Prediction of the electrophoretic mobilities of some carboxylic acids from theoretically derived descriptors

A 4-4-1 artificial neural network was constructed and trained for the prediction of the electrophoretic mobilities of some aliphatic and aromatic carboxylic acids based on quantitative structure–property relationships. The inputs of this network are theoretically derived descriptors that were chosen by the stepwise variables selection techniques. These descriptors are: shape factor, molecular surface area, the maximum value of electron density on atom in molecule, and the sum of atomic polarizability. In order to assess the accuracy and predictability of the proposed model, the cross-validation test was employed. The results obtained showed the ability of developed artificial neural network to prediction of electrophoretic mobilities of aliphatic and carboxylic acids. Also result reveals the superiority of the artificial neural network over the multiple linear regression models.