Computational Framework for Machine-Learning-Enabled 13C Fluxomics
Abstract
13C metabolic flux analysis (MFA) has emerged as a powerful tool for synthetic biology. This optimization-based approach suffers long computation time and unstable solutions depending on the initial guess. Here, we develop a machine-learning-based framework for 13C fluxomics. Specifically, training and test data sets are generated by metabolic network decomposition and flux sampling, in which flux ratios at metabolic nodes and simulated labeling patterns of metabolites are used as training targets and features, respectively. To improve prediction accuracy and simplify the model, automated processes are developed for flux ratio selection based on solvability and feature screening based on importance. We found that predictive performance can be significantly improved using both amino acids and central carbon metabolites in comparison with amino acids alone. Together with measured external fluxes, the predicted flux ratios determine the mass balance system, yielding global flux distributions. This approach is validated by flux estimation using both simulated and experimental data in comparison with canonical 13C MFA. The approach represents a reliable fluxomics method readily applicable to high-throughput metabolic phenotyping, which highlights the advances of intelligent learning algorithms in synthetic biology, specifically in the Test and Learn stage of the Design-Build-Test-Learn cycle.
- Publication Date:
- Research Org.:
- National Renewable Energy Laboratory (NREL), Golden, CO (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1832414
- Report Number(s):
- NREL/JA-2700-79465
Journal ID: ISSN 2161-5063; MainId:33691;UUID:94f5f211-988f-4066-8207-4721ad0a1344;MainAdminID:63232
- Grant/Contract Number:
- AC36-08GO28308
- Resource Type:
- Accepted Manuscript
- Journal Name:
- ACS Synthetic Biology
- Additional Journal Information:
- Journal Volume: 11; Journal Issue: 1; Journal ID: ISSN 2161-5063
- Publisher:
- American Chemical Society (ACS)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 59 BASIC BIOLOGICAL SCIENCES; 13C metabolic flux analysis; machine learning
Citation Formats
Wu, Chao, Yu, Jianping, Guarnieri, Michael, and Xiong, Wei. Computational Framework for Machine-Learning-Enabled 13C Fluxomics. United States: N. p., 2021.
Web. doi:10.1021/acssynbio.1c00189.
Wu, Chao, Yu, Jianping, Guarnieri, Michael, & Xiong, Wei. Computational Framework for Machine-Learning-Enabled 13C Fluxomics. United States. https://doi.org/10.1021/acssynbio.1c00189
Wu, Chao, Yu, Jianping, Guarnieri, Michael, and Xiong, Wei. Wed .
"Computational Framework for Machine-Learning-Enabled 13C Fluxomics". United States. https://doi.org/10.1021/acssynbio.1c00189. https://www.osti.gov/servlets/purl/1832414.
@article{osti_1832414,
title = {Computational Framework for Machine-Learning-Enabled 13C Fluxomics},
author = {Wu, Chao and Yu, Jianping and Guarnieri, Michael and Xiong, Wei},
abstractNote = {13C metabolic flux analysis (MFA) has emerged as a powerful tool for synthetic biology. This optimization-based approach suffers long computation time and unstable solutions depending on the initial guess. Here, we develop a machine-learning-based framework for 13C fluxomics. Specifically, training and test data sets are generated by metabolic network decomposition and flux sampling, in which flux ratios at metabolic nodes and simulated labeling patterns of metabolites are used as training targets and features, respectively. To improve prediction accuracy and simplify the model, automated processes are developed for flux ratio selection based on solvability and feature screening based on importance. We found that predictive performance can be significantly improved using both amino acids and central carbon metabolites in comparison with amino acids alone. Together with measured external fluxes, the predicted flux ratios determine the mass balance system, yielding global flux distributions. This approach is validated by flux estimation using both simulated and experimental data in comparison with canonical 13C MFA. The approach represents a reliable fluxomics method readily applicable to high-throughput metabolic phenotyping, which highlights the advances of intelligent learning algorithms in synthetic biology, specifically in the Test and Learn stage of the Design-Build-Test-Learn cycle.},
doi = {10.1021/acssynbio.1c00189},
journal = {ACS Synthetic Biology},
number = 1,
volume = 11,
place = {United States},
year = {Wed Oct 27 00:00:00 EDT 2021},
month = {Wed Oct 27 00:00:00 EDT 2021}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Fluxomics - connecting ‘omics analysis and phenotypes: Fluxomics - a systems biology tool
journal, January 2013
- Winter, Gal; Krömer, Jens O.
- Environmental Microbiology, Vol. 15, Issue 7
What is flux balance analysis?
journal, March 2010
- Orth, Jeffrey D.; Thiele, Ines; Palsson, Bernhard Ø
- Nature Biotechnology, Vol. 28, Issue 3
13C Metabolic Flux Analysis
journal, July 2001
- Wiechert, Wolfgang
- Metabolic Engineering, Vol. 3, Issue 3
Synergy between 13C-metabolic flux analysis and flux balance analysis for understanding metabolic adaption to anaerobiosis in E. coli
journal, January 2011
- Chen, Xuewen; Alonso, Ana P.; Allen, Doug K.
- Metabolic Engineering, Vol. 13, Issue 1
13C-based metabolic flux analysis
journal, May 2009
- Zamboni, Nicola; Fendt, Sarah-Maria; Rühl, Martin
- Nature Protocols, Vol. 4, Issue 6
13C metabolic flux analysis at a genome-scale
journal, November 2015
- Gopalakrishnan, Saratram; Maranas, Costas D.
- Metabolic Engineering, Vol. 32
Fluxomers: a new approach for 13C metabolic flux analysis
journal, January 2011
- Srour, Orr; Young, Jamey D.; Eldar, Yonina C.
- BMC Systems Biology, Vol. 5, Issue 1
Improving the Caenorhabditis elegans Genome Annotation Using Machine Learning
journal, February 2007
- Rätsch, Gunnar; Sonnenburg, Sören; Srinivasan, Jagan
- PLoS Computational Biology, Vol. 3, Issue 2
A primer on deep learning in genomics
journal, November 2018
- Zou, James; Huss, Mikael; Abid, Abubakar
- Nature Genetics, Vol. 51, Issue 1
Diffuse large B-cell lymphoma outcome prediction by gene-expression profiling and supervised machine learning
journal, January 2002
- Shipp, Margaret A.; Ross, Ken N.; Tamayo, Pablo
- Nature Medicine, Vol. 8, Issue 1
Predicting hepatitis B virus–positive metastatic hepatocellular carcinomas using gene expression profiling and supervised machine learning
journal, March 2003
- Ye, Qing-Hai; Qin, Lun-Xiu; Forgues, Marshonna
- Nature Medicine, Vol. 9, Issue 4
Chemogenomic profiling on a genome-wide scale using reverse-engineered gene networks
journal, March 2005
- di Bernardo, Diego; Thompson, Michael J.; Gardner, Timothy S.
- Nature Biotechnology, Vol. 23, Issue 3
Elucidating Compound Mechanism of Action by Network Perturbation Analysis
journal, July 2015
- Woo, Jung Hoon; Shimoni, Yishai; Yang, Wan Seok
- Cell, Vol. 162, Issue 2
Improved protein structure prediction using potentials from deep learning
journal, January 2020
- Senior, Andrew W.; Evans, Richard; Jumper, John
- Nature, Vol. 577, Issue 7792
Supervised machine learning algorithms for protein structure classification
journal, June 2009
- Jain, Pooja; Garibaldi, Jonathan M.; Hirst, Jonathan D.
- Computational Biology and Chemistry, Vol. 33, Issue 3
Machine learning methods for metabolic pathway prediction
journal, January 2010
- Dale, Joseph M.; Popescu, Liviu; Karp, Peter D.
- BMC Bioinformatics, Vol. 11, Issue 1
A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data
journal, May 2018
- Costello, Zak; Martin, Hector Garcia
- npj Systems Biology and Applications, Vol. 4, Issue 1
Combined network analysis and machine learning allows the prediction of metabolic pathways from tomato metabolomics data
journal, June 2019
- Toubiana, David; Puzis, Rami; Wen, Lingling
- Communications Biology, Vol. 2, Issue 1
Rapid Prediction of Bacterial Heterotrophic Fluxomics Using Machine Learning and Constraint Programming
journal, April 2016
- Wu, Stephen Gang; Wang, Yuxuan; Jiang, Wu
- PLOS Computational Biology, Vol. 12, Issue 4
SUMOFLUX: A Generalized Method for Targeted 13C Metabolic Flux Ratio Analysis
journal, September 2016
- Kogadeeva, Maria; Zamboni, Nicola
- PLOS Computational Biology, Vol. 12, Issue 9
EMUlator: An Elementary Metabolite Unit (EMU) Based Isotope Simulator Enabled by Adjacency Matrix
journal, April 2019
- Wu, Chao; Chen, Chia-hsin; Lo, Jonathan
- Frontiers in Microbiology, Vol. 10
Elementary metabolite units (EMU): A novel framework for modeling isotopic distributions
journal, January 2007
- Antoniewicz, Maciek R.; Kelleher, Joanne K.; Stephanopoulos, Gregory
- Metabolic Engineering, Vol. 9, Issue 1
Metabolic flux analysis in a nonstationary system: Fed-batch fermentation of a high yielding strain of E. coli producing 1,3-propanediol
journal, May 2007
- Antoniewicz, M.; Kraynie, D.; Laffend, L.
- Metabolic Engineering, Vol. 9, Issue 3
optGpSampler: An Improved Tool for Uniformly Sampling the Solution-Space of Genome-Scale Metabolic Networks
journal, February 2014
- Megchelenbrink, Wout; Huynen, Martijn; Marchiori, Elena
- PLoS ONE, Vol. 9, Issue 2
Selection of tracers for 13C-Metabolic Flux Analysis using Elementary Metabolite Units (EMU) basis vector methodology
journal, March 2012
- Crown, Scott B.; Antoniewicz, Maciek R.
- Metabolic Engineering, Vol. 14, Issue 2
Determination of Metabolic Flux Ratios From 13C-Experiments and Gas Chromatography-Mass Spectrometry Data
book, January 2007
- Nanchen, Annik; Fuhrer, Tobias; Sauer, Uwe
Systems-level metabolic flux profiling identifies fatty acid synthesis as a target for antiviral therapy
journal, September 2008
- Munger, Joshua; Bennett, Bryson D.; Parikh, Anuraag
- Nature Biotechnology, Vol. 26, Issue 10
Mapping photoautotrophic metabolism with isotopically nonstationary 13C flux analysis
journal, November 2011
- Young, Jamey D.; Shastri, Avantika A.; Stephanopoulos, Gregory
- Metabolic Engineering, Vol. 13, Issue 6
Genome-Based Metabolic Mapping and 13 C Flux Analysis Reveal Systematic Properties of an Oleaginous Microalga Chlorella protothecoides
journal, December 2014
- Wu, Chao; Xiong, Wei; Dai, Junbiao
- Plant Physiology, Vol. 167, Issue 2
The plasticity of cyanobacterial metabolism supports direct CO2 conversion to ethylene
journal, April 2015
- Xiong, Wei; Morgan, John A.; Ungerer, Justin
- Nature Plants, Vol. 1, Issue 5
Metabolic flux profiling of Escherichia coli mutants in central carbon metabolism using GC-MS: Metabolic flux profiling in E.���coli
journal, March 2003
- Fischer, Eliane; Sauer, Uwe
- European Journal of Biochemistry, Vol. 270, Issue 5
Deciphering flux adjustments of engineered E. coli cells during fermentation with changing growth conditions
journal, January 2017
- He, Lian; Xiu, Yu; Jones, J. Andrew
- Metabolic Engineering, Vol. 39
Rational design of 13C-labeling experiments for metabolic flux analysis in mammalian cells
journal, January 2012
- Crown, Scott B.; Ahn, Woo; Antoniewicz, Maciek R.
- BMC Systems Biology, Vol. 6, Issue 1
Theoretical aspects of 13C metabolic flux analysis with sole quantification of carbon dioxide labeling
journal, April 2005
- Yang, Tae Hoon; Heinzle, Elmar; Wittmann, Christoph
- Computational Biology and Chemistry, Vol. 29, Issue 2
Bidirectional reaction steps in metabolic networks: IV. Optimal design of isotopomer labeling experiments
journal, January 1999
- M�llney, Michael; Wiechert, Wolfgang; Kownatzki, Dirk
- Biotechnology and Bioengineering, Vol. 66, Issue 2
Estimation of flux ratios without uptake or release data: Application to serine and methionine metabolism
journal, September 2017
- Nilsson, Roland; Roci, Irena; Watrous, Jeramie
- Metabolic Engineering, Vol. 43
COBRApy: COnstraints-Based Reconstruction and Analysis for Python
journal, January 2013
- Ebrahim, Ali; Lerman, Joshua A.; Palsson, Bernhard O.
- BMC Systems Biology, Vol. 7, Issue 1
Bidirectional reaction steps in metabolic networks: I. Modeling and simulation of carbon isotope labeling experiments
journal, July 1997
- Wiechert, Wolfgang; de Graaf, Albert A.
- Biotechnology and Bioengineering, Vol. 55, Issue 1
Fluxomic Analysis Reveals Central Carbon Metabolism Adaptation for Diazotroph Azotobacter vinelandii Ammonium Excretion
journal, September 2019
- Wu, Chao; Herold, Ryan A.; Knoshaug, Eric P.
- Scientific Reports, Vol. 9, Issue 1