Fatemi M H, Karimian F
Department of Chemistry, University of Mazandaran, Babolsar, Iran.
J Colloid Interface Sci. 2007 Oct 15;314(2):665-72. doi: 10.1016/j.jcis.2007.06.047. Epub 2007 Jun 29.
The micelle-water partition coefficients of 81 organic compounds in SDS solution were predicted by quantitative structure-property relationship method. The multiple linear regression (MLR) and artificial neural network (ANN) techniques were used to build linear and nonlinear model, respectively. In this work the proposed QSPR models, both by MLR and ANN, contain identical descriptors which are zero order of Kier-Hall index, count of Hydrogen donors site [Zefirovs PC], average valency of a C atom, atomic charge weighted by partial positively charged surface area and minimum one electron reaction index for a C atom. The MLR model gave a root mean square (RMS) of 0.166, 0.25, and 0.289 for training, prediction and test sets, respectively, whereas ANN gave an RMS error of 0.06, 0.21, and 0.20 for training, prediction, and test sets, respectively. Comparison the results of these two methods reveals that those obtained by the ANN model are much better.
采用定量结构-性质关系方法预测了81种有机化合物在十二烷基硫酸钠（SDS）溶液中的胶束-水分配系数。分别运用多元线性回归（MLR）和人工神经网络（ANN）技术构建线性和非线性模型。在本研究中，由MLR和ANN提出的定量结构-性质关系（QSPR）模型包含相同的描述符，即基尔-霍尔指数的零阶、氢供体位点计数[泽菲罗夫斯PC]、碳原子的平均化合价、由部分带正电表面积加权的原子电荷以及碳原子的最小单电子反应指数。MLR模型在训练集、预测集和测试集上的均方根（RMS）分别为0.166、0.25和0.289，而ANN在训练集、预测集和测试集上的均方根误差分别为0.06、0.21和0.20。对这两种方法的结果进行比较可知，ANN模型得到的结果要好得多。
