A Machine Learning Approach for Efficient Selection of Enzyme Concentrations and Its Application for Flux Optimization

The metabolic engineering of pathways has been used extensively to produce molecules of interest on an industrial scale. Methods like gene regulation or substrate channeling helped to improve the desired product yield. Cell-free systems are used to overcome the weaknesses of engineered strains. One of the challenges in a cell-free system is selecting the optimized enzyme concentration for optimal yield. Here, a machine learning approach is used to select the enzyme concentration for the upper part of glycolysis. The artificial neural network approach (ANN) is known to be inefficient in extrapolating predictions outside the box: high predicted values will bump into a sort of “glass ceiling”. In order to explore this “glass ceiling” space, we developed a new methodology named glass ceiling ANN (GC-ANN). Principal component analysis (PCA) and data classification methods are used to derive a rule for a high flux, and ANN to predict the flux through the pathway using the input data of 121 balances of four enzymes in the upper part of glycolysis. The outcomes of this study are i. in silico selection of optimum enzyme concentrations for a maximum flux through the pathway and ii. experimental in vitro validation of the “out-of-the-box” fluxes predicted using this new approach. Surprisingly, flux improvements of up to 63% were obtained. Gratifyingly, these improvements are coupled with a cost decrease of up to 25% for the assay.

[1]  Nicolas Fontaine,et al.  Flux prediction using artificial neural network (ANN) for the upper part of glycolysis , 2019, PloS one.

[2]  Kristala L. J. Prather,et al.  Dynamic pathway regulation: recent advances and methods of construction. , 2017, Current opinion in chemical biology.

[3]  Neil Swainston,et al.  Selenzyme: enzyme selection tool for pathway design , 2017, bioRxiv.

[4]  Long Liu,et al.  Protein and metabolic engineering for the production of organic acids. , 2017, Bioresource technology.

[5]  Daniel N. Wilson,et al.  Proline-rich antimicrobial peptides targeting protein synthesis. , 2017, Natural product reports.

[6]  Yuan Lu Cell-free synthetic biology: Engineering in an open world , 2017, Synthetic and systems biotechnology.

[7]  Liming Liu,et al.  Engineering rTCA pathway and C4-dicarboxylate transporter for l-malic acid production , 2017, Applied Microbiology and Biotechnology.

[8]  Matthew K. Theisen,et al.  Industrial Biotechnology: Escherichia coli as a Host , 2016 .

[9]  J. Mayer,et al.  Chemical synthesis of peptides within the insulin superfamily , 2016, Journal of peptide science : an official publication of the European Peptide Society.

[10]  Scott Calabrese Barton,et al.  Substrate channelling as an approach to cascade reactions. , 2016, Nature chemistry.

[11]  Y. Zhang,et al.  Production of biofuels and biochemicals by in vitro synthetic biosystems: Opportunities and challenges. , 2015, Biotechnology advances.

[12]  Shangtian Yang,et al.  Metabolic and process engineering of Clostridium cellulovorans for biofuel production from cellulose. , 2015, Metabolic engineering.

[13]  Francisco Bolívar,et al.  Shikimic Acid Production in Escherichia coli: From Classical Metabolic Engineering Strategies to Omics Applied to Improve Its Production , 2015, Front. Bioeng. Biotechnol..

[14]  Zhou-Ran Lan,et al.  Optimization of Culture Medium for Maximal Production of Spinosad Using an Artificial Neural Network - Genetic Algorithm Modeling , 2015, Journal of Molecular Microbiology and Biotechnology.

[15]  Frédéric Cadet,et al.  Modeling of a Cell-Free Synthetic System for Biohydrogen Production , 2015 .

[16]  H. Hojo Recent progress in the chemical synthesis of proteins. , 2014, Current opinion in structural biology.

[17]  Jiangang Yang,et al.  Metabolic engineering of Escherichia coli and in silico comparing of carboxylation pathways for high succinate productivity under aerobic conditions. , 2014, Microbiological research.

[18]  Muhammad Wajid Ullah,et al.  Yeast cell-free enzyme system for bio-ethanol production at elevated temperatures , 2014 .

[19]  Jiayuan Sheng,et al.  Reconstitution of the peptidoglycan cytoplasmic precursor biosynthetic pathway in cell-free system and rapid screening of antisense oligonucleotides for Mur enzymes , 2014, Applied Microbiology and Biotechnology.

[20]  Dong In Kim,et al.  Metabolic engineering of Escherichia coli for the production of fumaric acid , 2013, Biotechnology and bioengineering.

[21]  Bradley Charles Bundy,et al.  Streamlined extract preparation for Escherichia coli-based cell-free protein synthesis by sonication or bead vortex mixing. , 2012, BioTechniques.

[22]  Jeong Wook Lee,et al.  Systems metabolic engineering of microorganisms for natural and non-natural chemicals. , 2012, Nature chemical biology.

[23]  Roman M. Balabin,et al.  Interpolation and extrapolation problems of multivariate regression in analytical chemistry: benchmarking the robustness on near-infrared (NIR) spectroscopy data. , 2012, The Analyst.

[24]  Y.‐H.P. Zhang,et al.  Substrate channeling and enzyme complexes for biotechnological applications. , 2011, Biotechnology advances.

[25]  A. Burgard,et al.  Metabolic engineering of Escherichia coli for direct production of 1,4-butanediol. , 2011, Nature chemical biology.

[26]  Y.‐H.P. Zhang,et al.  Renewable carbohydrates are a potential high-density hydrogen carrier , 2010 .

[27]  Y.‐H.P. Zhang,et al.  Production of biocommodities and bioelectricity by cell-free synthetic enzymatic pathway biotransformations: challenges and opportunities. , 2010, Biotechnology and bioengineering.

[28]  Jeffrey D Orth,et al.  What is flux balance analysis? , 2010, Nature Biotechnology.

[29]  James M Clomburg,et al.  Biofuel production in Escherichia coli: the role of metabolic engineering and synthetic biology , 2010, Applied Microbiology and Biotechnology.

[30]  J. Mielenz,et al.  Spontaneous high-yield production of hydrogen from cellulosic materials and water catalyzed by enzyme cocktails. , 2009, ChemSusChem.

[31]  N. Kikuchi,et al.  CellDesigner 3.5: A Versatile Modeling Tool for Biochemical Networks , 2008, Proceedings of the IEEE.

[32]  Sébastien Lê,et al.  FactoMineR: An R Package for Multivariate Analysis , 2008 .

[33]  Markus Ringnér,et al.  What is principal component analysis? , 2008, Nature Biotechnology.

[34]  D. Broomhead,et al.  Something from nothing − bridging the gap between constraint‐based and kinetic modelling , 2007, The FEBS journal.

[35]  Mudita Singhal,et al.  COPASI - a COmplex PAthway SImulator , 2006, Bioinform..

[36]  Christine Dillmann,et al.  Simplified modelling of metabolic pathways for flux prediction and optimization: lessons from an in vitro reconstruction of the upper part of glycolysis. , 2006, The Biochemical journal.

[37]  Gregory Stephanopoulos,et al.  Evaluation of regression models in metabolic physiology: predicting fluxes from isotopic data without knowledge of the pathway , 2006, Metabolomics.

[38]  Junhao Yang,et al.  Rapid expression of vaccine proteins for B-cell lymphoma in a cell-free system. , 2005, Biotechnology and bioengineering.

[39]  J. Stelling Mathematical models in microbial systems biology. , 2004, Current opinion in microbiology.

[40]  Ulf Leser,et al.  Finding kinetic parameters using text mining. , 2004, Omics : a journal of integrative biology.

[41]  B. Palsson,et al.  Identifying constraints that govern cell behavior: a key to converting conceptual to computational models in biology? , 2003, Biotechnology and bioengineering.

[42]  Hiroaki Kitano,et al.  CellDesigner: a process diagram editor for gene-regulatory and biochemical networks , 2003 .

[43]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[44]  Barbara M. Bakker,et al.  Can yeast glycolysis be understood in terms of in vitro kinetics of the constituent enzymes? Testing biochemistry. , 2000, European journal of biochemistry.

[45]  G. Fields,et al.  Chemical synthesis of proteins. , 2000, Trends in biotechnology.

[46]  M. J. Hall,et al.  Artificial neural networks as rainfall-runoff models , 1996 .

[47]  Paul Geladi,et al.  Principal Component Analysis , 1987, Comprehensive Chemometrics.

[48]  M. M. Bradford A rapid and sensitive method for the quantitation of microgram quantities of protein utilizing the principle of protein-dye binding. , 1976, Analytical biochemistry.

[49]  Umberto Michelucci,et al.  Training Neural Networks , 2018 .

[50]  Mohammad Hossein Morowvat,et al.  Medium Optimization by Artificial Neural Networks for Maximizing the Triglycerides-Rich Lipids from Biomass of Chlorella vulgaris , 2016 .

[51]  Anurag S Rathore,et al.  Design of experiments applications in bioprocessing: Concepts and approach , 2014, Biotechnology progress.

[52]  M. Jewett,et al.  Substrate replenishment and byproduct removal improve yeast cell-free protein synthesis. , 2014, Biotechnology journal.

[53]  Stefan Fritsch,et al.  neuralnet: Training of Neural Networks , 2010, R J..

[54]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[55]  Claus Weihs,et al.  klaR Analyzing German Business Cycles , 2005, Data Analysis and Decision Support.

[56]  Antje Chang,et al.  BRENDA, enzyme data and metabolic information , 2002, Nucleic Acids Res..

[57]  P. Brodelius Enzyme assays. , 1991, Current opinion in biotechnology.