Engineering of increased L-Threonine production in bacteria by combinatorial cloning and machine learning
The goal of this study is to develop a general strategy for bacterial engineering using an integrated synthetic biology and machine learning (ML) approach. This strategy was developed in the context of increasing L-threonine production in Escherichia coli ATCC 21277. A set of 16 genes was initially...
Main Authors: | , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-12-01
|
Series: | Metabolic Engineering Communications |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2214030123000081 |
_version_ | 1797405442995912704 |
---|---|
author | Paul Hanke Bruce Parrello Olga Vasieva Chase Akins Philippe Chlenski Gyorgy Babnigg Chris Henry Fatima Foflonker Thomas Brettin Dionysios Antonopoulos Rick Stevens Michael Fonstein |
author_facet | Paul Hanke Bruce Parrello Olga Vasieva Chase Akins Philippe Chlenski Gyorgy Babnigg Chris Henry Fatima Foflonker Thomas Brettin Dionysios Antonopoulos Rick Stevens Michael Fonstein |
author_sort | Paul Hanke |
collection | DOAJ |
description | The goal of this study is to develop a general strategy for bacterial engineering using an integrated synthetic biology and machine learning (ML) approach. This strategy was developed in the context of increasing L-threonine production in Escherichia coli ATCC 21277. A set of 16 genes was initially selected based on metabolic pathway relevance to threonine biosynthesis and used for combinatorial cloning to construct a set of 385 strains to generate training data (i.e., a range of L-threonine titers linked to each of the specific gene combinations). Hybrid (regression/classification) deep learning (DL) models were developed and used to predict additional gene combinations in subsequent rounds of combinatorial cloning for increased L-threonine production based on the training data. As a result, E. coli strains built after just three rounds of iterative combinatorial cloning and model prediction generated higher L-threonine titers (from 2.7 g/L to 8.4 g/L) than those of patented L-threonine strains being used as controls (4–5 g/L). Interesting combinations of genes in L-threonine production included deletions of the tdh, metL, dapA, and dhaM genes as well as overexpression of the pntAB, ppc, and aspC genes. Mechanistic analysis of the metabolic system constraints for the best performing constructs offers ways to improve the models by adjusting weights for specific gene combinations. Graph theory analysis of pairwise gene modifications and corresponding levels of L-threonine production also suggests additional rules that can be incorporated into future ML models. |
first_indexed | 2024-03-09T03:11:02Z |
format | Article |
id | doaj.art-7ecd1b4b29bf4bb09dc4bf3fb35386f3 |
institution | Directory Open Access Journal |
issn | 2214-0301 |
language | English |
last_indexed | 2024-03-09T03:11:02Z |
publishDate | 2023-12-01 |
publisher | Elsevier |
record_format | Article |
series | Metabolic Engineering Communications |
spelling | doaj.art-7ecd1b4b29bf4bb09dc4bf3fb35386f32023-12-04T05:21:52ZengElsevierMetabolic Engineering Communications2214-03012023-12-0117e00225Engineering of increased L-Threonine production in bacteria by combinatorial cloning and machine learningPaul Hanke0Bruce Parrello1Olga Vasieva2Chase Akins3Philippe Chlenski4Gyorgy Babnigg5Chris Henry6Fatima Foflonker7Thomas Brettin8Dionysios Antonopoulos9Rick Stevens10Michael Fonstein11Argonne National Laboratory, 9700 S. Cass Ave, Argonne, IL, 60439, USA; Corresponding author.University of Chicago, 5801 S. Ellis Ave, Chicago, IL, 60637, USABSMI, 1818 Skokie Blvd., #201, Northbrook, IL, 60062, USAArgonne National Laboratory, 9700 S. Cass Ave, Argonne, IL, 60439, USADepartment of Computer Science, Columbia University, New York, NY, 10027, USAArgonne National Laboratory, 9700 S. Cass Ave, Argonne, IL, 60439, USAArgonne National Laboratory, 9700 S. Cass Ave, Argonne, IL, 60439, USAArgonne National Laboratory, 9700 S. Cass Ave, Argonne, IL, 60439, USAArgonne National Laboratory, 9700 S. Cass Ave, Argonne, IL, 60439, USAArgonne National Laboratory, 9700 S. Cass Ave, Argonne, IL, 60439, USAArgonne National Laboratory, 9700 S. Cass Ave, Argonne, IL, 60439, USA; University of Chicago, 5801 S. Ellis Ave, Chicago, IL, 60637, USAArgonne National Laboratory, 9700 S. Cass Ave, Argonne, IL, 60439, USAThe goal of this study is to develop a general strategy for bacterial engineering using an integrated synthetic biology and machine learning (ML) approach. This strategy was developed in the context of increasing L-threonine production in Escherichia coli ATCC 21277. A set of 16 genes was initially selected based on metabolic pathway relevance to threonine biosynthesis and used for combinatorial cloning to construct a set of 385 strains to generate training data (i.e., a range of L-threonine titers linked to each of the specific gene combinations). Hybrid (regression/classification) deep learning (DL) models were developed and used to predict additional gene combinations in subsequent rounds of combinatorial cloning for increased L-threonine production based on the training data. As a result, E. coli strains built after just three rounds of iterative combinatorial cloning and model prediction generated higher L-threonine titers (from 2.7 g/L to 8.4 g/L) than those of patented L-threonine strains being used as controls (4–5 g/L). Interesting combinations of genes in L-threonine production included deletions of the tdh, metL, dapA, and dhaM genes as well as overexpression of the pntAB, ppc, and aspC genes. Mechanistic analysis of the metabolic system constraints for the best performing constructs offers ways to improve the models by adjusting weights for specific gene combinations. Graph theory analysis of pairwise gene modifications and corresponding levels of L-threonine production also suggests additional rules that can be incorporated into future ML models.http://www.sciencedirect.com/science/article/pii/S2214030123000081Strain engineeringThreonineMLHybrid-machine learningE. coliAI-Driven |
spellingShingle | Paul Hanke Bruce Parrello Olga Vasieva Chase Akins Philippe Chlenski Gyorgy Babnigg Chris Henry Fatima Foflonker Thomas Brettin Dionysios Antonopoulos Rick Stevens Michael Fonstein Engineering of increased L-Threonine production in bacteria by combinatorial cloning and machine learning Metabolic Engineering Communications Strain engineering Threonine ML Hybrid-machine learning E. coli AI-Driven |
title | Engineering of increased L-Threonine production in bacteria by combinatorial cloning and machine learning |
title_full | Engineering of increased L-Threonine production in bacteria by combinatorial cloning and machine learning |
title_fullStr | Engineering of increased L-Threonine production in bacteria by combinatorial cloning and machine learning |
title_full_unstemmed | Engineering of increased L-Threonine production in bacteria by combinatorial cloning and machine learning |
title_short | Engineering of increased L-Threonine production in bacteria by combinatorial cloning and machine learning |
title_sort | engineering of increased l threonine production in bacteria by combinatorial cloning and machine learning |
topic | Strain engineering Threonine ML Hybrid-machine learning E. coli AI-Driven |
url | http://www.sciencedirect.com/science/article/pii/S2214030123000081 |
work_keys_str_mv | AT paulhanke engineeringofincreasedlthreonineproductioninbacteriabycombinatorialcloningandmachinelearning AT bruceparrello engineeringofincreasedlthreonineproductioninbacteriabycombinatorialcloningandmachinelearning AT olgavasieva engineeringofincreasedlthreonineproductioninbacteriabycombinatorialcloningandmachinelearning AT chaseakins engineeringofincreasedlthreonineproductioninbacteriabycombinatorialcloningandmachinelearning AT philippechlenski engineeringofincreasedlthreonineproductioninbacteriabycombinatorialcloningandmachinelearning AT gyorgybabnigg engineeringofincreasedlthreonineproductioninbacteriabycombinatorialcloningandmachinelearning AT chrishenry engineeringofincreasedlthreonineproductioninbacteriabycombinatorialcloningandmachinelearning AT fatimafoflonker engineeringofincreasedlthreonineproductioninbacteriabycombinatorialcloningandmachinelearning AT thomasbrettin engineeringofincreasedlthreonineproductioninbacteriabycombinatorialcloningandmachinelearning AT dionysiosantonopoulos engineeringofincreasedlthreonineproductioninbacteriabycombinatorialcloningandmachinelearning AT rickstevens engineeringofincreasedlthreonineproductioninbacteriabycombinatorialcloningandmachinelearning AT michaelfonstein engineeringofincreasedlthreonineproductioninbacteriabycombinatorialcloningandmachinelearning |