Simultaneous prediction of the logarithmic capacity factor of aliphatic and aromatic compounds on five different stationary phases in reversed-phase liquid chromatography using artificial neural network

The main aim of the present work is a QSAR study based on multiple linear regressions (MLR) and artificial neural network (ANN) to prediction the retention behavior of solutes based on their structure. To this end, a data set of 65 aliphatic and aromatic compounds as solutes to five stationary phases (Zorbax SB-C18, Zorbax Rx-C18, Hypersil C18, Hypersil C8 and Zorbax C8) were analyzed to their structural descriptors and related to their retention behavior as expressed by the logarithms of their capacity factors (log kʹ). The selected descriptors that appeared in this model were selected by stepwise multiple regression (MLR). These descriptors together with Logarithms capacity factors of aliphatic and aromatic compounds in five different columns were used as inputs of constructed artificial neural network (ANN). Comparison between statistical results calculated for MLR and ANN model reveals that all statistics have improved considerably in case of ANN model. The improved statistics by the ANN would suggest the existence of nonlinear relation between selected molecular descriptors and their retention in reverse phase high performance liquid chromatography.