QSAR modelling of the toxicity to Tetrahymena pyriformis by balance of correlations

Balance of correlations is an approach to build up quantitative structure–property/activity relationships (QSPR/QSAR). This approach is based on a split into the subtraining, calibration and test sets instead of classic split into training and test sets. The function of the calibration set is the preliminary check up of the model. In other words, the calibration set is like a preliminary test set. Computational experiments (with the Monte Carlo method) have shown that the statistical characteristics of the prediction for the toxicity to Tetrahymena pyriformis (the 50% growth inhibition concentration, IGC₅₀) based on the balance of correlations are better than the statistical characteristics of the prediction based on the classic scheme.     

基于支持向量机、支持向量回归和分子对接的CYP450 1A2抑制剂的发现研究

支持向量机,支持向量回归和分子对接的计算方法已广泛应用于化合物的药理活性计算。为了提高计算的准确性和可靠性,拟以细胞色素P450酶1A2为研究载体,运用建立的联合SVM-SVR-Docking计算模型预测潜在的CYP1A2抑制剂。其中,建立的最优SVM定性模型训练集,内部测试集和外部测试集的准确率分别为99.432%,97.727%和91.667%。最优SVR定量模型训练集和测试集的R和MSE分别为0.763,0.013和0.753,0.056。实验表明两个模型具有较高的准确性和可靠性。通过对SVM和SVR模型结果的比较分析,发现连接性指数、分子构成描述符和官能团数目等分子描述符可能与CYP1A2抑制剂的辨识和活性预测密切相关。随后利用分子对接技术分析化合物与CYP1A2的结合构象及相互作用的稳定性。形成氢键相互作用的关键氨基酸包括THR124,ASP320;形成疏水相互作用的关键氨基酸包括ALA317和GLY316。所获得模型可用于天然产物化学成分中CYP1A2潜在抑制剂的活性计算及其介导的药物-药物相互作用预测提供理论指导,也为合理联合用药提供一定参考。共获得20个对CYP1A2具有潜在抑制活性的化合物。部分结果与文献结果相互印证,进一步说明了模型的准确性和联合计算策略的可靠性.     

Three-class classification models of logS and logP derived by using GA–CG–SVM approach

In this investigation, three-class classification models of aqueous solubility (logS) and lipophilicity (logP) have been developed by using a support vector machine (SVM) method combined with a genetic algorithm (GA) for feature selection and a conjugate gradient method (CG) for parameter optimization. A 5-fold cross-validation and an independent test set method were used to evaluate the SVM classification models. For logS, the overall prediction accuracy is 87.1% for training set and 90.0% for test set. For logP, the overall prediction accuracy is 81.0% for training set and 82.0% for test set. In general, for both logS and logP, the prediction accuracies of three-class models are slightly lower by several percent than those of two-class models. A comparison between the performance of GA–CG–SVM models and that of GA–SVM models shows that the SVM parameter optimization has a significant impact on the quality of SVM classification model. Electronic supplementary material  The online version of this article (doi:) contains supplementary material, which is available to authorized users. Hui Zhang and Ming-Li Xiang are contributed equally.