Hu Rongjing, Doucet Jean-Pierre, Delamar Michel, Zhang Ruisheng
Department of Chemistry, Lanzhou University, Lanzhou, Gansu 730000, PR China.
Eur J Med Chem. 2009 May;44(5):2158-71. doi: 10.1016/j.ejmech.2008.10.021. Epub 2008 Oct 30.
A quantitative structure-activity relationship study of a series of HIV-1 reverse transcriptase inhibitors (2-amino-6-arylsulfonylbenzonitriles and their thio and sulfinyl congeners) was performed. Topological and geometrical, as well as quantum mechanical energy-related and charge distribution-related descriptors generated from CODESSA, were selected to describe the molecules. Principal component analysis (PCA) was used to select the training set. Six techniques: multiple linear regression (MLR), multivariate adaptive regression splines (MARS), radial basis function neural networks (RBFNN), general regression neural networks (GRNN), projection pursuit regression (PPR) and support vector machine (SVM) were used to establish QSAR models for two data sets: anti-HIV-1 activity and HIV-1 reverse transcriptase binding affinity. Results showed that PPR and SVM models provided powerful capacity of prediction.
对一系列HIV-1逆转录酶抑制剂（2-氨基-6-芳基磺酰基苯甲腈及其硫代和亚磺酰基类似物）进行了定量构效关系研究。选择了由CODESSA生成的拓扑和几何描述符，以及与量子力学能量相关和电荷分布相关的描述符来描述分子。主成分分析（PCA）用于选择训练集。使用六种技术：多元线性回归（MLR）、多元自适应回归样条（MARS）、径向基函数神经网络（RBFNN）、广义回归神经网络（GRNN）、投影寻踪回归（PPR）和支持向量机（SVM），为两个数据集建立了定量构效关系模型：抗HIV-1活性和HIV-1逆转录酶结合亲和力。结果表明，PPR和SVM模型具有强大的预测能力。
