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

Title: A machine learning Automated Recommendation Tool for synthetic biology

Abstract

Abstract Synthetic biology allows us to bioengineer cells to synthesize novel valuable molecules such as renewable biofuels or anticancer drugs. However, traditional synthetic biology approaches involve ad-hoc engineering practices, which lead to long development times. Here, we present the Automated Recommendation Tool (ART), a tool that leverages machine learning and probabilistic modeling techniques to guide synthetic biology in a systematic fashion, without the need for a full mechanistic understanding of the biological system. Using sampling-based optimization, ART provides a set of recommended strains to be built in the next engineering cycle, alongside probabilistic predictions of their production levels. We demonstrate the capabilities of ART on simulated data sets, as well as experimental data from real metabolic engineering projects producing renewable biofuels, hoppy flavored beer without hops, fatty acids, and tryptophan. Finally, we discuss the limitations of this approach, and the practical consequences of the underlying assumptions failing.

Authors:
ORCiD logo; ; ORCiD logo; ORCiD logo
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); MINECO
OSTI Identifier:
1665911
Alternate Identifier(s):
OSTI ID: 1706666
Grant/Contract Number:  
AC02-05CH11231; SEV-2013-032
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; Bayesian inference; machine learning; metabolic engineering; synthetic biology

Citation Formats

Radivojević, Tijana, Costello, Zak, Workman, Kenneth, and Garcia Martin, Hector. A machine learning Automated Recommendation Tool for synthetic biology. United Kingdom: N. p., 2020. Web. https://doi.org/10.1038/s41467-020-18008-4.
Radivojević, Tijana, Costello, Zak, Workman, Kenneth, & Garcia Martin, Hector. A machine learning Automated Recommendation Tool for synthetic biology. United Kingdom. https://doi.org/10.1038/s41467-020-18008-4
Radivojević, Tijana, Costello, Zak, Workman, Kenneth, and Garcia Martin, Hector. Fri . "A machine learning Automated Recommendation Tool for synthetic biology". United Kingdom. https://doi.org/10.1038/s41467-020-18008-4.
@article{osti_1665911,
title = {A machine learning Automated Recommendation Tool for synthetic biology},
author = {Radivojević, Tijana and Costello, Zak and Workman, Kenneth and Garcia Martin, Hector},
abstractNote = {Abstract Synthetic biology allows us to bioengineer cells to synthesize novel valuable molecules such as renewable biofuels or anticancer drugs. However, traditional synthetic biology approaches involve ad-hoc engineering practices, which lead to long development times. Here, we present the Automated Recommendation Tool (ART), a tool that leverages machine learning and probabilistic modeling techniques to guide synthetic biology in a systematic fashion, without the need for a full mechanistic understanding of the biological system. Using sampling-based optimization, ART provides a set of recommended strains to be built in the next engineering cycle, alongside probabilistic predictions of their production levels. We demonstrate the capabilities of ART on simulated data sets, as well as experimental data from real metabolic engineering projects producing renewable biofuels, hoppy flavored beer without hops, fatty acids, and tryptophan. Finally, we discuss the limitations of this approach, and the practical consequences of the underlying assumptions failing.},
doi = {10.1038/s41467-020-18008-4},
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/s41467-020-18008-4

Save / Share:

Works referenced in this record:

Biotransformation of limonene by bacteria, fungi, yeasts, and plants
journal, March 2003

  • Duetz, W. A.; Bouwmeester, H.; Beilen, J. B.
  • Applied Microbiology and Biotechnology, Vol. 61, Issue 4
  • DOI: 10.1007/s00253-003-1221-y

Synthetic and systems biology for microbial production of commodity chemicals
journal, April 2016

  • Chubukov, Victor; Mukhopadhyay, Aindrila; Petzold, Christopher J.
  • npj Systems Biology and Applications, Vol. 2, Issue 1
  • DOI: 10.1038/npjsba.2016.9

Industrial brewing yeast engineered for the production of primary flavor determinants in hopped beer
journal, March 2018


DNA synthesis, assembly and applications in synthetic biology
journal, August 2012

  • Ma, Siying; Tang, Nicholas; Tian, Jingdong
  • Current Opinion in Chemical Biology, Vol. 16, Issue 3-4
  • DOI: 10.1016/j.cbpa.2012.05.001

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


The need for uncertainty quantification in machine-assisted medical decision making
journal, January 2019

  • Begoli, Edmon; Bhattacharya, Tanmoy; Kusnezov, Dimitri
  • Nature Machine Intelligence, Vol. 1, Issue 1
  • DOI: 10.1038/s42256-018-0004-1

A Kriging-Based Approach to Autonomous Experimentation with Applications to X-Ray Scattering
journal, August 2019


The future of metabolic engineering and synthetic biology: Towards a systematic practice
journal, May 2012


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


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

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

David Draper and E. I. George, and a rejoinder by the authors
journal, November 1999

  • Volinsky, Chris T.; Raftery, Adrian E.; Madigan, David
  • Statistical Science, Vol. 14, Issue 4
  • DOI: 10.1214/ss/1009212519

Hydrogenated monoterpenes as diesel fuel additives
journal, November 2009


Using Stacking to Average Bayesian Predictive Distributions (with Discussion)
journal, September 2018

  • Yao, Yuling; Vehtari, Aki; Simpson, Daniel
  • Bayesian Analysis, Vol. 13, Issue 3
  • DOI: 10.1214/17-BA1091

1,500 scientists lift the lid on reproducibility
journal, May 2016


Controlling an organic synthesis robot with machine learning to search for new reactivity
journal, July 2018


Raise standards for preclinical cancer research
journal, March 2012

  • Begley, C. Glenn; Ellis, Lee M.
  • Nature, Vol. 483, Issue 7391
  • DOI: 10.1038/483531a

Predictable tuning of protein expression in bacteria
journal, January 2016

  • Bonde, Mads T.; Pedersen, Margit; Klausen, Michael S.
  • Nature Methods, Vol. 13, Issue 3
  • DOI: 10.1038/nmeth.3727

Metabolic Network Prediction of Drug Side Effects
journal, March 2016


Believe it or not: how much can we rely on published data on potential drug targets?
journal, August 2011

  • Prinz, Florian; Schlange, Thomas; Asadullah, Khusru
  • Nature Reviews Drug Discovery, Vol. 10, Issue 9
  • DOI: 10.1038/nrd3439-c1

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


A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data
journal, May 2018


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


Next-Generation Experimentation with Self-Driving Laboratories
journal, June 2019


The automated lab
journal, December 2014


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

Turning Bayesian model averaging into Bayesian model combination
conference, July 2011

  • Monteith, Kristine; Carroll, James L.; Seppi, Kevin
  • 2011 International Joint Conference on Neural Networks (IJCNN 2011 - San Jose), The 2011 International Joint Conference on Neural Networks
  • DOI: 10.1109/IJCNN.2011.6033566

High-level semi-synthetic production of the potent antimalarial artemisinin
journal, April 2013

  • Paddon, C. J.; Westfall, P. J.; Pitera, D. J.
  • Nature, Vol. 496, Issue 7446
  • DOI: 10.1038/nature12051

A novel mammalian cell line development platform utilizing nanofluidics and optoelectro positioning technology
journal, September 2018

  • Le, Kim; Tan, Christopher; Gupta, Shivani
  • Biotechnology Progress, Vol. 34, Issue 6
  • DOI: 10.1002/btpr.2690

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

A New Polymer Platform for the Future — Sorona® from Corn Derived 1,3-Propanediol
journal, April 2005


Bioprocess automation on a Mini Pilot Plant enables fast quantitative microbial phenotyping
journal, January 2015

  • Unthan, Simon; Radek, Andreas; Wiechert, Wolfgang
  • Microbial Cell Factories, Vol. 14, Issue 1
  • DOI: 10.1186/s12934-015-0216-6

Improving the environmental impact of civil aircraft by fuel cell technology: concepts and technological progress
journal, January 2010

  • Renouard-Vallet, Gwénaëlle; Saballus, Martin; Schmithals, Gerrit
  • Energy & Environmental Science, Vol. 3, Issue 10
  • DOI: 10.1039/b925930a

Synthetic biology: from hype to impact
journal, March 2013


On-chip integration of droplet microfluidics and nanostructure-initiator mass spectrometry for enzyme screening
journal, January 2017

  • Heinemann, Joshua; Deng, Kai; Shih, Steve C. C.
  • Lab on a Chip, Vol. 17, Issue 2
  • DOI: 10.1039/C6LC01182A

Automated flow-based/digital microfluidic platform integrated with onsite electroporation process for multiplex genetic engineering applications
conference, January 2018


Translation rate is controlled by coupled trade-offs between site accessibility, selective RNA unfolding and sliding at upstream standby sites
journal, November 2013

  • Espah Borujeni, Amin; Channarasappa, Anirudh S.; Salis, Howard M.
  • Nucleic Acids Research, Vol. 42, Issue 4
  • DOI: 10.1093/nar/gkt1139

A CRISPR–Cas9 gene drive targeting doublesex causes complete population suppression in caged Anopheles gambiae mosquitoes
journal, September 2018

  • Kyrou, Kyros; Hammond, Andrew M.; Galizi, Roberto
  • Nature Biotechnology, Vol. 36, Issue 11
  • DOI: 10.1038/nbt.4245

Rewriting yeast central carbon metabolism for industrial isoprenoid production
journal, September 2016

  • Meadows, Adam L.; Hawkins, Kristy M.; Tsegaye, Yoseph
  • Nature, Vol. 537, Issue 7622
  • DOI: 10.1038/nature19769

Automated design of synthetic ribosome binding sites to control protein expression
journal, October 2009

  • Salis, Howard M.; Mirsky, Ethan A.; Voigt, Christopher A.
  • Nature Biotechnology, Vol. 27, Issue 10, p. 946-950
  • DOI: 10.1038/nbt.1568

Automated “Cells-To-Peptides” Sample Preparation Workflow for High-Throughput, Quantitative Proteomic Assays of Microbes
journal, August 2019


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


Metabolic engineering of Escherichia coli for limonene and perillyl alcohol production
journal, September 2013


Combining mechanistic and machine learning models for predictive engineering and optimization of tryptophan metabolism
journal, September 2020


A brief history of synthetic biology
journal, April 2014

  • Cameron, D. Ewen; Bashor, Caleb J.; Collins, James J.
  • Nature Reviews Microbiology, Vol. 12, Issue 5
  • DOI: 10.1038/nrmicro3239

Lessons from Two Design–Build–Test–Learn Cycles of Dodecanol Production in Escherichia coli Aided by Machine Learning
journal, May 2019


Big Data: Astronomical or Genomical?
journal, July 2015


High-throughput discovery metabolomics
journal, February 2015


Cell-free synthetic biology: Thinking outside the cell
journal, May 2012


Analytics for Metabolic Engineering
journal, September 2015

  • Petzold, Christopher J.; Chan, Leanne Jade G.; Nhan, Melissa
  • Frontiers in Bioengineering and Biotechnology, Vol. 3
  • DOI: 10.3389/fbioe.2015.00135

Machine Learning of Designed Translational Control Allows Predictive Pathway Optimization in Escherichia coli
journal, December 2018


Gaussian Processes for Machine Learning
book, January 2005


Metabolic Fluxes and Metabolic Engineering
journal, January 1999


A Droplet Microfluidic Platform for Automating Genetic Engineering
journal, February 2016


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

Manufacturing Molecules Through Metabolic Engineering
journal, December 2010


Towards a fully automated algorithm driven platform for biosystems design
journal, November 2019


Isoprenoid Pathway Optimization for Taxol Precursor Overproduction in Escherichia coli
journal, September 2010


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

Engineering Cellular Metabolism
journal, March 2016