Format

Send to

Choose Destination
Cell. 2019 May 30;177(6):1649-1661.e9. doi: 10.1016/j.cell.2019.04.016. Epub 2019 May 9.

A White-Box Machine Learning Approach for Revealing Antibiotic Mechanisms of Action.

Author information

1
Institute for Medical Engineering and Science and Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA.
2
Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA.
3
Novo Nordisk Foundation Center for Biosustainability, Technical University of Denmark, 2800 Lyngby, Denmark.
4
Institute for Medical Engineering and Science and Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA; Wyss Institute for Biologically Inspired Engineering, Harvard University, Boston, MA 02115, USA.
5
Department of Biomedical Engineering, Boston University, Boston, MA 02215, USA.
6
Novo Nordisk Foundation Center for Biosustainability, Technical University of Denmark, 2800 Lyngby, Denmark; Department of Bioengineering, University of California, San Diego, La Jolla, CA 92093, USA.
7
Department of Biology, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
8
Institute for Medical Engineering and Science and Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA; Wyss Institute for Biologically Inspired Engineering, Harvard University, Boston, MA 02115, USA. Electronic address: jimjc@mit.edu.

Abstract

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 to 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 purine biosynthesis participates in antibiotic lethality, which we validate experimentally. We show that antibiotic-induced adenine limitation increases ATP demand, which elevates central carbon metabolism activity and oxygen consumption, enhancing the killing effects of antibiotics. This work demonstrates how prospective network modeling can couple with machine learning to identify complex causal mechanisms underlying drug efficacy.

KEYWORDS:

ATP; LC-MS/MS; NADPH:NADP(+) ratio; adenylate energy charge; antibiotics; biochemical screen; machine learning; metabolism; network modeling; purine biosynthesis

PMID:
31080069
PMCID:
PMC6545570
[Available on 2020-05-30]
DOI:
10.1016/j.cell.2019.04.016
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center