Modeling of farnesyltransferase inhibition by some thiol and non-thiol peptidomimetic inhibitors using genetic neural networks and RDF approaches

An Analysis of QSAR Research Based on Machine Learning Concepts

Quantitative Structure-Activity Relationship (QSAR) is a popular approach developed to correlate chemical molecules with their biological activities based on their chemical structures. Machine learning techniques have proved to be promising solutions to QSAR modeling. Due to the significant role of machine learning strategies in QSAR modeling, this area of research has attracted much attention from researchers. A considerable amount of literature has been published on machine learning based QSAR modeling methodologies whilst this domain still suffers from lack of a recent and comprehensive analysis of these algorithms. This study systematically reviews the application of machine learning algorithms in QSAR, aiming to provide an analytical framework. For this purpose, we present a framework called 'ML-QSAR'. This framework has been designed for future research to: a) facilitate the selection of proper strategies among existing algorithms according to the application area requirements, b) help to develop and ameliorate current methods and c) providing a platform to study existing methodologies comparatively. In ML-QSAR, first a structured categorization is depicted which studied the QSAR modeling research based on machine models. Then several criteria are introduced in order to assess the models. Finally, inspired by aforementioned criteria the qualitative analysis is carried out.

Performance of radial distribution function-based descriptors in the chemoinformatic studies of HIV-1 protease

Aim: This letter investigates the role of radial distribution function-based descriptors for in silico design of new drugs. Methodology: The multiple linear regression models for HIV-1 protease and its complexes with a series of inhibitors were constructed. A detailed analysis of major atomic contributions to the radial distribution function descriptor weighted by the number of valence shell electrons identified residues Arg8, Asp29 and residues of the catalytic triad as crucial for the correlation with the inhibition constant, together with residues Asp30 and Ile50, whose mutations are known to cause an emergence of drug resistant variants. Conclusion: This study demonstrates an easy and fast assessment of the activity of potential drugs and the derivation of structural information of their complexes with the receptor or enzyme.

A stepwise protocol for neural network modeling of persistent postoperative facial pain in chronic rhinosinusitis

In the artificial neural network field, no universal algorithm of modeling ensures obtaining the best possible model for a given task. Researchers frequently regard artificial neural networks with suspicion caused by the lack of repeatability of single experiments. We propose a systematic approach that may increase the probability of finding the optimal network architecture. In the experiments, the average effectiveness in groups of networks rather than single networks should be compared. Such an approach facilitates the analysis of the results caused by changes in the network parameters, while the influence of chance effects becomes negligible. As an example of this protocol, we present optimization of a neural network applied for prediction of persistent facial pain in patients operated for chronic rhinosinusitis. In the stepwise approach, the percentage of correct predictions was gradually increased from 54% to 75% for the external validation set.

2D-QSAR study of some 2,5-diaminobenzophenone farnesyltransferase inhibitors by different chemometric methods

Quantitative structure activity relationship (QSAR) models can be used to predict the activity of new drug candidates in early stages of drug discovery. In the present study, the information of the ninety two 2,5-diaminobenzophenone-containing farnesyltranaferase inhibitors (FTIs) were taken from the literature. Subsequently, the structures of the molecules were optimized using Hyperchem software and molecular descriptors were obtained using Dragon software. The most suitable descriptors were selected using genetic algorithms-partial least squares and stepwise regression, where exhibited that the volume, shape and polarity of the FTIs are important for their activities. The two-dimensional QSAR models (2D-QSAR) were obtained using both linear methods (multiple linear regression) and non-linear methods (artificial neural networks and support vector machines). The proposed QSAR models were validated using internal validation method. The results showed that the proposed 2D-QSAR models were valid and they can be used for prediction of the activities of the 2,5-diaminobenzophenone-containing FTIs. In conclusion, the 2D-QSAR models (both linear and non-linear) showed good prediction capability and the non-linear models were exhibited more accuracy than the linear models.

Molecular Descriptors in Modelling the Tumour Necrosis Factor-α Converting Enzyme Inhibition Activity of Novel Tartrate-Based Analogues

The tumour necrosis factor-α converting enzyme inhibition activity of a series comprising of novel tartrate-based analogues has been quantitatively analysed in terms of molecular descriptors. The statistically validated quantitative structure-activity relationship models provided rationales to explain the inhibition activity of these congeners. The descriptors identified through combinatorial protocol in multiple linear regression analysis have highlighted the role of Moran autocorrelation of lag 7, weighted by atomic van der Waals volume, presence of both prime and nonprime amide carbonyl oxygen in the tartrate moiety and occurrence of five membered ring bearing substituents at varying sites. A few potential novel tartrate-based analogues have been suggested for further investigation.

CoMFA and CoMSIA analysis of tetrahydroquinolines as potential antimalarial agents

Comparative molecular field analysis (CoMFA) and comparative molecular similarity indices analysis (CoMSIA) were used on a dataset of compounds, some of them having been reported to inhibit Plasmodium falciparum protein, farnesyltransferase. The co-crystal structure of the lead molecule, BMS-214662 bound to Rat-PFT was used as a template. CoMFA yielded a good model, with r²(ncv) = 0.909, r²(cv) = 0.617 and was validated using an external set r²(pred) = 0.748). It compared favourably with CoMSIA. In the CoMFA model the steric and electrostatic fields exerted an almost equal influence on activity. The contour maps indicated the necessity for sterically large electropositive groups with electronegative tail to be present in these molecules for activity, and sterically large electronegative moieties on the sulfonamide linker. By incorporating these features some new compounds have been identified for further investigation.

Genetic algorithm optimization in drug design QSAR: Bayesian-regularized genetic neural networks (BRGNN) and genetic algorithm-optimized support vectors machines (GA-SVM)

Many articles in "in silico" drug design implemented genetic algorithm (GA) for feature selection, model optimization, conformational search, or docking studies. Some of these articles described GA applications to quantitative structure-activity relationships (QSAR) modeling in combination with regression and/or classification techniques. We reviewed the implementation of GA in drug design QSAR and specifically its performance in the optimization of robust mathematical models such as Bayesian-regularized artificial neural networks (BRANNs) and support vector machines (SVMs) on different drug design problems. Modeled data sets encompassed ADMET and solubility properties, cancer target inhibitors, acetylcholinesterase inhibitors, HIV-1 protease inhibitors, ion-channel and calcium entry blockers, and antiprotozoan compounds as well as protein classes, functional, and conformational stability data. The GA-optimized predictors were often more accurate and robust than previous published models on the same data sets and explained more than 65% of data variances in validation experiments. In addition, feature selection over large pools of molecular descriptors provided insights into the structural and atomic properties ruling ligand-target interactions.

Imidazole-containing farnesyltransferase inhibitors: 3D quantitative structure-activity relationships and molecular docking

One of the most promising anticancer and recent antimalarial targets is the heterodimeric zinc-containing protein farnesyltransferase (FT). In this work, we studied a highly diverse series of 192 Abbott-initiated imidazole-containing compounds and their FT inhibitory activities using 3D-QSAR and docking, in order to gain understanding of the interaction of these inhibitors with FT to aid development of a rational strategy for further lead optimization. We report several highly significant and predictive CoMFA and CoMSIA models. The best model, composed of CoMFA steric and electrostatic fields combined with CoMSIA hydrophobic and H-bond acceptor fields, had r (2) = 0.878, q (2) = 0.630, and r (pred) (2) = 0.614. Docking studies on the statistical outliers revealed that some of them had a different binding mode in the FT active site based on steric bulk and available active site space, explaining why the predicted activities differed from the experimental activities.

Computational neural network analysis of the affinity of N-n-alkylnicotinium salts for the alpha4beta2* nicotinic acetylcholine receptor

Based on an 85 molecule database, linear regression with different size datasets and an artificial neural network approach have been used to build mathematical relationships to fit experimentally obtained affinity values (K(i)) of a series of mono- and bis-quaternary ammonium salts from [(3)H]nicotine binding assays using rat striatal membrane preparations. The fitted results were then used to analyze the pattern among the experimental K(i) values of a set of N-n-alkylnicotinium analogs with increasing n-alkyl chain length from 1 to 20 carbons. The affinity of these N-n-alkylnicotinium compounds was shown to parabolically vary with increasing numbers of carbon atoms in the n-alkyl chain, with a local minimum for the C(4) (n-butyl) analogue. A decrease in K(i) value between C(12) and C(13) was also observed. The statistical results for the best neural network fit of the 85 experimental K(i) values are r(2) = 0.84, rmsd = 0.39; r(cv)(2) = 0.68, and loormsd = 0.56. The generated neural network model with the 85 molecule training set may also be of value for future predictions of K(i) values for new virtual compounds, which can then be identified, subsequently synthesized, and tested experimentally.

Modeling of acetylcholinesterase inhibition by tacrine analogues using Bayesian-regularized Genetic Neural Networks and ensemble averaging

Acetylcholinesterase inhibition was modeled for a set of 136 tacrine analogues using Bayesian-regularized Genetic Neural Networks (BRGNNs). In the BRGNN approach the Bayesian-regularization avoids overtraining/overfitting and the genetic algorithm (GA) allows exploring an ample pool of 3D-descriptors. The predictive capacity of our selected model was evaluated by averaging multiple validation sets generated as members of diverse-training set neural network ensembles (NNEs). The ensemble averaging provides reliable statistics. When 40 members are assembled, the NNE provides a reliable measure of training and test set R values of 0.921 and 0.851 respectively. In other respects, the ability of the nonlinear selected GA space for differentiating the data was evidenced when the total data set was well distributed in a Kohonen Self-Organizing Map (SOM). The location of the inhibitors in the map facilitates the analysis of the connection between compounds and serves as a useful tool for qualitative predictions.

QSAR study on tetrahydroquinoline analogues as plasmodium protein farnesyltransferase inhibitors: a comparison of rationales of malarial and mammalian enzyme inhibitory activities for selectivity

The quantitative structure-activity relationships of Plasmodium falciparum and Rat protein farnesyltransferase (PFT) inhibitory activities of 6-cyano-1-(3-methyl-3H-imidazoly-4-ylmethyl)-3-substituted-1,2,3,4-tetrahydroquinoline (THQ) analogues are investigated in order to explore the similarities/deviations between the two enzymes for these analogues. The structure space of a ligand (BMS-214662) bound to Rat-PFT (PDB code 1SA5) has been used as the conformational space of the compounds under investigation. The study has been carried out using the combinatorial protocol in multiple linear regression with several 2D- and 3D-descriptors from molecular operating environment (MOE) representing the physicochemical and electronic features of the compounds. The molecular potential energy and partially charged van der Waals surface areas have taken part in the PFT models. They suggested in favor of molecular arrangement with minimum energy and low positively/negatively charged surfaces for optimum Pf-PFT inhibitory activity. Furthermore, less hydrophobic compounds are preferred for the activity. The Rat-PFT inhibitory activity models suggested in favor of more negatively as well as more positively charged surface area descriptors for the better activity. The PLS analysis carried out on the descriptors of the Pf-PFT and Rat-PFT models suggested that among the parameters, the partially charged surface areas in the range -0.20 to -0.15 (PEOE_VSA-3) and -0.30 to -0.25 (PEOE_VSA-5), hydrophobicity (a_hyd, logP(o/w) and SlogP_VSA4), and electronic energy (PM3_Eele) of the molecules hold promise for modulating the Pf-PFT/R-PFT inhibitory activities of the compounds. This suggested the possibility of modulating the Pf-PFT/R-PFT inhibitory activities and bringing about selectivity in the THQ analogues for the malarial parasite enzyme.

Network models in drug discovery and regenerative medicine

Network motifs and modelling paradigms are attracting increasing attention as modelling tools in drug design and development, and in regenerative medicine. There is a gradual but inexorable convergence between these hitherto disparate disciplines. This review summarizes some very recent work in these areas, leading to an understanding of the complementary roles networks play and factors driving this convergence: network paradigms can be excellent ways of modelling and understanding drug molecules and their action, an understanding of the robustness and vulnerabilities of biological targets may improve the efficacy of drug design and discovery, drug design has an increasingly large role to play in directing stem cell properties, stem cell regulatory networks can be modelled in useful ways using network models at a reasonable level of scale, and the network tools of drug design are also very useful for the design of biomaterials used in regenerative medicine.

Search for new antagonist ligands for adenosine receptors from QSAR point of view. How close are we?

In view of the large libraries of nucleoside analogues that are now being handled in organic synthesis, the identification of drug biological activity is advisable prior to synthesis and this can be achieved by employing predictive biological property methods. In this sense, Quantitative Structure-Activity Relationships (QSAR) or docking approaches have emerged as promising tools. Although a large number of in silico approaches have been described in the literature for the prediction of different biological activities, the use of QSAR applications to develop adenosine receptor (AR) antagonists is not common as for the case of the antibiotics and anticancer compounds for instance. The intention of this review is to summarize the present knowledge concerning computational predictions of new molecules as adenosine receptor antagonists.

Protein radial distribution function (P-RDF) and Bayesian-Regularized Genetic Neural Networks for modeling protein conformational stability: Chymotrypsin inhibitor 2 mutants

Development of novel computational approaches for modeling protein properties is a main goal in applied Proteomics. In this work, we reported the extension of the radial distribution function (RDF) scores formalism to proteins for encoding 3D structural information with modeling purposes. Protein-RDF (P-RDF) scores measure spherical distributions on protein 3D structure of 48 amino acids/residues properties selected from the AAindex data base. P-RDF scores were tested for building predictive models of the change of thermal unfolding Gibbs free energy change (DeltaDeltaG) of chymotrypsin inhibitor 2 upon mutations. In this sense, an ensemble of Bayesian-Regularized Genetic Neural Networks (BRGNNs) yielded an optimum nonlinear model for the conformational stability. The ensemble predictor described about 84% and 70% variance of the data in training and test sets, respectively.

Inhibition of farnesyltransferase: a rational approach to treat cancer?

This article presents in brief the development of farnesyltransferase inhibitors (FTIs) and their preclinical and clinical status. In this review the mechanism of action of FTIs is discussed and their selectivity issue towards tumor cells is also addressed. The significant efficacy of FTIs as single or combined agents in preclinical studies stands in contrast with only moderate effects in Clinical Phase II-III studies. This suggests that there is a need to further explore and understand the complex mechanism of action of FTIs and their interaction with cytotoxic agents.

Quantitative structure carcinogenicity relationship for detecting structural alerts in nitroso-compounds

Prevention of environmentally induced cancers is a major health problem of which solutions depend on the rapid and accurate screening of potential chemical hazards. Lately, theoretical approaches such as the one proposed here - Quantitative Structure-Activity Relationship (QSAR) - are increasingly used for assessing the risks of environmental chemicals, since they can markedly reduce costs, avoid animal testing, and speed up policy decisions. This paper reports a QSAR study based on the Topological Substructural Molecular Design (TOPS-MODE) approach, aiming at predicting the rodent carcinogenicity of a set of nitroso-compounds selected from the Carcinogenic Potency Data Base (CPDB). The set comprises nitrosoureas (14 chemicals), N-nitrosamines (18 chemicals) C-nitroso-compounds (1 chemical), nitrosourethane (1 chemical) and nitrosoguanidine (1 chemical), which have been bioassayed in male rat using gavage as the route of administration. Here we are especially concerned in gathering the role of both parameters on the carcinogenic activity of this family of compounds. First, the regression model was derived, upon removal of one identified nitrosamine outlier, and was able to account for more than 84% of the variance in the experimental activity. Second, the TOPS-MODE approach afforded the bond contributions -- expressed as fragment contributions to the carcinogenic activity -- that can be interpreted and provide tools for better understanding the mechanisms of carcinogenesis. Finally, and most importantly, we demonstrate the potentialities of this approach towards the recognition of structural alerts for carcinogenicity predictions.

Application of genetic algorithm-kernel partial least square as a novel nonlinear feature selection method: Activity of carbonic anhydrase II inhibitors

This paper introduces the genetic algorithm-kernel partial least square (GA-KPLS), as a novel nonlinear feature selection method. This technique combines genetic algorithms (GAs) as powerful optimization methods with KPLS as a robust nonlinear statistical method for variable selection. This feature selection method is combined with artificial neural network to develop a nonlinear QSAR model for predicting activities of a series of substituted aromatic sulfonamides as carbonic anhydrase II (CA II) inhibitors. Eight simple one- and two-dimensional descriptors were selected by GA-KPLS and considered as inputs for developing artificial neural networks (ANNs). These parameters represent the role of acceptor-donor pair, hydrogen bonding, hydrosolubility and lipophilicity of the active sites and also the size of the inhibitors on inhibitor-isozyme interaction. The accuracy of 8-4-1 networks was illustrated by validation techniques of leave-one-out (LOO) and leave-multiple-out (LMO) cross-validations and Y-randomization. Superiority of this method (GA-KPLS-ANN) over the linear one (MLR) in a previous work and also the GA-PLS-ANN in which a linear feature selection method has been used indicates that the GA-KPLS approach is a powerful method for the variable selection in nonlinear systems.

Amino acid sequence autocorrelation vectors and bayesian-regularized genetic neural networks for modeling protein conformational stability: Gene V protein mutants

Development of novel computational approaches for modeling protein properties from their primary structure is the main goal in applied proteomics. In this work, we reported the extension of the autocorrelation vector formalism to amino acid sequences for encoding protein structural information with modeling purposes. Amino acid sequence autocorrelation (AASA) vectors were calculated by measuring the autocorrelations at sequence lags ranging from 1 to 15 on the protein primary structure of 48 amino acid/residue properties selected from the AAindex data base. A total of 720 AASA descriptors were tested for building predictive models of the change of thermal unfolding Gibbs free energy change (delta deltaG) of gene V protein upon mutation. In this sense, ensembles of Bayesian-regularized genetic neural networks (BRGNNs) were used for obtaining an optimum nonlinear model for the conformational stability. The ensemble predictor described about 88% and 66% variance of the data in training and test sets respectively. Furthermore, the optimum AASA vector subset not only helped to successfully model unfolding stability but also well distributed wild-type and gene V protein mutants on a stability self-organized map (SOM), when used for unsupervised training of competitive neurons.

Ensembles of Bayesian-regularized genetic neural networks for modeling of acetylcholinesterase inhibition by huprines

Acetylcholinesterase inhibition was modeled for a set of huprines using ensembles of Bayesian-regularized Genetic Neural Networks. In the Bayesian-regularized Genetic Neural Network approach the Bayesian regularization avoids overfitted regressions and the genetic algorithm allows exploring a wide pool of three-dimensional descriptors. The predictive capacity of our selected model was evaluated by averaging multiple validation sets generated as members of neural network ensembles. When 60 members are assembled, the neural network ensemble provides a reliable measure of training and test set R(2)-values of 0.945 and 0.850 respectively. In other respects, the ability of the nonlinear selected genetic algorithm space for differentiate the data were evidenced when total data set was well distributed in a Kohonen self-organizing map. The analysis of the self-organizing map zones allows establishing the main structural features differentiated by our vectorial space.

Quantitative structure–activity relationship studies for the prediction of antifungal activity of N-arylbenzenesulfonamides against Botrytis cinerea

The Botrytis cinerea is one of the most interesting fungal pathogens. It can infect almost every plant and plant part and cause early latent infections which damage the fruit before ripening. The QSAR is an alternative method for the research of new and better fungicides against B. cinerea. This paper describes the results of applying a topological sub-structural molecular design (TOPS-MODE) approach for predicting the antifungal activity of 28 N-arylbenzenesulfonamides. The model described 86.1% of the experimental variance, with a standard deviation of 0.223. Leave-one-out and leave-group-out cross validation was carried out with the aim of evaluating the predictive power of the model. The values of their respective squared correlations coefficients were 0.754 and 0.741. The TOPS-MODE approach was compared with three other predictive models, but none of these could explain more than 72.8% of the variance with the same number of variables. In addition, this approach enabled the assessment of the contribution of different bonds to antifungal activity, thereby making the relationships between structure and biological activity more transparent. It was found that the fungicidal activity of the chemicals analyzed was increased by the presence of a sulfonamide group bonded to two aromatics rings, making this group the most important of the molecule. The majority of the substituents present in the aromatic rings have an electron withdrawing effect and they contribute to a smaller degree than the sulfonamide group to the property under study. The aromatic moiety plays an important role in this activity; its contribution changes with different substituents. Generally, the nitro group has a positive and great contribution to the biological property but when this group is involved in some compounds in ortho effect with the SO2 moiety of the sulfonamide group a lower value of contribution is observed for both groups.

Quantitative Structure?Activity Relationship Modeling of Growth Hormone Secretagogues Agonist Activity of some Tetrahydroisoquinoline 1-Carboxamides

Growth hormone secretagogue agonist activities for a data set of 45 tetrahydroisoquinoline 1-carboxamides were modeled using several kinds of molecular descriptors from dragon software. A linear model with six variables selected from a large pool of two-dimensional descriptors described 80% of cross-validation data variance. Similar results were found for a model obtained from a pool of three-dimensional descriptors. Size and hydrophilicity-related atomic properties such as mass, polarizability, and van der Waals volume were determined to be the most relevant for the differential growth hormone secretagogue agonist activities of the compounds studied. In addition, Artificial Neural Networks were trained using optimum variables from the linear models; however, they were found to overfit the data and resulted in similar or lower predictive power.

Bayesian-regularized genetic neural networks applied to the modeling of non-peptide antagonists for the human luteinizing hormone-releasing hormone receptor

Bayesian-regularized genetic neural networks (BRGNNs) were used to model the binding affinity (IC(50)) for 128 non-peptide antagonists for the human luteinizing hormone-releasing hormone (LHRH) receptor using 2D spatial autocorrelation vectors. As a preliminary step, a linear dependence was established by multiple linear regression (MLR) approach, selecting the relevant descriptors by genetic algorithm (GA) feature selection. The linear model showed to fit the training set (N=102) with R(2)=0.746, meanwhile BRGNN exhibited a higher value of R(2)=0.871. Beyond the improvement of training set fitting, the BRGNN model overcame the linear one by being able to describe 85% of test set (N=26) variance in comparison with 73% the MLR model. Our non-linear QSAR model illustrates the importance of an adequate distribution of atomic properties represented in topological frames and reveals the electronegativities, masses and polarizabilities as the most influencing atomic properties in the structures of the heterocycles under analysis for having an appropriate LHRH antagonistic activity. Furthermore, the ability of the non-linear selected variables for differentiating the data was evidenced when total data set was well distributed in a Kohonen self-organizing map (SOM).

3D-QSAR analysis of antimalarial farnesyltransferase inhibitors based on a 2,5-diaminobenzophenone scaffold

With annual death tolls in the millions and emerging resistance to existing drugs, novel therapies are needed against malaria. Wiesner et al. recently developed a novel class of antimalarials derived from farnesyltransferase inhibitors based on a 2,5-diaminobenzophenone scaffold. The compounds displayed a wide range of activity, including submicromolar, against the multi-drug resistant Plasmodium falciparum strain Dd2. In order to investigate quantitatively the local physicochemical properties involved in the interaction between drug and biotarget, we used the 3D-QSAR methods CoMFA and CoMSIA to study some of the series, including the screened lead compound 2,5-bis-acylaminobenzophenone, 28 cinnamic acid derivatives, 29 N-(3-benzoyl-4-tolylacetylaminophenyl)-3-(5-aryl-2-furyl)acrylic acid amides, and 34 N-(4-substituted-amino-3-benzoylphenyl)-[5-(4-nitrophenyl)-2-furyl]acrylic acid amides. We found that steric, electrostatic, and hydrophobic properties of substituent groups play key roles in the bioactivity of the series of compounds, while hydrogen bonding interactions show no obvious impact. We built several highly predictive 3D-QSAR models, including a CoMSIA one composed of steric, electrostatic, and hydrophobic fields, with r(2)=0.94, q(2)=0.63, and r(pred)(2)=0.63. The results provide insight for optimization of this class of antimalarials for better activity and may prove helpful for further lead optimization.

QSAR studies about cytotoxicity of benzophenazines with dual inhibition toward both topoisomerases I and II: 3D-MoRSE descriptors and statistical considerations about variable selection

Deoxyribonucleic acid (DNA) topoisomerases are involved in diverse cellular processes, such as replication, transcription, recombination, and chromosome segregation. Searching new compounds that inhibit both topoisomerases I and II is very important due to the deficiency of the specific inhibitors to overcome multidrug resistance (MDR). A QSAR study was developed, employing the 3D-MoRSE descriptors and a set of 64 benzophenazines in order to model the inhibition of the topoisomerases I and II, expressed by the cytotoxicity of these compounds (IC(50)) versus drug-resistant human small cell lung carcinoma line cell H69/LX4. A comparison with other approaches such as the Topological, BCUT, Galvez topological charge indexes, 2D autocorrelations, Randić molecular profile, Geometrical, RDF, and WHIM descriptors was carried out. The mathematical models were obtained by means of the multiple regression analysis (MRA) and the variables were selected using the genetic algorithm. The model relative to the 3D-MoRSE descriptors was considered as the best, taking into account its statistical parameters. It was able to describe more than 82.2% of the variance in the experimental activity once the outliers were extracted.

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.

Amino Acid Sequence Autocorrelation Vectors and Ensembles of Bayesian-Regularized Genetic Neural Networks for Prediction of Conformational Stability of Human Lysozyme Mutants

Development of novel computational approaches for modeling protein properties from their primary structure is a main goal in applied proteomics. In this work, we reported the extension of the autocorrelation vector formalism to amino acid sequences for encoding protein structural information with modeling purposes. Amino Acid Sequence Autocorrelation (AASA) vectors were calculated by measuring the autocorrelations at sequence lags ranging from 1 to 15 on the protein primary structure of 48 amino acid/residue properties selected from the AAindex database. A total of 720 AASA descriptors were tested for building predictive models of the thermal unfolding Gibbs free energy change of human lysozyme mutants. In this sense, ensembles of Bayesian-Regularized Genetic Neural Networks (BRGNNs) were used for obtaining an optimum nonlinear model for the conformational stability. The ensemble predictor described about 88% and 68% variance of the data in training and test sets, respectively. Furthermore, the optimum AASA vector subset was shown not only to successfully model unfolding thermal stability but also to distribute wild-type and mutant lysozymes on a stability Self-organized Map (SOM) when used for unsupervised training of competitive neurons.

2D Autocorrelation modeling of the negative inotropic activity of calcium entry blockers using Bayesian-regularized genetic neural networks

Negative inotropic potency of 60 benzothiazepine-like calcium entry blockers (CEBs), Diltiazem analogs, was successfully modeled using Bayesian-regularized genetic neural networks (BRGNNs) and 2D autocorrelation vectors. This approach yielded reliable and robust models whilst by means of a linear genetic algorithm (GA) search routine no multilinear regression model was found describing more than 50% of the training set. On the contrary, the optimum neural network predictor with five inputs described about 84% and 65% variances of 50 randomly selected training and test sets. Autocorrelation vectors in the nonlinear model contained information regarding 2D spatial distributions on the CEB structure of van der Waals volumes, electronegativities, and polarizabilities. However, a sensitivity analysis of the network inputs pointed out to the electronegativity and polarizability 2D topological distributions at substructural fragments of sizes 3 and 4 as the most relevant features governing the nonlinear modeling of the negative inotropic potency.

Genetic neural network modeling of the selective inhibition of the intermediate-conductance Ca2+-activated K+ channel by some triarylmethanes using topological charge indexes descriptors

Selective inhibition of the intermediate-conductance Ca(2+)-activated K(+ )channel (IK (Ca)) by some clotrimazole analogs has been successfully modeled using topological charge indexes (TCI) and genetic neural networks (GNNs). A neural network monitoring scheme evidenced a highly non-linear dependence between the IK (Ca) blocking activity and TCI descriptors. Suitable subsets of descriptors were selected by means of genetic algorithm. Bayesian regularization was implemented in the network training function with the aim of assuring good generalization qualities to the predictors. GNNs were able to yield a reliable predictor that explained about 97% data variance with good predictive ability. On the contrary, the best multivariate linear equation with descriptors selected by linear genetic search, only explained about 60%. In spite of when using the descriptors from the linear equations to train neural networks yielded higher fitted models, such networks were very unstable and had relative low predictive ability. However, the best GNN BRANN 2 had a Q ( 2 ) of LOO of cross-validation equal to 0.901 and at the same time exhibited outstanding stability when calculating 80 randomly constructed training/test sets partitions. Our model suggested that structural fragments of size three and seven have relevant influence on the inhibitory potency of the studied IK (Ca) channel blockers. Furthermore, inhibitors were well distributed regarding its activity levels in a Kohonen self-organizing map (KSOM) built using the inputs of the best neural network predictor.