基于SVR和k-近邻群的组合预测在QSAR中的应用

为提高定量构效关系(QSAR)研究的预测精度,发展了一种新的基于支持向量机回归(SVR)非线性筛选分子结构描述符、基于k-近邻群的非线性组合预测方法.首先以均方误差(MSE)最小为原则,以留一法通过多轮末尾淘汰实施分子结构描述符的非线性SVR汰选并给出最优核函数和相应保留描述符;其次基于待测样本与训练样本保留描述符向量的欧氏距离,以不同k-近邻群子模型双重留一法预测值反映样本集的异质性;然后基于MSE最小,以留一法通过多轮末尾淘汰实施近邻群子模型的非线性SVR汰选并给出最优核函数和相应保留子模型;最后基于保留子模型以双重留一法实施组合预测.以取代苯胺和苯酚类化合物对大型溞的QSAR实例验证表明:新方法在所有参比模型中预测精度最高,且能更精细地反映描述符与化合物毒性间的非线性关系,具结构风险最小、非线性、适于小样本,能有效克服过拟合、维数灾和局极小,非线性筛选描述符和子模型,非线性组合预测,自动选择最优核函数及其相应参数,泛化推广能力优异、预测精度高等诸多优点,在QSAR研究中有广泛应用前景.     

Constructing optimum blood brain barrier QSAR models using a combination of 4D-molecular similarity measures and cluster analysis

A new method, using a combination of 4D-molecular similarity measures and cluster analysis to construct optimum QSAR models, is applied to a data set of 150 chemically diverse compounds to build optimum blood-brain barrier (BBB) penetration models. The complete data set is divided into subsets based on 4D-molecular similarity measures using cluster analysis. The compounds in each cluster subset are further divided into a training set and a test set. Predictive QASAR models are constructed for each cluster subset using the corresponding training sets. These QSAR models best predict test set compounds which are assigned to the same cluster subset, based on the 4D-molecular similarity measures, from which the models are derived. The results suggest that the specific properties governing blood-brain barrier permeability may vary across chemically diverse compounds. Partitioning compounds into chemically similar classes is essential to constructing predictive blood-brain barrier penetration models embedding the corresponding key physiochemical properties of a given chemical class.     

The Non-Grid Technique for Modeling 3D QSAR Using Self-Organizing Neural Network (SOM) and PLS Analysis: Application to Steroids and Colchicinoids

Abstract

A novel method for modeling 3D QSAR has been developed. The method involves a multiple training of a series of self-organizing networks (SOM). The obtained networks have been used for processing the data of one reference molecule. A scheme for the analysis of such data with the PLS analysis has been proposed and tested using the steroids data with corticosteroid binding globulin (CBG) affinity. The predictivity of the CBG models measured with the SDEP parameter is among the best one reported. Although 3-D QSAR models for colchicinoid series is far less predictive, it allows for a discussion on the relative influence of the structural motifs of these compounds.     

Local and global quantitative structure-activity relationship modeling and prediction for the baseline toxicity

The predictive accuracy of the model is of the most concern for computational chemists in quantitative structure-activity relationship (QSAR) investigations. It is hypothesized that the model based on analogical chemicals will exhibit better predictive performance than that derived from diverse compounds. This paper develops a novel scheme called "clustering first, and then modeling" to build local QSAR models for the subsets resulted from clustering of the training set according to structural similarity. For validation and prediction, the validation set and test set were first classified into the corresponding subsets just as those of the training set, and then the prediction was performed by the relevant local model for each subset. This approach was validated on two independent data sets by local modeling and prediction of the baseline toxicity for the fathead minnow. In this process, hierarchical clustering was employed for cluster analysis, k-nearest neighbor for classification, and partial least squares for the model generation. The statistical results indicated that the predictive performances of the local models based on the subsets were much superior to those of the global model based on the whole training set, which was consistent with the hypothesis. This approach proposed here is promising for extension to QSAR modeling for various physicochemical properties, biological activities, and toxicities.     

基于范数指数定量构效关系预测β-环糊精络合常数

环糊精在药剂学领域中是一类重要的包结化合物, 其中络合物稳定常数(logK)是一个关键评价参数. 本研究基于扩展距离矩阵提出了一组范数指数, 利用多种计算方法构建了系列定量构效关系模型, 并对233种化合物与β-环糊精的logK进行了计算预测. 计算结果表明基于扩展距离矩阵范数建立的系列定量构效关系模型均能较好预测logK; 其中利用最小二乘-支撑向量机方法建立的模型预测效果最好, 其预测结果的相关性系数R和留一、留十交叉验证相关性系数(Q_LOO,Q_LTO)分别为0.9587、0.8775和0.8732. 与文献方法对比结果表明, 本工作的预测结果在准确性和稳定性上有着显著的改善, 且能分辨同分异构体. 本课题组前期研究成果和本项工作表明基于范数指数构建的定量构效关系不仅适用于计算化合物的基础物理化学性质, 还能应用到化学反应过程相关常数的准确预测.     

3D QSAR and molecular docking studies of benzimidazole derivatives as hepatitis C virus NS5B polymerase inhibitors

The urgent need for novel HCV antiviral agents has provided an impetus for understanding the structural requisites of NS5B polymerase inhibitors at the molecular level. Toward this objective, comparative molecular field analysis (CoMFA) and comparative molecular similarity indices analysis (CoMSIA) of 67 HCV NS5B polymerase inhibitors were performed using two methods. First, ligand-based 3D QSAR studies were performed based on the lowest energy conformations employing the atom fit alignment method. Second, receptor-based 3D QSAR models were derived from the predicted binding conformations obtained by docking all NS5B inhibitors at the allosteric binding site of NS5B (PDB ID: 2dxs). Results generated from the ligand-based model were found superior (r2cv values of 0.630 for CoMFA and 0.668 for CoMSIA) to those obtained by the receptor-based model (r2cv values of 0.536 and 0.561 for CoMFA and CoMSIA, respectively). The predictive ability of the models was validated using a structurally diversified test set of 22 compounds that had not been included in a preliminary training set of 45 compounds. The predictive r2 values for the ligand-based CoMFA and CoMSIA models were 0.734 and 0.800, respectively, while the corresponding predictive r2 values for the receptor-based CoMFA and CoMSIA models were 0.538 and 0.639, respectively. The greater potency of the tryptophan derivatives over that of the tyrosine derivatives was interpreted based on CoMFA steric and electrostatic contour maps. The CoMSIA results revealed that for a NS5B inhibitor to have appreciable inhibitory activity it requires hydrogen bond donor and acceptor groups at the 5-position of the indole ring and an R substituent at the chiral carbon, respectively. Interpretation of the CoMFA and CoMSIA contour maps in context of the topology of the allosteric binding site of NS5B provided insight into NS5B-inhibitor interactions. Taken together, the present 3D QSAR models were found to accurately predict the HCV NS5B polymerase inhibitory activity of structurally diverse test set compounds and to yield reliable clues for further optimization of the benzimidazole derivatives in the data set.     

The Learned Symmetry Concept in Revealing Quantitative Structure-Activity Relationships With Artificial Neural Networks

Abstract

A method to build QSAR models based on substituent constants for congeneric sets of compounds having several topologically equivalent substituent positions was proposed. The approach is based on the application of artificial neural networks (learning to construct nonlinear structure-activity relationships taking into account necessary symmetry properties of training set structures) to a training set expanded by adding the copies of compounds with the same activity values but with permuted assignment of equivalent substituent positions. The better predictive power of these constructed models, as compared with the performances of neural network models for non-expanded sets was demonstrated for the calcium channel blockers of 1,4-dihydropyridine type and for hallucinogenic phenylalkylamines.     

3D-QSAR and molecular modeling of HIV-1 integrase inhibitors

Three-dimensional quantitative structure-activity relationship (3D QSAR) methods were applied on a series of inhibitors of HIV-1 integrase with respect to their inhibition of 3-processing and 3-end joining steps in vitro.The training set consisted of 27 compounds belonging to the class of thiazolothiazepines. The predictive ability of each model was evaluated using test set I consisting of four thiazolothiazepines and test set II comprised of seven compounds belonging to an entirely different structural class of coumarins. Maximum Common Substructure (MCS) based method was used to align the molecules and this was compared with other known methods of alignment. Two methods of 3D QSAR: comparative molecular field analysis (CoMFA) and comparative molecular similarity indices analysis (CoMSIA) were analyzed in terms of their predictive abilities. CoMSIA produced significantly better results for all correlations. The results indicate a strong correlation between the inhibitory activity of these compounds and the steric and electrostatic fields around them. CoMSIA models with considerable internal as well as external predictive ability were obtained. A poor correlation obtained with hydrophobic field indicates that the binding of thiazolothiazepines to HIV-1 integrase is mainly enthalpic in nature. Further the most active compound of the series was docked into the active site using the crystal structure of integrase. The binding site was formed by the amino acid residues 64-67, 116, 148, 151-152, 155-156, and 159. The comparison of coefficient contour maps with the steric and electrostatic properties of the receptor shows high level of compatibility.     

Virtual screening using binary kernel discrimination: effect of noisy training data and the optimization of performance

Binary kernel discrimination (BKD) uses a training set of compounds, for which structural and qualitative activity data are available, to produce a model that can then be applied to the structures of other compounds in order to predict their likely activity. Experiments with the MDL Drug Data Report database show that the optimal value of the smoothing parameter, and hence the predictive power of BKD, is crucially dependent on the number of false positives in the training set. It is also shown that the best results for BKD are achieved using one particular optimization method for the determination of the smoothing parameter that lies at the heart of the method and using the Jaccard/Tanimoto coefficient in the kernel function that is used to compute the similarity between a test set molecule and the members of the training set.     

QSAR modelling using combined simple competitive learning networks and RBF neural networks

The aim of this study was to propose a QSAR modelling approach based on the combination of simple competitive learning (SCL) networks with radial basis function (RBF) neural networks for predicting the biological activity of chemical compounds. The proposed QSAR method consisted of two phases. In the first phase, an SCL network was applied to determine the centres of an RBF neural network. In the second phase, the RBF neural network was used to predict the biological activity of various phenols and Rho kinase (ROCK) inhibitors. The predictive ability of the proposed QSAR models was evaluated and compared with other QSAR models using external validation. The results of this study showed that the proposed QSAR modelling approach leads to better performances than other models in predicting the biological activity of chemical compounds. This indicated the efficiency of simple competitive learning networks in determining the centres of RBF neural networks.     

The non-grid technique for modeling 3D QSAR using self-organizing neural network (SOM) and PLS analysis: application to steroids and colchicinoids

A novel method for modeling 3D QSAR has been developed. The method involves a multiple training of a series of self-organizing networks (SOM). The obtained networks have been used for processing the data of one reference molecule. A scheme for the analysis of such data with the PLS analysis has been proposed and tested using the steroids data with corticosteroid binding globulin (CBG) affinity. The predictivity of the CBG models measured with the SDEP parameter is among the best one reported. Although 3-D QSAR models for colchicinoid series is far less predictive, it allows for a discussion on the relative influence of the structural motifs of these compounds.     

Performance of (consensus) kNN QSAR for predicting estrogenic activity in a large diverse set of organic compounds

A novel method (in the context of quantitative structure-activity relationship (QSAR)) based on the k nearest neighbour (kNN) principle, has recently been introduced for the derivation of predictive structure-activity relationships. Its performance has been tested for estimating the estrogen binding affinity of a diverse set of 142 organic molecules. Highly predictive models have been obtained. Moreover, it has been demonstrated that consensus-type kNN QSAR models, derived from the arithmetic mean of individual QSAR models were statistically robust and provided more accurate predictions than the great majority of the individual QSAR models. Finally, the consensus QSAR method was tested with 3D QSAR and log P data from a widely used steroid benchmark data set.