skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data

Abstract

New synthetic biology capabilities hold the promise of dramatically improving our ability to engineer biological systems. However, a fundamental hurdle in realizing this potential is our inability to accurately predict biological behavior after modifying the corresponding genotype. Kinetic models have traditionally been used to predict pathway dynamics in bioengineered systems, but they take significant time to develop, and rely heavily on domain expertise. Here, we show that the combination of machine learning and abundant multiomics data (proteomics and metabolomics) can be used to effectively predict pathway dynamics in an automated fashion. The new method outperforms a classical kinetic model, and produces qualitative and quantitative predictions that can be used to productively guide bioengineering efforts. This method systematically leverages arbitrary amounts of new data to improve predictions, and does not assume any particular interactions, but rather implicitly chooses the most predictive ones.

Authors:
 [1];  [2]
  1. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Joint BioEnergy Inst. (JBEI), Emeryville, CA (United States)
  2. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Joint BioEnergy Inst. (JBEI), Emeryville, CA (United States); Basque Center for Applied Mathematics (BCAM), Bilbao (Spain)
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Biological and Environmental Research (BER) (SC-23)
OSTI Identifier:
1510759
DOE Contract Number:  
AC02-05CH11231
Resource Type:
Journal Article
Journal Name:
npj Systems Biology and Applications
Additional Journal Information:
Journal Volume: 4; Journal Issue: 1; Journal ID: ISSN 2056-7189
Publisher:
Springer Nature
Country of Publication:
United States
Language:
English
Subject:
59 BASIC BIOLOGICAL SCIENCES

Citation Formats

Costello, Zak, and Martin, Hector Garcia. A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data. United States: N. p., 2018. Web. doi:10.1038/s41540-018-0054-3.
Costello, Zak, & Martin, Hector Garcia. A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data. United States. doi:10.1038/s41540-018-0054-3.
Costello, Zak, and Martin, Hector Garcia. Tue . "A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data". United States. doi:10.1038/s41540-018-0054-3. https://www.osti.gov/servlets/purl/1510759.
@article{osti_1510759,
title = {A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data},
author = {Costello, Zak and Martin, Hector Garcia},
abstractNote = {New synthetic biology capabilities hold the promise of dramatically improving our ability to engineer biological systems. However, a fundamental hurdle in realizing this potential is our inability to accurately predict biological behavior after modifying the corresponding genotype. Kinetic models have traditionally been used to predict pathway dynamics in bioengineered systems, but they take significant time to develop, and rely heavily on domain expertise. Here, we show that the combination of machine learning and abundant multiomics data (proteomics and metabolomics) can be used to effectively predict pathway dynamics in an automated fashion. The new method outperforms a classical kinetic model, and produces qualitative and quantitative predictions that can be used to productively guide bioengineering efforts. This method systematically leverages arbitrary amounts of new data to improve predictions, and does not assume any particular interactions, but rather implicitly chooses the most predictive ones.},
doi = {10.1038/s41540-018-0054-3},
journal = {npj Systems Biology and Applications},
issn = {2056-7189},
number = 1,
volume = 4,
place = {United States},
year = {2018},
month = {5}
}

Works referenced in this record:

Integrated multi-omics of the human gut microbiome in a case study of familial type 1 diabetes
journal, October 2016


The new frontier of genome engineering with CRISPR-Cas9
journal, November 2014


Systems-level analysis of mechanisms regulating yeast metabolic flux
journal, October 2016


Circadian Metabolomics in Time and Space
journal, January 2017


Clostridium thermocellum ATCC27405 transcriptomic, metabolomic and proteomic profiles after ethanol stress
journal, January 2012


Genetical Implications of the Structure of Deoxyribonucleic Acid
journal, May 1953

  • Watson, J. D.; Crick, F. H. C.
  • Nature, Vol. 171, Issue 4361
  • DOI: 10.1038/171964b0

Private traits and attributes are predictable from digital records of human behavior
journal, March 2013

  • Kosinski, M.; Stillwell, D.; Graepel, T.
  • Proceedings of the National Academy of Sciences, Vol. 110, Issue 15
  • DOI: 10.1073/pnas.1218772110

Principal component analysis of proteomics (PCAP) as a tool to direct metabolic engineering
journal, March 2015


Metabolic ensemble modeling for strain engineers
journal, October 2011


Mastering the game of Go with deep neural networks and tree search
journal, January 2016

  • Silver, David; Huang, Aja; Maddison, Chris J.
  • Nature, Vol. 529, Issue 7587
  • DOI: 10.1038/nature16961

Natural products as biofuels and bio-based chemicals: fatty acids and isoprenoids
journal, January 2015

  • Beller, Harry R.; Lee, Taek Soon; Katz, Leonard
  • Natural Product Reports, Vol. 32, Issue 10
  • DOI: 10.1039/C5NP00068H

Approximative kinetic formats used in metabolic network modeling
journal, January 2005

  • Heijnen, Joseph J.
  • Biotechnology and Bioengineering, Vol. 91, Issue 5
  • DOI: 10.1002/bit.20558

The fluxes through glycolytic enzymes in Saccharomyces cerevisiae are predominantly regulated at posttranscriptional levels
journal, September 2007

  • Daran-Lapujade, P.; Rossell, S.; van Gulik, W. M.
  • Proceedings of the National Academy of Sciences, Vol. 104, Issue 40
  • DOI: 10.1073/pnas.0707476104

Granger causality in integrated GC–MS and LC–MS metabolomics data reveals the interface of primary and secondary metabolism
journal, October 2012


CircadiOmics: integrating circadian genomics, transcriptomics, proteomics and metabolomics
journal, July 2012

  • Patel, Vishal R.; Eckel-Mahan, Kristin; Sassone-Corsi, Paolo
  • Nature Methods, Vol. 9, Issue 8
  • DOI: 10.1038/nmeth.2111

A Whole-Cell Computational Model Predicts Phenotype from Genotype
journal, July 2012


Real-Time Digitization of Metabolomics Patterns from a Living System Using Mass Spectrometry
journal, July 2014

  • Heinemann, Joshua; Noon, Brigit; Mohigmi, Mohammad J.
  • Journal of The American Society for Mass Spectrometry, Vol. 25, Issue 10
  • DOI: 10.1007/s13361-014-0922-z

A genome-scale Escherichia coli kinetic metabolic model k-ecoli457 satisfying flux data for multiple mutant strains
journal, December 2016

  • Khodayari, Ali; Maranas, Costas D.
  • Nature Communications, Vol. 7, Issue 1
  • DOI: 10.1038/ncomms13806

Ensemble Modeling of Metabolic Networks
journal, December 2008


Systems metabolic engineering of microorganisms for natural and non-natural chemicals
journal, May 2012

  • Lee, Jeong Wook; Na, Dokyun; Park, Jong Myoung
  • Nature Chemical Biology, Vol. 8, Issue 6
  • DOI: 10.1038/nchembio.970

A targeted proteomics toolkit for high-throughput absolute quantification of Escherichia coli proteins
journal, November 2014


Improving Fatty Acid Availability for Bio-Hydrocarbon Production in Escherichia coli by Metabolic Engineering
journal, October 2013


From the first drop to the first truckload: commercialization of microbial processes for renewable chemicals
journal, December 2013


Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning
journal, July 2015

  • Alipanahi, Babak; Delong, Andrew; Weirauch, Matthew T.
  • Nature Biotechnology, Vol. 33, Issue 8
  • DOI: 10.1038/nbt.3300

Toward robotic cars
journal, April 2010


A microfluidics-based in vitro model of the gastrointestinal human–microbe interface
journal, May 2016

  • Shah, Pranjul; Fritz, Joëlle V.; Glaab, Enrico
  • Nature Communications, Vol. 7, Issue 1
  • DOI: 10.1038/ncomms11535

Characterizing Strain Variation in Engineered E. coli Using a Multi-Omics-Based Workflow
journal, May 2016


Reverse engineering and identification in systems biology: strategies, perspectives and challenges
journal, February 2014

  • Villaverde, Alejandro F.; Banga, Julio R.
  • Journal of The Royal Society Interface, Vol. 11, Issue 91
  • DOI: 10.1098/rsif.2013.0505

13C Metabolic Flux Analysis
journal, July 2001


Synthetic biology in mammalian cells: next generation research tools and therapeutics
journal, January 2014

  • Lienert, Florian; Lohmueller, Jason J.; Garg, Abhishek
  • Nature Reviews Molecular Cell Biology, Vol. 15, Issue 2
  • DOI: 10.1038/nrm3738

Acyl-CoA synthetases: fatty acid uptake and metabolic channeling
journal, December 2008

  • Digel, Margarete; Ehehalt, Robert; Stremmel, Wolfgang
  • Molecular and Cellular Biochemistry, Vol. 326, Issue 1-2
  • DOI: 10.1007/s11010-008-0003-3

A kinetic model of Escherichia coli core metabolism satisfying multiple sets of mutant flux data
journal, September 2014


Pseudo-transition Analysis Identifies the Key Regulators of Dynamic Metabolic Adaptations from Steady-State Data
journal, October 2015

  • Gerosa, Luca; Haverkorn van Rijsewijk, Bart R. B.; Christodoulou, Dimitris
  • Cell Systems, Vol. 1, Issue 4
  • DOI: 10.1016/j.cels.2015.09.008

Smoothing and Differentiation of Data by Simplified Least Squares Procedures.
journal, July 1964

  • Savitzky, Abraham.; Golay, M. J. E.
  • Analytical Chemistry, Vol. 36, Issue 8
  • DOI: 10.1021/ac60214a047

Metabolic engineering of Saccharomyces cerevisiae for the production of triacetic acid lactone
journal, September 2014


Channeling in native microbial pathways: Implications and challenges for metabolic engineering
journal, November 2017


Integrated omics for the identification of key functionalities in biological wastewater treatment microbial communities: Integrated omics to discover microbial functions
journal, February 2015

  • Narayanasamy, Shaman; Muller, Emilie E. L.; Sheik, Abdul R.
  • Microbial Biotechnology, Vol. 8, Issue 3
  • DOI: 10.1111/1751-7915.12255

Synthetic biology: from hype to impact
journal, March 2013


Genome-scale metabolic network modeling results in minimal interventions that cooperatively force carbon flux towards malonyl-CoA
journal, September 2011


A wellness study of 108 individuals using personal, dense, dynamic data clouds
journal, July 2017

  • Price, Nathan D.; Magis, Andrew T.; Earls, John C.
  • Nature Biotechnology, Vol. 35, Issue 8
  • DOI: 10.1038/nbt.3870

Synthetic biology devices for in vitro and in vivo diagnostics
journal, November 2015

  • Slomovic, Shimyn; Pardee, Keith; Collins, James J.
  • Proceedings of the National Academy of Sciences, Vol. 112, Issue 47
  • DOI: 10.1073/pnas.1508521112

Pathway Thermodynamics Highlights Kinetic Obstacles in Central Metabolism
journal, February 2014


Ensemble Modeling for Aromatic Production in Escherichia coli
journal, September 2009


Ensemble Modeling of Hepatic Fatty Acid Metabolism with a Synthetic Glyoxylate Shunt
journal, April 2010


Community-integrated omics links dominance of a microbial generalist to fine-tuned resource usage
journal, November 2014

  • Muller, Emilie E. L.; Pinel, Nicolás; Laczny, Cédric C.
  • Nature Communications, Vol. 5, Issue 1
  • DOI: 10.1038/ncomms6603

Real-time metabolome profiling of the metabolic switch between starvation and growth
journal, September 2015

  • Link, Hannes; Fuhrer, Tobias; Gerosa, Luca
  • Nature Methods, Vol. 12, Issue 11
  • DOI: 10.1038/nmeth.3584

Special Report: The birth of biotechnology
journal, January 2003


Dynamical effects of overparametrization in nonlinear models
journal, January 1995


Correlation analysis of targeted proteins and metabolites to assess and engineer microbial isopentenol production: Targeted Proteomics-Based Correlation Analysis
journal, May 2014

  • George, Kevin W.; Chen, Amy; Jain, Aakriti
  • Biotechnology and Bioengineering, Vol. 111, Issue 8
  • DOI: 10.1002/bit.25226

Genome‐scale models of metabolism and gene expression extend and refine growth phenotype prediction
journal, January 2013

  • O'Brien, Edward J.; Lerman, Joshua A.; Chang, Roger L.
  • Molecular Systems Biology, Vol. 9, Issue 1
  • DOI: 10.1038/msb.2013.52

Multiple High-Throughput Analyses Monitor the Response of E. coli to Perturbations
journal, April 2007


Big Data: Astronomical or Genomical?
journal, July 2015


High-throughput discovery metabolomics
journal, February 2015


A Survey on Transfer Learning
journal, October 2010

  • Pan, Sinno Jialin; Yang, Qiang
  • IEEE Transactions on Knowledge and Data Engineering, Vol. 22, Issue 10
  • DOI: 10.1109/TKDE.2009.191

Effects of spatiotemporal variations on metabolic control: Approximate analysis using (log)linear kinetic models
journal, April 1997


A Method to Constrain Genome-Scale Models with 13C Labeling Data
journal, September 2015

  • García Martín, Héctor; Kumar, Vinay Satish; Weaver, Daniel
  • PLOS Computational Biology, Vol. 11, Issue 9
  • DOI: 10.1371/journal.pcbi.1004363

The dynamic microbiome
journal, February 2014


Towards kinetic modeling of genome-scale metabolic networks without sacrificing stoichiometric, thermodynamic and physiological constraints
journal, August 2013

  • Chakrabarti, Anirikh; Miskovic, Ljubisa; Soh, Keng Cher
  • Biotechnology Journal, Vol. 8, Issue 9
  • DOI: 10.1002/biot.201300091

A method for analysis and design of metabolism using metabolomics data and kinetic models: Application on lipidomics using a novel kinetic model of sphingolipid metabolism
journal, September 2016

  • Savoglidis, Georgios; da Silveira dos Santos, Aline Xavier; Riezman, Isabelle
  • Metabolic Engineering, Vol. 37
  • DOI: 10.1016/j.ymben.2016.04.002

The Experiment Data Depot: A Web-Based Software Tool for Biological Experimental Data Storage, Sharing, and Visualization
journal, September 2017

  • Morrell, William C.; Birkel, Garrett W.; Forrer, Mark
  • ACS Synthetic Biology, Vol. 6, Issue 12
  • DOI: 10.1021/acssynbio.7b00204

Synthetic Biology Moving into the Clinic
journal, September 2011


Thermodynamics-Based Metabolic Flux Analysis
journal, March 2007

  • Henry, Christopher S.; Broadbelt, Linda J.; Hatzimanikatis, Vassily
  • Biophysical Journal, Vol. 92, Issue 5
  • DOI: 10.1529/biophysj.106.093138

Ensemble modeling for strain development of l-lysine-producing Escherichia coli
journal, July 2009

  • Contador, Carolina A.; Rizk, Matthew L.; Asenjo, Juan A.
  • Metabolic Engineering, Vol. 11, Issue 4-5, p. 221-233
  • DOI: 10.1016/j.ymben.2009.04.002

Biofuel alternatives to ethanol: pumping the microbial well
journal, July 2008

  • Fortman, J. L.; Chhabra, Swapnil; Mukhopadhyay, Aindrila
  • Trends in Biotechnology, Vol. 26, Issue 7, p. 375-381
  • DOI: 10.1016/j.tibtech.2008.03.008

Dermatologist-level classification of skin cancer with deep neural networks
journal, January 2017

  • Esteva, Andre; Kuprel, Brett; Novoa, Roberto A.
  • Nature, Vol. 542, Issue 7639
  • DOI: 10.1038/nature21056

General mass action kinetics
journal, January 1972

  • Horn, F.; Jackson, R.
  • Archive for Rational Mechanics and Analysis, Vol. 47, Issue 2
  • DOI: 10.1007/BF00251225

    Works referencing / citing this record:

    Technical Advances to Accelerate Modular Type I Polyketide Synthase Engineering towards a Retro-biosynthetic Platform
    journal, June 2019

    • Pang, Bo; Valencia, Luis E.; Wang, Jessica
    • Biotechnology and Bioprocess Engineering, Vol. 24, Issue 3
    • DOI: 10.1007/s12257-019-0083-9