TAS2R receptor response helps predict new antimicrobial molecules for the 21stcentury

Abstract

AbstractArtificial intelligence (AI) requires the provision of learnable data to successfully deliver requisite prediction power. In this article, it is demonstrable that standard physico-chemical parameters, while useful, were insufficient for development of powerful antimicrobial prediction algorithms. Initial models that focussed solely on the values extractable from the knowledge on the electrotopological, structural, constitutional descriptors did not meet the acceptance criteria for classifying antimicrobial activity. In contrast, efforts to conceptually define the diametric opposite of an antimicrobial compound helped to advance the category description into a learnable trait. Interestingly, the inclusion of ligand-receptor information using the ability of the molecules to stimulate transmembrane TAS2R receptor helped to increase the ability to distinguish antimicrobial molecules from the inactive ones. This novel approach to the development of AI models has allowed the development of models for the design and selection of newer, more powerful antimicrobial agents. This is especially valuable in an age where antimicrobial resistance could be ruinous to modern health systems.