Advances in flux balance analysis by integrating machine learning and mechanism-based models

Sahu, Ankur; Blätke, Mary Ann; Szymański, Jędrzej; Töpfer, Nadine

doi:10.1016/j.csbj.2021.08.004

Cited by 40 publications

(27 citation statements)

References 157 publications

(120 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So far, AI techniques are usually employed to complement theory-based biological modelling, e.g. for selecting molecular features which are used as inputs of FBA models [ 93 ], aiding to generate constraint-based models by determining more precise flux boundaries [ 94 ], and analysing simulation results with AI techniques [ 94 ]. However, this kind of integration does not belong to the focus of our review of hybrid modelling methods, where we expect to see at least two modelling formalisms, each representing a part of a system.…”

Section: Hybrid Modelling Methodsmentioning

confidence: 99%

Hybrid modelling of biological systems: current progress and future prospects

Liu

Heiner

Gilbert

2022

Briefings in Bioinformatics

View full text Add to dashboard Cite

Integrated modelling of biological systems is becoming a necessity for constructing models containing the major biochemical processes of such systems in order to obtain a holistic understanding of their dynamics and to elucidate emergent behaviours. Hybrid modelling methods are crucial to achieve integrated modelling of biological systems. This paper reviews currently popular hybrid modelling methods, developed for systems biology, mainly revealing why they are proposed, how they are formed from single modelling formalisms and how to simulate them. By doing this, we identify future research requirements regarding hybrid approaches for further promoting integrated modelling of biological systems.

show abstract

Section: Hybrid Modelling Methodsmentioning

confidence: 99%

Hybrid modelling of biological systems: current progress and future prospects

Liu

Heiner

Gilbert

2022

Briefings in Bioinformatics

View full text Add to dashboard Cite

show abstract

“…Machine learning complements FBA by extracting relevant information from interacting datasets and improving result interpretation [109]. The in-depth combination of machine learning and artificial intelligence, automated training, and calibration based on the large amounts of real data further improves the accuracy and efficiency of phenotypic prediction [110].…”

Section: Conclusion and Prospectsmentioning

confidence: 99%

In silico cell factory design driven by comprehensive genome-scale metabolic models: development and challenges

Liu

et al. 2022

Syst Microbiol and Biomanuf

View full text Add to dashboard Cite

Genome-scale metabolic models (GEMs) have been widely used to design cell factories in silico. However, initial flux balance analysis only considers stoichiometry and reaction direction constraints, so it cannot accurately describe the distribution of metabolic flux under the control of various regulatory mechanisms. In the recent years, by introducing enzymology, thermodynamics, and other multiomics-based constraints into GEMs, the metabolic state of cells under different conditions was more accurately simulated and a series of algorithms have been presented for microbial phenotypic analysis. Herein, the development of multiconstrained GEMs was reviewed by taking the constraints of enzyme kinetics, thermodynamics, and transcriptional regulatory mechanisms as examples. This review focused on introducing and summarizing GEMs application tools and cases in cell factory design. The challenges and prospects of GEMs development were also discussed.

show abstract

“…Naturally, ML approaches were developed to efficiently integrate the data and enhance the predictive power of CBM. However, as described by Sahu et al [12], in MFA, the interplay between CBM and ML is still showing a gap: some approaches use ML as input for CBM, others use CBM as input for ML, but none of them can do both, like we attempt to do in this paper with the Artificial Metabolic Networks (AMNs) hybrid model.…”

Section: Introductionmentioning

confidence: 97%

“…However, as described by Sahu et al . 13 , the interplay between FBA and ML still shows a gap: some approaches use ML results as input for FBA, others use FBA results as input for ML, but none of them embed FBA into ML, as we do in this paper with the Artificial Metabolic Networks (AMNs) hybrid models.…”

Section: Introductionmentioning

confidence: 98%

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

Faure

Mollet

Liebermeister

et al. 2022

Preprint

View full text Add to dashboard Cite

Metabolic networks have largely been exploited as mechanistic tools to predict the behavior of microorganisms with a defined genotype in different environments. However, flux predictions by constraint-based modeling approaches are limited in quality unless labor-intensive experiments including the measurement of media intake fluxes, are performed. Using machine learning instead of an optimization of biomass flux - on which most existing constraint-based methods are based - provides ways to improve flux and growth rate predictions. In this paper, we show how Recurrent Neural Networks can surrogate constraint-based modeling and make metabolic networks suitable for backpropagation and consequently be used as an architecture for machine learning. We refer to our hybrid - mechanistic and neural network - models as Artificial Metabolic Networks (AMN). We showcase AMN and illustrate its performance with an experimental dataset of Escherichia coli growth rates in 73 different media compositions. We reach a regression coefficient of R2=0.78 on cross-validation sets. We expect AMNs to provide easier discovery of metabolic insights and prompt new biotechnological applications.

show abstract

Advances in flux balance analysis by integrating machine learning and mechanism-based models

Abstract: Graphical abstract

Cited by 40 publications

References 157 publications

Hybrid modelling of biological systems: current progress and future prospects

Hybrid modelling of biological systems: current progress and future prospects

In silico cell factory design driven by comprehensive genome-scale metabolic models: development and challenges

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

Contact Info

Product

Resources

About