Recent advances on constraint-based models by integrating machine learning.

Research that meaningfully integrates constraint-based modeling with machine learning is at its infancy but holds much promise. Here, we consider where machine learning has been implemented within the constraint-based modeling reconstruction framework and highlight the need to develop approaches that can identify meaningful features from large-scale data and connect them to biological mechanisms to establish causality to connect genotype to phenotype. We motivate the construction of iterative integrative schemes where machine learning can fine-tune the input constraints in a constraint-based model or contrarily, constraint-based model simulation results are analyzed by machine learning and reconciled with experimental data. This can iteratively refine a constraint-based model until there is consistency between experimental data, machine learning results, and constraint-based model simulations.

[1]  Daniel Machado,et al.  Systematic Evaluation of Methods for Integration of Transcriptomic Data into Constraint-Based Models of Metabolism , 2014, PLoS Comput. Biol..

[2]  Marinka Zitnik,et al.  Data Fusion by Matrix Factorization , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Markus J. Herrgård,et al.  Network-based prediction of human tissue-specific metabolism , 2008, Nature Biotechnology.

[4]  Hong Liu,et al.  Incorporating microbial community data with machine learning techniques to predict feed substrates in microbial fuel cells. , 2019, Biosensors & bioelectronics.

[5]  Peter D. Karp,et al.  Machine learning methods for metabolic pathway prediction , 2010 .

[6]  Sutanu Nandi,et al.  An integrative machine learning strategy for improved prediction of essential genes in Escherichia coli metabolism using flux-coupled features. , 2017, Molecular bioSystems.

[7]  Renchu Guan,et al.  Multi-label Deep Learning for Gene Function Annotation in Cancer Pathways , 2018, Scientific Reports.

[8]  M. Saunders,et al.  DynamicME: dynamic simulation and refinement of integrated models of metabolism and protein expression , 2018, bioRxiv.

[9]  Andrus Seiman,et al.  Model-based metabolism design: constraints for kinetic and stoichiometric models , 2018, Biochemical Society transactions.

[10]  F. Doyle,et al.  Dynamic flux balance analysis of diauxic growth in Escherichia coli. , 2002, Biophysical journal.

[11]  Marcus Oswald,et al.  Machine learning based analyses on metabolic networks supports high-throughput knockout screens , 2008, BMC Systems Biology.

[12]  Bas Teusink,et al.  Accelerating the reconstruction of genome-scale metabolic networks , 2006, BMC Bioinformatics.

[13]  Zhuowen Tu,et al.  Similarity network fusion for aggregating data types on a genomic scale , 2014, Nature Methods.

[14]  Partho Sen,et al.  Metabolic Modeling of Human Gut Microbiota on a Genome Scale: An Overview , 2019, Metabolites.

[15]  Eduardo Agosin,et al.  Expanding a dynamic flux balance model of yeast fermentation to genome-scale , 2011, BMC Systems Biology.

[16]  Yuxuan Wang,et al.  Rapid Prediction of Bacterial Heterotrophic Fluxomics Using Machine Learning and Constraint Programming , 2016, PLoS Comput. Biol..

[17]  Aarash Bordbar,et al.  Elucidating dynamic metabolic physiology through network integration of quantitative time-course metabolomics , 2017, Scientific Reports.

[18]  Jeffrey D. Orth,et al.  Systematizing the generation of missing metabolic knowledge , 2010, Biotechnology and bioengineering.

[19]  Alioune Ngom,et al.  A review on machine learning principles for multi-view biological data integration , 2016, Briefings Bioinform..

[20]  Adam M. Feist,et al.  Identification of growth-coupled production strains considering protein costs and kinetic variability , 2018, Metabolic engineering communications.

[21]  Robert Hoehndorf,et al.  Prediction of Metabolic Pathway Involvement in Prokaryotic UniProtKB Data by Association Rule Mining , 2016, PloS one.

[22]  Ronan M. T. Fleming,et al.  Do genome-scale models need exact solvers or clearer standards? , 2015, Molecular systems biology.

[23]  Neil Swainston,et al.  Machine Learning of Designed Translational Control Allows Predictive Pathway Optimization in Escherichia coli. , 2019, ACS synthetic biology.

[24]  Feiping Nie,et al.  Multiview Consensus Graph Clustering , 2019, IEEE Transactions on Image Processing.

[25]  Jennifer L Reed,et al.  Advances in gap-filling genome-scale metabolic models and model-driven experiments lead to novel metabolic discoveries. , 2018, Current opinion in biotechnology.

[26]  Jason A. Papin,et al.  Community standards to facilitate development and address challenges in metabolic modeling , 2019, bioRxiv.

[27]  B. Palsson,et al.  A protocol for generating a high-quality genome-scale metabolic reconstruction , 2010 .

[28]  Steffen Klamt,et al.  OptMDFpathway: Identification of metabolic pathways with maximal thermodynamic driving force and its application for analyzing the endogenous CO2 fixation potential of Escherichia coli , 2018, PLoS Comput. Biol..

[29]  Miriam L. Land,et al.  Trace: Tennessee Research and Creative Exchange Prodigal: Prokaryotic Gene Recognition and Translation Initiation Site Identification Recommended Citation Prodigal: Prokaryotic Gene Recognition and Translation Initiation Site Identification , 2022 .

[30]  B. Palsson,et al.  Systems approach to refining genome annotation , 2006, Proceedings of the National Academy of Sciences.

[31]  Steffen Klamt,et al.  Memote: A community driven effort towards a standardized genome-scale metabolic model test suite , 2018, bioRxiv.

[32]  Christoph B. Messner,et al.  Machine Learning Predicts the Yeast Metabolome from the Quantitative Proteome of Kinase Knockouts , 2018, Cell systems.

[33]  Barry A. Bunin,et al.  Machine Learning Models and Pathway Genome Data Base for Trypanosoma cruzi Drug Discovery , 2015, PLoS neglected tropical diseases.

[34]  David S. Wishart,et al.  BioTransformer: a comprehensive computational tool for small molecule metabolism prediction and metabolite identification , 2019, Journal of Cheminformatics.

[35]  Zak Costello,et al.  A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data , 2018, npj Systems Biology and Applications.

[36]  Miguel Rocha,et al.  Methods for automated genome-scale metabolic model reconstruction. , 2018, Biochemical Society transactions.

[37]  R. Sharan,et al.  Metabolic Network Prediction of Drug Side Effects. , 2016, Cell systems.

[38]  Hongbin Yang,et al.  Multiclassification Prediction of Enzymatic Reactions for Oxidoreductases and Hydrolases Using Reaction Fingerprints and Machine Learning Methods , 2018, J. Chem. Inf. Model..

[39]  Prospero C. Naval,et al.  Parameter estimation using Simulated Annealing for S-system models of biochemical networks , 2007, Bioinform..

[40]  Chris J. Myers,et al.  The Systems Biology Markup Language (SBML): Language Specification for Level 3 Version 2 Core Release 2 , 2018, J. Integr. Bioinform..

[41]  Juho Rousu,et al.  Metabolite Identification through Machine Learning — Tackling CASMI Challenge Using FingerID , 2013, Metabolites.

[42]  Daniel C. Zielinski,et al.  Machine learning applied to enzyme turnover numbers reveals protein structural correlates and improves metabolic models , 2018, Nature Communications.

[43]  Masaru Tomita,et al.  GEM System: automatic prototyping of cell-wide metabolic pathway models from genomes , 2006, BMC Bioinformatics.

[44]  Di Liu,et al.  Machine learning framework for assessment of microbial factory performance , 2019, PloS one.

[45]  Jörg Stelling,et al.  Integrating -omics data into genome-scale metabolic network models: principles and challenges. , 2018, Essays in biochemistry.

[46]  Ljubisa Miskovic,et al.  iSCHRUNK--In Silico Approach to Characterization and Reduction of Uncertainty in the Kinetic Models of Genome-scale Metabolic Networks. , 2016, Metabolic engineering.

[47]  Aidong Yang,et al.  Flux Balance Analysis Incorporating a Coarse-grained Proteome Constraint for Predicting Overflow Metabolism in Escherichia Coli , 2019, Computer Aided Chemical Engineering.

[48]  Tom M. Conrad,et al.  Omic data from evolved E. coli are consistent with computed optimal growth from genome-scale models , 2010, Molecular systems biology.

[49]  Rick L. Stevens,et al.  The RAST Server: Rapid Annotations using Subsystems Technology , 2008, BMC Genomics.

[50]  Torsten Seemann,et al.  Prokka: rapid prokaryotic genome annotation , 2014, Bioinform..

[51]  Yixin Chen,et al.  Integrating Flux Balance Analysis into Kinetic Models to Decipher the Dynamic Metabolism of Shewanella oneidensis MR-1 , 2012, PLoS Comput. Biol..

[52]  S. Oliver,et al.  An integrated approach to characterize genetic interaction networks in yeast metabolism , 2011, Nature Genetics.