A comparative QSAR study of aryl-substituted isobenzofuran-1(3H)-ones inhibitors

A comparative workflow, including linear and nonlinear QSAR models, was carried out to evaluate the predictive accuracy of models and predict the inhibition activity of a series of arylsubstituted isobenzofuran1(3H)ones. The data set consisted of 34 compounds was classified into the training and test sets, randomly. Molecular descriptors were selected using the genetic algorithm (GA) as a feature selection tool. Various linear models based on multiple linear regression (MLR), principle component regression (PCR) and partial least square (PLS) and nonlinear models based on artificial neural network (ANN), adaptive networkbased fuzzy inference system (ANFIS) and support vector machine (SVM) methods were developed and compared. The accuracy of the models was studied by leaveoneout crossvalidation (Q_LOO^2), Yrandomization test and group of compounds as external test set. Six descriptors were selected by GA to develop predictive models. With respect to the linear models, GAPCR method was more accurate than the reset with statistical results of 〖 R〗_train^2=0.883, R_test^2=0.897,〖 R〗_(adj,train)^2=0.829,〖 R〗_(adj,test)^2=0.849,〖 F〗_train=24.07 and F_test=34.17. In case of nonlinear models, GASVM (R_train^2=0.992 and R_test^2=0.997) showed high predictive accuracy for the inhibitory activity. It was found that the selected descriptors have the major roles in interpretation of biological activities of the compounds.