Display options
Cite
Medlock GL, Papin JA. Guiding the Refinement of Biochemical Knowledgebases with Ensembles of Metabolic Networks and Machine Learning. Cell Syst. 2020;10(1):109-119.e3doi: 10.1016/j.cels.2019.11.006.
Medlock, G. L., & Papin, J. A. (2020). Guiding the Refinement of Biochemical Knowledgebases with Ensembles of Metabolic Networks and Machine Learning. Cell systems, 10(1), 109-119.e3. https://doi.org/10.1016/j.cels.2019.11.006
Medlock, Gregory L, and Papin, Jason A. "Guiding the Refinement of Biochemical Knowledgebases with Ensembles of Metabolic Networks and Machine Learning." Cell systems vol. 10,1 (2020): 109-119.e3. doi: https://doi.org/10.1016/j.cels.2019.11.006
Medlock GL, Papin JA. Guiding the Refinement of Biochemical Knowledgebases with Ensembles of Metabolic Networks and Machine Learning. Cell Syst. 2020 Jan 22;10(1):109-119.e3. doi: 10.1016/j.cels.2019.11.006. Epub 2020 Jan 08. PMID: 31926940; PMCID: PMC6975163.
Copy Download .nbib Format: NLM
Share it on

Cell Syst. 2020 Jan 22;10(1):109-119.e3. doi: 10.1016/j.cels.2019.11.006. Epub 2020 Jan 08.

Guiding the Refinement of Biochemical Knowledgebases with Ensembles of Metabolic Networks and Machine Learning.

Cell systems

Gregory L Medlock, Jason A Papin

Affiliations

  1. Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, USA.
  2. Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, USA; Department of Medicine, Division of Infectious Diseases & International Health, University of Virginia, Charlottesville, VA, USA; Department of Biochemistry & Molecular Genetics, University of Virginia, Charlottesville, VA, USA. Electronic address: [email protected].

PMID: 31926940 PMCID: PMC6975163 DOI: 10.1016/j.cels.2019.11.006

Abstract

Mechanistic models explicitly represent hypothesized biological knowledge. As such, they offer more generalizability than data-driven models. However, identifying model curation efforts that improve performance for mechanistic models is nontrivial. Here, we develop a solution to this problem for genome-scale metabolic models. We generate an ensemble of models, each equally consistent with experimental data, then perform simulations with them. We apply machine learning to the simulation output to identify model structure variation that maximally influences simulations. These variants are high-priority candidates for curation through removal, addition, or reannotation in the model. We apply this approach, automated metabolic model ensemble-driven elimination of uncertainty with statistical learning (AMMEDEUS), to 29 bacterial species to improve gene essentiality predictions. We explore targets for individual species and compile pan-species targets to improve the database used during model construction. AMMEDEUS is an automated and performance-driven recommendation system that complements intuition during curation of biochemical knowledgebases.

Copyright © 2019 The Authors. Published by Elsevier Inc. All rights reserved.

Keywords: ensemble modeling; machine learning; mechanistic models; metabolic modeling; metabolism; model curation; systems biology

References

  1. Nucleic Acids Res. 2017 Jan 4;45(D1):D535-D542 - PubMed
  2. Nat Biotechnol. 2017 Jan;35(1):81-89 - PubMed
  3. Nat Chem Biol. 2012 Oct;8(10):848-54 - PubMed
  4. Amino Acids. 2011 Jun;41(1):7-27 - PubMed
  5. Proc Natl Acad Sci U S A. 2006 Nov 14;103(46):17480-4 - PubMed
  6. J Bacteriol. 2011 Aug;193(16):4199-213 - PubMed
  7. Appl Environ Microbiol. 2002 Jul;68(7):3321-7 - PubMed
  8. PLoS Comput Biol. 2019 Apr 11;15(4):e1006507 - PubMed
  9. Nucleic Acids Res. 2017 Jan 4;45(D1):D940-D944 - PubMed
  10. Mol Syst Biol. 2010 Jul;6:390 - PubMed
  11. BMC Genomics. 2009 Jul 01;10:291 - PubMed
  12. PLoS Comput Biol. 2014 Oct 16;10(10):e1003882 - PubMed
  13. Nat Biotechnol. 2010 Sep;28(9):977-82 - PubMed
  14. Proc Natl Acad Sci U S A. 2002 Jan 22;99(2):966-71 - PubMed
  15. Appl Environ Microbiol. 2002 Nov;68(11):5656-62 - PubMed
  16. Amino Acids. 2006 Feb;30(1):1-15 - PubMed
  17. Nat Protoc. 2010 Jan;5(1):93-121 - PubMed
  18. Proc Natl Acad Sci U S A. 2014 Dec 30;111(52):18507-12 - PubMed
  19. PLoS Comput Biol. 2018 Oct 18;14(10):e1006541 - PubMed
  20. J Cheminform. 2015 Aug 28;7:44 - PubMed
  21. PLoS Comput Biol. 2017 Mar 6;13(3):e1005413 - PubMed
  22. Biophys J. 2008 Dec 15;95(12):5606-17 - PubMed
  23. Mol Syst Biol. 2009;5:320 - PubMed
  24. Nature. 2015 Jan 15;517(7534):369-72 - PubMed
  25. Nat Biotechnol. 2007 Sep;25(9):1001-6 - PubMed
  26. Int J Vitam Nutr Res. 2008 Jul-Sep;78(4-5):169-74 - PubMed
  27. Nat Biotechnol. 2014 May;32(5):447-52 - PubMed
  28. Bioinformatics. 2003 Mar 1;19(4):524-31 - PubMed
  29. Mol Cells. 2005 Jun 30;19(3):365-74 - PubMed
  30. Bioinformatics. 2005 Apr 15;21(8):1603-9 - PubMed
  31. Bioinformatics. 2017 Aug 1;33(15):2416-2418 - PubMed
  32. BMC Syst Biol. 2013 Aug 08;7:74 - PubMed

MeSH terms

Publication Types

Grant support