QSAR of antilipid peroxidative activity of substituted benzodioxoles using chemometric tools

Interpretation of ANN-based QSAR models for prediction of antioxidant activity of flavonoids

Quantitative structure-activity relationships (QSARs) built using machine learning methods, such as artificial neural networks (ANNs) are powerful in prediction of (antioxidant) activity from quantum mechanical (QM) parameters describing the molecular structure, but are usually not interpretable. This obvious difficulty is one of the most common obstacles in application of ANN-based QSAR models for design of potent antioxidants or elucidating the underlying mechanism. Interpreting the resulting models is often omitted or performed erroneously altogether. In this work, a comprehensive comparative study of six methods (PaD, PaD₂ , weights, stepwise, perturbation and profile) for exploration and interpretation of ANN models built for prediction of Trolox-equivalent antioxidant capacity (TEAC) QM descriptors, is presented. Sum of ranking differences (SRD) was used for ranking of the six methods with respect to the contributions of the calculated QM molecular descriptors toward TEAC. The results show that the PaD, PaD₂ and profile methods are the most stable and give rise to realistic interpretation of the observed correlations. Therefore, they are safely applicable for future interpretations without the opinion of an experienced chemist or bio-analyst. © 2018 Wiley Periodicals, Inc.

Predictive chemometric modeling of DPPH free radical-scavenging activity of azole derivatives using 2D- and 3D-quantitative structure–activity relationship tools

Background: The endogenous antioxidants often fail to manage the systemic free radical overload resulting from extensive exposure to environmental pollutants and improper diet. Such free-radical burden over a prolonged period leads to oxidative stress, which in turn, promotes an array of fatal diseases. Results: Five different in silico methodologies have been employed here for a series of azole derivatives, which identify the essential structural attributes of the molecules and quantify the contributions of the prime molecular prerequisites for designing compounds with improved antioxidant activity. Conclusion: The importance of the different constituents is quantitatively analyzed using the descriptor-based quantitative structure–activity relationship and group-based quantitative structure–activity relationship models while the pharmacophore, comparative molecular similarity index analysis and hologram quantitative structure–activity relationship models serve as essential query tools for screening of azole compounds in order to select potent antioxidant molecules.