that the rate constant of esterification of phenols is highly influenced by the electronic properties of the C2--C1--O--H fragment of the parent molecule. Indeed, the C2--X and C4--X bonds (corresponding to ortho and para substituents) were found as highly influential parameters. All of the eight calculated QTMS indices were found significant however, lambda1, lambda2, lambda3, epsilon, and K(r) were detected as highly influential parameters.

Quantitative Structure−Activity (Affinity) Relationship (QSAR) Study on Protonation and Cationization of α-Amino Acids

A quantitative structure-activity (affinity) relationship (QSAR) study is carried out to model the proton, sodium, copper, and silver cation affinities of alpha-amino acids (AA). Stepping multiple linear regression (MLR), partial least squares (PLS), and artificial neural network (ANN) approaches are applied to elucidate the multiple factors affecting these affinities. The MLR and PLS models reveal that the variation in proton affinity is attributed to the highest electrophilic superdelocalizability of nitrogen (major) and the number of rotatable bonds (minor) in AA. The noncovalent interactions, especially ion-dipole interactions, are responsible for the changes in Na+ affinity. The ionization potential, dipole moment of the side chain, and degree of linearity are the properties of AA that give the best correlation with the Cu+ and Ag+ affinities. The ANN models are developed to study the relationships (linear or nonlinear) between the molecular descriptors and binding affinities. The ANN models show higher predictive power. The QSAR models are used to study the binding forms of AA (neutral vs zwitterionic) upon protonation/cationization. To our knowledge, this is the first attempt to carry out a QSAR study on protonated/cationized AlphaAlpha to elucidate their binding properties. In virtue of the Na+ affinity ANN model, the Na+ affinities of dihydroxyphenylalanine (DOPA) were predicted. This work may pave the way for the success of applying similar approaches to peptides or proteins (with AA as the building blocks) in the future.

Accurate prediction of the blood-brain partitioning of a large set of solutes usingab initiocalculations and genetic neural network modeling

A genetic algorithm-based artificial neural network model has been developed for the accurate prediction of the blood-brain barrier partitioning (in logBB scale) of chemicals. A data set of 123 logBB (115 old molecules and 8 new molecules) of a diverse set of chemicals was chosen in this study. The optimum 3D geometry of the molecules was estimated by the ab initio calculations at the level of RHF/STO-3G, and consequently, different electronic descriptors were calculated for each molecule. Indeed, logP as a measure of hydrophobicity and different topological indices were also calculated. A three-layered artificial neural network with backpropagation of an error-learning algorithm was employed to process the nonlinear relationship between the calculated descriptors and logBB data. Genetic algorithm was used as a feature selection method to select the most relevant set of descriptors as the input of the network. Modeling of the logBB data by the only quantum descriptors produced a 5:4:1 ANN structure with RMS error of validation and crossvalidation equal to 0.224 and 0.227, respectively. Better nonlinear model (RMS(V) and RMS(CV) equals to 0.097 and 0.099, respectively) was obtained by the incorporation of the logP and the principal components of the topological indices to electronic descriptors. The ultimate performances of the models were obtained by the application of the models to predict the logBB of 23 molecules that did not have contribution in the steps of model development. The best model produced RMS error of prediction 0.140, and could predict about 98% of variances in the logBB data.

Linear and nonlinear QSAR study of N-hydroxy-2-[(phenylsulfonyl)amino]acetamide derivatives as matrix metalloproteinase inhibitors

The inhibitory activity (IC50) toward matrix metalloproteinases (MMP-1, MMP-2, MMP-3, MMP-9, and MMP-13) of N-hydroxy-2-[(phenylsulfonyl)amino]acetamide derivatives (HPSAAs) has been successfully modeled using 2D autocorrelation descriptors. The relevant molecular descriptors were selected by linear and nonlinear genetic algorithm (GA) feature selection using multiple linear regression (MLR) and Bayesian-regularized neural network (BRANN) approaches, respectively. The quality of the models was evaluated by means of cross-validation experiments and the best results correspond to nonlinear ones (Q2>0.7 for all models). Despite the high correlation between the studied compound IC50 values, the 2D autocorrelation space brings different descriptors for each MMP inhibition. On the basis of these results, these models contain useful molecular information about the ligand specificity for MMP S'1, S1, and S'2 pockets.

Toward an Optimal Procedure for PC-ANN Model Building: Prediction of the Carcinogenic Activity of a Large Set of Drugs

The performances of the three novel QSAR algorithms, principal component-artificial neural network modeling method combining with three factor selection procedures named eigenvalue ranking, correlation ranking, and genetic algorithm (ER-PC-ANN, CR-PC-ANN, PC-GA-ANN, respectively), are compared by application of these model to the prediction of the carcinogenic activity of a large set of drugs (735 drugs) belonging to a diverse type of compounds. A total number of 1350 theoretical descriptors are calculated for each molecule. The matrix of calculated descriptors (with 735 x 1350 dimension) is subjected to PCA. 95% of the variances in the matrix are explained by the first 137 principal components (PC's). From the pool of 137 PC's, the factor selection methods (ER, CR, and GA) are employed to select the best set of PC's for PC-ANN modeling. In the ER-PC-ANN, the PC's are successively entered into the ANN based on their decreasing eigenvalue. In the CR-PC-ANN, the ANN is first employed to model the nonlinear relationship between each one of the PC's and the carcinogen activity separately. Then, the PC's are ranked based on their decreasing correlating ability and entered to the input layer of the network one after another. Finally, a search algorithm (i.e. genetic algorithm) is used to find the best set of PC's. Both the external and cross-validation methods are used to validate the performances of the resulting models. One is able to see that the results obtained by the PC-GA-ANN and CR-PC-ANN procedures are superior to those resulted from the EV-PC-ANN. Comparison of the results reveals that the results produced by the PC-GA-ANN algorithm are better than those produced by CR-PC-ANN. However, the difference is not significant.