A White-Box Machine Learning Approach for Revealing Antibiotic Mechanisms of Action
© 2019 Elsevier Inc. 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 l...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Elsevier BV
2021
|
| Online Access: | https://hdl.handle.net/1721.1/135182 |
| _version_ | 1811082875858059264 |
|---|---|
| author | Yang, Jason H Wright, Sarah N Hamblin, Meagan McCloskey, Douglas Alcantar, Miguel A Schrübbers, Lars Lopatkin, Allison J Satish, Sangeeta Nili, Amir Palsson, Bernhard O Walker, Graham C Collins, James J |
| author2 | Massachusetts Institute of Technology. Institute for Medical Engineering & Science |
| author_facet | Massachusetts Institute of Technology. Institute for Medical Engineering & Science Yang, Jason H Wright, Sarah N Hamblin, Meagan McCloskey, Douglas Alcantar, Miguel A Schrübbers, Lars Lopatkin, Allison J Satish, Sangeeta Nili, Amir Palsson, Bernhard O Walker, Graham C Collins, James J |
| author_sort | Yang, Jason H |
| collection | MIT |
| description | © 2019 Elsevier Inc. 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. Causal metabolic pathways underlying antibiotic lethality in bacteria are illuminated by a network model-driven machine learning approach, overcoming limitations of existing “black-box” approaches that cannot reveal causal relationships from large biological datasets. |
| first_indexed | 2024-09-23T12:11:21Z |
| format | Article |
| id | mit-1721.1/135182 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T12:11:21Z |
| publishDate | 2021 |
| publisher | Elsevier BV |
| record_format | dspace |
| spelling | mit-1721.1/1351822024-03-20T19:57:53Z A White-Box Machine Learning Approach for Revealing Antibiotic Mechanisms of Action Yang, Jason H Wright, Sarah N Hamblin, Meagan McCloskey, Douglas Alcantar, Miguel A Schrübbers, Lars Lopatkin, Allison J Satish, Sangeeta Nili, Amir Palsson, Bernhard O Walker, Graham C Collins, James J Massachusetts Institute of Technology. Institute for Medical Engineering & Science Massachusetts Institute of Technology. Department of Biological Engineering Massachusetts Institute of Technology. Department of Biology © 2019 Elsevier Inc. 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. Causal metabolic pathways underlying antibiotic lethality in bacteria are illuminated by a network model-driven machine learning approach, overcoming limitations of existing “black-box” approaches that cannot reveal causal relationships from large biological datasets. 2021-10-27T20:11:08Z 2021-10-27T20:11:08Z 2019 2020-06-19T17:13:01Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/135182 en 10.1016/J.CELL.2019.04.016 Cell Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier BV PMC |
| spellingShingle | Yang, Jason H Wright, Sarah N Hamblin, Meagan McCloskey, Douglas Alcantar, Miguel A Schrübbers, Lars Lopatkin, Allison J Satish, Sangeeta Nili, Amir Palsson, Bernhard O Walker, Graham C Collins, James J A White-Box Machine Learning Approach for Revealing Antibiotic Mechanisms of Action |
| title | A White-Box Machine Learning Approach for Revealing Antibiotic Mechanisms of Action |
| title_full | A White-Box Machine Learning Approach for Revealing Antibiotic Mechanisms of Action |
| title_fullStr | A White-Box Machine Learning Approach for Revealing Antibiotic Mechanisms of Action |
| title_full_unstemmed | A White-Box Machine Learning Approach for Revealing Antibiotic Mechanisms of Action |
| title_short | A White-Box Machine Learning Approach for Revealing Antibiotic Mechanisms of Action |
| title_sort | white box machine learning approach for revealing antibiotic mechanisms of action |
| url | https://hdl.handle.net/1721.1/135182 |
| work_keys_str_mv | AT yangjasonh awhiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT wrightsarahn awhiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT hamblinmeagan awhiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT mccloskeydouglas awhiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT alcantarmiguela awhiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT schrubberslars awhiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT lopatkinallisonj awhiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT satishsangeeta awhiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT niliamir awhiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT palssonbernhardo awhiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT walkergrahamc awhiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT collinsjamesj awhiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT yangjasonh whiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT wrightsarahn whiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT hamblinmeagan whiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT mccloskeydouglas whiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT alcantarmiguela whiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT schrubberslars whiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT lopatkinallisonj whiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT satishsangeeta whiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT niliamir whiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT palssonbernhardo whiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT walkergrahamc whiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction AT collinsjamesj whiteboxmachinelearningapproachforrevealingantibioticmechanismsofaction |