PM3 semi-empirical method was used to develop the quantitative structure-activity relationship (QSAR) for predicting the anticonvulsant activity of some acetamido-N-benzylacetamide derivative. In order to to find the optimized geometry of the studied molecules, three types of molecular descriptors were used in deriving quantitative relation between anticonvulsant activity and structural properties. The relevant molecular descriptors were selected by Genetic Function Algorithm (GFA). The optimum model has squared correlation coefficient (R)2 value of 0.98, adjusted squared correlation coefficient (R2adj ) value of 0.98, Leave one out (LOO) cross validation coefficient (Q2) value of 0.96. The external set used for confirming the predictive power of the model has its R2pred = 0.89. These confirm the stability, robustness and predictability of the model.
