A quantitative structure activity relationship study on HIV-1integrase inhibitors

Quantitative structure activites relationship (QSAR) study has been done on Dihydro pyrimidin 4- carboxamide and diketo analogues acting as HIV-1 integrase inhibitos. Genetic algorithm (GA), artificial neural network (ANN) and multiple linear regression (MLR) were used to create the non-linear and linear QSAR models. GA-ANN model was much better than other models. The root-mean-square errors of the training set and the test set for Dihydro pyrimidine 4-carboxamide GA-ANN model using jack-knife were 0.1465, 0.9568, R2=0.82, respectively. For diketo compounds were 0.1403, 0.2248, R2 = 0.70, respectively.

کلیدواژه ها:

QSAR ، Dihydro pyriminine ، Genetic Algorithm ، Diketo acid ، Diketo ester ، HIV-1 inhibitors