Determination of partitioning of drug molecules using immobilized liposome chromatography and chemometrics methods

The quantitative structure-property relationship (QSPR) of drug molecules against the immobilized liposome chromatography partitioning (log Ks) was studied. The genetic algorithm (GA) was employed to select the variables that resulted in the best-fitted models. After the variables were selected, the linear multivariate regressions (e.g. partial least squares (PLS)) as well as the non-linear regressions (e.g. the kernel PLS (KPLS) and Levenberg-Marquardt artificial neural network (L-M ANN)) were utilized to construct the linear and non-linear QSPR models. The correlation coefficient cross validation (Q2) and relative error for calibration, prediction and test sets L-M ANN model are (0.987, 0.971, 0.952) and (3.14, 3.54, 6.61), respectively. The obtained results using L-M ANN were compared with those of GA-PLS and GA-KPLS, exhibiting that the L-M ANN model demonstrated a better performance than that of the other models. This is the first research on the QSPR of the drug molecules against the log Ks using the GA-KPLS and L-M ANN. Copyright (c) 2011 John Wiley & Sons, Ltd.