Computer-aided design of novel antibacterial 3-hydroxypyridine-4-ones: application of QSAR methods based on the MOLMAP approach

Abstract

3-Hydroxypyridine-4-one derivatives have shown good inhibitory activity against bacterial strains. In this work we report the application of MOLMAP descriptors based on empirical physicochemical properties with genetic algorithm partial least squares (GA-PLS) and counter propagation artificial neural networks (CP-ANN) methods to propose some novel 3-hydroxypyridine-4-one derivatives with improved antibacterial activity against Staphylococcus aureus. A large collection of 302 novel derivatives of this chemical scaffold was selected for this purpose. The activity classes of these compounds were determined using the two quantitative structure activity relationships models. To evaluate the predictability and accuracy of the obtained models, nineteen compounds belonging to all three activity classes were prepared and the activity of them was determined against S. aureus. Comparing the experimental results and the predicted activity classes revealed the accuracy of the obtained models. Seventeen of the nineteen synthesized molecules were correctly predicted by GA-PLS model according to the antimicrobial evaluation method. Molecules 5f and 5h proved to be moderately active and active experimentally, but were predicted as inactive and moderately active compounds, respectively by this model. The CP-ANN based prediction was correct for sixteen out of the nineteen synthesized molecules. 5a, 5h and 5q were moderately active and active based on the antimicrobial assays, but they were introduced as members of inactive, moderately active and inactive classes of compounds, respectively according to CP-ANN model.

QSAR and docking studies of some 1,2,3,4-tetrahydropyrimidines: evaluation of gp41 as possible target for anti-HIV-1 activity

“…When the receptor structure is not available, the information which the ligands carry sheds light on the drug design and discovery plans. Defining statistical models which describe the dependence of the biological properties to the structural features of the bioactive compounds, quantitative structure activity relationship (QSAR) studies, are the most known examples of ligand-based approaches (Sabet et al, 2012;Mansourian et al, 2013;Macchiarulo et al, 2004;Mishra et al, 2014). Each of these approaches has advantages and disadvantages.…”

Chemometrics tools in QSAR/QSPR studies: A historical perspective

“…The purpose of feature extraction is finding the best linear/ nonlinear combination of features based on a dimensionality reduction approaches [310][311][312][313]. Principal component analysis (PCA) [310,314], Rényientropy [315], hierarchical discriminate regression (HDR) [316], independent component analysis (ICA) [317], multidimensional scaling (MDS) [318], partial least squares (PLS) [319], nonlinear mapping (NLM) [320,321] and molecular maps (MOLMAP) [322][323][324] are the mostly applied feature extraction techniques.…”

Machine‐Learning Techniques Applied to Antibacterial Drug Discovery

“…In 2012, Sabet et al (29) studied thirty-one 3-hydroxypyridine-4-one and 3-hydroxypyran-4-one antibiotics, known chelators that act by depriving bacteria of iron cations. An ANN was trained to use bond-based physiochemical (MOLMAP) molecular descriptors to classify these 31 compounds by their experimentally determined MIC values.…”