Prediction of hydrophile-lipophile balance values of anionic surfactants using a quantitative structure-property...

A quantitative structure-property relationship study was performed on the hydrophile-lipophile balance (HLB) values of anionic surfactants. Stepwise multiple linear regression (MLR) and nonlinear radial basis function neural network (RBFNN) were used to build the models. A four-descriptor equation with the squared correlation coefficient (R(2)) of 0.983 and root mean square error (RMS) of 1.7309 were obtained for the training set, and R(2)=0.989, RMS=1.3509 for the external test set. The RBFNN model gave better results: R(2)=0.997, RMS=0.6750 for the training set and R(2)=0.991, RMS=1.1895 for test set. The QSPR model established may provide a new powerful method for predicting HLB values of anionic surfactants.