Ghasemi Jahanbakhsh, Ahmadi Shahin
Chemistry Department, Faculty of Sciences, Razi University, Kermanshah, Iran.
Ann Chim. 2007 Jan-Feb;97(1-2):69-83. doi: 10.1002/adic.200690087.
Quantitative structure-property relationship (QSPR) analysis has been directed to a series of pure nonionic surfactants containing linear alkyl, cyclic alkyl, and alkey phenyl ethoxylates. Modeling of cloud point of these compounds as a function of the theoretically derived descriptors was established by multiple linear regression (MLR) and partial least squares (PLS) regression. In this study, a genetic algorithm (GA) was applied as a variable selection method in QSPR analysis. The results indicate that the GA is a very effective variable selection approach for QSPR analysis. The comparison of the two regression methods used showed that PLS has better prediction ability than MLR.
定量结构-性质关系（QSPR）分析针对的是一系列含有直链烷基、环烷基和烷基苯基乙氧基化物的纯非离子表面活性剂。通过多元线性回归（MLR）和偏最小二乘（PLS）回归建立了这些化合物的浊点与理论推导描述符之间的函数关系模型。在本研究中，遗传算法（GA）被用作QSPR分析中的变量选择方法。结果表明，GA是一种非常有效的QSPR分析变量选择方法。对所使用的两种回归方法的比较表明，PLS比MLR具有更好的预测能力。
