用多元线性回归分析和支持向量机预测 ACAT2 抑制剂的生物活性。
Prediction of bioactivity of ACAT2 inhibitors by multilinear regression analysis and support vector machine.
机构信息
State Key Laboratory of Chemical Resource Engineering, Department of Pharmaceutical Engineering, Beijing University of Chemical Technology, P.O. Box 53, 15 BeiSanHuan East Road, Beijing 100029, China.
出版信息
Bioorg Med Chem Lett. 2013 Jul 1;23(13):3788-92. doi: 10.1016/j.bmcl.2013.04.087. Epub 2013 May 9.
Two quantitative structure-activity relationships (QSAR) models for predicting 95 compounds inhibiting Acyl-coenzyme A: cholesterol acyltransferase2 (ACAT2) were developed. The whole data set was randomly split into a training set including 72 compounds and a test set including 23 compounds. The molecules were represented by 11 descriptors calculated by software ADRIANA.Code. Then the inhibitory activity of ACAT2 inhibitors was predicted using multilinear regression (MLR) analysis and support vector machine (SVM) method, respectively. The correlation coefficients of the models for the test sets were 0.90 for MLR model, and 0.91 for SVM model. Y-randomization was employed to ensure the robustness of the SVM model. The atom charge and electronegativity related descriptors were important for the interaction between the inhibitors and ACAT2.
建立了两个预测 95 种抑制酰基辅酶 A：胆固醇酰基转移酶 2（ACAT2）化合物的定量构效关系（QSAR）模型。整个数据集被随机分为一个包含 72 种化合物的训练集和一个包含 23 种化合物的测试集。分子由软件 ADRIANA.Code 计算的 11 个描述符表示。然后，分别使用多元线性回归（MLR）分析和支持向量机（SVM）方法预测 ACAT2 抑制剂的抑制活性。对于测试集，模型的相关系数分别为 MLR 模型的 0.90 和 SVM 模型的 0.91。Y 随机化用于确保 SVM 模型的稳健性。原子电荷和电负性相关描述符对于抑制剂与 ACAT2 之间的相互作用很重要。
Zotero 插件