Faculty Opinions recommendation of A White-Box Machine Learning Approach for Revealing Antibiotic Mechanisms of Action.
JENS KVIST NIELSEN · Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature · 2019
Current machine learning techniques enable robust association of biological signals with measured phenotypes, but these approaches are incapable of identifying causal relationships.Here we develop an integrated "white-box" biochemical screening, network modeling and machine learning approach for revealing causal mechanisms and apply this approach towards understanding antibiotic efficacy.We counter-screen diverse metabolites against bactericidal antibiotics in Escherichia coli and simulate their corresponding metabolic states using a genome-scale metabolic network model.Regression of the measured screening data on model simulations reveals that