Aug 2026· ACS Omega· Vol 11, pp. 50249 - 50263· 0 citations· 12 references
Medicine
TL;DR
This study demonstrates the effectiveness of XGBoost in predicting complex combinatorial designs and highlights the potential of combining machine learning and transcriptomic insights to optimize non-native biochemical production in yeast.
Abstract
Optimization of microbial production by synthetic biology is essential for industrial and sustainable biotechnology applications. β-carotene is a high-value compound that can be heterologously produced in the budding yeast Saccharomyces cerevisiae, providing an alternative to natural extraction. In this study, we aimed to enhance β-carotene production by machine learning–guided combinatorial strain engineering and transcriptomic analyses. We fine-tuned the expression of rate-limiting enzymes in the mevalonate (MVA) pathway through combinatorial engineering of promoters and terminators. XGBoost was applied to the Design-Build-Test-Learn (DBTL) cycle to facilitate rapid optimization. In the second DBTL cycle of 1 mL culture screening, fine-tuning MVA gene expression resulted in a 139% improvement in β-carotene titer. Additionally, guided by transcriptomic insights into altered expression of iron uptake genes, we supplemented β-carotene production cultures with iron, resulting in a 70.54% increase in β-carotene titer. Furthermore, integrating the fine-tuned MVA cassette with iron supplementation in 250 mL shake-flasks yielded up to 72.07 mg/L of β-carotene at 72 h, representing a 67.79% increase compared to the β-carotene-producing strain without MVA gene fine-tuning. Our study demonstrates the effectiveness of XGBoost in predicting complex combinatorial designs and highlights the potential of combining machine learning and transcriptomic insights to optimize non-native biochemical production in yeast.
The utility of ML-assisted evolution for engineering Rubisco with improved carboxylation efficiency and potential for enhancing crop productivity is demonstrated.
Julie L. McDonald, Jiachen Lin, Yunlong Zhao et al.· bioRxiv· 0 citations
Oleaginous yeasts, particularly Yarrowia lipolytica, are increasingly used as microbial platforms for producing lipids and other value-added compounds from renewable feedstocks. Their biotechnological utility derives from active lipid metabolism, broad substrate flexibility, and expanding engineering tools, but efficient production requires transcriptional programs that match changing metabolic states during fermentation. Because carbon flux is redistributed across growth, nutrient limitation, lipid accumulation, and production phases, static constitutive expression is often insufficient for optimal pathway performance. Promoter engineering therefore provides a key strategy to control expression strength, timing, and responsiveness in oleaginous yeasts. This review summarizes the metabolic basis of phase-dependent gene expression demand, examines constitutive, inducible, and dynamic promoter systems, and discusses how machine learning can support promoter prediction and design. Current challenges, including limited host-specific datasets, context dependence, and uncertain robustness to scale-up, are also discussed. These advances provide a basis for more precise and scalable engineering of oleaginous yeast cell factories.
Akhmad Awaludin Agustiar, Zewei Lu, Dianqi Yang et al.· Biotechnology Advances· 0 citations
Abstract Organisms that thrive in extreme environments provide natural experiments in evolution, revealing the genetic regulators that orchestrate complex phenotypic change. Wine yeast (WY) are specialized strains that are adapted to survive in the wine making environment while producing high concentrations of ethanol. In addition to large genomic changes that differentiate WY from yeast used in other industries, SNP and polyglutamine tract polymorphism in the transcriptional regulator Med15 are associated with the fermentation efficiency and stress response phenotypes of WY. In this study, we investigated the transcriptional differences during wine fermentation in transgenic lab strain yeast having integrated WY MED15 alleles. Compared to the unmodified lab strain (MED15LAB), the same strain in which the MED15 locus was replaced with a MED15 allele from yeast isolated from palm wine, the fermented sap of palm (oil, date, coconut) trees (MED15WY23), exhibited enhanced expression of amino acid biosynthesis genes as well as stress resistance and metabolic adaptation genes. Our experimental data confirm the role of arginine in efficient fermentation and suggest that certain MED15 alleles alter the expression patterns of arginine pathway genes in some cases improving carbon flux under nitrogen stress. The global benefits conferred by natural polymorphisms in a single transcriptional regulator highlight Med15 as a target for engineering of strains devoted to various types of alcohol production.
David G. Cooper, Emma Grunkemeyer, Jan S. Fassler· Microbial Genomics· 0 citations
L-(+)-tartaric acid (L-TA) is a high-value chiral organic acid essential for food and pharmaceuticals. Despite its industrial importance, sustainable green production is constrained by the lack of a fully defined biosynthetic pathway. Here, we report the de novo biosynthesis of L-TA in Saccharomyces cerevisiae through reaction-guided enzyme mining, experimental validation, and Enzyme Commission-specific Catalytic Hybrid Optimizer (ECHO)-assisted enzyme prioritization. We first elucidate the elusive two-step conversion from precursor 5-keto-D-gluconic acid (5-KGA) to L-TA, catalyzed by transketolase (TK) and succinate semialdehyde dehydrogenase (SSDH). To optimize this critical step, we develop the ECHO. This multimodal framework integrates sequence, substrate, and pocket-aware structural information to identify high-performance TK-SSDH pairs. By integrating this pathway with de novo precursor synthesis, cofactor engineering, and semi-rational protein engineering, a final L-TA titer of 6.59 mg L−1 was achieved in a 5-L bioreactor. By connecting computational mining and metabolic assembly through a multi-module engineering strategy, our study establishes a green platform for L-TA production and demonstrates an effective workflow for synthetic pathway design. L-(+)-tartaric acid (L-TA) is a high-value chiral organic acid for food and pharmaceuticals. Here the authors produce L-TA in S. cerevisiae through reaction-guided enzyme mining and Enzyme Commission-specific Catalytic Hybrid Optimizer (ECHO)-assisted enzyme prioritization.
Xuan Zhou, Jiaheng Hou, Zikai Wang et al.· Nature Communications· 0 citations
PHO4 is identified as a promising candidate target for improving high concentration ethanol fermentation efficiency and provides a framework to understand the phosphate-dependent regulatory effects of PHO4 allelic variation and offer a transferable strategy for strain improvement.
This study demonstrates the combined optimization of isozyme combination and environmental stress to elevate the synthesis of astaxanthin and other carotenoids in D. salina, providing new research ideas and experimental evidence for the future construction of high-yield engineered algal strains.
Hao Zhang, Yifan Kong, Yaping Shao et al.· World Journal of Microbiolog...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
