Abstarct: In this project, quantitative structure–activity relationship studies was conducted on the inhibition constant (ki) of 77 drug compounds of Piperazinyl Glutamate Pyridine derivatives as Inhibition of platelet aggregation. The stepwise multiple linear regression method was used to select the most important descxriptors. Then selected descxriptors were used as input for QSAR model generation using multiple linear regression) MLR( and artificial neural network)ANN(. The validation of the MLR and ANN models was performed using test set, leave-one-out and Y-Randomization techniques. The obtained results are shown, determination coefficients for prediction of inhibition constant of the test set by MLR and ANN models were 0.9458 and 0.9661 respectively. In the second part of this study, MLR and ANN methods were used for modeling and accurate prediction of anti–HIV activities for a some of 5,6-Dihydroxypyrimidine-4-carboxamide derivatives. Training set was used in the selection the best MLR and ANN models by cross validation technique. The determination coefficient obtained for the test set by MLR and ANN models were o.9836 and 0.9837 respectively. The results obtained are shown proper prediction power of proposed models.