Quantitative structure-activity antimalarial relationships have been studied for 63 analogues of 2-aziridinyl and 2,3-bis(aziridinyl)-1,4-naphthoquinonyl sulfonate and acylate derivatives by means of multiple linear regression (MLR) and artificial neural networks (ANN). The antimalarial activity [-log(IC50x10(6))] of the compounds studied were well correlated with descriptors encoding the chemical structure. Using the pertinent descriptors revealed by a stepwise procedure in the multiple linear regression technique, a correlation coefficient of 0.9394 (s=0.2121) for the training set was obtained for the ANN model in a [3-5-1] configuration. The results show that the antimalarial activity of 2-aziridinyl and 2,3-bis(aziridinyl)-1,4-naphthoquinonyl sulfonate and acylate derivatives is strongly dependent on hydrophobic character, hydrogen-bond acceptors and also steric factors of the substituents.