EUVIMEDEUVIMED entdecken
Open Access

Species identification and strain discrimination of fermentation yeasts Saccharomyces cerevisiae and Saccharomyces uvarum using Raman spectroscopy and convolutional neural networks

Kaidi Wang iD, Jing Chen, Jay Martiniuk, Xiangyun Ma, Qifeng Li, Vivien Measday iD, Xiaonan Lu iD

Applied and Environmental Microbiology · 2023

DOI: 10.1128/aem.01673-23 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied and Environmental Microbiology, 2023. Verfasst von Kaidi Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Food, Nutrition and Health Program, Faculty of Land and Food Systems, The University of British Columbia, Vancouver, British Columbia, Canada. Hauptthemen laut MEDLINE: Wine, Saccharomyces cerevisiae. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 93 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Gouvernement du Canada | Natural Sciences and Engineering Research Council of Canada (NSERC).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable typing of yeast strains is of great importance to the alcoholic beverage industry to ensure a reliable fermentation process and high-quality products. Saccharomyces cerevisiae is the most used yeast species in wine, sake, and ale beer fermentation, whereas Saccharomyces uvarum is more commonly used for cider fermentation and, due to its cryotolerance, white wine production. We propose a promising method for species identification and strain discrimination of S. cerevisiae and S. uvarum using Raman spectroscopy in combination with convolutional neural networks (CNNs). Raman spectra collected from various S. cerevisiae and S. uvarum strains were accurately classified at the species level using random forest. Cultivation time and temperature did not significantly affect the spectral reproducibility and discrimination capability. An overall accuracy of 91.9% was achieved to discriminate 27 yeast isolates at the strain level using a CNN model. Raman-CNN further identified eight yeast isolates spiked in grape juice with an accuracy of 98.1%. Raman spectral signatures derived from diverse protein and lipid compositions may contribute to this discrimination. The proposed approach also precisely predicted the concentration of a specific yeast strain within a yeast mixture with an R 2 of 0.9913 and an average error of 4.09%. The entire analysis can be completed within 1 hour following cultivation and only requires simple sample preparation and low consumable cost. Taken together, Raman spectroscopy coupled with CNN is a robust, accurate, and reliable approach for typing of fermentation yeast strains. IMPORTANCE The use of S. cerevisiae and S. uvarum yeast starter cultures is a common practice in the alcoholic beverage fermentation industry. As yeast strains from different or the same species have variable fermentation properties, rapid and reliable typing of yeast strains plays an important role in the final quality of the product. In this study, Raman spectroscopy combined with CNN achieved accurate identification of S. cerevisiae and S. uvarum isolates at both the species and strain levels in a rapid, non-destructive, and easy-to-operate manner. This approach can be utilized to test the identity of commercialized dry yeast products and to monitor the diversity of yeast strains during fermentation. It provides great benefits as a high-throughput screening method for agri-food and the alcoholic beverage fermentation industry. This proposed method has the potential to be a powerful tool to discriminate S. cerevisiae and S. uvarum strains in taxonomic, ecological studies and fermentation applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

WineSaccharomyces cerevisiaeFermentationNeural Networks, ComputerYeastsSpectrum Analysis, RamanSaccharomyces

Stichwörter der Autor:innen

Raman spectroscopyconvolutional neural networksfermentation yeastprincipal component analysisrandom foreststrain discrimination

Autor:innen und Institutionen

  • Food, Nutrition and Health Program, Faculty of Land and Food Systems, The University of British Columbia, Vancouver, British Columbia, Canada.
  • Department of Food Science and Agricultural Chemistry, Faculty of Agricultural and Environmental Sciences, McGill University, Sainte-Anne-de-Bellevue, Quebec, Canada.
  • Wine Research Centre, Faculty of Land and Food Systems, The University of British Columbia, Vancouver, British Columbia, Canada.
  • School of Precision Instrument and Optoelectronics Engineering, Tianjin University, Tianjin, China.

ORCID-Profile: Kaidi Wang, Vivien Measday, Xiaonan Lu

Förderung

  • Gouvernement du Canada | Natural Sciences and Engineering Research Council of Canada (NSERC)

Zitieren

APA

Wang, K., Chen, J., Martiniuk, J., Ma, X., Li, Q., Measday, V., & Lu, X. (2023). Species identification and strain discrimination of fermentation yeasts Saccharomyces cerevisiae and Saccharomyces uvarum using Raman spectroscopy and convolutional neural networks. Applied and Environmental Microbiology. https://doi.org/10.1128/aem.01673-23

Vancouver

Wang K, Chen J, Martiniuk J, Ma X, Li Q, Measday V, et al. Species identification and strain discrimination of fermentation yeasts Saccharomyces cerevisiae and Saccharomyces uvarum using Raman spectroscopy and convolutional neural networks. Applied and Environmental Microbiology. 2023. doi:10.1128/aem.01673-23

BibTeX
@article{Wang2023,
  author = {Wang, Kaidi and Chen, Jing and Martiniuk, Jay and Ma, Xiangyun and Li, Qifeng and Measday, Vivien and Lu, Xiaonan},
  title = {Species identification and strain discrimination of fermentation yeasts Saccharomyces cerevisiae and Saccharomyces uvarum using Raman spectroscopy and convolutional neural networks},
  journal = {Applied and Environmental Microbiology},
  year = {2023},
  doi = {10.1128/aem.01673-23}
}
Kostenlos starten →