Exploring QSARs for Inhibitory Activity of Cyclic Urea and Nonpeptide-Cyclic Cyanoguanidine Derivatives HIV-1 Protease Inhibitors by Artificial Neural Network

Abstract

Quantitative structure–activity relationship study using artificial neural network (ANN) methodology were conducted to predict the inhibition constants of 127 symmetrical and unsymmetrical cyclic urea and cyclic cyanoguanidine derivatives containing different substituent groups such as: benzyl, isopropyl, 4-hydroxybenzyl, ketone, oxime, pyrazole, imidazole, triazole and having anti-HIV-1 protease activities. The results obtained by artificial neural network give advanced regression models with good prediction ability. The two optimal artificial neural network models obtained have coefficients of determination of 0.746 and 0.756. The lowest prediction’s root mean square error obtained is 0.607. Artificial neural networks provide improved models for heterogeneous data sets without splitting them into families. Both the external and cross-validation methods are used to validate the performances of the resulting models. Randomization test is employed to check the suitability of the models.