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.     

Adaptive machine learning for protein engineering

Machine-learning models that learn from data to predict how protein sequence encodes function are emerging as a useful protein engineering tool. However, when using these models to suggest new protein designs, one must deal with the vast combinatorial complexity of protein sequences. Here, we review how to use a sequence-to-function machine-learning surrogate model to select sequences for experimental measurement. First, we discuss how to select sequences through a single round of machine-learning optimization. Then, we discuss sequential optimization, where the goal is to discover optimized sequences and improve the model across multiple rounds of training, optimization, and experimental measurement.     

Leveraging ShuffleNet transfer learning to enhance handwritten character recognition

Handwritten character recognition has continually been a fascinating field of study in pattern recognition due to its numerous real-life applications, such as the reading tools for blind people and the reading tools for handwritten bank cheques. Therefore, the proper and accurate conversion of handwriting into organized digital files that can be easily recognized and processed by computer algorithms is required for various applications and systems. This paper proposes an accurate and precise autonomous structure for handwriting recognition using a ShuffleNet convolutional neural network to produce a multi-class recognition for the offline handwritten characters and numbers. The developed system utilizes the transfer learning of the powerful ShuffleNet CNN to train, validate, recognize, and categorize the handwritten character/digit images dataset into 26 classes for the English characters and ten categories for the digit characters. The experimental outcomes exhibited that the proposed recognition system achieves extraordinary overall recognition accuracy peaking at 99.50% outperforming other contrasted character recognition systems reported in the state-of-art. Besides, a low computational cost has been observed for the proposed model recording an average of 2.7 (ms) for the single sample inferencing.     

Artificial intelligence and machine learning for medical imaging: A technology review

Artificial intelligence (AI) has recently become a very popular buzzword, as a consequence of disruptive technical advances and impressive experimental results, notably in the field of image analysis and processing. In medicine, specialties where images are central, like radiology, pathology or oncology, have seized the opportunity and considerable efforts in research and development have been deployed to transfer the potential of AI to clinical applications. With AI becoming a more mainstream tool for typical medical imaging analysis tasks, such as diagnosis, segmentation, or classification, the key for a safe and efficient use of clinical AI applications relies, in part, on informed practitioners. The aim of this review is to present the basic technological pillars of AI, together with the state-of-the-art machine learning methods and their application to medical imaging. In addition, we discuss the new trends and future research directions. This will help the reader to understand how AI methods are now becoming an ubiquitous tool in any medical image analysis workflow and pave the way for the clinical implementation of AI-based solutions.     

Strategies for systems-level metabolic engineering

Bio-based production of chemicals, fuels and materials is becoming more and more important due to the increasing environmental problems and sharply increasing oil price. To make these biobased processes economically competitive, the biotechnology industry explores new ways to improve the performance of microbial strains in fermentation processes. In contrast to the random mutagenesis and/or intuitive local metabolic engineering practiced in the past, we are now moving towards global-scale metabolic engineering, aided by various experimental and computational tools. This has recently led to some remarkable achievements for the overproduction of valueadded products. In this review, we highlight several relevant gene manipulation tools and computational tools using genome-scale stoichiometric models, and provide useful strategies for successful metabolic engineering along with selected exemplary studies.     

In silico,in vitro,and in vivo machine learning in synthetic biology and metabolic engineering

Among the main learning methods reviewed in this study and used in synthetic biology and metabolic engineering are supervised learning, reinforcement and active learning, and in vitro or in vivo learning.In the context of biosynthesis, supervised machine learning is being exploited to predict biological sequence activities, predict structures and engineer sequences, and optimize culture conditions.Active and reinforcement learning methods use training sets acquired through an iterative process generally involving experimental measurements. They are applied to design, engineer, and optimize metabolic pathways and bioprocesses.The nascent but promising developments with in vitro and in vivo learning comprise molecular circuits performing simple tasks such as pattern recognition and classification.     

Modeling cancer metabolism on a genome scale

Cancer cells have fundamentally altered cellular metabolism that is associated with their tumorigenicity and malignancy. In addition to the widely studied Warburg effect, several new key metabolic alterations in cancer have been established over the last decade, leading to the recognition that altered tumor metabolism is one of the hallmarks of cancer. Deciphering the full scope and functional implications of the dysregulated metabolism in cancer requires both the advancement of a variety of omics measurements and the advancement of computational approaches for the analysis and contextualization of the accumulated data. Encouragingly, while the metabolic network is highly interconnected and complex, it is at the same time probably the best characterized cellular network. Following, this review discusses the challenges that genome‐scale modeling of cancer metabolism has been facing. We survey several recent studies demonstrating the first strides that have been done, testifying to the value of this approach in portraying a network‐level view of the cancer metabolism and in identifying novel drug targets and biomarkers. Finally, we outline a few new steps that may further advance this field.     

Synthetic biology tools for engineering Yarrowia lipolytica

The non-conventional oleaginous yeast Yarrowia lipolytica shows great industrial promise. It naturally produces certain compounds of interest but can also artificially generate non-native metabolites, thanks to an engineering process made possible by the significant expansion of a dedicated genetic toolbox. In this review, we present recently developed synthetic biology tools that facilitate the manipulation of Y. lipolytica, including 1) DNA assembly techniques, 2) DNA parts for constructing expression cassettes, 3) genome-editing techniques, and 4) computational tools.     

AI applications to medical images: From machine learning to deep learning

PurposeArtificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context.MethodsA narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections.ResultsWe first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way.ConclusionsBiomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practice.     

肥胖人群肠道菌群特征分析及机器学习模型

【背景】肠道菌群与人体健康之间的关系吸引了越来越多的关注,成为目前热门的研究热点。【目的】基于美国肠道计划公开数据库,对肥胖和健康人群肠道菌群进行比较分析,解析肥胖人群肠道菌群特征,并基于肠道菌群建立机器学习模型预测人群肥胖的状态,为基于肠道菌群干预肥胖提供理论基础。【方法】从公开数据库中获取美国肠道计划中的肠道菌数据,经过筛选得到1 655个健康(18.530)成年人的肠道菌群数据。针对α多样性,进行了Wilcox秩和检验分析并通过Logsitic回归判定α多样性与肥胖之间的关系;对Unweighted UniFrac、WeightedUniFrac和Bray-Curtis三种β多样性距离进行主成分分析(principalcomponent analysis,PCA),探索肥胖与健康人群在肠道菌群组成上的差异;对于物种差异,进行Wilcox秩和检验探索差异菌属;通过PICRUSt分析预测可能的代谢通路,同时与肠道菌群进行相关性分析。利用Scikit-Learn软件包基于属水平的肠道菌群数据建立肥胖分类机器学习模型,并进行网络搜...     

Active and machine learning-based approaches to rapidly enhance microbial chemical production

In order to make renewable fuels and chemicals from microbes, new methods are required to engineer microbes more intelligently. Computational approaches, to engineer strains for enhanced chemical production typically rely on detailed mechanistic models (e.g., kinetic/stoichiometric models of metabolism)—requiring many experimental datasets for their parameterization—while experimental methods may require screening large mutant libraries to explore the design space for the few mutants with desired behaviors. To address these limitations, we developed an active and machine learning approach (ActiveOpt) to intelligently guide experiments to arrive at an optimal phenotype with minimal measured datasets. ActiveOpt was applied to two separate case studies to evaluate its potential to increase valine yields and neurosporene productivity in Escherichia coli. In both the cases, ActiveOpt identified the best performing strain in fewer experiments than the case studies used. This work demonstrates that machine and active learning approaches have the potential to greatly facilitate metabolic engineering efforts to rapidly achieve its objectives.     

CRISPR-derived genome editing technologies for metabolic engineering

In metabolic engineering, genome editing tools make it much easier to discover and evaluate relevant genes and pathways and construct strains. Clustered regularly interspaced palindromic repeats (CRISPR)-associated (Cas) systems now have become the first choice for genome engineering in many organisms includingindustrially relevant ones. Targeted DNA cleavage by CRISPR-Cas provides variousgenome engineering modes such as indels, replacements, large deletions, knock-in and chromosomal rearrangements, while host-dependent differences in repair pathways need to be considered. The versatility of the CRISPR system has given rise to derivative technologies that complement nuclease-based editing, which causes cytotoxicity especially in microorganisms. Deaminase-mediated base editing installs targeted point mutations with much less toxicity. CRISPRi and CRISPRa can temporarily control gene expression without changing the genomic sequence. Multiplex, combinatorial and large scale editing are made possible by streamlined design and construction of gRNA libraries to further accelerates comprehensive discovery, evaluation and building of metabolic pathways. This review summarizes the technical basis and recent advances in CRISPR-related genome editing tools applied for metabolic engineering purposes, with representative examples of industrially relevant eukaryotic and prokaryotic organisms.     

Using machine learning to predict the effects and consequences of mutations in proteins

Machine and deep learning approaches can leverage the increasingly available massive datasets of protein sequences, structures, and mutational effects to predict variants with improved fitness. Many different approaches are being developed, but systematic benchmarking studies indicate that even though the specifics of the machine learning algorithms matter, the more important constraint comes from the data availability and quality utilized during training. In cases where little experimental data are available, unsupervised and self-supervised pre-training with generic protein datasets can still perform well after subsequent refinement via hybrid or transfer learning approaches. Overall, recent progress in this field has been staggering, and machine learning approaches will likely play a major role in future breakthroughs in protein biochemistry and engineering.     

Integrated knowledge mining,genome-scale modeling,and machine learning for predicting Yarrowia lipolytica bioproduction

Predicting bioproduction titers from microbial hosts has been challenging due to complex interactions between microbial regulatory networks, stress responses, and suboptimal cultivation conditions. This study integrated knowledge mining, feature extraction, genome-scale modeling (GSM), and machine learning (ML) to develop a model for predicting Yarrowia lipolytica chemical titers (i.e., organic acids, terpenoids, etc.). First, Y. lipolytica production data, including cultivation conditions, genetic engineering strategies, and product information, was manually collected from literature (~100 papers) and stored as either numerical (e.g., substrate concentrations) or categorical (e.g., bioreactor modes) variables. For each case recorded, central pathway fluxes were estimated using GSMs and flux balance analysis (FBA) to provide metabolic features. Second, a ML ensemble learner was trained to predict strain production titers. Accurate predictions on the test data were obtained for instances with production titers >1 g/L (R² = 0.87). However, the model had reduced predictability for low performance strains (0.01–1 g/L, R² = 0.29) potentially due to biosynthesis bottlenecks not captured in the features. Feature ranking indicated that the FBA fluxes, the number of enzyme steps, the substrate inputs, and thermodynamic barriers (i.e., Gibbs free energy of reaction) were the most influential factors. Third, the model was evaluated on other oleaginous yeasts and indicated there were conserved features for some hosts that can be potentially exploited by transfer learning. The platform was also designed to assist computational strain design tools (such as OptKnock) to screen genetic targets for improved microbial production in light of experimental conditions.     

Modular,synthetic chromosomes as new tools for large scale engineering of metabolism

The construction of powerful cell factories requires intensive genetic engineering for the addition of new functionalities and the remodeling of native pathways and processes. The present study demonstrates the feasibility of extensive genome reprogramming using modular, specialized de novo-assembled neochromosomes in yeast. The in vivo assembly of linear and circular neochromosomes, carrying 20 native and 21 heterologous genes, enabled the first de novo production in a microbial cell factory of anthocyanins, plant compounds with a broad range of pharmacological properties. Turned into exclusive expression platforms for heterologous and essential metabolic routes, the neochromosomes mimic native chromosomes regarding mitotic and genetic stability, copy number, harmlessness for the host and editability by CRISPR/Cas9. This study paves the way for future microbial cell factories with modular genomes in which core metabolic networks, localized on satellite, specialized neochromosomes can be swapped for alternative configurations and serve as landing pads for the addition of functionalities.     

CRISPR-Cas9 for the genome engineering of cyanobacteria and succinate production

Cyanobacteria hold promise as a cell factory for producing biofuels and bio-derived chemicals, but genome engineering of cyanobacteria such as Synechococcus elongatus PCC 7942 poses challenges because of their oligoploidy nature and long-term instability of the introduced gene. CRISPR-Cas9 is a newly developed RNA-guided genome editing system, yet its application for cyanobacteria engineering has yet to be reported. Here we demonstrated that CRISPR-Cas9 system can effectively trigger programmable double strand break (DSB) at the chromosome of PCC 7942 and provoke cell death. With the co-transformation of template plasmid harboring the gene cassette and flanking homology arms, CRISPR-Cas9-mediated DSB enabled precise gene integration, ameliorated the homologous recombination efficiency and allowed the use of lower amount of template DNA and shorter homology arms. The CRISPR-Cas9-induced cell death imposed selective pressure and enhanced the chance of concomitant integration of gene cassettes into all chromosomes of PCC 7942, hence accelerating the process of obtaining homogeneous and stable recombinant strains. We further explored the feasibility of engineering cyanobacteria by CRISPR-Cas9-assisted simultaneous glgc knock-out and gltA/ppc knock-in, which improved the succinate titer to 435.0±35.0 μg/L, an ≈11-fold increase when compared with that of the wild-type cells. These data altogether justify the use of CRISPR-Cas9 for genome engineering and manipulation of metabolic pathways in cyanobacteria.     

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.     

Metabolic modeling of spatial heterogeneity of biofilms in microbial fuel cells reveals substrate limitations in electrical current generation

Microbial fuel cells (MFCs) have been proposed as an alternative energy resource for the conversion of organic compounds to electricity. In an MFC, microorganisms such as Geobacter sulfurreducens form an anode‐associated biofilm that can completely oxidize organic matter (electron donor) to carbon dioxide with direct electron transfer to the anode (electron acceptor). Mathematical models are useful in analyzing biofilm processes; however, existing models rely on Nernst–Monod type expressions, and evaluate extracellular processes separated from the intracellular metabolism of the microorganism. Thus, models that combine both extracellular and intracellular components, while addressing spatial heterogeneity, are essential for improved representation of biofilm processes. The goal of this work is to develop a model that integrates genome‐scale metabolic models with the model of biofilm environment. This integrated model shows the variations of electrical current production and biofilm thickness under the presence/absence of NH₄ in the bulk solution, and under varying maintenance energy demands. Further, sensitivity analysis suggested that conductivity is not limiting electrical current generation and that increasing cell density can lead to enhanced current generation. In addition, the modeling results also highlight instances such as the transformation into respiring cells, where the mechanism of electrical current generation during biofilm development is not yet clearly understood.