Systems Metabolic Engineering Meets Machine Learning: A New Era for Data-Driven Metabolic Engineering

Promoting lignocellulosic biorefinery by machine learning: progress, perspectives and challenges

The lignocellulosic biorefinery involves pretreatment, enzymatic hydrolysis, mixed sugar fermentation, and optional anaerobic digestion. This pipeline could be effectively implemented through machine learning (ML)-guided process optimization and strain modification rather than experimental or experience-based ones. This review takes a holistic perspective on the entire pipeline, discussing how ML could aid lignocellulosic, while other published work has focused on individual modules within the pipeline. This review also explores the model construction and evaluation strategies and highlights the emerging potential of transfer learning and hybrid ML models to address data insufficiency and improve model interpretability. Furthermore, challenges and future prospects of ML in lignocellulosic biorefinery will be elaborated in this review. Integrating ML into lignocellulosic biorefinery offers a promising pathway towards sustainable and competitive biorefinery systems.

Recent advances in genetic engineering and chemical production in yeast species

Yeasts have emerged as well-suited microbial cell factory for the sustainable production of biofuels, organic acids, terpenoids, and specialty chemicals. This ability is bolstered by advances in genetic engineering tools, including CRISPR-Cas systems and modular cloning in both conventional (Saccharomyces cerevisiae) and non-conventional (Yarrowia lipolytica, Rhodotorula toruloides, Candida krusei) yeasts. Additionally, genome-scale metabolic models and machine learning approaches have accelerated efforts to create a broad range of compounds that help reduce dependency on fossil fuels, mitigate climate change, and offer sustainable alternatives to petrochemical-derived counterparts. In this review, we highlight the cutting-edge genetic tools driving yeast metabolic engineering and then explore the diverse applications of yeast-based platforms for producing value-added products. Collectively, this review underscores the pivotal role of yeast biotechnology in efforts to build a sustainable bioeconomy.

Applications of artificial intelligence and machine learning in dynamic pathway engineering

Dynamic pathway engineering aims to build metabolic production systems embedded with intracellular control mechanisms for improved performance. These control systems enable host cells to self-regulate the temporal activity of a production pathway in response to perturbations, using a combination of biosensors and feedback circuits for controlling expression of heterologous enzymes. Pathway design, however, requires assembling together multiple biological parts into suitable circuit architectures, as well as careful calibration of the function of each component. This results in a large design space that is costly to navigate through experimentation alone. Methods from artificial intelligence (AI) and machine learning are gaining increasing attention as tools to accelerate the design cycle, owing to their ability to identify hidden patterns in data and rapidly screen through large collections of designs. In this review, we discuss recent developments in the application of machine learning methods to the design of dynamic pathways and their components. We cover recent successes and offer perspectives for future developments in the field. The integration of AI into metabolic engineering pipelines offers great opportunities to streamline design and discover control systems for improved production of high-value chemicals.

Optimizing Ethanol Production in Saccharomyces cerevisiae at Ambient and Elevated Temperatures through Machine Learning-Guided Combinatorial Promoter Modifications

Bioethanol has gained popularity in recent decades as an ecofriendly alternative to fossil fuels due to increasing concerns about global climate change. However, economically viable ethanol fermentation remains a challenge. High-temperature fermentation can reduce production costs, but Saccharomyces cerevisiae yeast strains normally ferment poorly under high temperatures. In this study, we present a machine learning (ML) approach to optimize bioethanol production in S. cerevisiae by fine-tuning the promoter activities of three endogenous genes. We created 216 combinatorial strains of S. cerevisiae by replacing native promoters with five promoters of varying strengths to regulate ethanol production. Promoter replacement resulted in a 63% improvement in ethanol production at 30 °C. We created an ML-guided workflow by utilizing XGBoost to train high-performance models based on promoter strengths and cellular metabolite concentrations obtained from ethanol production of 216 combinatorial strains at 30 °C. This strategy was then applied to optimize ethanol production at 40 °C, where we selected 31 strains for experimental fermentation. This reduced experimental load led to a 7.4% increase in ethanol production in the second round of the ML-guided workflow. Our study offers a comprehensive library of promoter strength modifications for key ethanol production enzymes, showcasing how machine learning can guide yeast strain optimization and make bioethanol production more cost-effective and efficient. Furthermore, we demonstrate that metabolic engineering processes can be accelerated and optimized through this approach.

Integration of metabolism and regulation reveals rapid adaptability to growth on non-native substrates

Engineering synthetic heterotrophy is a key to the efficient bio-based valorization of renewable and waste substrates. Among these, engineering hemicellulosic pentose utilization has been well-explored in Saccharomyces cerevisiae (yeast) over several decades-yet the answer to what makes their utilization inherently recalcitrant remains elusive. Through implementation of a semi-synthetic regulon, we find that harmonizing cellular and engineering objectives are a key to obtaining highest growth rates and yields with minimal metabolic engineering effort. Concurrently, results indicate that "extrinsic" factors-specifically, upstream genes that direct flux of pentoses into central carbon metabolism-are rate-limiting. We also reveal that yeast metabolism is innately highly adaptable to rapid growth on non-native substrates and that systems metabolic engineering (i.e., functional genomics, network modeling, etc.) is largely unnecessary. Overall, this work provides an alternate, novel, holistic (and yet minimalistic) approach based on integrating non-native metabolic genes with a native regulon system.

Evolving tolerance of Yarrowia lipolytica to hydrothermal liquefaction aqueous phase waste

Hydrothermal liquefaction (HTL) is an emerging method for thermochemical conversion of wet organic waste and biomass into renewable biocrude. HTL also produces an aqueous phase (HTL-AP) side stream containing 2-4% light organic compounds that require treatment. Although anaerobic digestion (AD) of HTL-AP has shown promise, lengthy time periods were required for AD microbial communities to adapt to metabolic inhibitors in HTL-AP. An alternative for HTL-AP valorization was recently demonstrated using two engineered strains of Yarrowia lipolytica, E26 and Diploid TAL, for the overproduction of lipids and the polyketide triacetic acid lactone (TAL) respectively. These strains tolerated up to 10% HTL-AP (v/v) in defined media and up to 25% (v/v) HTL-AP in rich media. In this work, adaptive laboratory evolution (ALE) of these strains increased the bulk population tolerance for HTL-AP to up to 30% (v/v) in defined media and up to 35% (v/v) for individual isolates in rich media. The predominate organic acids within HTL-AP (acetic, butyric, and propionic) were rapidly consumed by the evolved Y. lipolytica strains. A TAL-producing isolate (strain 144-3) achieved a nearly 3-fold increase in TAL titer over the parent strain while simultaneously reducing the chemical oxygen demand (COD) of HTL-AP containing media. Fermentation with HTL-AP as the sole nutrient source demonstrated direct conversion of waste into TAL at 10% theoretical yield. Potential genetic mutations of evolved TAL production strains that could be imparting tolerance were explored. This work advances the potential of Y. lipolytica to biologically treat and simultaneously extract value from HTL wastewater. KEY POINTS: • Adaptive evolution of two Y. lipolytica strains enhanced their tolerance to waste. • Y. lipolytica reduces chemical oxygen demand in media containing waste. • Y. lipolytica can produce triacetic acid lactone directly from wastewater.

Advances in mining and expressing microbial biosynthetic gene clusters

Natural products (NPs) especially the secondary metabolites originated from microbes exhibit great importance in biomedical, industrial and agricultural applications. However, mining biosynthetic gene clusters (BGCs) to produce novel NPs has been hindered owing that a large population of environmental microbes are unculturable. In the past decade, strategies to explore BGCs directly from (meta)genomes have been established along with the fast development of high-throughput sequencing technologies and the powerful bioinformatics data-processing tools, which greatly expedited the exploitations of novel BGCs from unculturable microbes including the extremophilic microbes. In this review, we firstly summarized the popular bioinformatics tools and databases available to mine novel BGCs from (meta)genomes based on either pure cultures or pristine environmental samples. Noticeably, approaches rooted from machine learning and deep learning with focuses on the prediction of ribosomally synthesized and post-translationally modified peptides (RiPPs) were dramatically increased in recent years. Moreover, synthetic biology techniques to express the novel BGCs in culturable native microbes or heterologous hosts were introduced. This working pipeline including the discovery and biosynthesis of novel NPs will greatly advance the exploitations of the abundant but unexplored microbial BGCs.

Current status and future prospects in cannabinoid production through in vitro culture and synthetic biology

For centuries, cannabis has been a rich source of fibrous, pharmaceutical, and recreational ingredients. Phytocannabinoids are the most important and well-known class of cannabis-derived secondary metabolites and display a broad range of health-promoting and psychoactive effects. The unique characteristics of phytocannabinoids (e.g., metabolite likeness, multi-target spectrum, and safety profile) have resulted in the development and approval of several cannabis-derived drugs. While most work has focused on the two main cannabinoids produced in the plant, over 150 unique cannabinoids have been identified. To meet the rapidly growing phytocannabinoid demand, particularly many of the minor cannabinoids found in low amounts in planta, biotechnology offers promising alternatives for biosynthesis through in vitro culture and heterologous systems. In recent years, the engineered production of phytocannabinoids has been obtained through synthetic biology both in vitro (cell suspension culture and hairy root culture) and heterologous systems. However, there are still several bottlenecks (e.g., the complexity of the cannabinoid biosynthetic pathway and optimizing the bioprocess), hampering biosynthesis and scaling up the biotechnological process. The current study reviews recent advances related to in vitro culture-mediated cannabinoid production. Additionally, an integrated overview of promising conventional approaches to cannabinoid production is presented. Progress toward cannabinoid production in heterologous systems and possible avenues for avoiding autotoxicity are also reviewed and highlighted. Machine learning is then introduced as a powerful tool to model, and optimize bioprocesses related to cannabinoid production. Finally, regulation and manipulation of the cannabinoid biosynthetic pathway using CRISPR- mediated metabolic engineering is discussed.

Recent advances in machine learning applications in metabolic engineering

Metabolic engineering encompasses several widely-used strategies, which currently hold a high seat in the field of biotechnology when its potential is manifesting through a plethora of research and commercial products with a strong societal impact. The genomic revolution that occurred almost three decades ago has initiated the generation of large omics-datasets which has helped in gaining a better understanding of cellular behavior. The itinerary of metabolic engineering that has occurred based on these large datasets has allowed researchers to gain detailed insights and a reasonable understanding of the intricacies of biosystems. However, the existing trail-and-error approaches for metabolic engineering are laborious and time-intensive when it comes to the production of target compounds with high yields through genetic manipulations in host organisms. Machine learning (ML) coupled with the available metabolic engineering test instances and omics data brings a comprehensive and multidisciplinary approach that enables scientists to evaluate various parameters for effective strain design. This vast amount of biological data should be standardized through knowledge engineering to train different ML models for providing accurate predictions in gene circuits designing, modification of proteins, optimization of bioprocess parameters for scaling up, and screening of hyper-producing robust cell factories. This review briefs on the premise of ML, followed by mentioning various ML methods and algorithms alongside the numerous omics datasets available to train ML models for predicting metabolic outcomes with high-accuracy. The combinative interplay between the ML algorithms and biological datasets through knowledge engineering have guided the recent advancements in applications such as CRISPR/Cas systems, gene circuits, protein engineering, metabolic pathway reconstruction, and bioprocess engineering. Finally, this review addresses the probable challenges of applying ML in metabolic engineering which will guide the researchers toward novel techniques to overcome the limitations.

Prediction of strain engineerings that amplify recombinant protein secretion through the machine learning approach MaLPHAS

This article presents a discussion of the process of precision fermentation (PF), describing the history of the space, the expected 70% growth over the next 5 years, various applications of precision fermented products, and the markets available to be disrupted by the technology. A range of prokaryotic and eukaryotic host organisms used for PF are described, with the advantages, disadvantages and applications of each. The process of setting up PF and strain engineering is described, as well as various ways that computational analysis and design techniques can be employed to assist PF engineering. The article then describes the design and implementation of a machine learning method, machine learning predictions having amplified secretion (MaLPHAS) to predict strain engineerings, which optimise the secretion of a recombinant protein. This approach showed an in silico cross-validated R 2 accuracy on the training data of up to 46.6% and in an in vitro test on a Komagataella phaffii strain, identified one gene engineering out of five predicted, which was shown to double the secretion of a heterologous protein and outperform three of the best-known edits from the literature for improving secretion in K. phaffii.

Interpretable machine learning methods for predictions in systems biology from omics data

Machine learning has become a powerful tool for systems biologists, from diagnosing cancer to optimizing kinetic models and predicting the state, growth dynamics, or type of a cell. Potential predictions from complex biological data sets obtained by “omics” experiments seem endless, but are often not the main objective of biological research. Often we want to understand the molecular mechanisms of a disease to develop new therapies, or we need to justify a crucial decision that is derived from a prediction. In order to gain such knowledge from data, machine learning models need to be extended. A recent trend to achieve this is to design “interpretable” models. However, the notions around interpretability are sometimes ambiguous, and a universal recipe for building well-interpretable models is missing. With this work, we want to familiarize systems biologists with the concept of model interpretability in machine learning. We consider data sets, data preparation, machine learning methods, and software tools relevant to omics research in systems biology. Finally, we try to answer the question: “What is interpretability?” We introduce views from the interpretable machine learning community and propose a scheme for categorizing studies on omics data. We then apply these tools to review and categorize recent studies where predictive machine learning models have been constructed from non-sequential omics data.

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.

Data-Driven Synthetic Cell Factories Development for Industrial Biomanufacturing

Revolutionary breakthroughs in artificial intelligence (AI) and machine learning (ML) have had a profound impact on a wide range of scientific disciplines, including the development of artificial cell factories for biomanufacturing. In this paper, we review the latest studies on the application of data-driven methods for the design of new proteins, pathways, and strains. We first briefly introduce the various types of data and databases relevant to industrial biomanufacturing, which are the basis for data-driven research. Different types of algorithms, including traditional ML and more recent deep learning methods, are also presented. We then demonstrate how these data-based approaches can be applied to address various issues in cell factory development using examples from recent studies, including the prediction of protein function, improvement of metabolic models, and estimation of missing kinetic parameters, design of non-natural biosynthesis pathways, and pathway optimization. In the last section, we discuss the current limitations of these data-driven approaches and propose that data-driven methods should be integrated with mechanistic models to complement each other and facilitate the development of synthetic strains for industrial biomanufacturing.

Production of Vitamin K by Wild-Type and Engineered Microorganisms

Vitamin K is a fat-soluble vitamin that mainly exists as phylloquinone or menaquinone in nature. Vitamin K plays an important role in blood clotting and bone health in humans. For use as a nutraceutical, vitamin K is produced by natural extraction, chemical synthesis, and microbial fermentation. Natural extraction and chemical synthesis methods for vitamin K production have limitations, such as low yield of products and environmental concerns. Microbial fermentation is a more sustainable process for industrial production of natural vitamin K than two other methods. Recent advanced genetic technology facilitates industrial production of vitamin K by increasing the yield and productivity of microbial host strains. This review covers (i) general information about vitamin K and microbial host, (ii) current titers of vitamin K produced by wild-type microorganisms, and (iii) vitamin K production by engineered microorganisms, including the details of strain engineering strategies. Finally, current limitations and future directions for microbial production of vitamin K are also discussed.

Phenotype analysis of cultivation processes via unsupervised machine learning: Demonstration for Clostridium pasteurianum

A novel approach of phenotype analysis of fermentation-based bioprocesses based on unsupervised learning (clustering) is presented. As a prior identification of phenotypes and conditional interrelations is desired to control fermentation performance, an automated learning method to output reference phenotypes (defined as vector of biomass-specific rates) was developed and the necessary computing process and parameters were assessed. For its demonstration, time series data of 90 Clostridium pasteurianum cultivations were used which feature a broad spectrum of solventogenic and acidogenic phenotypes, while 14 clusters of phenotypic manifestations were identified. The analysis of reference phenotypes showed distinct differences, where potential conditionalities were exemplary isolated. Further, cluster-based balancing of carbon and ATP or the use of reference phenotypes as indicator for bioprocess monitoring were demonstrated to highlight the perks of this approach. Overall, such analysis depends strongly on the quality of the data and experimental validations will be required before conclusions. However, the automated, streamlined and abstracted approach diminishes the need of individual evaluation of all noisy dataset and showed promising results, which could be transferred to strains with comparably wide-ranging phenotypic manifestations or as indicators for repeated bioprocesses with clearly defined target.

Directed evolution of biofuel-responsive biosensors for automated optimization of branched-chain alcohol biosynthesis

The biosynthesis of short-chain alcohols is a carbon-neutral alternative to petroleum-derived production, but strain screening operations are encumbered by laborious analytics. Here, we built, characterized and applied whole cell biosensors by directed evolution of the transcription factor AlkS for screening microbial strain libraries producing industrially relevant alcohols. A selected AlkS variant was applied for in situ product detection in two screening applications concerning key steps in alcohol production. Further, the biosensor strains enabled the implementation of an automated, robotic platform-based workflow with data clustering, which readily allowed the identification of significantly improved strain variants for isopentanol production.

Improving the performance of machine learning models for biotechnology: The quest for deus ex machina

Machine learning is becoming an integral part of the Design-Build-Test-Learn cycle in biotechnology. Machine learning models learn from collected datasets such as omics data and predict a defined outcome, which has led to both production improvements and predictive tools in the field. Robust prediction of the behavior of microbial cell factories and production processes not only greatly increases our understanding of the function of such systems, but also provides significant savings of development time. However, many pitfalls when modeling biological data - bad fit, noisy data, model instability, low data quantity and imbalances in the data - cause models to suffer in their performance. Here we provide an accessible, in-depth analysis on the problems created by these pitfalls, as well as means of their detection and mediation, with a focus on supervised learning. Assessing the state of the art, we show that, currently, in-depth analyses of model performance are often absent and must be improved. This review provides a toolbox for the analysis of model robustness and performance, and simultaneously proposes a standard for the community to facilitate future work. It is further accompanied by an interactive online tutorial on the discussed issues.

Exploiting unconventional prokaryotic hosts for industrial biotechnology

Developing cost-efficient biotechnological processes is a major challenge in replacing fossil-based industrial production processes. The remarkable progress in genetic engineering ensures efficient and fast tailoring of microbial metabolism for a wide range of bioconversions. However, improving intrinsic properties such as tolerance, handling, growth, and substrate consumption rates is still challenging. At the same time, synthetic biology tools are becoming easier applicable and transferable to nonmodel organisms. These trends have resulted in the exploitation of new and unconventional microbial systems with sophisticated properties, which render them promising hosts for the bio-based industry. Here, we highlight the metabolic and cellular capabilities of representative prokaryotic newcomers and discuss the potential and drawbacks of these hosts for industrial application.

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.

Metabolomics-Guided Elucidation of Plant Abiotic Stress Responses in the 4IR Era: An Overview

Plants are constantly challenged by changing environmental conditions that include abiotic stresses. These are limiting their development and productivity and are subsequently threatening our food security, especially when considering the pressure of the increasing global population. Thus, there is an urgent need for the next generation of crops with high productivity and resilience to climate change. The dawn of a new era characterized by the emergence of fourth industrial revolution (4IR) technologies has redefined the ideological boundaries of research and applications in plant sciences. Recent technological advances and machine learning (ML)-based computational tools and omics data analysis approaches are allowing scientists to derive comprehensive metabolic descriptions and models for the target plant species under specific conditions. Such accurate metabolic descriptions are imperatively essential for devising a roadmap for the next generation of crops that are resilient to environmental deterioration. By synthesizing the recent literature and collating data on metabolomics studies on plant responses to abiotic stresses, in the context of the 4IR era, we point out the opportunities and challenges offered by omics science, analytical intelligence, computational tools and big data analytics. Specifically, we highlight technological advancements in (plant) metabolomics workflows and the use of machine learning and computational tools to decipher the dynamics in the chemical space that define plant responses to abiotic stress conditions.

Rational engineering strategies for achieving high-yield, high-quality and high-stability of natural product production in actinomycetes

Actinomycetes are recognized as excellent producers of microbial natural products, which have a wide range of applications, especially in medicine, agriculture and stockbreeding. The three main indexes of industrialization (titer, purity and stability) must be taken into overall consideration in the manufacturing process of natural products. Over the past decades, synthetic biology techniques have expedited the development of industrially competitive strains with excellent performances. Here, we summarize various rational engineering strategies for upgrading the performance of industrial actinomycetes, which include enhancing the yield of natural products, eliminating the by-products and improving the genetic stability of engineered strains. Furthermore, the current challenges and future perspectives for optimizing the industrial strains more systematically through combinatorial engineering strategies are also discussed.

Streamlining Natural Products Biomanufacturing With Omics and Machine Learning Driven Microbial Engineering

Increasing demands for the supply of biopharmaceuticals have propelled the advancement of metabolic engineering and synthetic biology strategies for biomanufacturing of bioactive natural products. Using metabolically engineered microbes as the bioproduction hosts, a variety of natural products including terpenes, flavonoids, alkaloids, and cannabinoids have been synthesized through the construction and expression of known and newly found biosynthetic genes primarily from model and non-model plants. The employment of omics technology and machine learning (ML) platforms as high throughput analytical tools has been increasingly leveraged in promoting data-guided optimization of targeted biosynthetic pathways and enhancement of the microbial production capacity, thereby representing a critical debottlenecking approach in improving and streamlining natural products biomanufacturing. To this end, this mini review summarizes recent efforts that utilize omics platforms and ML tools in strain optimization and prototyping and discusses the beneficial uses of omics-enabled discovery of plant biosynthetic genes in the production of complex plant-based natural products by bioengineered microbes.

Automated engineering of synthetic metabolic pathways for efficient biomanufacturing

Metabolic engineering involves the engineering and optimization of processes from single-cell to fermentation in order to increase production of valuable chemicals for health, food, energy, materials and others. A systems approach to metabolic engineering has gained traction in recent years thanks to advances in strain engineering, leading to an accelerated scaling from rapid prototyping to industrial production. Metabolic engineering is nowadays on track towards a truly manufacturing technology, with reduced times from conception to production enabled by automated protocols for DNA assembly of metabolic pathways in engineered producer strains. In this review, we discuss how the success of the metabolic engineering pipeline often relies on retrobiosynthetic protocols able to identify promising production routes and dynamic regulation strategies through automated biodesign algorithms, which are subsequently assembled as embedded integrated genetic circuits in the host strain. Those approaches are orchestrated by an experimental design strategy that provides optimal scheduling planning of the DNA assembly, rapid prototyping and, ultimately, brings forward an accelerated Design-Build-Test-Learn cycle and the overall optimization of the biomanufacturing process. Achieving such a vision will address the increasingly compelling demand in our society for delivering valuable biomolecules in an affordable, inclusive and sustainable bioeconomy.

Machine learning for metabolic engineering: A review

Machine learning provides researchers a unique opportunity to make metabolic engineering more predictable. In this review, we offer an introduction to this discipline in terms that are relatable to metabolic engineers, as well as providing in-depth illustrative examples leveraging omics data and improving production. We also include practical advice for the practitioner in terms of data management, algorithm libraries, computational resources, and important non-technical issues. A variety of applications ranging from pathway construction and optimization, to genetic editing optimization, cell factory testing, and production scale-up are discussed. Moreover, the promising relationship between machine learning and mechanistic models is thoroughly reviewed. Finally, the future perspectives and most promising directions for this combination of disciplines are examined.

High-throughput screening for high-efficiency small-molecule biosynthesis

Systems metabolic engineering faces the formidable task of rewiring microbial metabolism to cost-effectively generate high-value molecules from a variety of inexpensive feedstocks for many different applications. Because these cellular systems are still too complex to model accurately, vast collections of engineered organism variants must be systematically created and evaluated through an enormous trial-and-error process in order to identify a manufacturing-ready strain. The high-throughput screening of strains to optimize their scalable manufacturing potential requires execution of many carefully controlled, parallel, miniature fermentations, followed by high-precision analysis of the resulting complex mixtures. This review discusses strategies for the design of high-throughput, small-scale fermentation models to predict improved strain performance at large commercial scale. Established and promising approaches from industrial and academic groups are presented for both cell culture and analysis, with primary focus on microplate- and microfluidics-based screening systems.

Combining mechanistic and machine learning models for predictive engineering and optimization of tryptophan metabolism

Through advanced mechanistic modeling and the generation of large high-quality datasets, machine learning is becoming an integral part of understanding and engineering living systems. Here we show that mechanistic and machine learning models can be combined to enable accurate genotype-to-phenotype predictions. We use a genome-scale model to pinpoint engineering targets, efficient library construction of metabolic pathway designs, and high-throughput biosensor-enabled screening for training diverse machine learning algorithms. From a single data-generation cycle, this enables successful forward engineering of complex aromatic amino acid metabolism in yeast, with the best machine learning-guided design recommendations improving tryptophan titer and productivity by up to 74 and 43%, respectively, compared to the best designs used for algorithm training. Thus, this study highlights the power of combining mechanistic and machine learning models to effectively direct metabolic engineering efforts.

Next-generation metabolic engineering approaches towards development of plant cell suspension cultures as specialized metabolite producing biofactories

Plant cell suspension culture (PCSC) has emerged as a viable technology to produce plant specialized metabolites (PSM). While Taxol® and ginsenoside are two examples of successfully commercialized PCSC-derived PSM, widespread utilization of the PCSC platform has yet to be realized primarily due to a lack of understanding of the molecular genetics of PSM biosynthesis. Recent advances in computational, molecular and synthetic biology tools provide the opportunity to rapidly characterize and harness the specialized metabolic potential of plants. Here, we discuss the prospects of integrating computational modeling, artificial intelligence, and precision genome editing (CRISPR/Cas and its variants) toolboxes to discover the genetic regulators of PSM. We also explore how synthetic biology can be applied to develop metabolically optimized PSM-producing native and heterologous PCSC systems. Taken together, this review provides an interdisciplinary approach to realize and link the potential of next-generation computational and molecular tools to convert PCSC into commercially viable PSM-producing biofactories.

Increasing metabolic pathway flux by using machine learning models

Machine learning is transforming many industries through self-improving models that are fueled by big data and high computing power. The field of metabolic engineering, which uses cellular biochemical network to manufacture useful small molecules, has also witnessed the first wave of machine learning applications in the past five years, covering reaction route design, enzyme selection, pathway engineering and process optimization. This review focuses on pathway engineering, and uses a few recent studies to illustrate (1) how machine learning models can be useful in overcoming an evident rate-limiting step, and (2) how the models may be used to exhaustively search - or guide optimization algorithms to search - a large design space when the cellular regulation of the reaction network is more convoluted.

Metabolic pathway engineering: Perspectives and applications

BACKGROUND

Metabolic engineering aims at contriving microbes as biocatalysts for enhanced and cost-effective production of countless secondary metabolites. These secondary metabolites can be treated as the resources of industrial chemicals, pharmaceuticals and fuels. Plants are also crucial targets for metabolic engineers to produce necessary secondary metabolites. Metabolic engineering of both microorganism and plants also contributes towards drug discovery. In order to implement advanced metabolic engineering techniques efficiently, metabolic engineers should have detailed knowledge about cell physiology and metabolism. Principle behind methodologies: Genome-scale mathematical models of integrated metabolic, signal transduction, gene regulatory and protein-protein interaction networks along with experimental validation can provide such knowledge in this context. Incorporation of omics data into these models is crucial in the case of drug discovery. Inverse metabolic engineering and metabolic control analysis (MCA) can help in developing such models. Artificial intelligence methodology can also be applied for efficient and accurate metabolic engineering.

CONCLUSION

In this review, we discuss, at the beginning, the perspectives of metabolic engineering and its application on microorganism and plant leading to drug discovery. At the end, we elaborate why inverse metabolic engineering and MCA are closely related to modern metabolic engineering. In addition, some crucial steps ensuring efficient and optimal metabolic engineering strategies have been discussed. Moreover, we explore the use of genomics data for the activation of silent metabolic clusters and how it can be integrated with metabolic engineering. Finally, we exhibit a few applications of artificial intelligence to metabolic engineering.

Systems and synthetic biology tools for advanced bioproduction hosts

The genomic revolution ushered in an era of discovery and characterization of enzymes from novel organisms that fueled engineering of microbes to produce commodity and high-value compounds. Over the past decade advances in synthetic biology tools in recent years contributed to significant progress in metabolic engineering efforts to produce both biofuels and bioproducts resulting in several such related items being brought to market. These successes represent a burgeoning bio-economy; however, significant resources and time are still necessary to progress a system from proof-of-concept to market. In order to fully realize this potential, methods that examine biological systems in a comprehensive, systematic and high-throughput manner are essential. Recent success in synthetic biology has coincided with the development of systems biology and analytical approaches that kept pace and scaled with technology development. Here, we review a selection of systems biology methods and their use in synthetic biology approaches for microbial biotechnology platforms.