Quantitative Structure Property Relationships Study of Mobility of Some Benzoaromatic Carboxylate Derivatives by Partial Least Squares and Least-square Support Vector Machine

Abstract

A quantitative structure-property relationship (QSPR) study is suggested for the prediction of mobilities (m) of benzoaromatic carboxylates. Ab initio theory was used to calculate some quantum chemical descriptors including electrostatic potentials and local charges at each atom, HOMO and LUMO energies, etc. Also, Dragon software was used to calculate some descriptors such as WIHM and GETAWAY. Modeling of the mobility of benzoaromatic carboxylate derivatives as a function of molecular structures was established by means of the least squares support vector machines (LS-SVM). This model was applied for the prediction of the mobility of benzoaromatic carboxylates, which were not in the modeling procedure. The resulted model showed high prediction ability with root mean square error of prediction (RMSEP) of 3.734, 1.931 and 0.018 for MLR, PLS and LS-SVM, respectively. Results have shown that the introduction of LS-SVM for quantum chemical, WIHM and GETAWAY descriptors drastically enhances the ability of prediction in QSAR studies superior to multiple linear regression (MLR) and partial least squares (PLS).