QSAR analysis for some diaryl-substituted pyrazoles as CCR2 inhibitors by GA-stepwise MLR

Quantitative relationships between calculated molecular structure and 26 diaryl-substituted pyrazoles CCR2 inhibitors were investigated by GA-stepwise multiple linear regression. In multiple linear regression analysis, the quantitative structure-activity relationship models were constructed by grouping descriptors and also dual selection of variables using genetic algorithm and stepwise selection methods from each group of the pool of all calculated descriptors. The accuracy of the proposed multiple linear regression model was demonstrated using the following evaluation techniques: cross-validation, validation through an external test set, and Y-randomization. Furthermore, the domain of applicability that shows the area of reliable predictions was defined. The prediction results were in good agreement with the experimental values.