Genetic Algorithm-multiple Linear Regression Research Articles

Toward molecular modeling of thiophene distribution between the ionic liquid and hydrocarbon phases: Effect of hydrocarbon structure

In the present study, Quantitative Structure-Properties Relationship (QSPR) methodology has been employed to propose predictive and descriptive models for the prediction of thiophene distribution between the ionic liquid (IL) and hydrocarbon-rich phases in ternary systems containing IL, thiophene, and hydrocarbon solvent. By comprehensive literature survey, three different datasets (the first dataset:[C2MIM][EtSO4] (1) – thiophene (2) – six different hydrocarbon solvents (3), the second dataset: [C8MIM][BF4] (1) – thiophene (2) – eight different hydrocarbon solvents (3), and the third dataset: [C8MIM][NTF2] (1) – thiophene (2) – eight different hydrocarbon solvents(3)) with total 179 data points were found for model development. After categorizing the data points to the train and test data in each data set, QSPR models were constructed for each data set using genetic algorithm multiple linear regression (GA-MLR). Acceptable values of the statistical parameters such as root mean square error (RMSE), absolute relative deviation (ARD), and average absolute relative deviation (AARD) confirmed the validity of the developed model for each data set. The validity of models was also confirmed by external validation. It was found that the polarity number (Pol) of hydrocarbon solvent, as a topological descriptor which relates to the steric properties of molecular structures, has a remarkable effect on the thiophene distribution between the IL and hydrocarbon-rich phases.

Developing quantitative structure–retention relationship model to prediction of retention factors of some alkyl-benzenes in nano-LC

The present study intends to develop the quantitative structure–retention relationship (QSRR) models to predict the retention factor of some alkyl-benzenes on micro-dispersed sintered nano-diamond (MSND) and silica-gel stationary phases as new and common stationary phase, respectively, in normal-phase HPLC. Genetic algorithm–multiple linear regression (GA–MLR) method employed for implementation of QSRR models. The square of correlation coefficient (R2) was 0.997 and 0.961, and the SE was 1.06 and 1.93, respectively, for the training and test sets of GA–MLR model on MSND stationary phase. In addition, the R2 was 0.994 and 0.984, and the SE was 0.01 for both the training and test sets of GA–MLR model on silica-gel stationary phase. The statistical parameters and the result of validation tests of these models confirm the fitness, robustness, and predictability of developed QSRR models. The mean effect analysis on the best models introduced the polarizability as the most significant factor that effects on the retention factor of solutes on both studied stationary phases. This similarity confirms the suggestion of MSND as a common stationary phase for normal-phase HPLC. The developed models enable to predict the retention factor of other alkyl-benzenes on both MSND and silica-gel stationary phases on their applicability domain.

Prediction of the sorption coefficient for the adsorption of PAHs on MWCNT based on hybrid QSPR-molecular docking approach

In this study, quantitative structure–property relationship (QSPR) methodology employed for modeling of the sorption coefficient (log KCNT) of 13 polycyclic aromatic hydrocarbons (PAHs) on multiwall carbon nanotube (MWCNT) adsorbent. A molecular docking simulation used to present a reliable and accurate QSPR model with defining the distance and best orientation of PAHs structures on nano-adsorbent. A genetic algorithm-multiple linear regression method was employed for implementation of QSPR model. In this model, the square of correlation coefficients (R2) was 0.945 and 0.890, and the root mean square errors (RMSE) were 0.08 and 0.18 for the training and test sets, respectively. Also, inspection to selected descriptors indicates the electrostatic and steric parameters of PAHs are the predominant factors responsible on the log KCNT values. These results can be used for prediction of sorption coefficient of other PAHs by MWCNT and modify the surface of the adsorbent for improving the log KCNT.

Quantitative Prediction of Thiazole Derivatives as Potent Xanthine Oxidase Inhibitors

AbstractIn humans, xanthine oxidase (XO) is a critical rate‐limiting enzyme in biosynthesis of uric acid. Moreover, XO is the most promising target to control uric acid levels and the treat of hyperuricemia and gout. However, XO inhibitors can effectively treat gout through the inhibition of urate synthesis, and by impairing the conversion of hypoxanthine and xanthine to uric acid. In this paper, four different quantitative structure‐activity relationship (QSAR) models of 80 thiazole derivatives were constructed to comprehend chemical‐biological interactions and predict their bioactivities using GA‐MLR (Genetic Algorithm‐Multiple Linear Regression), HQSAR (Hologram Quantitative Structure Activity Relationship), Topomer CoMFA (Comparative Molecular Field Analysis) and CoMSIA (Comparative Molecular Similarity Indices Analysis) methods. Furthermore, R2 and Q2 of the obtained GA‐MLR, HQSAR, Topomer CoMFA and CoMSIA models are 0.956 and 0.911, 0.932 and 0.876, 0.946 and 0.917, 0.964 and 0.877, respectively. In addition, the external predictive values of the GA‐MLR, HQSAR, Topomer CoMFA and CoMSIA models are 0.963, 0.936, 0.973 and 0.934, respectively. Therefore, all QSAR models exhibited good prediction performances, which can be used to quantitatively evaluate bioactivity and screen new XO inhibitors. Moreover, topological charge index, atomic electronegativity and polarizability, atomic van der Waals volumes and hydrophobic van der Waals surface area are very relevant to bioactivity of thiazole derivatives.

Activity and toxicity modelling of some NCI selected compounds against leukemia P388ADR cell line using genetic algorithm-multiple linear regressions

Cancer-causing nature is one of the toxicological endpoints bringing about the most elevated concern. Likewise, the standard bioassays in rodents used to survey the cancer-mitigating capability of chemicals and medications are expensive and require the sacrifice of animals. Thus, we have endeavored the development of a worldwide QSAR model utilizing an information set of 85 compounds, including drugs for their anti-leukemia potential. Considering expansive number of information focuses with different structural elements utilized for model development (ntraining = 68) and model validation (ntest = 17), the model developed in this study has an encouraging statistical quality (leave-one-out Q2 = 0.833, R2pred = 0.716) for pLC50 and (leave-one-out Q2 = 0.744, R2pred = 0.614) for pGI50. Our developed model suggests that the absence of methanal fragments, low dipole moment and presence of some 2D autocorrelated molecular descriptors reduces the carcinogenicity. Branching, size and shape are found to be crucial factors for drug-mitigating carcinogenicity.

Effect of dissolved organic matter on pre-equilibrium passive sampling: A predictive QSAR modeling study

Pre-equilibrium passive sampling is a simple and promising technique for studying sampling kinetics, which is crucial to determine the distribution, transfer and fate of hydrophobic organic compounds (HOCs) in environmental water and organisms. Environmental water samples contain complex matrices that complicate the traditional calibration process for obtaining the accurate rate constants. This study proposed a QSAR model to predict the sampling rate constants of HOCs (polycyclic aromatic hydrocarbons (PAHs), polychlorinated biphenyls (PCBs) and pesticides) in aqueous systems containing complex matrices. A homemade flow-through system was established to simulate an actual aqueous environment containing dissolved organic matter (DOM) i.e. humic acid (HA) and (2-Hydroxypropyl)-β-cyclodextrin (β-HPCD)), and to obtain the experimental rate constants. Then, a quantitative structure-activity relationship (QSAR) model using Genetic Algorithm-Multiple Linear Regression (GA-MLR) was found to correlate the experimental rate constants to the system state including physicochemical parameters of the HOCs and DOM which were calculated and selected as descriptors by Density Functional Theory (DFT) and Chem 3D. The experimental results showed that the rate constants significantly increased as the concentration of DOM increased, and the enhancement factors of 70-fold and 34-fold were observed for the HOCs in HA and β-HPCD, respectively. The established QSAR model was validated as credible (RAdj.2=0.862) and predictable (Q2=0.835) in estimating the rate constants of HOCs for complex aqueous sampling, and a probable mechanism was developed by comparison to the reported theoretical study. Main finding of the workThe present study established a QSAR model of passive sampling rate constants and calibrated the effect of DOM on the sampling kinetics.

QSAR and Structure-Based Docking Studies of Aryl Pyrido[2,3-d]pyrimidin-7(8H)-ones

The target of the present study has been to carry out computer-aided anticancer drug design utilizing genetic algorithm-multiple linear regression (GA-MLR) based quantitative structure activity relationship (QSAR) of fibroblast growth factor (FGFr) inhibition of pyrido[2,3-d]pyrimidine-7(8H)-one compounds utilizing different classes of computed structural descriptors. A QSAR model was developed utilizing a combination of constitutional, functional group, geometrical and atom-centered fragment indices by multiple linear regression method and the model validation was performed by searching the predictability of the QSAR models. After outlier analyses through applicability domain, the model validation results were improved. In this connection, molecular docking studies were performed to predict the mode of binding and important structural features necessary for producing biological activities. This attempt could be helpful for further modeling of potent less toxic anticancer chemotherapeutics in these congeners.

A Simple, Robust and Efficient Computational Method for n-Octanol/Water Partition Coefficients of Substituted Aromatic Drugs

In this paper, multiple linear regression (MLR) was used to build quantitative structure property relationship (QSPR) of n-octanol-water partition coefficient (logPo/w) of 195 substituted aromatic drugs. The molecular descriptors were calculated for each compound by the VLifeMDS. By applying genetic algorithm/multiple linear regressions (GA/MLR) the most relevant descriptors were selected to build a QSPR model. The robustness of the model was characterized by the statistical validation and applicability domain (AD). The prediction results from MLR are in good agreement with the experimental values. The R2 and Q2LOO for MLR are 0.9433, 0.9341. The AD of the model was analyzed based on the Williams plot. The effects of different selected descriptors are described.

Application of GA-MLR for QSAR Modeling of the Arylthioindole Class of Tubulin Polymerization Inhibitors as Anticancer Agents.

Microtubules are dynamic filamentous cytoskeletal proteins which have used widely in cancer chemotherapy. Generally, the action of these compounds depends on binding to the tubulin proteins which are α, β -heterodimers that form the core of the microtubules. Arylthioindoles (ATIs) inhibit tubulin polymerization by binding to the colchicine site, inhibiting the binding of colchicine to tubulin. QSAR modeling play an important role in modern medicinal chemistry, presenting a unique potential for transforming the early phases of drug research, in terms of time and money savings. In this study we are intending to achieve some useful information about the structural properties of mentioned ATIs using the QSAR modeling method. In this research, the QSAR modeling has been employed to evaluate the efficacy of ATIs derivatives in the inhibition of tubulin polymerization. The best multivariate linear model for each training and test data subset calculated using both genetic algorithm-multiple linear regressions (GA-MLR) and stepwise-multiple linear regressions (S-MLR) methods. The best RS trial set has been selected by comparing the two different QSAR modeling results in all train and test subsets. Finally, the S-MLR and GA-MLR results were compared for finding the best random selection (RS) subset. The molecular structures and experimental activity values for inhibition of tubulin polymerization obtained from the literature. Here, using Dragon package over 1185 molecular descriptors such as RDF, GETAWAY, WHIM, 3D-MoRSE descriptors, and functional group descriptors derived for proper characterizing the arylthioindole derivatives structures. These molecular descriptors reduced to 437 one by eliminating the constant variables, collinear descriptors and the variables having low correlation with response. In fact in order to obtain the best RS subsets in the mentioned method, the random samplings of the training subset (80% of data) were carried out 20 times and the remaining molecules (20% of data) considered as external validation set. The QSAR models were constructed using stepwise-MLR and GA-MLR. In order to select important variables the GA-MLR and S-MLR methods applied on the training subsets after data splitting. The best MLR models (models with high fitness function values) with four, five and six variables built to obtain the best QSAR model. The best MLR model had four parameters in both GA-MLR and S-MLR methods. The best significant relationships, using comparison of Q2 of models, for the IC50 values of tubulin assembly in the models obtained in S-MLR and GA-MLR methods are presented for all of the random sets and SOM set. The result of external validation indicates that in the study of inhibition of tubulin polymerization, the Q2test values are 0.7242 and 0.3215 for GA-MLR and S-MLR methods respectively. Considering the results which obtained in both methods it can be concluded that in variable selecting the GA-MLR method is more powerful than the S-MLR method.

The “double cross-validation” software tool for MLR QSAR model development

Quantitative structure–activity relationship (QSAR) modeling is a widely used computational technique applied in various fields including rational drug design, toxicity and property prediction of chemicals and pharmaceuticals, environmental risk assessment and fate modeling. External validation is generally considered as the gold standard in evaluating the model predictivity performance, at least to a group of QSAR practitioners. External validation is commonly performed by employing the hold-out method, where the original dataset is divided into training and test sets; the training set is employed for model building and model selection, while the test set is solely used in model assessment. However, since the composition of the training set remains the same in this method, it is not certain that the resultant model is optimal as there may be a bias in descriptor selection. This problem is more evident for the multiple linear regression (MLR) models than more robust and generalized partial least squares (PLS) and principal component regression (PCR) models. Thus, employing double cross-validation technique could be a better choice, in which the training set is further divided into ‘n’ calibration and validation sets resulting in diverse compositions. In the present work, we have developed an open access “Double Cross-Validation (DCV)” software tool which can be used to perform multiple linear regression (MLR) model development by employing the double cross-validation technique. Two variable selection methods, namely, stepwise MLR (S-MLR) and genetic algorithm MLR (GA-MLR) are incorporated in this tool and optionally, this tool also performs a data-pretreatment prior to the application of double cross-validation. Also, we have performed a study using the “Double Cross-Validation” tool on three different datasets in order to find out which technique among the hold-out and double cross-validation performs better in the selection of an optimal model in terms of model predictive performance checked on the test set. The performance of the tool in generating predictive PLS models is also compared. The “Double Cross-Validation” (version 2.0) tool is freely available to download from the sites http://teqip.jdvu.ac.in/QSAR_Tools/ and http://dtclab.webs.com/software-tools.

한강수질 평가를 위한 COD (화학적 산소 요구량) 모델 평가

Objectives: The objective of this study was to build COD regression models for the Han River and evaluate water quality. Methods: Water quality data sets for the dry season (as of January) during a four-year period (2012-2015) were collected from the database of the Han River automatic water quality monitoring stations. Statistical techniques, including combined genetic algorithm-multiple linear regression (GA-MLR) were used to build five-descriptor COD models. Multivariate statistical techniques such as principal component analysis (PCA) and cluster analysis (CA) are useful tools for extracting meaningful information. Results: The r² of the best COD models provided significant high values (> 0.8) between 2012 and 2015. Total organic carbon (TOC) was a surrogate indicator for COD (as COD/TOC) with high reliability (r²=0.63 in 2012, r²=0.75 for 2013, r²=0.79 for 2014 and r²=0.85 for 2015). The ratios of COD/TOC were calculated as 2.08 in 2012, 1.79 in 2013, 1.52 and 1.45 in 2015, indicating that biodegradability in the water body of the Han River was being sustained, thereby further improving water quality. The BOD/COD ratio supported these findings. The cluster analysis revealed higher annual levels of microorganisms and phosphorous at stations along the Hangang-Seoul and Hantangang areas. Nevertheless, the overall water quality over the last four years showed an observable trend toward continuous improvement. These findings also suggest that non-point pollution control strategies should consider the influence of upstreams and downstreams to protect water quality in the Han River. Conclusion: This data analysis procedure provided an efficient and comprehensive tool to interpret complex water quality data matrices. Results from a trend analysis provided much important information about sources and parameters for Han River water quality management.

Prediction of CO2 loading of amines in carbon capture process using membrane contactors: A molecular modeling

Separation of carbon dioxide from gas streams with respect to CO2 negative environmental effects is one of the most significant parts of gas separation processes. For this purpose, using membrane contactors is a promising technology and finding high performance solvents is crucial to development of this technology. Aqueous solutions of amines are the most employed solvents for this aim. The fact that performance of amines in carbon capture is greatly affected by variation in their molecular structure has been proven. Quantitative structure property relationship (QSPR) is a technique which employs molecular structure related variables known as descriptor for modeling. In this paper, QSPR method is employed for modeling and predicting CO2 loading of different amines after absorption and desorption steps in carbon removal process using membrane contactors. Physico-chemical and theoretical descriptors were calculated for a data set including sixteen amines. Variable selection and model development were performed by genetic algorithm-multiple linear regression (GA-MLR) method. Developed models could predict CO2 loading of amines’ solutions after absorption and desorption by coefficient of determination of 0.986 and 0.989 and standard error of the estimate equal to 0.0572 and 0.0496, respectively. In comparison between desorption and absorption model, desorption model is more accurate and absorption model provides simpler descriptors. Validity of the developed models were confirmed by different statistical tests and models showed high predictability power. Furthermore, mechanistic interpretation was applied in order to explain the relation between CO2 loading and descriptors which appeared in the models. It was found out that steric hindrance effect has a more significant influence on desorption than absorption.

Prediction of photolysis half-lives of dihydroindolizines by genetic algorithm-multiple linear regression (GA-MLR)

Quantitative structure–property relationship study was carried out for the prediction of photolysis half-lives of dihydroindolizines. Genetic algorithm variable selection was used in the multiple linear regression modeling. Four descriptors including topological (AAC), 2D-Autocorrelations (GATS7m), 3D-MoRSE (Mor19p), and GETAWAY (HATS3p) descriptors were selected by the algorithm, revealing that a hybrid of topologic, geometric, and electronic features of the molecule affects photolysis half-life of studied photochromic compounds. The results showed that the developed model provides statistically significant predictions of photolysis half-lives of dihydroindolizines. Copyright © 2016 John Wiley & Sons, Ltd.

QSAR and Structure Based Molecular Docking of Angelicin Compounds: an Attempt to Drug Design against Swine Influenza

There has been a great challenge of research and discovery of novel medicinal leads against swine influenza since 2009. Rational drug design utilizing pharmacoinformatics tools has been augmented now-a-days for in-silico screening of lead compounds prior to experimental synthesis, structural elucidation, biological evaluation and finally clinical trials to make the cost efficient drug design and discovery research. There is hardly any specific chemotherapeutics for the treatment against deadly swine influenza viral infection. Therefore, it is an urgent need to design and develop new anti-viral lead compounds active against swine influenza. Quantitative structure activity relationship (QSAR) has been used to develop models that correlate biological activity of angelicin compounds derived from published literature and their computed structural properties. The approach started by generation of a series of descriptors including topological, three dimensional, constitutional, functional groups and atom fragment indices respectively solely calculated from the compounds in the data set. In this study, data set consists of 53 angelicin compounds along with their inhibitory concentration 50% (IC50, μM) against H1N1 swine influenza virus. Genetic algorithm-multiple linear regression (GA-MLR) analysis technique has been to generate a number of QSAR models. The models were validated statistically incorporating training and test set approaches. Finally, structure-based molecular docking study has been performed for interpretation of the mode of binding of the angelicin compounds toward H1N1 target. QSAR and molecular docking analysis of these congeners have not yet been reported. Therefore, this study has significant impact for designing of the highly active compounds in this series that are useful for the treatment of swine influenza. In-silico structure based docking model could be helpful for design and screening of congeneric compounds having mode of binding similarity.

Assessment through Statistical Methods of Water Quality Parameters(WQPs) in the Han River in Korea

Objective: This study was conducted to develop a chemical oxygen demand (COD) regression model using water quality monitoring data (January, 2014) obtained from the Han River auto-monitoring stations. Methods: Surface water quality data at 198 sampling stations along the six major areas were assembled and analyzed to determine the spatial distribution and clustering of monitoring stations based on 18 WQPs and regression modeling using selected parameters. Statistical techniques, including combined genetic algorithm-multiple linear regression (GA-MLR), cluster analysis (CA) and principal component analysis (PCA) were used to build a COD model using water quality data. Results: A best GA-MLR model facilitated computing the WQPs for a 5-descriptor COD model with satisfactory statistical results (<TEX>$r^2=92.64$</TEX>,<TEX>$Q{^2}_{LOO}=91.45$</TEX>,<TEX>$Q{^2}_{Ext}=88.17$</TEX>). This approach includes variable selection of the WQPs in order to find the most important factors affecting water quality. Additionally, ordination techniques like PCA and CA were used to classify monitoring stations. The biplot based on the first two principal components (PCs) of the PCA model identified three distinct groups of stations, but also differs with respect to the correlation with WQPs, which enables better interpretation of the water quality characteristics at particular stations as of January 2014. Conclusion: This data analysis procedure appears to provide an efficient means of modelling water quality by interpreting and defining its most essential variables, such as TOC and BOD. The water parameters selected in a COD model as most important in contributing to environmental health and water pollution can be utilized for the application of water quality management strategies. At present, the river is under threat of anthropogenic disturbances during festival periods, especially at upstream areas.

QSAR study of VEGFR-2 inhibitors by using genetic algorithm-multiple linear regressions (GA-MLR) and genetic algorithm-support vector machine (GA-SVM): a comparative approach

The quantitative structure–activity relationship (QSAR) of the novel 4-aminopyrimidine-5-carbaldehyde oxime derivatives as effective and selective inhibitors of potent VEGFR-2 was studied. A suitable set of the molecular descriptors was calculated, and the most impressive descriptors were subsequently selected using genetic algorithm (GA) variable selection approach. To construct robust models, the GA was combined with multiple linear regression and support vector machine, respectively, as GA-MLR and GA-SVM. The predictive quality of the QSAR model was examined for an external set of six compounds, randomly chosen out of 32 compounds in the original data set. The accuracy of the proposed models was further confirmed using cross-validation, validation through an external test set and Y-randomization approaches. Based on the selected descriptors, we have identified some key features in the 4-aminopyrimidine-5-carbaldehyde oxime derivatives that are responsible for potent VEGFR-2 inhibitory activity. The analyses may be used to design more potent 4-aminopyrimidine-5-carbaldehyde oxime derivatives and predict their activities prior to synthesis.

QSAR study of CK2 inhibitors by GA-MLR and GA-SVM methods

In this work, the quantitative structure–activity relationship models were developed for predicting activity of a series of compounds such as CK2 inhibitors using multiple linear regressions and support vector machine methods. The data set consisted of 48 compounds was divided into two subsets of training and test set, randomly. The most relevant molecular descriptors were selected using the genetic algorithm as a feature selection tool. The predictive ability of the models was evaluated using Y-randomization test, cross-validation and external test set. The genetic algorithm-multiple linear regression model with six selected molecular descriptors was obtained and showed high statistical parameters (R2train=0.893, R2test=0.921, Q2LOO=0.844, F=43.17, RMSE=0.287). Comparison of the results between GA-MLR and GA-SVM demonstrates that GA-SVM provided better results for the training set compounds; however, the predictive quality for both models is acceptable. The results suggest that atomic mass and polarizabilities and also number of heteroatom in molecules are the main independent factors contributing to the CK2 inhibition activity. The predicted results of this study can be used to design new and potent CK2 inhibitors.

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.

Solubility modeling in three supercritical carbon dioxide, ethane and trifluoromethane fluids by one set of molecular descriptors

Quantitative structure property relationships (QSPR) were developed for the first time predicting of solubility in supercritical carbon dioxide, ethane and trifluoromethane over a wide range of pressures (5.1–36.2MPa) and temperatures (308–343K). A large number of descriptors were calculated and a subset of calculated descriptors was selected by genetic algorithm–multiple linear regression (GA–MLR). Four molecular descriptors and three experimental descriptors such as pressure, temperature and melting point were selected as the most feasible descriptors for prediction of solubility in three supercritical fluids. The data set consisted of 14 molecules in various temperatures and pressures, which form 586 solubility data. Modeling of the relationship between selected descriptors and solubility data was achieved by linear (multiple linear regression; MLR) and nonlinear (artificial neural network; ANN) methods. The artificial neural network architectures and their parameters were optimized simultaneously. The root mean squares error (RMSE) for supercritical carbon dioxide, ethane and trifluoromethane were 0.56, 0.68 and 0.72, respectively. The performance of the ANN models was also compared with multiple linear regression models and the results showed the superiority of the ANN over MLR model.

Design, synthesis, crystal structure, insecticidal activity, molecular docking, and QSAR studies of novel N3-substituted imidacloprid derivatives.

Three novel series of N3-substituted imidacloprid derivatives were designed and synthesized, and their structures were identified on the basis of satisfactory analytical and spectral ((1)H NMR, (13)C NMR, MS, elemental analysis, and X-ray) data. Preliminary bioassays indicated that all of the derivatives exhibited significant insecticidal activities against Aphis craccivora, with LC50 values ranging from 0.00895 to 0.49947 mmol/L, and the insecticidal activities of some of them were comparable to those of the control imidacloprid. Some key structural features related to their insecticidal activities were identified, and the binding modes between target compounds and nAChR model were also further explored by molecular docking. By comparing the interaction features of imidacloprid and compound 26 with highest insecticidal activity, the origin of the high insecticidal activity of compound 26 was identified. On the basis of the conformations generated by molecular docking, a satisfactory 2D-QSAR model with six selected descriptors was built using genetic algorithm-multiple linear regression (GA-MLR) method. The analysis of the built model showed the molecular size, shape, and the ability to form hydrogen bond were important for insecticidal potency. The information obtained in the study will be very helpful for the design of new derivatives with high insecticidal activities.