Prediction of partition coefficient of some 3-hydroxy pyridine-4-one derivatives using combined partial least square regression and genetic algorithm

A quantiatative structure property relationship (QSPR) treatment was used to a data set consisting of diverse 3-hydroxypyridine-4-one derivatives to relate the logarithmic function of octanol:water partition coefficients (denoted by log po/w) with theoretical molecular descriptors. Evaluation of a test set of 6 compounds with the developed partial least squares (PLS) model revealed that this model is reliable with a good predictability. Since the QSPR study was performed on the basis of theoretical descriptors calculated completely from the molecular structures, the proposed model could potentially provide useful information about the activity of the studied compounds. Various tests and criteria such as leave-one-out cross validation, leave-many-out cross validation, and also criteria suggested by Tropsha were employed to examine the predictability and robustness of the developed model.