Prediction of the antimicrobial activity of quaternary ammonium salts against Staphylococcus aureus using artificial neural networks

The study of the quantitative structure-activity relationship (QSAR) on antibacterial activity in a series of new imidazole derivatives against Staphylococcus aureus was conducted using artificial neural networks (ANNs). Antibacterial activity against S. aureus was associated with a number of physicochemical and structural parameters of the examined imidazole derivatives. The designed regression and classification models were useful in determining the antibacterial properties of quaternary ammonium salts against S. aureus. The developed models of artificial neural networks were characterized by high predictability (93.57% accuracy of classification, regression model: training data R = 0.92, test data R = 0.92, validation data R = 0.91). ANNs are considered to be a useful tool in supporting the design of synthesis and further biological experiments in the logical search for new antimicrobial substances. Data analysis using ANNs enables the optimization and reduction of labor costs by narrowing the compound synthesis to achieve the desired properties. (c) 2021 The Author(s). Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Automated summary

The study utilized artificial neural networks to investigate the antibacterial activity of imidazole derivatives against Staphylococcus aureus, resulting in the development of highly predictive regression and classification models. These models proved useful in determining the antibacterial properties of quaternary ammonium salts against S. aureus, showcasing the potential of ANNs in supporting synthesis design and the search for new antimicrobial substances.