Toropov A A, Toropova A P, Raska I
Uzbek Academy of Sciences, Institute of Geology and Geophysics, Khodzhibaev street 49, 100041 Tashkent, Uzbekistan.
Eur J Med Chem. 2008 Apr;43(4):714-40. doi: 10.1016/j.ejmech.2007.05.007. Epub 2007 Jun 3.
Simplified molecular input line entry system (SMILES) has been utilized in constructing quantitative structure-property relationships (QSPR) for octanol/water partition coefficient of vitamins and organic compounds of different classes by optimal descriptors. Statistical characteristics of the best model (vitamins) are the following: n=17, R(2)=0.9841, s=0.634, F=931 (training set); n=7, R(2)=0.9928, s=0.773, F=690 (test set). Using this approach for modeling octanol/water partition coefficient for a set of organic compounds gives a model that is statistically characterized by n=69, R(2)=0.9872, s=0.156, F=5184 (training set) and n=70, R(2)=0.9841, s=0.179, F=4195 (test set).
简化分子线性输入规范（SMILES）已被用于通过优化描述符构建不同类别维生素和有机化合物的正辛醇/水分配系数的定量结构-性质关系（QSPR）。最佳模型（维生素）的统计特征如下：n = 17，R² = 0.9841，s = 0.634，F = 931（训练集）；n = 7，R² = 0.9928，s = 0.773，F = 690（测试集）。使用这种方法对一组有机化合物的正辛醇/水分配系数进行建模，得到一个统计特征为n = 69，R² = 0.9872，s = 0.156，F = 5184（训练集）和n = 70，R² = 0.9841，s = 0.179，F = 4195（测试集）的模型。
