Quantitative Structure–Micellization Relationship Study of Gemini Surfactants Using Genetic‐PLS and Genetic‐MLR

Abstract

AbstractA Quantitative structure‐property relationship analysis had been applied to a set of gemini surfactants which were of special interest because of their roles in environmental samples. Modeling of the critical micelle concentrations (CMC) of 94 gemini surfactants as a function of their theoretically‐derived descriptors (i.e. topological indices) was established by means of multiple linear regression (MLR) and partial least squares (PLS) regression methods. The genetic algorithm was used to find a set of descriptors that resulted in the best‐fitted models. The results showed that both MLR (with 9 selected descriptors) and PLS (with 20 selected descriptors) methods could model the relationship between CMC of gemini surfactants and their topological descriptors perfectly. However, better results obtained by PLS regression. The stability and validity of models were tested by cross‐validation technique and by prediction of the response values for the prediction set. The average relative error of prediction for the best MLR and PLS models, was equal to 2.94 and 0.36, respectively. Also, the respective squares of correlation coefficients of these models were 0.979 and 0.985.