Bioethanol production estimated from volatile compositions in hydrolysates of lignocellulosic biomass by deep learning

Building a machine-learning model to predict optimal mevalonate pathway gene expression levels for efficient production of a carotenoid in yeast

Simultaneous modification of the expression levels of many metabolic enzyme genes results in diverse expression ratios of these genes; however, the relationship between gene expression levels and chemical productivity remains unclear. However, clarification of this relationship is expected to improve the productivity of useful chemicals. Supervised machine learning is considered to be an effective means to clarify this relationship. In this study, to improve the productivity of carotenoids in yeast Saccharomyces cerevisiae, we aimed to build a machine-learning model that can predict the optimal gene expression level for carotenoid production. First, we obtained data on the expression levels of mevalonate pathway enzyme genes and carotenoid production. Then, based on these data, we built a machine-learning model to predict carotenoid productivity based on gene expression levels. The prediction accuracy of 0.6292 (coefficient of determination) was achieved using the test data. The maximum predicted carotenoid productivity was 4.3 times higher in the engineered strain than in the parental strain, suggesting that the expression levels of the mevalonate pathway enzyme genes tHMG1 and ERG8 have a particularly large impact on carotenoid productivity. This study could be one of the important achievements in addressing the uncertainty of genotype-phenotype correlations, which is one of the challenges facing metabolic engineering strategies.

Engineering yeast cell factories to produce biodegradable plastics and their monomers: Current status and prospects

Traditional plastic products have caused serious environmental pollution due to difficulty to be degraded in the natural environment. In the recent years, biodegradable plastics are receiving increasing attention due to advantages in natural degradability and environmental friendliness. Biodegradable plastics have potential to be used in food, agriculture, industry, medicine and other fields. However, the high production cost of such plastics is the bottleneck that limits their commercialization and application. Yeasts, including budding yeast and non-conventional yeasts, are widely studied to produce biodegradable plastics and their organic acid monomers. Compared to bacteria, yeast strains are more tolerable to multiple stress conditions including low pH and high temperature, and also have other advantages such as generally regarded as safe, and no phage infection. In addition, synthetic biology and metabolic engineering of yeast have enabled its rapid and efficient engineering for bioproduction using various renewable feedstocks, especially lignocellulosic biomass. This review focuses on the recent progress in biosynthesis technology and strategies of monomeric organic acids for biodegradable polymers, including polylactic acid (PLA), polyhydroxyalkanoate (PHA), polybutylene succinate (PBS), and polybutylene adipate terephthalate (PBAT) using yeast cell factories. Improving the performance of yeast as a cell factory and strategies to improve yeast acid stress tolerance are also discussed. In addition, the critical challenges and future prospects for the production of biodegradable plastic monomer using yeast are also discussed.

Mechanisms, methods and applications of machine learning in bio-alcohol production and utilization: A review

Bio-alcohols have been proven promising alternatives to fossil fuels. Machine learning (ML), as an analytical tool for uncovering intrinsic correlations and mining data connotations, is also becoming widely used in the field of bio-alcohols. This article reviews the mechanisms, methods, and applications of ML in the bio-alcohols field. In terms of mechanisms, we describe the workflow of ML applications, emphasizing the importance of a well-defined research problem and complete feature engineering for a robust model. Prediction and optimization are the main application scenarios. In terms of methods, we illustrate the characteristics of different ML models and analyze their applicability in the bio-alcohol field. The role of ML in the production of bio-methanol by pyrolysis and gasification, as well as in the three stages of fermentation for bioethanol production are highlighted. In terms of utilization, ML is used to optimize engine performance and reduce emissions. This review provides guidance on how to use novel ML methods in the bio-alcohol field, showing the potential of ML to streamline work in the whole biofuel field.

Construction of a machine-learning model to predict the optimal gene expression level for efficient production of D-lactic acid in yeast

The modification of gene expression is being researched in the production of useful chemicals by metabolic engineering of the yeast Saccharomyces cerevisiae. When the expression levels of many metabolic enzyme genes are modified simultaneously, the expression ratio of these genes becomes diverse; the relationship between the gene expression ratio and chemical productivity remains unclear. In other words, it is challenging to predict phenotypes from genotypes. However, the productivity of useful chemicals can be improved if this relationship is clarified. In this study, we aimed to construct a machine-learning model that can be used to clarify the relationship between gene expression levels and D-lactic acid productivity and predict the optimal gene expression level for efficient D-lactic acid production in yeast. A machine-learning model was constructed using data on D-lactate dehydrogenase and glycolytic genes expression (13 dimensions) and D-lactic acid productivity. The coefficient of determination of the completed machine-learning model was 0.6932 when using the training data and 0.6628 when using the test data. Using the constructed machine-learning model, we predicted the optimal gene expression level for high D-lactic acid production. We successfully constructed a machine-learning model to predict both D-lactic acid productivity and the suitable gene expression ratio for the production of D-lactic acid. The technique established in this study could be key for predicting phenotypes from genotypes, a problem faced by recent metabolic engineering strategies.

Smart sustainable biorefineries for lignocellulosic biomass

Lignocellulosic biomass (LCB) is considered as a sustainable feedstock for a biorefinery to generate biofuels and other bio-chemicals. However, commercialization is one of the challenges that limits cost-effective operation of conventional LCB biorefinery. This article highlights some studies on the sustainability of LCB in terms of cost-competitiveness and environmental impact reduction. In addition, the development of computational intelligence methods such as Artificial Intelligence (AI) as a tool to aid the improvement of LCB biorefinery in terms of optimization, prediction, classification, and decision support systems. Lastly, this review examines the possible research gaps on the production and valorization in a smart sustainable biorefinery towards circular economy.

Recent advances in metabolic engineering-integration of in silico design and experimental analysis of metabolic pathways

Microorganisms are widely used to produce valuable compounds. Because thousands of metabolic reactions occur simultaneously and many metabolic reactions are related to target production and cell growth, the development of a rational design method for metabolic pathway modification to optimize target production is needed. In this paper, recent advances in metabolic engineering are reviewed, specifically considering computational pathway modification design and experimental evaluation of metabolic fluxes by ¹³C-metabolic flux analysis. Computational tools for seeking effective gene deletion targets and recruiting heterologous genes are described in flux balance analysis approaches. A kinetic model and adaptive laboratory evolution were applied to identify and eliminate the rate-limiting step in metabolic pathways. Data science-based approaches for process monitoring and control are described to maximize the performance of engineered cells in bioreactors.

Machine learning modeling of the effects of media formulated with various yeast extracts on heterologous protein production in Escherichia coli

In microbial manufacturing, yeast extract is an important component of the growth media. The production of heterologous proteins often varies because of the yeast extract composition. To identify why this reduces protein production, the effects of yeast extract composition on the growth and green fluorescent protein (GFP) production of engineered Escherichia coli were investigated using a deep neural network (DNN)-mediated metabolomics approach. We observed 205 peaks from the various yeast extracts using gas chromatography-mass spectrometry. Principal component analyses of the peaks identified at least three different clusters. Using 20 different compositions of yeast extract in M9 media, the yields of cells and GFP in the yeast extract-containing media were higher than those in the control without yeast extract by approximately 3.0- to 5.0-fold and 1.5- to 2.0-fold, respectively. We compared machine learning models and found that DNN best fit the data. To estimate the importance of each variable, we performed DNN with a mean increase error calculation based on a permutation algorithm. This method identified the significant components of yeast extract. DNN learning with varying numbers of input variables provided the number of significant components. The influence of specific components on cell growth and GFP production was confirmed with a validation cultivation.

Soft-sensor development for monitoring the lysine fermentation process

Monitoring cell growth and target production in working fermentors is important for stabilizing high level production. In this study, we developed a novel soft sensor for estimating the concentration of a target product (lysine), substrate (sucrose), and bacterial cell in commercially working fermentors using machine learning combined with available on-line process data. The lysine concentration was accurately estimated in both linear and nonlinear models; however, the nonlinear models were also suitable for estimating the concentrations of sucrose and bacterial cells. Data enhancement by time interpolation improved the model prediction accuracy and eliminated unnecessary fluctuations. Furthermore, the soft sensor developed based on the dataset of the same process parameters in multiple fermentor tanks successfully estimated the fermentation behavior of each tank. Machine learning-based soft sensors may represent a novel monitoring system for digital transformation in the field of biotechnological processes.