Guiding the Refinement of Biochemical Knowledgebases with Ensembles of Metabolic Networks and Machine Learning

Machine learning for the advancement of genome-scale metabolic modeling

Constraint-based modeling (CBM) has evolved as the core systems biology tool to map the interrelations between genotype, phenotype, and external environment. The recent advancement of high-throughput experimental approaches and multi-omics strategies has generated a plethora of new and precise information from wide-ranging biological domains. On the other hand, the continuously growing field of machine learning (ML) and its specialized branch of deep learning (DL) provide essential computational architectures for decoding complex and heterogeneous biological data. In recent years, both multi-omics and ML have assisted in the escalation of CBM. Condition-specific omics data, such as transcriptomics and proteomics, helped contextualize the model prediction while analyzing a particular phenotypic signature. At the same time, the advanced ML tools have eased the model reconstruction and analysis to increase the accuracy and prediction power. However, the development of these multi-disciplinary methodological frameworks mainly occurs independently, which limits the concatenation of biological knowledge from different domains. Hence, we have reviewed the potential of integrating multi-disciplinary tools and strategies from various fields, such as synthetic biology, CBM, omics, and ML, to explore the biochemical phenomenon beyond the conventional biological dogma. How the integrative knowledge of these intersected domains has improved bioengineering and biomedical applications has also been highlighted. We categorically explained the conventional genome-scale metabolic model (GEM) reconstruction tools and their improvement strategies through ML paradigms. Further, the crucial role of ML and DL in omics data restructuring for GEM development has also been briefly discussed. Finally, the case-study-based assessment of the state-of-the-art method for improving biomedical and metabolic engineering strategies has been elaborated. Therefore, this review demonstrates how integrating experimental and in silico strategies can help map the ever-expanding knowledge of biological systems driven by condition-specific cellular information. This multiview approach will elevate the application of ML-based CBM in the biomedical and bioengineering fields for the betterment of society and the environment.

Emerging tools and best practices for studying gut microbial community metabolism

The human gut microbiome vastly extends the set of metabolic reactions catalysed by our own cells, with far-reaching consequences for host health and disease. However, our knowledge of gut microbial metabolism relies on a handful of model organisms, limiting our ability to interpret and predict the metabolism of complex microbial communities. In this Perspective, we discuss emerging tools for analysing and modelling the metabolism of gut microorganisms and for linking microorganisms, pathways and metabolites at the ecosystem level, highlighting promising best practices for researchers. Continued progress in this area will also require infrastructure development to facilitate cross-disciplinary synthesis of scientific findings. Collectively, these efforts can enable a broader and deeper understanding of the workings of the gut ecosystem and open new possibilities for microbiome manipulation and therapy.

Emerging methods for genome-scale metabolic modeling of microbial communities

Genome-scale metabolic models (GEMs) are consolidating as platforms for studying mixed microbial populations, by combining biological data and knowledge with mathematical rigor. However, deploying these models to answer research questions can be challenging due to the increasing number of available computational tools, the lack of universal standards, and their inherent limitations. Here, we present a comprehensive overview of foundational concepts for building and evaluating genome-scale models of microbial communities. We then compare tools in terms of requirements, capabilities, and applications. Next, we highlight the current pitfalls and open challenges to consider when adopting existing tools and developing new ones. Our compendium can be relevant for the expanding community of modelers, both at the entry and experienced levels.

Machine Learning and Deep Learning in Synthetic Biology: Key Architectures, Applications, and Challenges

Machine learning (ML), particularly deep learning (DL), has made rapid and substantial progress in synthetic biology in recent years. Biotechnological applications of biosystems, including pathways, enzymes, and whole cells, are being probed frequently with time. The intricacy and interconnectedness of biosystems make it challenging to design them with the desired properties. ML and DL have a synergy with synthetic biology. Synthetic biology can be employed to produce large data sets for training models (for instance, by utilizing DNA synthesis), and ML/DL models can be employed to inform design (for example, by generating new parts or advising unrivaled experiments to perform). This potential has recently been brought to light by research at the intersection of engineering biology and ML/DL through achievements like the design of novel biological components, best experimental design, automated analysis of microscopy data, protein structure prediction, and biomolecular implementations of ANNs (Artificial Neural Networks). I have divided this review into three sections. In the first section, I describe predictive potential and basics of ML along with myriad applications in synthetic biology, especially in engineering cells, activity of proteins, and metabolic pathways. In the second section, I describe fundamental DL architectures and their applications in synthetic biology. Finally, I describe different challenges causing hurdles in the progress of ML/DL and synthetic biology along with their solutions.

A computational model of Pseudomonas syringae metabolism unveils a role for branched-chain amino acids in Arabidopsis leaf colonization

Bacterial pathogens adapt their metabolism to the plant environment to successfully colonize their hosts. In our efforts to uncover the metabolic pathways that contribute to the colonization of Arabidopsis thaliana leaves by Pseudomonas syringae pv tomato DC3000 (Pst DC3000), we created iPst19, an ensemble of 100 genome-scale network reconstructions of Pst DC3000 metabolism. We developed a novel approach for gene essentiality screens, leveraging the predictive power of iPst19 to identify core and ancillary condition-specific essential genes. Constraining the metabolic flux of iPst19 with Pst DC3000 gene expression data obtained from naïve-infected or pre-immunized-infected plants, revealed changes in bacterial metabolism imposed by plant immunity. Machine learning analysis revealed that among other amino acids, branched-chain amino acids (BCAAs) metabolism significantly contributed to the overall metabolic status of each gene-expression-contextualized iPst19 simulation. These predictions were tested and confirmed experimentally. Pst DC3000 growth and gene expression analysis showed that BCAAs suppress virulence gene expression in vitro without affecting bacterial growth. In planta, however, an excess of BCAAs suppress the expression of virulence genes at the early stages of infection and significantly impair the colonization of Arabidopsis leaves. Our findings suggesting that BCAAs catabolism is necessary to express virulence and colonize the host. Overall, this study provides valuable insights into how plant immunity impacts Pst DC3000 metabolism, and how bacterial metabolism impacts the expression of virulence.

Combined mechanistic modeling and machine-learning approaches in systems biology - A systematic literature review

BACKGROUND AND OBJECTIVE

Mechanistic-based Model simulations (MM) are an effective approach commonly employed, for research and learning purposes, to better investigate and understand the inherent behavior of biological systems. Recent advancements in modern technologies and the large availability of omics data allowed the application of Machine Learning (ML) techniques to different research fields, including systems biology. However, the availability of information regarding the analyzed biological context, sufficient experimental data, as well as the degree of computational complexity, represent some of the issues that both MMs and ML techniques could present individually. For this reason, recently, several studies suggest overcoming or significantly reducing these drawbacks by combining the above-mentioned two methods. In the wake of the growing interest in this hybrid analysis approach, with the present review, we want to systematically investigate the studies available in the scientific literature in which both MMs and ML have been combined to explain biological processes at genomics, proteomics, and metabolomics levels, or the behavior of entire cellular populations.

METHODS

Elsevier Scopus®, Clarivate Web of Science™ and National Library of Medicine PubMed® databases were enquired using the queries reported in Table 1, resulting in 350 scientific articles.

RESULTS

Only 14 of the 350 documents returned by the comprehensive search conducted on the three major online databases met our search criteria, i.e. present a hybrid approach consisting of the synergistic combination of MMs and ML to treat a particular aspect of systems biology.

CONCLUSIONS

Despite the recent interest in this methodology, from a careful analysis of the selected papers, it emerged how examples of integration between MMs and ML are already present in systems biology, highlighting the great potential of this hybrid approach to both at micro and macro biological scales.

Modeling of astaxanthin biosynthesis via machine learning, mathematical and metabolic network modeling

Natural astaxanthin is synthesized by diverse organisms including: bacteria, fungi, microalgae, and plants involving complex cellular processes, which depend on numerous interrelated parameters. Nonetheless, existing knowledge regarding astaxanthin biosynthesis and the conditions influencing astaxanthin accumulation is fairly limited. Thus, manipulation of the growth conditions to achieve desired biomass and astaxanthin yields can be a complicated process requiring cost-intensive and time-consuming experiment-based research. As a potential solution, modeling and simulation of biological systems have recently emerged, allowing researchers to predict/estimate astaxanthin production dynamics in selected organisms. Moreover, mathematical modeling techniques would enable further optimization of astaxanthin synthesis in a shorter period of time, ultimately contributing to a notable reduction in production costs. Thus, the present review comprehensively discusses existing mathematical modeling techniques which simulate the bioaccumulation of astaxanthin in diverse organisms. Associated challenges, solutions, and future perspectives are critically analyzed and presented.

Recent advances in data- and knowledge-driven approaches to explore primary microbial metabolism

With the rapid progress in metabolomics and sequencing technologies, more data on the metabolome of single microbes and their communities become available, revealing the potential of microorganisms to metabolize a broad range of chemical compounds. The analysis of microbial metabolomics datasets remains challenging since it inherits the technical challenges of metabolomics analysis, such as compound identification and annotation, while harboring challenges in data interpretation, such as distinguishing metabolite sources in mixed samples. This review outlines the recent advances in computational methods to analyze primary microbial metabolism: knowledge-based approaches that take advantage of metabolic and molecular networks and data-driven approaches that employ machine/deep learning algorithms in combination with large-scale datasets. These methods aim at improving metabolite identification and disentangling reciprocal interactions between microbes and metabolites. We also discuss the perspective of combining these approaches and further developments required to advance the investigation of primary metabolism in mixed microbial samples.

Integrating Omics Data in Genome-Scale Metabolic Modeling: A Methodological Perspective for Precision Medicine

Recent advancements in omics technologies have generated a wealth of biological data. Integrating these data within mathematical models is essential to fully leverage their potential. Genome-scale metabolic models (GEMs) provide a robust framework for studying complex biological systems. GEMs have significantly contributed to our understanding of human metabolism, including the intrinsic relationship between the gut microbiome and the host metabolism. In this review, we highlight the contributions of GEMs and discuss the critical challenges that must be overcome to ensure their reproducibility and enhance their prediction accuracy, particularly in the context of precision medicine. We also explore the role of machine learning in addressing these challenges within GEMs. The integration of omics data with GEMs has the potential to lead to new insights, and to advance our understanding of molecular mechanisms in human health and disease.

Extracting functionally accurate context-specific models of Atlantic salmon metabolism

Constraint-based models (CBMs) are used to study metabolic network structure and function in organisms ranging from microbes to multicellular eukaryotes. Published CBMs are usually generic rather than context-specific, meaning that they do not capture differences in reaction activities, which, in turn, determine metabolic capabilities, between cell types, tissues, environments, or other conditions. Only a subset of a CBM's metabolic reactions and capabilities are likely to be active in any given context, and several methods have therefore been developed to extract context-specific models from generic CBMs through integration of omics data. We tested the ability of six model extraction methods (MEMs) to create functionally accurate context-specific models of Atlantic salmon using a generic CBM (SALARECON) and liver transcriptomics data from contexts differing in water salinity (life stage) and dietary lipids. Three MEMs (iMAT, INIT, and GIMME) outperformed the others in terms of functional accuracy, which we defined as the extracted models' ability to perform context-specific metabolic tasks inferred directly from the data, and one MEM (GIMME) was faster than the others. Context-specific versions of SALARECON consistently outperformed the generic version, showing that context-specific modeling better captures salmon metabolism. Thus, we demonstrate that results from human studies also hold for a non-mammalian animal and major livestock species.

Teasing out missing reactions in genome-scale metabolic networks through hypergraph learning

GEnome-scale Metabolic models (GEMs) are powerful tools to predict cellular metabolism and physiological states in living organisms. However, due to our imperfect knowledge of metabolic processes, even highly curated GEMs have knowledge gaps (e.g., missing reactions). Existing gap-filling methods typically require phenotypic data as input to tease out missing reactions. We still lack a computational method for rapid and accurate gap-filling of metabolic networks before experimental data is available. Here we present a deep learning-based method - CHEbyshev Spectral HyperlInk pREdictor (CHESHIRE) - to predict missing reactions in GEMs purely from metabolic network topology. We demonstrate that CHESHIRE outperforms other topology-based methods in predicting artificially removed reactions over 926 high- and intermediate-quality GEMs. Furthermore, CHESHIRE is able to improve the phenotypic predictions of 49 draft GEMs for fermentation products and amino acids secretions. Both types of validation suggest that CHESHIRE is a powerful tool for GEM curation to reveal unknown links between reactions and observed metabolic phenotypes.

New perspectives into the vaginal microbiome with systems biology

The vaginal microbiome (VMB) is critical to female reproductive health; however, the mechanisms associated with optimal and non-optimal states remain poorly understood due to the complex community structure and dynamic nature. Quantitative systems biology techniques applied to the VMB have improved understanding of community composition and function using primarily statistical methods. In contrast, fewer mechanistic models that use a priori knowledge of VMB features to develop predictive models have been implemented despite their use for microbiomes at other sites, including the gastrointestinal tract. Here, we explore systems biology approaches that have been applied in the VMB, highlighting successful techniques and discussing new directions that hold promise for improving understanding of health and disease.

etiBsu1209: A comprehensive multiscale metabolic model for Bacillus subtilis

Genome-scale metabolic models (GEMs) have been widely used to guide the computational design of microbial cell factories, and to date, seven GEMs have been reported for Bacillus subtilis, a model gram-positive microorganism widely used in bioproduction of functional nutraceuticals and food ingredients. However, none of them are widely used because they often lead to erroneous predictions due to their low predictive power and lack of information on regulatory mechanisms. In this work, we constructed a new version of GEM for B. subtilis (iBsu1209), which contains 1209 genes, 1595 metabolites, and 1948 reactions. We applied machine learning to fill gaps, which formed a relatively complete metabolic network able to predict with high accuracy (89.3%) the growth of 1209 mutants under 12 different culture conditions. In addition, we developed a visualization and code-free software, Model Tool, for multiconstraints model reconstruction and analysis. We used this software to construct etiBsu1209, a multiscale model that integrates enzymatic constraints, thermodynamic constraints, and transcriptional regulatory networks. Furthermore, we used etiBsu1209 to guide a metabolic engineering strategy (knocking out fabI and yfkN genes) for the overproduction of nutraceutical menaquinone-7, and the titer increased to 153.94 mg/L, 2.2-times that of the parental strain. To the best of our knowledge, etiBsu1209 is the first comprehensive multiscale model for B. subtilis and can serve as a solid basis for rational computational design of B. subtilis cell factories for bioproduction.

Emerging computational paradigms to address the complex role of gut microbial metabolism in cardiovascular diseases

The human gut microbiota and its associated perturbations are implicated in a variety of cardiovascular diseases (CVDs). There is evidence that the structure and metabolic composition of the gut microbiome and some of its metabolites have mechanistic associations with several CVDs. Nevertheless, there is a need to unravel metabolic behavior and underlying mechanisms of microbiome-host interactions. This need is even more highlighted when considering that microbiome-secreted metabolites contributing to CVDs are the subject of intensive research to develop new prevention and therapeutic techniques. In addition to the application of high-throughput data used in microbiome-related studies, advanced computational tools enable us to integrate omics into different mathematical models, including constraint-based models, dynamic models, agent-based models, and machine learning tools, to build a holistic picture of metabolic pathological mechanisms. In this article, we aim to review and introduce state-of-the-art mathematical models and computational approaches addressing the link between the microbiome and CVDs.

Deep Learning Concepts and Applications for Synthetic Biology

Synthetic biology has a natural synergy with deep learning. It can be used to generate large data sets to train models, for example by using DNA synthesis, and deep learning models can be used to inform design, such as by generating novel parts or suggesting optimal experiments to conduct. Recently, research at the interface of engineering biology and deep learning has highlighted this potential through successes including the design of novel biological parts, protein structure prediction, automated analysis of microscopy data, optimal experimental design, and biomolecular implementations of artificial neural networks. In this review, we present an overview of synthetic biology-relevant classes of data and deep learning architectures. We also highlight emerging studies in synthetic biology that capitalize on deep learning to enable novel understanding and design, and discuss challenges and future opportunities in this space.

New synthetic biology tools for metabolic control

In industrial bioprocesses, microbial metabolism dictates the product yields, and therefore, our capacity to control it has an enormous potential to help us move towards a bio-based economy. The rapid development of multiomics data has accelerated our systematic understanding of complex metabolic regulatory mechanisms, which allow us to develop tools to manipulate them. In the last few years, machine learning-based metabolic modeling, Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR) derived synthetic biology tools, and synthetic genetic circuits have been widely used to control the metabolism of microorganisms, manipulate gene expression, and build synthetic pathways for bioproduction. This review describes the latest developments for metabolic control, and focuses on the trends and challenges of metabolic engineering strategies.

Genome-Scale Metabolic Modeling Enables In-Depth Understanding of Big Data

Genome-scale metabolic models (GEMs) enable the mathematical simulation of the metabolism of archaea, bacteria, and eukaryotic organisms. GEMs quantitatively define a relationship between genotype and phenotype by contextualizing different types of Big Data (e.g., genomics, metabolomics, and transcriptomics). In this review, we analyze the available Big Data useful for metabolic modeling and compile the available GEM reconstruction tools that integrate Big Data. We also discuss recent applications in industry and research that include predicting phenotypes, elucidating metabolic pathways, producing industry-relevant chemicals, identifying drug targets, and generating knowledge to better understand host-associated diseases. In addition to the up-to-date review of GEMs currently available, we assessed a plethora of tools for developing new GEMs that include macromolecular expression and dynamic resolution. Finally, we provide a perspective in emerging areas, such as annotation, data managing, and machine learning, in which GEMs will play a key role in the further utilization of Big Data.

Bacteriophage self-counting in the presence of viral replication

When host cells are in low abundance, temperate bacteriophages opt for dormant (lysogenic) infection. Phage lambda implements this strategy by increasing the frequency of lysogeny at higher multiplicity of infection (MOI). However, it remains unclear how the phage reliably counts infecting viral genomes even as their intracellular number increases because of replication. By combining theoretical modeling with single-cell measurements of viral copy number and gene expression, we find that instead of hindering lambda's decision, replication facilitates it. In a nonreplicating mutant, viral gene expression simply scales with MOI rather than diverging into lytic (virulent) and lysogenic trajectories. A similar pattern is followed during early infection by wild-type phage. However, later in the infection, the modulation of viral replication by the decision genes amplifies the initially modest gene expression differences into divergent trajectories. Replication thus ensures the optimal decision-lysis upon single-phage infection and lysogeny at higher MOI.

Enhancing Microbiome Research through Genome-Scale Metabolic Modeling

Construction and analysis of genome-scale metabolic models (GEMs) is a well-established systems biology approach that can be used to predict metabolic and growth phenotypes. The ability of GEMs to produce mechanistic insight into microbial ecological processes makes them appealing tools that can open a range of exciting opportunities in microbiome research. Here, we briefly outline these opportunities, present current rate-limiting challenges for the trustworthy application of GEMs to microbiome research, and suggest approaches for moving the field forward.

The E. coli Whole-Cell Modeling Project

The Escherichia coli whole-cell modeling project seeks to create the most detailed computational model of an E. coli cell in order to better understand and predict the behavior of this model organism. Details about the approach, framework, and current version of the model are discussed. Currently, the model includes the functions of 43% of characterized genes, with ongoing efforts to include additional data and mechanisms. As additional information is incorporated in the model, its utility and predictive power will continue to increase, which means that discovery efforts can be accelerated by community involvement in the generation and inclusion of data. This project will be an invaluable resource to the E. coli community that could be used to verify expected physiological behavior, to predict new outcomes and testable hypotheses for more efficient experimental design iterations, and to evaluate heterogeneous data sets in the context of each other through deep curation.

Protein Abundance Prediction Through Machine Learning Methods

Proteins are responsible for most physiological processes, and their abundance provides crucial information for systems biology research. However, absolute protein quantification, as determined by mass spectrometry, still has limitations in capturing the protein pool. Protein abundance is impacted by translation kinetics, which rely on features of codons. In this study, we evaluated the effect of codon usage bias of genes on protein abundance. Notably, we observed differences regarding codon usage patterns between genes coding for highly abundant proteins and genes coding for less abundant proteins. Analysis of synonymous codon usage and evolutionary selection showed a clear split between the two groups. Our machine learning models predicted protein abundances from codon usage metrics with remarkable accuracy, achieving strong correlation with experimental data. Upon integration of the predicted protein abundance in enzyme-constrained genome-scale metabolic models, the simulated phenotypes closely matched experimental data, which demonstrates that our predictive models are valuable tools for systems metabolic engineering approaches.

A gap-filling algorithm for prediction of metabolic interactions in microbial communities

The study of microbial communities and their interactions has attracted the interest of the scientific community, because of their potential for applications in biotechnology, ecology and medicine. The complexity of interspecies interactions, which are key for the macroscopic behavior of microbial communities, cannot be studied easily experimentally. For this reason, the modeling of microbial communities has begun to leverage the knowledge of established constraint-based methods, which have long been used for studying and analyzing the microbial metabolism of individual species based on genome-scale metabolic reconstructions of microorganisms. A main problem of genome-scale metabolic reconstructions is that they usually contain metabolic gaps due to genome misannotations and unknown enzyme functions. This problem is traditionally solved by using gap-filling algorithms that add biochemical reactions from external databases to the metabolic reconstruction, in order to restore model growth. However, gap-filling algorithms could evolve by taking into account metabolic interactions among species that coexist in microbial communities. In this work, a gap-filling method that resolves metabolic gaps at the community level was developed. The efficacy of the algorithm was tested by analyzing its ability to resolve metabolic gaps on a synthetic community of auxotrophic Escherichia coli strains. Subsequently, the algorithm was applied to resolve metabolic gaps and predict metabolic interactions in a community of Bifidobacterium adolescentis and Faecalibacterium prausnitzii, two species present in the human gut microbiota, and in an experimentally studied community of Dehalobacter and Bacteroidales species of the ACT-3 community. The community gap-filling method can facilitate the improvement of metabolic models and the identification of metabolic interactions that are difficult to identify experimentally in microbial communities.

Synergisms of machine learning and constraint-based modeling of metabolism for analysis and optimization of fermentation parameters

Recent noteworthy advances in the development of high-performing microbial and mammalian strains have enabled the sustainable production of bio-economically valuable substances such as bio-compounds, biofuels, and biopharmaceuticals. However, to obtain an industrially viable mass-production scheme, much time and effort are required. The robust and rational design of fermentation processes requires analysis and optimization of different extracellular conditions and medium components, which have a massive effect on growth and productivity. In this regard, knowledge- and data-driven modeling methods have received much attention. Constraint-based modeling (CBM) is a knowledge-driven mathematical approach that has been widely used in fermentation analysis and optimization due to its capabilities of predicting the cellular phenotype from genotype through high-throughput means. On the other hand, machine learning (ML) is a data-driven statistical method that identifies the data patterns within sophisticated biological systems and processes, where there is inadequate knowledge to represent underlying mechanisms. Furthermore, ML models are becoming a viable complement to constraint-based models in a reciprocal manner when one is used as a pre-step of another. As a result, more predictable model is produced. This review highlights the applications of CBM and ML independently and the combination of these two approaches for analyzing and optimizing fermentation parameters. This article is protected by copyright. All rights reserved.

Community standards to facilitate development and address challenges in metabolic modeling

Standardization of data and models facilitates effective communication, especially in computational systems biology. However, both the development and consistent use of standards and resources remain challenging. As a result, the amount, quality, and format of the information contained within systems biology models are not consistent and therefore present challenges for widespread use and communication. Here, we focused on these standards, resources, and challenges in the field of constraint-based metabolic modeling by conducting a community-wide survey. We used this feedback to (i) outline the major challenges that our field faces and to propose solutions and (ii) identify a set of features that defines what a "gold standard" metabolic network reconstruction looks like concerning content, annotation, and simulation capabilities. We anticipate that this community-driven outline will help the long-term development of community-inspired resources as well as produce high-quality, accessible models within our field. More broadly, we hope that these efforts can serve as blueprints for other computational modeling communities to ensure the continued development of both practical, usable standards and reproducible, knowledge-rich models.

PhenoMapping: a protocol to map cellular phenotypes to metabolic bottlenecks, identify conditional essentiality, and curate metabolic models

Targeted identification of cellular processes responsible for a phenotype is of major importance in guiding efforts in bioengineering and medicine. Genome-scale metabolic models (GEMs) are widely used to integrate various types of omics data and study the cellular physiology under different conditions. Here, we present PhenoMapping, a protocol that uses GEMs, omics, and phenotypic data to map cellular processes and observed phenotypes. PhenoMapping also classifies genes as conditionally and unconditionally essential and guides a comprehensive curation of GEMs. For complete details on the use and execution of this protocol, please refer to Stanway et al. (2019) and Krishnan et al. (2020).

gapseq: informed prediction of bacterial metabolic pathways and reconstruction of accurate metabolic models

Genome-scale metabolic models of microorganisms are powerful frameworks to predict phenotypes from an organism's genotype. While manual reconstructions are laborious, automated reconstructions often fail to recapitulate known metabolic processes. Here we present gapseq ( https://github.com/jotech/gapseq ), a new tool to predict metabolic pathways and automatically reconstruct microbial metabolic models using a curated reaction database and a novel gap-filling algorithm. On the basis of scientific literature and experimental data for 14,931 bacterial phenotypes, we demonstrate that gapseq outperforms state-of-the-art tools in predicting enzyme activity, carbon source utilisation, fermentation products, and metabolic interactions within microbial communities.

Addressing uncertainty in genome-scale metabolic model reconstruction and analysis

The reconstruction and analysis of genome-scale metabolic models constitutes a powerful systems biology approach, with applications ranging from basic understanding of genotype-phenotype mapping to solving biomedical and environmental problems. However, the biological insight obtained from these models is limited by multiple heterogeneous sources of uncertainty, which are often difficult to quantify. Here we review the major sources of uncertainty and survey existing approaches developed for representing and addressing them. A unified formal characterization of these uncertainties through probabilistic approaches and ensemble modeling will facilitate convergence towards consistent reconstruction pipelines, improved data integration algorithms, and more accurate assessment of predictive capacity.

Reconstructing organisms in silico: genome-scale models and their emerging applications

Escherichia coli is considered to be the best-known microorganism given the large number of published studies detailing its genes, its genome and the biochemical functions of its molecular components. This vast literature has been systematically assembled into a reconstruction of the biochemical reaction networks that underlie E. coli's functions, a process which is now being applied to an increasing number of microorganisms. Genome-scale reconstructed networks are organized and systematized knowledge bases that have multiple uses, including conversion into computational models that interpret and predict phenotypic states and the consequences of environmental and genetic perturbations. These genome-scale models (GEMs) now enable us to develop pan-genome analyses that provide mechanistic insights, detail the selection pressures on proteome allocation and address stress phenotypes. In this Review, we first discuss the overall development of GEMs and their applications. Next, we review the evolution of the most complete GEM that has been developed to date: the E. coli GEM. Finally, we explore three emerging areas in genome-scale modelling of microbial phenotypes: collections of strain-specific models, metabolic and macromolecular expression models, and simulation of stress responses.

Systematically gap-filling the genome-scale metabolic model of CHO cells

OBJECTIVE

Chinese hamster ovary (CHO) cells are the leading cell factories for producing recombinant proteins in the biopharmaceutical industry. In this regard, constraint-based metabolic models are useful platforms to perform computational analysis of cell metabolism. These models need to be regularly updated in order to include the latest biochemical data of the cells, and to increase their predictive power. Here, we provide an update to iCHO1766, the metabolic model of CHO cells.

RESULTS

We expanded the existing model of Chinese hamster metabolism with the help of four gap-filling approaches, leading to the addition of 773 new reactions and 335 new genes. We incorporated these into an updated genome-scale metabolic network model of CHO cells, named iCHO2101. In this updated model, the number of reactions and pathways capable of carrying flux is substantially increased.

CONCLUSIONS

The present CHO model is an important step towards more complete metabolic models of CHO cells.

Deep learning meets metabolomics: a methodological perspective

Deep learning (DL), an emerging area of investigation in the fields of machine learning and artificial intelligence, has markedly advanced over the past years. DL techniques are being applied to assist medical professionals and researchers in improving clinical diagnosis, disease prediction and drug discovery. It is expected that DL will help to provide actionable knowledge from a variety of 'big data', including metabolomics data. In this review, we discuss the applicability of DL to metabolomics, while presenting and discussing several examples from recent research. We emphasize the use of DL in tackling bottlenecks in metabolomics data acquisition, processing, metabolite identification, as well as in metabolic phenotyping and biomarker discovery. Finally, we discuss how DL is used in genome-scale metabolic modelling and in interpretation of metabolomics data. The DL-based approaches discussed here may assist computational biologists with the integration, prediction and drawing of statistical inference about biological outcomes, based on metabolomics data.

Harnessing the potential of artificial neural networks for predicting protein glycosylation

Kinetic models offer incomparable insight on cellular mechanisms controlling protein glycosylation. However, their ability to reproduce site-specific glycoform distributions depends on accurate estimation of a large number of protein-specific kinetic parameters and prior knowledge of enzyme and transport protein levels in the Golgi membrane. Herein we propose an artificial neural network (ANN) for protein glycosylation and apply this to four recombinant glycoproteins produced in Chinese hamster ovary (CHO) cells, two monoclonal antibodies and two fusion proteins. We demonstrate that the ANN model accurately predicts site-specific glycoform distributions of up to eighteen glycan species with an average absolute error of 1.1%, correctly reproducing the effect of metabolic perturbations as part of a hybrid, kinetic/ANN, glycosylation model (HyGlycoM), as well as the impact of manganese supplementation and glycosyltransferase knock out experiments as a stand-alone machine learning algorithm. These results showcase the potential of machine learning and hybrid approaches for rapidly developing performance-driven models of protein glycosylation.

Medusa: Software to build and analyze ensembles of genome-scale metabolic network reconstructions

Uncertainty in the structure and parameters of networks is ubiquitous across computational biology. In constraint-based reconstruction and analysis of metabolic networks, this uncertainty is present both during the reconstruction of networks and in simulations performed with them. Here, we present Medusa, a Python package for the generation and analysis of ensembles of genome-scale metabolic network reconstructions. Medusa builds on the COBRApy package for constraint-based reconstruction and analysis by compressing a set of models into a compact ensemble object, providing functions for the generation of ensembles using experimental data, and extending constraint-based analyses to ensemble scale. We demonstrate how Medusa can be used to generate ensembles and perform ensemble simulations, and how machine learning can be used in conjunction with Medusa to guide the curation of genome-scale metabolic network reconstructions. Medusa is available under the permissive MIT license from the Python Packaging Index (https://pypi.org) and from github (https://github.com/opencobra/Medusa), and comprehensive documentation is available at https://medusa.readthedocs.io/en/latest.