Development of non-peptide ACE inhibitors as novel and potent cardiovascular therapeutics: An in silico modelling approach

Angiotensin-converting enzyme (ACE) inhibitors have been acknowledged as first-line agents for the treatment of hypertension and a variety of cardiovascular disorders. In this context, quantitative structure–activity relationship (QSAR) models for a series of non-peptide compounds as ACE inhibitors are developed based on Simplified Molecular Input-Line Entry System (SMILES) notation and local graph invariants. Three random splits into the training and test sets are used. The Monte Carlo method is applied for model development. Molecular docking studies are used for the final assessment of the developed QSAR model and the design of novel inhibitors. The statistical quality of the developed model is good. Molecular fragments responsible for the increase/decrease of the studied activity are calculated. The computer-aided design of new compounds, as potential ACE inhibitors, is presented. The predictive potential of the applied approach is tested, and the robustness of the model is proven using different methods. The results obtained from molecular docking studies are in excellent correlation with the results from QSAR studies. The presented study may be useful in the search for novel cardiovascular therapeutics based on ACE inhibition.     

Monte Carlo-based QSAR modeling of dimeric pyridinium compounds and drug design of new potent acetylcholine esterase inhibitors for potential therapy of <Emphasis Type="Italic">myasthenia gravis</Emphasis>

The Monte Carlo method was used for QSAR modeling of dimeric pyridinium compounds as acetylcholine esterase inhibitors. QSAR model was developed for a series of 39 dimeric pyridinium compounds. QSAR models were calculated with the representation of the molecular structure by the simplified molecular-input line-entry system. One split into the training and test set have been examined. The statistical quality of the developed model is very good. The calculated model for dimeric pyridinium derivatives had following statistical parameters: r ² = 0.9477 for the training set and r ² = 0.9332 the test set. Structural indicators considered as molecular fragments responsible for the increase and decrease in the inhibition activity have been defined. The computer-aided design of new dimeric pyridinium compounds potential acetylcholine esterase inhibitors with the application of defined structural alerts has been presented.     

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.     

Three useful dimensions for domain applicability in QSAR models using random forest

One popular metric for estimating the accuracy of prospective quantitative structure-activity relationship (QSAR) predictions is based on the similarity of the compound being predicted to compounds in the training set from which the QSAR model was built. More recent work in the field has indicated that other parameters might be equally or more important than similarity. Here we make use of two additional parameters: the variation of prediction among random forest trees (less variation among trees indicates more accurate prediction) and the prediction itself (certain ranges of activity are intrinsically easier to predict than others). The accuracy of prediction for a QSAR model, as measured by the root-mean-square error, can be estimated by cross-validation on the training set at the time of model-building and stored as a three-dimensional array of bins. This is an obvious extension of the one-dimensional array of bins we previously proposed for similarity to the training set [Sheridan et al. J. Chem. Inf. Comput. Sci.2004, 44, 1912-1928]. We show that using these three parameters simultaneously adds much more discrimination in prediction accuracy than any single parameter. This approach can be applied to any QSAR method that produces an ensemble of models. We also show that the root-mean-square errors produced by cross-validation are predictive of root-mean-square errors of compounds tested after the model was built.     

机器学习方法用于建立乙酰胆碱酯酶抑制剂的分类模型

我们构建了表征乙酰胆碱酯酶抑制剂分子组成、电荷、拓扑、几何结构及物理化学性质等特征的1559个描述符,通过Fischer Score排序过滤和Monte Carlo模拟退火法相结合进行变量筛选得到37个描述符,然后分别用支持向量学习机(SVM)、人工神经网络(ANN)和k-近邻(k-NN)等机器学习方法建立了乙酰胆碱酯酶抑制剂的分类预测模型.对于训练集的515个样本,通过五重交叉验证,各机器学习方法对正样本,负样本和总样本的平均预测精度分别为87.3%-92.7%,67.0%-81.0%和79.4%-88.2%;通过y-scrambling方法验证SVM模型是否偶然相关,结果正样本,负样本和总样本的平均预测精度分别为72.7%-82.5%,41.0%-53.0%和62.1%-69.1%,明显低于实际所建模型的预测精度,表明所建模型不存在偶然相关;对172个没有参与建模的外部独立测试样本,各机器学习方法对正样本,负样本和总样本的预测精度分别为93.3%-100.0%,74.6%-89.6%和86.1%-95.9%.所建模型中,SVM模型预测精度最好,且明显高于其它文献报道结果.     

Outlier detection in near-infrared spectroscopic analysis by using Monte Carlo cross-validation

An outlier detection method is proposed for near-infrared spectral analysis. The underlying philosophy of the method is that,in random test(Monte Carlo) cross-validation,the probability of outliers presenting in good models with smaller prediction residual error sum of squares(PRESS) or in bad models with larger PRESS should be obviously different from normal samples. The method builds a large number of PLS models by using random test cross-validation at first,then the models are sorted by the PRESS,and at last the outliers are recognized according to the accumulative probability of each sample in the sorted models. For validation of the proposed method,four data sets,including three published data sets and a large data set of tobacco lamina,were investigated. The proposed method was proved to be highly efficient and veracious compared with the conventional leave-one-out(LOO) cross validation method.