Identification of dual-targeted Mycobacterium tuberculosis aminoacyl-tRNA synthetase inhibitors using machine learning

Abstract

Background: The most serious challenge in the treatment of tuberculosis is the multidrug resistance of Mycobacterium tuberculosis to existing antibiotics. As a strategy to overcome resistance we used a multitarget drug design approach. The purpose of the work was to discover dual-targeted inhibitors of mycobacterial LeuRS and MetRS with machine learning. Methods: The artificial neural networks were built using module nnet from R 3.6.1. The inhibitory activity of compounds toward LeuRS and MetRS was investigated in aminoacylation assays. Results: Using a machine-learning approach, we identified dual-targeted inhibitors of LeuRS and MetRS among 2-(quinolin-2-ylsulfanyl)-acetamide derivatives. The most active compound inhibits MetRS and LeuRS with IC50 values of 33 μm and 23.9 μm, respectively. Conclusion: 2-(Quinolin-2-ylsulfanyl)-acetamide scaffold can be useful for further research.