Herein, we present a validated predictive QSAR model to provide more insight into the relationship between the molecular properties of diketo acid and carboxamide derivatives as well as HIV-I integrase inhibition. A set of 40 diketo acid and carboxamide derivatives possessing integrase inhibitory activity was subjected to 2D-QSAR using Discovery studio V3.5. The QSAR results presented here were based on a genetic function algorithm (GFA) approach. Logarithmic inverse values of IC50 (µM) were taken as the dependent variables, and physicochemical parameters were taken as the independent variable. A suitable set of molecular descriptors was calculated using GFA approach (max 500 generations). Results showed that radius of gyration, Zagreb index, Wiener index and minimized energy are statistically significant with the correlation coefficient value of 0.820 and play an important role in HIV-1 integrase inhibition.