Abstract
The goal of this research is to promote the growth of predictive QSAR models of 4-anilinoquinazoline and derivatives against EGFR kinase using several statistical techniques especially principal components analysis (PCA), multiple linear regression (MLR) and nonlinear regression (RNLM) calculations. We choose the validation method to examine the execution and the equilibrium of this model. We accordingly propose a quantitative model (non-linear and linear QSAR models), and we interpret the activity of the compounds relying on the multivariate statistical analysis. The topological descriptors were computed, respectively, with ACD/ChemSketch and MarvinSketch programs. The electronic descriptors were computed with Gaussian 09. This study demonstrates that multiple regression and multiple non-linear regression analyses predict well the studied activity. Statistically speaking, a very important outcome was given by this model and a good stability to data variation in leave-one-out cross-validation was shown.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call