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

Title: Combining mechanistic and machine learning models for predictive engineering and optimization of tryptophan metabolism

Abstract

Abstract Through advanced mechanistic modeling and the generation of large high-quality datasets, machine learning is becoming an integral part of understanding and engineering living systems. Here we show that mechanistic and machine learning models can be combined to enable accurate genotype-to-phenotype predictions. We use a genome-scale model to pinpoint engineering targets, efficient library construction of metabolic pathway designs, and high-throughput biosensor-enabled screening for training diverse machine learning algorithms. From a single data-generation cycle, this enables successful forward engineering of complex aromatic amino acid metabolism in yeast, with the best machine learning-guided design recommendations improving tryptophan titer and productivity by up to 74 and 43%, respectively, compared to the best designs used for algorithm training. Thus, this study highlights the power of combining mechanistic and machine learning models to effectively direct metabolic engineering efforts.

Authors:
ORCiD logo; ORCiD logo; ORCiD logo; ORCiD logo; ORCiD logo; ; ; ; ORCiD logo; ORCiD logo; ORCiD logo; ; ORCiD logo; ORCiD logo
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Energy Efficiency and Renewable Energy (EERE); European Commission Horizon 2020; MINECO; CORFO
OSTI Identifier:
1665913
Alternate Identifier(s):
OSTI ID: 1706667
Grant/Contract Number:  
AC02- 05CH11231; AC02-05CH11231; 722287; 686070; SEV-2013-0323; 17IEAT-73382
Resource Type:
Published Article
Journal Name:
Nature Communications
Additional Journal Information:
Journal Name: Nature Communications Journal Volume: 11 Journal Issue: 1; Journal ID: ISSN 2041-1723
Publisher:
Nature Publishing Group
Country of Publication:
United Kingdom
Language:
English
Subject:
59 BASIC BIOLOGICAL SCIENCES; Applied microbiology; metabolic engineering; synthetic biology

Citation Formats

Zhang, Jie, Petersen, Søren D., Radivojevic, Tijana, Ramirez, Andrés, Pérez-Manríquez, Andrés, Abeliuk, Eduardo, Sánchez, Benjamín J., Costello, Zak, Chen, Yu, Fero, Michael J., Martin, Hector Garcia, Nielsen, Jens, Keasling, Jay D., and Jensen, Michael K. Combining mechanistic and machine learning models for predictive engineering and optimization of tryptophan metabolism. United Kingdom: N. p., 2020. Web. https://doi.org/10.1038/s41467-020-17910-1.
Zhang, Jie, Petersen, Søren D., Radivojevic, Tijana, Ramirez, Andrés, Pérez-Manríquez, Andrés, Abeliuk, Eduardo, Sánchez, Benjamín J., Costello, Zak, Chen, Yu, Fero, Michael J., Martin, Hector Garcia, Nielsen, Jens, Keasling, Jay D., & Jensen, Michael K. Combining mechanistic and machine learning models for predictive engineering and optimization of tryptophan metabolism. United Kingdom. https://doi.org/10.1038/s41467-020-17910-1
Zhang, Jie, Petersen, Søren D., Radivojevic, Tijana, Ramirez, Andrés, Pérez-Manríquez, Andrés, Abeliuk, Eduardo, Sánchez, Benjamín J., Costello, Zak, Chen, Yu, Fero, Michael J., Martin, Hector Garcia, Nielsen, Jens, Keasling, Jay D., and Jensen, Michael K. Fri . "Combining mechanistic and machine learning models for predictive engineering and optimization of tryptophan metabolism". United Kingdom. https://doi.org/10.1038/s41467-020-17910-1.
@article{osti_1665913,
title = {Combining mechanistic and machine learning models for predictive engineering and optimization of tryptophan metabolism},
author = {Zhang, Jie and Petersen, Søren D. and Radivojevic, Tijana and Ramirez, Andrés and Pérez-Manríquez, Andrés and Abeliuk, Eduardo and Sánchez, Benjamín J. and Costello, Zak and Chen, Yu and Fero, Michael J. and Martin, Hector Garcia and Nielsen, Jens and Keasling, Jay D. and Jensen, Michael K.},
abstractNote = {Abstract Through advanced mechanistic modeling and the generation of large high-quality datasets, machine learning is becoming an integral part of understanding and engineering living systems. Here we show that mechanistic and machine learning models can be combined to enable accurate genotype-to-phenotype predictions. We use a genome-scale model to pinpoint engineering targets, efficient library construction of metabolic pathway designs, and high-throughput biosensor-enabled screening for training diverse machine learning algorithms. From a single data-generation cycle, this enables successful forward engineering of complex aromatic amino acid metabolism in yeast, with the best machine learning-guided design recommendations improving tryptophan titer and productivity by up to 74 and 43%, respectively, compared to the best designs used for algorithm training. Thus, this study highlights the power of combining mechanistic and machine learning models to effectively direct metabolic engineering efforts.},
doi = {10.1038/s41467-020-17910-1},
journal = {Nature Communications},
number = 1,
volume = 11,
place = {United Kingdom},
year = {2020},
month = {9}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1038/s41467-020-17910-1

Save / Share:

Works referenced in this record:

Multiplex metabolic pathway engineering using CRISPR/Cas9 in Saccharomyces cerevisiae
journal, March 2015


Inactivation of Pyruvate Kinase or the Phosphoenolpyruvate: Sugar Phosphotransferase System Increases Shikimic and Dehydroshikimic Acid Yields from Glucose in Bacillus subtilis
journal, January 2014

  • Licona-Cassani, Cuauhtemoc; Lara, Alvaro R.; Cabrera-Valladares, Natividad
  • Journal of Molecular Microbiology and Biotechnology, Vol. 24, Issue 1
  • DOI: 10.1159/000355264

Improvement of NADPH bioavailability in Escherichia coli through the use of phosphofructokinase deficient strains
journal, April 2013

  • Wang, Yipeng; San, Ka-Yiu; Bennett, George N.
  • Applied Microbiology and Biotechnology, Vol. 97, Issue 15
  • DOI: 10.1007/s00253-013-4859-0

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


Evolution of feedback-inhibited  /  barrel isoenzymes by gene duplication and a single mutation
journal, January 2003

  • Hartmann, M.; Schneider, T. R.; Pfeil, A.
  • Proceedings of the National Academy of Sciences, Vol. 100, Issue 3
  • DOI: 10.1073/pnas.0337566100

Opportunities at the Intersection of Synthetic Biology, Machine Learning, and Automation
journal, July 2019

  • Carbonell, Pablo; Radivojevic, Tijana; García Martín, Héctor
  • ACS Synthetic Biology, Vol. 8, Issue 7
  • DOI: 10.1021/acssynbio.8b00540

Nucleotide sequence and expression of Escherichia coli trpR, the structural gene for the trp aporepressor.
journal, December 1980

  • Gunsalus, R. P.; Yanofsky, C.
  • Proceedings of the National Academy of Sciences, Vol. 77, Issue 12
  • DOI: 10.1073/pnas.77.12.7117

Global analysis of protein structural changes in complex proteomes
journal, September 2014

  • Feng, Yuehan; De Franceschi, Giorgia; Kahraman, Abdullah
  • Nature Biotechnology, Vol. 32, Issue 10
  • DOI: 10.1038/nbt.2999

Coupling S-adenosylmethionine–dependent methylation to growth: Design and uses
journal, March 2019


Metabolic engineering of muconic acid production in Saccharomyces cerevisiae
journal, January 2013


Engineered Reversal of Function in Glycolytic Yeast Promoters
journal, May 2019


Model-driven discovery of underground metabolic functions in Escherichia coli
journal, January 2015

  • Guzmán, Gabriela I.; Utrilla, José; Nurk, Sergey
  • Proceedings of the National Academy of Sciences, Vol. 112, Issue 3
  • DOI: 10.1073/pnas.1414218112

Large scale active-learning-guided exploration for in vitro protein production optimization
journal, April 2020


Engineering of Escherichia coli central metabolism for aromatic metabolite production with near theoretical yield.
journal, January 1994


Improving the phenotype predictions of a yeast genome‐scale metabolic model by incorporating enzymatic constraints
journal, August 2017

  • Sánchez, Benjamín J.; Zhang, Cheng; Nilsson, Avlant
  • Molecular Systems Biology, Vol. 13, Issue 8
  • DOI: 10.15252/msb.20167411

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

Expression-level optimization of a multi-enzyme pathway in the absence of a high-throughput assay
journal, September 2013

  • Lee, Michael E.; Aswani, Anil; Han, Audrey S.
  • Nucleic Acids Research, Vol. 41, Issue 22
  • DOI: 10.1093/nar/gkt809

Robust statistics for outlier detection
journal, January 2011

  • Rousseeuw, Peter J.; Hubert, Mia
  • WIREs Data Mining and Knowledge Discovery, Vol. 1, Issue 1
  • DOI: 10.1002/widm.2

Analysis of feedback-resistant anthranilate synthases from Saccharomyces cerevisiae.
journal, January 1993


A Cas9-based toolkit to program gene expression in Saccharomyces cerevisiae
journal, November 2016

  • Reider Apel, Amanda; d'Espaux, Leo; Wehrs, Maren
  • Nucleic Acids Research, Vol. 45, Issue 1
  • DOI: 10.1093/nar/gkw1023

Connecting central carbon and aromatic amino acid metabolisms to improve de novo 2-phenylethanol production in Saccharomyces cerevisiae
journal, December 2019


Creation and analysis of biochemical constraint-based models using the COBRA Toolbox v.3.0
journal, February 2019


A comprehensive strategy enabling high-resolution functional analysis of the yeast genome
journal, July 2008

  • Breslow, David K.; Cameron, Dale M.; Collins, Sean R.
  • Nature Methods, Vol. 5, Issue 8
  • DOI: 10.1038/nmeth.1234

Pathway swapping: Toward modular engineering of essential cellular processes
journal, December 2016

  • Kuijpers, Niels G. A.; Solis-Escalante, Daniel; Luttik, Marijke A. H.
  • Proceedings of the National Academy of Sciences, Vol. 113, Issue 52
  • DOI: 10.1073/pnas.1606701113

Next-Generation Machine Learning for Biological Networks
journal, June 2018


Parallel tempering: Theory, applications, and new perspectives
journal, January 2005

  • Earl, David J.; Deem, Michael W.
  • Physical Chemistry Chemical Physics, Vol. 7, Issue 23
  • DOI: 10.1039/b509983h

Targeted proteomics for metabolic pathway optimization: Application to terpene production
journal, March 2011

  • Redding-Johanson, Alyssa M.; Batth, Tanveer S.; Chan, Rossana
  • Metabolic Engineering, Vol. 13, Issue 2
  • DOI: 10.1016/j.ymben.2010.12.005

Evolution of 3-deoxy-D-arabino-heptulosonate-7-phosphate synthase-encoding genes in the yeast Saccharomyces cerevisiae
journal, June 2005

  • Helmstaedt, K.; Strittmatter, A.; Lipscomb, W. N.
  • Proceedings of the National Academy of Sciences, Vol. 102, Issue 28
  • DOI: 10.1073/pnas.0504238102

Quorum-sensing linked RNA interference for dynamic metabolic pathway control in Saccharomyces cerevisiae
journal, May 2015


CasEMBLR: Cas9-Facilitated Multiloci Genomic Integration of in Vivo Assembled DNA Parts in Saccharomyces cerevisiae
journal, March 2015


Identification of dosage-sensitive genes in Saccharomyces cerevisiae using the genetic tug-of-war method
journal, December 2012


Comprehensive understanding of Saccharomyces cerevisiae phenotypes with whole‐cell model WM_S288C
journal, February 2020

  • Ye, Chao; Xu, Nan; Gao, Cong
  • Biotechnology and Bioengineering, Vol. 117, Issue 5
  • DOI: 10.1002/bit.27298

Systems Metabolic Engineering Meets Machine Learning: A New Era for Data‐Driven Metabolic Engineering
journal, May 2019


Multiple signalling pathways trigger the exquisite sensitivity of yeast gluconeogenic mRNAs to glucose
journal, May 1996


Genome-wide structure and organization of eukaryotic pre-initiation complexes
journal, January 2012


EasyClone: method for iterative chromosomal integration of multiple genes Saccharomyces cerevisiae
journal, March 2014

  • Jensen, Niels B.; Strucko, Tomas; Kildegaard, Kanchana R.
  • FEMS Yeast Research, Vol. 14, Issue 2
  • DOI: 10.1111/1567-1364.12118

Rationally reduced libraries for combinatorial pathway optimization minimizing experimental effort
journal, March 2016

  • Jeschek, Markus; Gerngross, Daniel; Panke, Sven
  • Nature Communications, Vol. 7, Issue 1
  • DOI: 10.1038/ncomms11163

Machine and deep learning meet genome-scale metabolic modeling
journal, July 2019


Application of Bayesian approach to numerical methods of global and stochastic optimization
journal, June 1994


In vivoandin vitroStudies of TrpR-DNA Interactions
journal, April 1996

  • Yang, Jie; Gunasekera, Angelo; Lavoie, Teresa A.
  • Journal of Molecular Biology, Vol. 258, Issue 1
  • DOI: 10.1006/jmbi.1996.0232

A machine learning Automated Recommendation Tool for synthetic biology
journal, September 2020


The Lack of A Priori Distinctions Between Learning Algorithms
journal, October 1996


Combinatorial pathway optimization for streamlined metabolic engineering
journal, October 2017


Absolute Quantification of Protein and mRNA Abundances Demonstrate Variability in Gene-Specific Translation Efficiency in Yeast
journal, May 2017


Biosensor-based engineering of biosynthetic pathways
journal, December 2016


Coordination of microbial metabolism
journal, March 2014

  • Chubukov, Victor; Gerosa, Luca; Kochanowski, Karl
  • Nature Reviews Microbiology, Vol. 12, Issue 5
  • DOI: 10.1038/nrmicro3238

Metabolic flux responses to deletion of 20 core enzymes reveal flexibility and limits of E. coli metabolism
journal, September 2019


Improving carotenoids production in yeast via adaptive laboratory evolution
journal, January 2014


The emergence of adaptive laboratory evolution as an efficient tool for biological discovery and industrial biotechnology
journal, December 2019


Metabolic Fluxes and Metabolic Engineering
journal, January 1999


Manufacturing Molecules Through Metabolic Engineering
journal, December 2010


Saccharomyces Genome Database: the genomics resource of budding yeast
journal, November 2011

  • Cherry, J. M.; Hong, E. L.; Amundsen, C.
  • Nucleic Acids Research, Vol. 40, Issue D1
  • DOI: 10.1093/nar/gkr1029

Metabolic engineering of a tyrosine-overproducing yeast platform using targeted metabolomics
journal, May 2015

  • Gold, Nicholas D.; Gowen, Christopher M.; Lussier, Francois-Xavier
  • Microbial Cell Factories, Vol. 14, Issue 1
  • DOI: 10.1186/s12934-015-0252-2

iML1515, a knowledgebase that computes Escherichia coli traits
journal, October 2017

  • Monk, Jonathan M.; Lloyd, Colton J.; Brunk, Elizabeth
  • Nature Biotechnology, Vol. 35, Issue 10
  • DOI: 10.1038/nbt.3956

What is flux balance analysis?
journal, March 2010

  • Orth, Jeffrey D.; Thiele, Ines; Palsson, Bernhard Ø
  • Nature Biotechnology, Vol. 28, Issue 3
  • DOI: 10.1038/nbt.1614

Revising the Representation of Fatty Acid, Glycerolipid, and Glycerophospholipid Metabolism in the Consensus Model of Yeast Metabolism
journal, August 2013

  • Aung, Hnin W.; Henry, Susan A.; Walker, Larry P.
  • Industrial Biotechnology, Vol. 9, Issue 4
  • DOI: 10.1089/ind.2013.0013

Model-Assisted Fine-Tuning of Central Carbon Metabolism in Yeast through dCas9-Based Regulation
journal, October 2019


Phosphofructokinase 1 Glycosylation Regulates Cell Growth and Metabolism
journal, August 2012


Constraining the metabolic genotype–phenotype relationship using a phylogeny of in silico methods
journal, February 2012

  • Lewis, Nathan E.; Nagarajan, Harish; Palsson, Bernhard O.
  • Nature Reviews Microbiology, Vol. 10, Issue 4
  • DOI: 10.1038/nrmicro2737

Pushing product formation to its limit: Metabolic engineering of Corynebacterium glutamicum for l-leucine overproduction
journal, March 2014


Computing the functional proteome: recent progress and future prospects for genome-scale models
journal, August 2015