芳香/杂环磺胺类碳酸酐酶Ⅱ抑制剂的活性定量预测(英文)

In silico prediction of the inhibitory activity of aromatic/ heterocyclic sulfonamides inhibitors of human carbonic anhydrase Ⅱ

对125个磺胺类碳酸酐酶Ⅱ抑制剂的生物活性进行了预测研究。利用ADRIANA.Code软件计算得到了化合物的一系列2D和3D结构描述符,从中选用了12个描述符进行建模。分别用数学随机划分的方法和Kohonen自组织神经网络的方法把数据集划分成两组不同的训练集和测试集。对于这两组不同的训练集和测试集,分别利用多元线性回归(MLR)和支持向量机(SVM)的方法进行建模,共得到4个模型。其中SVM得到的2个模型,训练集的相关系数在0.92以上,测试集预测的相关系数都在0.90以上。所有模型可进一步用于碳酸酐酶Ⅱ抑制剂的虚拟筛选。

Several quantitative models for the prediction of inhibitory activity of the 125 sulfonamide inhibitors of human carbonic anhydrase II （hCA Ⅱ） enzyme were developed. The molecules were represented by 12 selected 2D and 3D molecular descriptors calculated by the ADRIANA.Code. The whole dataset was split into a training set and a test set using two different methods： （1） by a random selection; and （2） on the basis of a Kohonen＇s self-organizing map （SOM）. Then the inhibitory activity of the sulfonamide inhibitors ofhCA II was predicted using a multilinear regression （MLR） analysis and a support vector machine （SVM）. For the two SVM models, for the training sets, both the correlation coefficients of 0.92 were obtained; for the test sets, the correlation coefficients of over 0.90 were achieved. All models obtained in this study could be used to for further virtual screening research of inhibitors of human carbonic anhydrase Ⅱ.