We have assembled and piloted a chemical biology pipeline for identifying components of bacterial metabolism that contribute to antibiotic tolerance and susceptibility. We counterscreened bactericidal antibiotics against different metabolites in E. coli and observed that metabolic supplementation significantly altered antibiotic sensitivity in a drug-class specific manner. Genome-scale metabolic modeling was performed to estimate metabolic states associated with each metabolic perturbation and machine learning was applied to predict consensus pathways that may underlie antibiotic sensitivity across drug classes. These studies identified drug transport, central metabolism, and serine metabolism as candidate pathways, each of which was validated by published data in the literature. This pipeline is now being scaled up to identify metabolic components specific to the four major antibiotics used to treat M. tuberculosis.