A neural-mechanistic hybrid approach improving the predictive power of genome-scale metabolic models

被引:25
|
作者
Faure, Leon [1 ]
Mollet, Bastien [2 ,3 ]
Liebermeister, Wolfram [4 ]
Faulon, Jean-Loup [1 ,5 ]
机构
[1] Univ Paris Saclay, MICALIS Inst, INRAE, AgroParisTech, F-78350 Jouy En Josas, France
[2] Ecole Normale Super Lyon, F-69342 Lyon, France
[3] Univ Paris Saclay, UMR MIA, INRAE, AgroParisTech, F-91120 Palaiseau, France
[4] Univ Paris Saclay, MaIAGE, INRAE, F-78350 Jouy En Josas, France
[5] Univ Manchester, Manchester Inst Biotechnol, Manchester M1 7DN, England
关键词
ESCHERICHIA-COLI; RESOURCE-ALLOCATION; NETWORKS; OPTIMIZATION;
D O I
10.1038/s41467-023-40380-0
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Constraint-based metabolic models have been used for decades to predict the phenotype of microorganisms in different environments. However, quantitative predictions are limited unless labor-intensive measurements of media uptake fluxes are performed. We show how hybrid neural-mechanistic models can serve as an architecture for machine learning providing a way to improve phenotype predictions. We illustrate our hybrid models with growth rate predictions of Escherichia coli and Pseudomonas putida grown in different media and with phenotype predictions of gene knocked-out Escherichia coli mutants. Our neural-mechanistic models systematically outperform constraint-based models and require training set sizes orders of magnitude smaller than classical machine learning methods. Our hybrid approach opens a doorway to enhancing constraint-based modeling: instead of constraining mechanistic models with additional experimental measurements, our hybrid models grasp the power of machine learning while fulfilling mechanistic constrains, thus saving time and resources in typical systems biology or biological engineering projects.
引用
收藏
页数:14
相关论文
共 50 条
  • [31] Defining the nutritional input for genome-scale metabolic models: A roadmap
    Marinos, Georgios
    Kaleta, Christoph
    Waschina, Silvio
    PLOS ONE, 2020, 15 (08):
  • [32] Leveraging genome-scale metabolic models for human health applications
    Chowdhury, Shomeek
    Fong, Stephen S.
    CURRENT OPINION IN BIOTECHNOLOGY, 2020, 66 : 267 - 276
  • [33] Next-generation genome-scale models for metabolic engineering
    King, Zachary A.
    Lloyd, Colton J.
    Feist, Adam M.
    Palsson, Bernhard O.
    CURRENT OPINION IN BIOTECHNOLOGY, 2015, 35 : 23 - 29
  • [34] Applicatons of Genome-Scale Metabolic Models in Biotechnology and Systems Medicine
    Zhang, Cheng
    Hua, Qiang
    FRONTIERS IN PHYSIOLOGY, 2016, 6
  • [35] MetaboTools: A Comprehensive Toolbox for Analysis of Genome-Scale Metabolic Models
    Aurich, Maike K.
    Fleming, Ronan M. T.
    Thiele, Ines
    FRONTIERS IN PHYSIOLOGY, 2016, 7
  • [36] MapMaker and PathTracer for tracking carbon in genome-scale metabolic models
    Tervo, Christopher J.
    Reed, Jennifer L.
    BIOTECHNOLOGY JOURNAL, 2016, 11 (05) : 648 - 661
  • [37] Critical assessment of genome-scale metabolic models of Arabidopsis thaliana
    Amirzakaria, Javad Zamani
    Marashi, Sayed-Amir
    Malboobi, Mohammad Ali
    Lohrasebi, Tahmineh
    Forouzan, Esmail
    MOLECULAR OMICS, 2022, 18 (04) : 328 - 335
  • [38] Metingear: a development environment for annotating genome-scale metabolic models
    May, John W.
    James, A. Gordon
    Steinbeck, Christoph
    BIOINFORMATICS, 2013, 29 (17) : 2213 - 2215
  • [39] Methods for integration of transcriptomic data in genome-scale metabolic models
    Kim, Min Kyung
    Lun, Desmond S.
    COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL, 2014, 11 (18): : 59 - 65
  • [40] Recent advances in reconstruction and applications of genome-scale metabolic models
    Kim, Tae Yong
    Sohn, Seung Bum
    Kim, Yu Bin
    Kim, Won Jun
    Lee, Sang Yup
    CURRENT OPINION IN BIOTECHNOLOGY, 2012, 23 (04) : 617 - 623