Nonlinear Quantitative Structure-activity Relationship Research Articles

The discussion of descriptors for the QSAR model and molecular dynamics simulation of benzimidazole derivatives as corrosion inhibitors

The corrosion inhibition performances of 20 protonated benzimidazole derivatives were studied using theoretical methods. Nuclear Independent Chemical Shift (NICS), the measurement of aromaticity, demonstrated good correlation with inhibition efficiencies and was used as a descriptor. Binding energies were calculated on the basis of molecular dynamics simulations using a realistic corrosive environment. Some improved descriptors correlate well with experimental inhibition efficiencies. A reliable nonlinear quantitative structure–activity relationship model was constructed by a support vector machine approach. The correlation coefficient and root-mean-square error were 0.96 and 6.79%, respectively. Additionally, six new benzimidazole molecules were designed, and their inhibition efficiencies were predicted.

Nonlinear QSAR modeling for predicting cytotoxicity of ionic liquids in leukemia rat cell line: an aid to green chemicals designing.

Safety assessment and designing of safer ionic liquids (ILs) are among the priorities of the chemists and toxicologists today. Computational approaches have been considered as appropriate methods for prior safety assessment of chemicals and tools to aid in structural designing. The present study is an attempt to investigate the chemical attributes of a wide variety of ILs towards their cytotoxicity in leukemia rat cell line IPC-81 through the development of nonlinear quantitative structure-activity relationship (QSAR) models in the light of the OECD principles for QSAR development. Here, the cascade correlation network (CCN), probabilistic neural network (PNN), and generalized regression neural networks (GRNN) QSAR models were established for the discrimination of ILs in four categories of cytotoxicity and their end-point prediction using few simple descriptors. The diversity and nonlinearity of the considered dataset were evaluated through computing the Euclidean distance and Brock-Dechert-Scheinkman statistics. The constructed QSAR models were validated with external test data. The predictive power of these models was established through a variety of stringent parameters recommended in QSAR literature. The classification QSARs rendered the accuracy of >86%, and the regression models yielded correlation (R(2)) of >0.90 in test data. The developed QSAR models exhibited high statistical confidence and identified the structural elements of the ILs responsible for their cytotoxicity and, hence, could be useful tools in structural designing of safer and green ILs.

Nonlinear QSAR models with high-dimensional descriptor selection and SVR improve toxicity prediction and evaluation of phenols on Photobacterium phosphoreum

Assessment of the risk of chemicals is an important task in the environmental protection. In this paper, we developed quantitative structure–activity relationship (QSAR) methods to evaluate the toxicity of phenol to Photobacterium phosphoreum, which is an important indicator for water quality. We first built support vector regression (SVR) model using three descriptors, and the SVR model (t=2) had the highest external prediction ability (MSEext=0.068, Qext2=0.682), about 40% higher than literature model's. Second, to identify more effective descriptors, we applied in-house methods to select descriptors with clear meanings from 2835 descriptors calculated by the PCLIENT and used them to construct the SVR models. Our results showed that our twenty new QSAR models significantly increased the standard regression coefficient on test set (MSEext values ranged from 0.003 to 0.063 and Qext2 values ranged from 0.708 to 0.985). The Y random response permutation test and different splits of training/test datasets also supported the excellent predictive power of the best SVR model. We further evaluated the regression significance of our SVR model and the importance of each single descriptor of the model according to the interpretability analysis. Our work provided useful theoretical understanding of the toxicity of phenol analogues.

Molecular structural characteristics important in drug-HSA binding.

A non-linear quantitative structure activity relationship (QSAR) model based on 350 drug molecules was developed as a predictive tool for drug protein binding, by correlating experimentally measured protein binding values with ten calculated molecular descriptors using a radial basis function (RBF) neural network. The developed model has a statistically significant overall correlation value (r > 0.73), a high efficiency ratio (0.986), and a good predictive squared correlation coefficient (q(2)) of 0.532, which is regarded as producing a robust and high quality QSAR model. The developed model may be used for the screening of drug candidate molecules that have high protein binding data, filtering out compounds that are unlikely to be protein bound, and may assist in the dose adjustment for drugs that are highly protein bound. The advantage of using such a model is that the percentage of a potential drug candidate that is protein bound (PB (%)) can be simply predicted from its molecular structure.

QSAR Study of the Inhibitors of the Acetyl-CoA Carboxylase 1 and 2 using Bayesian Regularized Genetic Neural Networks: A Comparative Study

Linear and non-linear quantitative structure-activity relationship (QSAR) models were presented for modeling and predicting anti-diabetic activities of a set of inhibitors of acetyl-CoA carboxylase 1 and 2 (ACC1 and ACC2). Different algorithms were utilized to choose the best variables among large numbers of descriptors and then these selected descriptors were used for non-linear (artificial neural network) and linear (multiple linear regression) modeling. The variable selection methods were consisted of stepwise-multiple linear regression (stepwise-MLR), successive projections algorithm (SPA), genetic algorithm-multiple linear regression (GA-MLR) and Bayesian regularized genetic neural networks (BRGNNs). The prediction abilities of the models were evaluated by Monte Carlo cross validation (MCCV) in variable selection and modeling steps. The results revealed that the best variables for describing the inhibition mechanism of ACC were among topological charge indices, radial distribution function, geometrical, and autocorrelation descriptors. The statistical parameters of R2 and root mean square error (RMSE) indicated that BRGNNs is superior for modeling the inhibitory activity of ACC modulators over the other methods. The sensitivity analysis together with the frequency of the selected molecular descriptors in this work can establish an understanding to the mechanism of ACC inhibitory activity of small molecules.

Quantitative prediction of lipase reaction in ionic liquids by QSAR using COSMO-RS molecular descriptors

Linear and nonlinear quantitative structure–activity relationship (QSAR) models based on COSMO-RS screening charge density distribution (σ-profile) were developed to predict the activity and enantioselectivity of lipase from Candida antarctica lipase B (Novozym 435) and Rhizomucor miehei (Lipozyme RM-IM) in the kinetic resolution of (R,S)-1-phenylethanol with vinyl acetate in ionic liquids. The σ-profile distribution areas of ionic liquids (Sσ-profile) were used as numerical molecular descriptors to establish the QSAR models. The models were developed based on experimental data of seventeen ionic liquids (training set) and their predictability were validated with another experimental data set of five ionic liquids (testing set). The results showed that COSMO-RS σ-profile of ionic liquids could be used as excellent independent variable for prediction of enzymatic reactions in ionic liquids. The nonlinear QSAR models based on artificial neural networks methods showed better predictive ability (R2>0.91) than linear QSAR models based on multiple linear regression methods.

Calculation of Hildebrand solubility parameters of some polymers using QSPR methods based on LS-SVM technique and theoretical molecular descriptors

In this work, some chemometrics methods are applied for the modeling and prediction of the Hildebrand solubility parameter of some polymers. A genetic algorithm (GA) method is designed for the selection of variables to construct two models using the multiple linear regression (MLR) and least square-support vector machine (LS-SVM) methods in order to predict the Hildebrand solubility parameter. The MLR method is used to build a linear relationship between the molecular descriptors and the Hildebrand solubility parameter for these compounds. Then the LS-SVM method is utilized to construct the non-linear quantitative structure-activity relationship (QSAR) models. The results obtained using the LS-SVM method are then compared with those obtained for the MLR method; it was revealed that the LS-SVM model was much better than the MLR one. The root-mean-square errors of the training set and the test set for the LS-SVM model were 0.2912 and 0.2427, and the correlation coefficients were 0.9662 and 0.9518, respectively. This paper provides a new and effective method for predicting the Hildebrand solubility parameter for some polymers, and also reveals that the LS-SVM method can be used as a powerful chemometrics tool for the quantitative structure-property relationship (QSPR) studies.

Quantitative structure–activity relationship model for amino acids as corrosion inhibitors based on the support vector machine and molecular design

The inhibition performance of nineteen amino acids was studied by theoretical methods. The affection of acidic solution and protonation of inhibitor were considered in molecular dynamics simulation and the results indicated that the protonated amino-group was not adsorbed on Fe (110) surface. Additionally, a nonlinear quantitative structure–activity relationship (QSAR) model was built by the support vector machine. The correlation coefficient was 0.97 and the root mean square error, the differences between predicted and experimental inhibition efficiencies (%), was 1.48. Furthermore, five new amino acids were theoretically designed and their inhibition efficiencies were predicted by the built QSAR model.

Determination of Optimum Values of Descriptors to Set Filters for Synthetic Tri-Pyrrole Derivatives (Prodiginines) Against Multi Drug Resistant Strain of <i>Plasmodium Falciparum</i>

In the present study, we have carried out extensive non-linear Quantitative-Structure Activity Relationship (QSAR) analysis to correlate in vitro anti-malarial activity against multi drug resistant strain of Plasmodium falciparum. Forty-three synthetic prodiginines with different structural features were used for their potential antimalarial activity. Linear, bilinear, biexponential and parabolic equations were developed. These equations were compared to determine the optimum values of descriptors for very useful and easily interpretable descriptors. The optimum values of these descriptors could be helpful in finding and optimizing a good lead compound. Obtained correlations reveal that various factors like lipophilicity, molecular weight and number of bonds have non-linear relation with the anti-malarial activity.

Prediction on the Inhibition Ratio of Pyrrolidine Derivatives on Matrix Metalloproteinase Based on Gene Expression Programming

Quantitative structure-activity relationships (QSAR) were developed to predict the inhibition ratio of pyrrolidine derivatives on matrix metalloproteinase via heuristic method (HM) and gene expression programming (GEP). The descriptors of 33 pyrrolidine derivatives were calculated by the software CODESSA, which can calculate quantum chemical, topological, geometrical, constitutional, and electrostatic descriptors. HM was also used for the preselection of 5 appropriate molecular descriptors. Linear and nonlinear QSAR models were developed based on the HM and GEP separately and two prediction models lead to a good correlation coefficient (R 2) of 0.93 and 0.94. The two QSAR models are useful in predicting the inhibition ratio of pyrrolidine derivatives on matrix metalloproteinase during the discovery of new anticancer drugs and providing theory information for studying the new drugs.

A quantitative structure–activity relationship study of anti-HIV activity of substituted HEPT using nonlinear models

We performed studies on extended series of 79 HEPT ligands (1-[(2-hydroxyethoxy)methyl]-6-(phenylthio)thymine), inhibitors of HIV reverse-transcriptase with anti-HIV biological activity, using quantitative structure–activity relationship (QSAR) methods that imply analysis of correlations and representation of models. A suitable set of molecular descriptors was calculated, and the genetic algorithm was employed to select those descriptors which resulted in the best-fit models. The kernel partial least square and Levenberg–Marquardt artificial neural network were utilized to construct the nonlinear QSAR models. The proposed methods will be of great significance in this research, and would be expected to apply to other similar research fields.

Overlapping structure features selection in linear and non-linear QSAR

Multiple linear regressions (MLR) and support vector machine (SVM) supervised linear and non-linear quantitative structure–activity relationship (QSAR) models were developed for a dataset of (81) N–N-disubstituted trifluoro-3-amino-2-propanol derivatives. QSAR dataset was divided into training set (64) and tests (17) to facilitate external validation. QSAR models derived from MLR and SVM yielded appreciable internal and external predictability. Though SVM models were found statistically fit, MLR models attained more effective and consistent predictability of training and test set. It is important to mention that molecular descriptors (structural information) selected in linear and non-linear QSAR models belong to same categories and code for same structural properties. These different descriptors coding for same structural properties are identified and discussed as overlapping structure features in linear and non-linear QSAR models. Molecular descriptors deduced in relation with biological responses are EEig09d, R3u+, P1P1C6, EPS0 and nCb- in MLR aided linear QSAR models and EEig07d, R6u+, P2C6, G1p and Mor12m in SVM aided non-linear. QSAR models are found reliable for further optimization of N–N-disubstituted trifluoro-3-amino-2-propanol CETP inhibitory activity. Concluding remarks include selection of overlapping structure features in linear (MLR) and non-linear (SVM) models and utility of statistical approaches in QSAR. These overlapping features may reveal underlying structural properties which convert a linear relationship to non-linear and better understandings of bio-chemical aspects of QSAR models to medicinal chemists.

ANN-QSAR Model for Virtual Screening of Androstenedione C-Skeleton Containing Phytomolecules and Analogues for Cytotoxic Activity Against Human Breast Cancer Cell Line MCF-7

The present study deals with the development of an artificial neural network based quantitative structure activity relationship (QSAR) model for virtual screening of active compounds which contain androstenedione carbonskeleton or their similar skeleton at the core. An empirical data modeling (with fitted data mapping) has been performed on the basis of bioassay record for human breast cancer cell line MCF7. The whole experimental data set was considered as test set. Standard feed-forward back-propagation neural network technique was applied to build the model. Leave-One- Out (LOO) cross-validation was performed to evaluate the performance of the model. The mapped model became the basis for selection best mapped compounds followed by development of Pharmacophore specific secondary QSAR model. In the present study, two best mapped molecules '4beta-hydroxy Withanolide-E' and '7, 8-Dehydrocalotropin' were used for development of the secondary QSAR model. These secondary-QSAR models were resulted with R2 LOOCV value 0.9845 and 0.9666 respectively. Docking studies, in silico phamacokinetic and toxicity analysis was also done for selected compounds. The screened compounds CID_73621, CID_16757497, CID_301751, CID_390666 and CID_46830222 were found with promising binding affinity value with aromatase with reference to the co-crystallized control compound androstenedione. Due to excellent extent of variance coverage in ANN based QSAR map model, it can be used as a robust non-linear QSAR model for androstenedione carbon-skeleton containing molecules and the protocol can be used to derive secondary QSAR models for other compounds set.

Quantum Chemical QSAR Models to Distinguish Between Inhibitory Activities of Sulfonamides Against Human Carbonic Anhydrases I and II and Bovine IV Isozymes

Linear and nonlinear quantitative structure activity relationship models for predicting the inhibitory activities of sulfonamides toward different carbonic anhydrase isozymes were developed based on multilinear regression, principal component-artificial neural network and correlation ranking-principal component analysis, to identify a set of structurally based numerical descriptors. Multilinear regression was used to build linear quantitative structure activity relationship models using 53 compounds with their quantum chemical descriptors. For each type of isozyme, separate quantitative structure activity relationship models were obtained. It was found that the hydration energy plays a significant role in the binding of ligands to the CAI isozyme, whereas the presence of five-membered ring was detected as a major factor for the binding to the CAII isozyme. It was also found that the softness exhibited significant effect on the binding to CAIV isozyme. Principal component-artificial neural network and correlation ranking-principal component analysis analyses provide models with better prediction capability for the three types of the carbonic anhydrase isozyme inhibitory activity than those obtained by multilinear regression analysis. The best models, with improved prediction capability, were obtained for the hCAII isozyme activity. Models predictivity was evaluated by cross-validation, using an external test set and chance correlation test.

Application of an expert system based on Genetic Algorithm–Adaptive Neuro-Fuzzy Inference System (GA–ANFIS) in QSAR of cathepsin K inhibitors

One strategy to potentially improve the success of drug design and development is to use chemometrics methods early in the process to propose molecules and scaffolds with ideal binding and to clarify physicochemical features influencing in their activity. Adaptive Neuro-Fuzzy Interference System (ANFIS) was used to construct the nonlinear quantitative structure–activity relationship (QSAR) model. The Genetic Algorithm (GA) was used to select descriptors which are responsible for the cathepsin K inhibitory activity of studied compounds. ANFIS regression is a nonlinear regression technique developed to relate many regressors to one or several response variables. The accuracy of the generated QSAR model (R2=0.916) is described using various evaluation techniques, such as leave-one-out procedure (RLOO2=0.875) and validation through an external test set (Rpred2=0.932).

Linear and nonlinear quantitative structure–activity relationship modeling of the HIV-1 reverse transcriptase inhibiting activities of thiocarbamates

For a series of thiocarbamates, non-nucleoside HIV-1 reverse transcriptase inhibitors, few descriptors have been selected from a large pool of theoretical molecular descriptors by means of the ant colony optimization (ACO) feature selection method. The selected descriptors were correlated with the bioactivities of the molecules using the well known multiple linear regression (MLR) and partial least squares (PLS) regression techniques, and, to account for nonlinearity, also PLS coupled to radial basis function (RBF) on the one hand and radial basis function neural network (RBFNN) on the other. In this case study, the RBF/PLS results were better than those from the other modeling techniques applied. The prediction ability of the ACO/RBF/PLS-based quantitative structure–activity relationship (QSAR) model was found to be significantly superior to comparative molecular field analysis (CoMFA) and comparative molecular similarity index analysis (CoMSIA) models previously established for this series of compounds. It was also demonstrated that RBF as a nonlinear approach is useful in deriving simple and predictive QSAR models, without the need to recourse to expeditious 3D methodologies.

A quantitative structure–activity relationship study on HIV-1 integrase inhibitors using genetic algorithm, artificial neural networks and different statistical methods

In this work, quantitative structure–activity relationship (QSAR) study has been done on tricyclic phthalimide analogues acting as HIV-1 integrase inhibitors. Forty compounds were used in this study. Genetic algorithm (GA), artificial neural network (ANN) and multiple linear regressions (MLR) were utilized to construct the non-linear and linear QSAR models. It revealed that the GA–ANN model was much better than other models. For this purpose, ab initio geometry optimization performed at B3LYP level with a known basis set 6–31G (d). Hyperchem, ChemOffice and Gaussian 98W softwares were used for geometry optimization of the molecules and calculation of the quantum chemical descriptors. To include some of the correlation energy, the calculation was done with the density functional theory (DFT) with the same basis set and Becke’s three parameter hybrid functional using the LYP correlation functional (B3LYP/6–31G (d)). For the calculations in solution phase, the polarized continuum model (PCM) was used and also included optimizations at gas-phase B3LYP/6–31G (d) level for comparison. In the aqueous phase, the root–mean–square errors of the training set and the test set for GA–ANN model using jack–knife method, were 0.1409, 0.1804, respectively. In the gas phase, the root–mean–square errors of the training set and the test set for GA–ANN model were 0.1408, 0.3103, respectively. Also, the R2 values in the aqueous and the gas phase were obtained as 0.91, 0.82, respectively.

An accurate nonlinear QSAR model for the antitumor activities of chloroethylnitrosoureas using neural networks

The quantitative structure–activity relationship (QSAR) studies are investigated in a series of chloroethylnitrosoureas (CENUs) acting as alkylating agents of tumors by neural networks (NNs). The QSAR model is described inaccurately by the traditional multiple linear regression (MLR) model for the substitution of CENUs at N-3, whose characteristics play key roles in the biological activity. A nonlinear QSAR study is undertaken by a three-layered NN model, using molecular descriptors that are known to be responsible for the antitumor activity to optimize the input variables of the MLR model. The results demonstrate that NN models present the relationship between antitumor activity and molecular descriptors clearly, and they yield predictions in excellent agreement with the experiment's obtained values ( R 2 = 0.983). The R 2 value is 0.983 for the 5-8-1 NN model, compared with 0.506 for the MLR model, and the nonlinear model is able to account for 98.3% of the variance of antitumor activities.

Prediction of the binding affinities of adenosine A2A receptor antagonists based on the heuristic method and support vector machine

Support vector machine (SVM) was used to develop a nonlinear quantitative structure–activity relationship (QSAR) model for the prediction of the activities of the adenosine A2A receptor antagonists. Six molecular descriptors selected by the heuristic method (HM) in CODESSA were used as inputs for SVM. The results obtained by SVM were compared with those obtained by HM. The mean squared errors (MSEs) for the training set given by HM and SVM are 0.08 and 0.05, respectively, which shows the performance of SVM model is better than that of the HM model.

QSAR prediction of D 2 receptor antagonistic activity of 6-methoxy benzamides

Quantitative structure–activity relationship (QSAR) method was used to predict the pIC 50 value of 58 derivatives of 6-methoxy benzamides in this work. The artificial neural network (ANN) and multiple linear regressions (MLR) were used to construct the non-linear and linear QSAR models, respectively. The standard errors in the prediction of pIC 50 for training, internal and external test sets, are; 0.280, 0.446 and 0.382 by MLR model and are; 0.175, 0.326 and 0.296 by ANN model, respectively. Also these models were further examined by cross-validation methods which produce the statistics of Q 2 = 0.8340 and SPRESS = 0.322 for MLR model and Q 2 = 0.8055 and SPRESS = 0.219 for ANN model.