QSAR Study on Anti-HIV-1 Activity of 4-Oxo-1,4-dihydroquinoline and 4-Oxo-4H-pyrido[1,2-a]pyrimidine Derivatives Using SW-MLR, Artificial Neural Network and Filtering Methods

Abstract

Predictive quantitative structure–activity relationship was performed on the novel 4-oxo-1,4-dihydroquinoline and 4-oxo-4H-pyrido[1,2-a]pyrimidine derivatives to explore relationship between the structure of synthesized compounds and their anti-HIV-1 activities. In this way, the suitable set of the molecular descriptors was calculated and the important descriptors using the variable selections of the stepwise technique were selected. Multiple linear regression (MLR) and artificial neural network (ANN) as nonlinear system were used for constructing QSAR models. The predictive quality of the quantitative structure–activity relationship models was tested for an external set of five compounds, randomly chosen out of 25 compounds. The findings exhibited that stepwise-ANN model was more efficient at prediction activity of both training and test sets with high statistical qualities. Based on QSAR models results, electronegativity, the atomic masses, the atomic van der Waals volumes, the molecular symmetry and polarizability were found to be important factors controlling the anti-HIV-1 activity.