QSAR Study of Artemisinin Analogues as Antimalarial Drugs by Neural Network and Replacement Method

Abstract

AbstractQuantitative structure–activity relationship (QSAR) models were derived for 179 analogues of artemisinin, a potent antimalarial agent. Molecular descriptors derived solely from molecular structure were used to represent molecular structure. Utilizing replacement method, a subset of 11 descriptors was selected. General regression neural network (GRNN) was used to construct the nonlinear QSAR models in all stages of study. The relative standard error percent in antimalarial activity predictions for the training set by the application of cross-validation (RMSE-CV) was 0.43, and for test set (RMSEtest) was 0.51. GRNN analysis yielded predicted activities in the excellent agreement with the experimentally obtained values (R2training = 0.967 and R2test = 0.918). The mean absolute error for the test set was computed as 0.4115.