PREDICTION OF BIOLOGICAL ACTIVITY OF PYRAZOLO [3, 4-B] QUINOLINYL ACITAMIDE BY QSAR RESULTS
Larbi Elmchichi, Adnane Aouidate, Fatima Zahra El Chokrafi, Adib Ghaleb, Fouad Khalil, Tahar Lakhlifi, Mohammed Bouachrıne · RHAZES: Green and Applied Chemistry · 2018
In search to discovery newer drugs for treatment of cancer, we performed a QSAR study on a series of pyrazolo [3,4-b] quinolinyl acetamide composed of 18 molecules, to predict the anticancer activity of these compounds, and to find a correlation between the biological activity and the various descriptors, using principal components analysis(PCA), multiple linear regression (MLR), multiple non-linear regression (MNLR) and the artificial neural network (ANN). The used descriptors were computed, with ACD/ChemSketch and ChemBioDraw Ultra 14.0 programs. The best generated MLR and MNLR models exhibit determination coefficients R2 of 0.88 and 0.91 as well as the Leave One Out cross validation determination coefficients Q2 of 0.77 and 0.59, respectively. Moreover, the predictive ability of those models was evaluated by the external validation using a test set of four compounds with predicted determination coefficients R2test of 0.97 and 0.87, respectively. The artificial neural network (ANN) method, showed a correlation coefficient of 0.896 with an architecture 3-2-1. The results obtained from this study show that the topological descriptors and the various calculated parameters are sufficient to predict the biological activity of derivatives of pyrazolo[3, 4-b] quinolinyl acetamide