润滑剂分子结构与粘度和表面张力的定量关系

用偏最小二乘法(PLS)和人工神经网络(ANN)方法对润滑剂分子结构与表面张力和粘度之间的关系进行了定性分析和定量计算,采用的结构参数有分配系数、分子体积、分子表面积、溶度积、摩尔折射度和等张比容。定性分析结果与实验结果一致,定量计算结果与实验结果符合较好。     

应用量化参数和CoMFA法研究苯甲酸类化合物的结构和其pKa值的相关性

人工神经网;应用量化参数和CoMFA法研究苯甲酸类化合物的结构和其pKa值的相关性     

Multi-way PLS modeling of structure-activity data by incorporating electrostatic and lipophilic potentials on molecular surface

We devised and elaborated a surface-based three-dimensional-quantitative structure-activity relationship (3D-QSAR) method, which had been proposed in the previous study. This approach can be applied to more general case where both the electrostatic and lipophilic potentials on molecular surface simultaneously change. The 3D coordinates of all sampling points on molecular surface are projected into a 2D map by Kohonen neural network (KNN). Each node in the map is coded by the associated molecular electrostatic potential (MEP) or molecular lipophilic potential (MLP) values. The electrostatic and lipophilic KNN maps are generated for each compound and the four-way array is constructed by collecting two KNN maps of all samples. The correlation between four-way array and biological activity is examined by four-way partial least-squares (PLS). For validation, the structure-activity data of estrogen receptor antagonists was investigated. The four-way PLS model gave the high statistics at calibration and validation stages. The coefficients of the four-way PLS model back-projected on molecular surface had a reasonable 3D distribution and it was nicely consistent with active site of the estrogen receptor which was recently made clear by X-ray crystallography.     

Multi-way PLS modeling of structure–activity data by incorporating electrostatic and lipophilic potentials on molecular surface

We devised and elaborated a surface-based three-dimensional-quantitative structure–activity relationship (3D-QSAR) method, which had been proposed in the previous study. This approach can be applied to more general case where both the electrostatic and lipophilic potentials on molecular surface simultaneously change. The 3D coordinates of all sampling points on molecular surface are projected into a 2D map by Kohonen neural network (KNN). Each node in the map is coded by the associated molecular electrostatic potential (MEP) or molecular lipophilic potential (MLP) values. The electrostatic and lipophilic KNN maps are generated for each compound and the four-way array is constructed by collecting two KNN maps of all samples. The correlation between four-way array and biological activity is examined by four-way partial least-squares (PLS). For validation, the structure–activity data of estrogen receptor antagonists was investigated. The four-way PLS model gave the high statistics at calibration and validation stages. The coefficients of the four-way PLS model back-projected on molecular surface had a reasonable 3D distribution and it was nicely consistent with active site of the estrogen receptor which was recently made clear by X-ray crystallography.     

Sample-distance partial least squares: PLS optimized for many variables,with application to CoMFA

Summary Three-dimensional molecular modeling can provide an unlimited number m of structural properties. Comparative Molecular Field Analysis (CoMFA), for example, may calculate thousands of field values for each model structure. When m is large, partial least squares (PLS) is the statistical method of choice for fitting and predicting biological responses. Yet PLS is usually implemented in a property-based fashion which is optimal only for small m. We describe here a sample-based formulation of PLS which can be used to fit any single response (bioactivity). SAMPLS reduces all explanatory data to the pairwise distances among n sample (molecules), or equivalently to an n-by-n covariance matrix C. This matrix, unmodified, can be used to fit all PLS components. Furthermore, SAMPLS will validate the model by modern resampling techniques, at a cost independent of m. We have implemented SAMPLS as a Fortran program and have reproduced conventional and cross-validated PLS analyses of data from two published studies. Full (leaveach-out) cross-validation of a typical CoMFA takes 0.2 CPU s. SAMPLS is thus ideally suited to structure-activity analysis based on CoMFA fields or bonded topology. The sample-distance formulation also relates PLS to methods like cluster analysis and nonlinear mapping, and shows how drastically PLS simplifies the information in CoMFA fields.Abbreviations PLS partial least squares - SAMPLS sample-distance partial least squares - CoMFA comparative molecular field analysis.     

化合物的空间取向对CoMFA结果的影响

Our work shows that different compound orientations have different results in Comparative Molecular Field Analysis(CoMFA).For three analyzed compound series, the squared correlation coefficients of cross-validation(q2)could vary as largely as 0.30～0.40 among all possible orientations. The reason for this comes from the routine adopted by CoMFA which uses discrete, regularly arrayed grids to represent the molecular field. Therefore, different orientations may map their molecular fields differently onto the grid and accordingly give different results from partial least square (PLS)analyses. We have developed a method all-orientation searching, to seek for the orientation with the best CoMFA result. And ,we suggest that all-orientation searching should be incorporated into the standard CoMFA procedure.     

Regularized regression analysis of digitized molecular structures in organic reactions for quantification of steric effects

In organic chemistry, Comparative Molecular Field Analysis (CoMFA) can be defined as a regression analysis between reaction outcomes and molecular fields, wherein we can extract and visualize important structural information from the coefficients of the constructed regression models. In CoMFA, partial least‐squares (PLS) regression, which determines all coefficients in the model, is used for fitting the regression models. However, in organic reactions, steric effects are observed only near the reactive site, indicating that a large number of regression coefficients in the CoMFA of organic reactions should be assigned as 0. The regularized regression method, LASSO/Elastic Net, allows us to fit the regression model while assigning 0 values to unimportant coefficients. Although LASSO/Elastic Net should be suitable for CoMFA, there is no example of its use for organic reaction analysis. Herein, we examine the performance of LASSO/Elastic Net for the quantification of steric effects in CoMFA. We employ digitized molecular structures (the indicator field) as molecular fields that represent steric effects. LASSO/Elastic Net regressions provide highly interpretable models that include less noise than those from PLS regression. © 2017 Wiley Periodicals, Inc.     

Comparative Molecular Similarity Index Analysis (CoMSIA) to study hydrogen-bonding properties and to score combinatorial libraries

Comparative molecular field analysis has been applied to a data set of thermolysin inhibitors. Fields expressed in terms of molecular similarity indices (CoMSIA) have been used instead of the usually applied Lennard-Jones- and Coulomb-type potentials (CoMFA). Five different properties, assumed to cover the major contributions responsible for ligand binding, have been considered: steric, electrostatic, hydrophobic, and hydrogen-bond donor or acceptor properties. The statistical evaluation of the field properties by PLS analysis reveals a similar predictive potential to CoMFA. However, significantly improved and easily interpretable contour maps are obtained. The features in these maps intuitively suggest where to modify a molecular structure in terms of physicochemical properties and functional groups in order to improve its binding affinity. They can also be interpreted with respect to the known structural protein environment of thermolysin. Most of the highlighted regions in the maps are mirrored by features in the surrounding environment required for binding. Using the derived correlation model, different members of a combinatorial library designed for thermolysin inhibition have been scored for affinity. The results obtained demonstrate the prediction power of the CoMSIA method.     

3D-QSAR of Benzothiazole Derivatives as Potent Anticancer Agents

Comparative molecular field analysis (CoMFA) method was applied to study three-dimensional quantitative structure activity relationship (3D-QSAR) of a series of benzothiazole derivatives as potent anticancer agents. The CoMFA model of cross-validation and the partial-least-square (PLS) model of non cross-validation have been well established. The best CoMFA model gives a good cross-validation coe±cient of 0.642 and a conventional correlation coe±cient of 0.976. Moreover, the estimated standard error is 0.161 and the statistical square deviation ratio F(3;20) is 111.4. The statistical parameters of the best CoMFA model show this model is reasonable and has predictive ability. The CoMFA results suggest that an electron-withdrawing group or atom (e.g. F atom) linking to the first atom (C19) of substituent R can increase the positive charges of C19 and its fi-site atoms, which lie in the blue-colored regions in the electrostatic field contour map of CoMFA, and thus can improve the activity of the compound. Meanwhile, selecting an R with an appropriatevolume is also advantageous for improving the activity.     

The comparison of geometric and electronic properties of molecular surfaces by neural networks: Application to the analysis of corticosteroid-binding globulin activity of steroids

Summary It is shown how a self-organizing neural network such as the one introduced by Kohonen can be used to analyze features of molecular surfaces, such as shape and the molecular electrostatic potential. On the one hand, two-dimensional maps of molecular surface properties can be generated and used for the comparison of a set of molecules. On the other hand, the surface geometry of one molecule can be stored in a network and this network can be used as a template for the analysis of the shape of various other molecules. The application of these techniques to a series of steroids exhibiting a range of binding activities to the corticosteroid-binding globulin receptor allows one to pinpoint the essential features necessary for biological activity.     

Three-dimensional quantitative structure--property relationship (3D-QSPR) models for prediction of thermodynamic properties of polychlorinated biphenyls (PCBs): enthalpy of sublimation

Three-dimensional quantitative structure--property relationship (3D-QSPR) models have been constructed using comparative molecular field analysis (CoMFA) to correlate the sublimation enthalpies at 298.15 K of a series of polychlorinated biphenyls (PCBs) with their CoMFA-calculated physicochemical properties. Various alignment schemes, such as atom fit, as is, and inertial were employed in this study. Separate CoMFA models were developed using different partial charge formalisms, namely, electrostatic potential (ESP) and Gasteiger-Marsili (GM) charges. Among the four different CoMFA models constructed for sublimation enthalpy (Delta(sub)H(m)(298.15 K)), the model that combined atom fit alignment and ESP charges yielded the greatest self-consistency (r(2) = 0.976) and internal predictive ability (r(cv)(2) = 0.750). This CoMFA model was used to predict Delta(sub)H(m)(298.15 K) of PCBs for which the corresponding experimental values are unavailable in the literature.     

Comparative molecular field analysis and molecular modeling studies of 20-(S)- camptothecin analogs as inhibitors of DNA topoisomerase I and anticancer/antitumor agents

Conformational studies and comparative molecular field analysis (CoMFA) were undertakenfor a series of camptothecin (CPT) analogs to correlate topoisomerase I inhibition with thesteric and electrostatic properties of 32 known compounds. The resulting CoMFA modelshave been used to make predictions on novel CPT derivatives. Using the newly derived MM3parameters, a molecular database of the 32 CPT analogs was created. Various point atomiccharges were generated and assigned to the MM3 minimized structures, which were used inpartial least-squares analyses. Overall, CoMFA models with the greatest predictive validitywere obtained when both the R- and S-isomers were included in the data set, andsemiempirical charges were calculated for MM3 minimized low-energy lactone structures. Across-validated R2 of 0.758 and a non-cross-validated R2 of 0.916 were obtained for MM3minimized structures with PM3 ESP charges for the 32 CPT analogs. The derived QSARequations were used to assign topoisomerase I inhibition values for compounds in this studyand compounds not included in the original data set. Prior to its appearance in the literature,an IC50 of 103 nM was predicted for the 10,11-oxazole derivative. This CoMFA predictedvalue compared favorably with the recently reported value of 150 nM. The CoMFA modelwas also evaluated by predicting the activities of recently reported 11-aza CPT and trionederivatives. The predicted activity (IC50 = 249 nM) for 11-aza CPT compared well with thereported value of 383 nM.     

几种改进的CoMFA方法比较研究血小板活化因子拮抗剂

由于传统的比较分子场分析(CoMFA)方法本身存在一些缺陷，使得分子的叠合 规则以及叠合分子的空间取向和空间位置等因素对q~2的影响很大，因此相继提出 了几种改进的CoMFA方法。为了优化CoMFA结果，应用传统的CoMFA方法和交叉验证 的R~2引导的区域选择法(q~2-GRS)、全取向搜索法（AOS）、全空间搜索法（APS） 以及比较分子相似性指数(CoMSIA)等四种改进的CoMFA方法，对18个pinusolide类 衍生物这类新发现的血小板活化因子（PAF）拮抗剂进行了比较研究。结果表明四 种改进的CoMFA方法得到的q~2值均比传统CoMFA的高。q~2-GRS方法得到的q~2值有 所提高，但综合结果并不理想，AOS与APS得到的q~2较为理想，而在CoMSIA中， q~2几乎不受空间取向或空间位置的影响。同时我们引人基于样本的偏最小二乘法 （SAMPLS）取代原AOS／APS程序中的传统PLS进行统计分析，明显提高了其运行速 度。最后，根据q~2最高的CoMFA模型和CoMSIA模型设计了几个预测活性更高的 pinusolide类似物。     

Partial least squares modeling and genetic algorithm optimization in quantitative structure-activity relationships

Quantitative structure-activity relationship (QSAR) studies based on chemometric techniques are reviewed. Partial least squares (PLS) is introduced as a novel robust method to replace classical methods such as multiple linear regression (MLR). Advantages of PLS compared to MLR are illustrated with typical applications. Genetic algorithm (GA) is a novel optimization technique which can be used as a search engine in variable selection. A novel hybrid approach comprising GA and PLS for variable selection developed in our group (GAPLS) is described. The more advanced method for comparative molecular field analysis (CoMFA) modeling called GA-based region selection (GARGS) is described as well. Applications of GAPLS and GARGS to QSAR and 3D-QSAR problems are shown with some representative examples. GA can be hybridized with nonlinear modeling methods such as artificial neural networks (ANN) for providing useful tools in chemometric and QSAR.     

A Quantitative Structure–Activity Relationship Study of Calpeptin (Calpain Inhibitor) as an Anticancer Agent

Calpeptin analogs show anticancer properties with inhibition of calpain. In this work, we applied a quantitative structure–activity relationship (QSAR) model on 34 calpeptin derivatives to select the most appropriate compound. QSAR was employed to generate the models and predict the more significant compounds through a series of calpeptin derivatives. The HyperChem, Gaussian 09, and Dragon software programs were used for geometry optimization of the molecules. The 2D and 3D molecular structures were drawn by ChemDraw (Ultra 16.0) and Chem3D (Pro16.0) software. The Unscrambler program was used for the analysis of data. Multiple linear regression (MLR‐MLR), partial least‐squares (MLR‐PLS1), principal component regression (MLR‐PCR), a genetic algorithm‐artificial neural networks (GA‐ANN), and a novel similarity analysis‐artificial neural network (SA‐ANN) method were used to create QSAR models. Among the three MLR models, MLR‐MLR provided better statistical parameters. The R² and RMSE of the prediction were estimated as 0.8248 and 0.26, respectively. Nevertheless, the constructed model using GA‐ANN revealed the best statistical parameters among the studied methods (R² test = 0.9643, RMSE test = 0.0155, R² train = 0.9644, RMSE train = 0.0139). The GA‐ANN model is found to be the most favorable method among the statistical methods and can be employed for designing new calpeptin analogs as potent calpain inhibitors in cancer treatment.