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

At present study, quantitative structure activites relationship (QSAR) study has been done on eighteen chemical compounds of diketo benzylindole analogues as HIV-1 integrase inhibitors. Genetic algorithm (GA), artificial neural network (ANN), multiple linear regression (MLR), partial least squares (PLS), principal component regression (PCR), and least absolute shrinkage and selection operator (LASSO) were used to create QSAR models. It revealed that GA-ANN model was much better than other models. For this purpose, ab initio geometry optimization performed at B3LYP level with a known basis set 6-31G (d). Hyperchem, Chemoffice ,Gaussian 03 softwares and dragon were used for geometry optimization of the molecules and calculation of the quantum chemical descriptors. The root- mean- square errors of the training set and the test set for benzylindole GA- ANN model using Jack-Knife were 0.1378, 0.4512, with R2=0.82, respectively. The six most significant descriptors which were selected by GA are as follows: D/D ,X3, A4X,SIC3, X3, BAC

کلیدواژه ها:

QSAR ، Genetic Algorithm ، Artificial Neural Network ، Diketo benzylindole ، HIV-1 inhibitors