Send to

Choose Destination
Drug Test Anal. 2012 Feb;4(2):151-7. doi: 10.1002/dta.262. Epub 2011 Mar 25.

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

Author information

Faculty of Sciences, Islamic Azad University, Ilam Branch, Ilam, Iran.


The quantitative structure-property relationship (QSPR) of drug molecules against the immobilized liposome chromatography partitioning (log K(s)) 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 (Q(2)) 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 K(s) using the GA-KPLS and L-M ANN.

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Wiley
Loading ...
Support Center