Rapid detection of six Oceanobacillus species in Daqu starter using single-cell Raman spectroscopy combined with machine learning - Research article

Aug 5, 2026

Many traditional fermented foods and beverages depend on multi-species starter cultures, yet the microbial community in Daqu starters varies because fermentation occurs in an open environment. A rapid, accurate identification method is essential to protect final product quality. This study uses single-cell Raman spectroscopy combined with machine learning to monitor six Oceanobacillus species in Daqu, building a Raman–taxonomy reference database and selecting SVM as the best classifier.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Role of Daqu microbiota in baijiu fermentation

Factors influencing Daqu microbial structure

Materials and Methods

Single-cell Raman spectroscopy workflow

Machine-learning classification and validation

Results

Detection of six Oceanobacillus species in Daqu

Reference database and model performance

Fermentation-time prediction and PLSR reliability

Discussion

DOI: 10.1111/1751-7915 .14416 R E S E A R C H A R T I C L E Rapid detection of six Oceanobacillus species in Daqu starter using single-cell Raman spectroscopy combined with machine learning Lei Xu1,2 | Yuan Liang1 | Wei E Huang3,4 | Lin-Dong Shang5 | Li-Juan Chai2 | Xiao-Juan Zhang2 | Jin-Song Shi6 | Bei Li5 | Yun Wang3 | Zheng-Hong Xu1,2,7 | Zhen-Ming Lu1,2,7 1Key Laboratory of Industrial Biotechnology of Ministry of Education, School of Biotechnology, Jiangnan University, Wuxi, China 2National Engineering Research Center of Cereal Fermentation and Food Biomanufacturing, Jiangnan University, Wuxi, China 3Oxford Suzhou Centre for Advanced Research, Suzhou, China 4Department of Engineering Science, University of Oxford, Oxford, UK 5State Key Laboratory of Applied Optics, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, China 6School of Life Sciences and Health Engineering, Jiangnan University, Wuxi, China 7National Engineering Research Center of Solid-State Brewing, Luzhou, China Correspondence Yun Wang, Oxford Suzhou Centre for Advanced Research, Suzhou 215000, P. R. China. Email: [yun.wang@oxford-oscar.cn](yun.wang@oxford-oscar.cn) Zheng-Hong Xu and Zhen-Ming Lu, Key Laboratory of Industrial Biotechnology of Ministry of Education, School of Biotechnology, Jiangnan University, Wuxi 214122, China. Email: [zhenghxu@jiangnan.edu.cn](zhenghxu@jiangnan.edu.cn) and [zmlu@jiangnan.edu.cn](zmlu@jiangnan.edu.cn) Funding information National Key Research and Development Program of China, Grant/Award Number: 2022YFD2101204-01; Jiangsu Provincial project, Grant/Award Number: JSSCRC2021560; SEID project, Grant/ Award Number: YZCXPT2022204 Abstract Many traditional fermented foods and beverages industries around the world request the addition of multi-species starter cultures. However, the microbial community in starter cultures is subject to fluctuations due to their exposure to an open environment during fermentation. A rapid detection approach to identify the microbial composition of starter culture is essential to ensure the quality of the final products. Here, we applied single-cell Raman spectroscopy (SCRS) combined with machine learning to monitor Oceanobacillus species in Daqu starter, which plays crucial roles in the process of Chinese baijiu. First, a total of six Oceanobacillus species (O. caeni, O. kimchii, O. iheyensis, O. sojae, O. oncorhynchi subsp. Oncorhynchi and O. profundus) were detected in 44 Daqu samples by amplicon sequencing and isolated by pure culture. Then, we created a reference database of these Oceanobacillus strains which correlated their taxonomic data and single-cell Raman spectra (SCRS) . Based on the SCRS dataset, five machine-learning algorithms were used to classify Oceanobacillus strains, among which support vector machine (SVM) showed the highest rate of accuracy. For validation of SVM-based model, we employed a synthetic microbial community composed of varying proportions of Oceanobacillus species and demonstrated a remarkable accuracy, with a mean error was less than 1% between the predicted result and the expected value. The relative abundance of six different Oceanobacillus species during Daqu fermentation was predicted within 60 min using this method, and the reliability of the method was proved by correlating the Raman spectrum with theamplicon sequencing profiles by partial least squares regression. Our study provides a rapid, non-destructive and label-free approach for rapid identification of Oceanobacillus species in Daqu starter culture, contributing to realtime monitoring of fermentation process and ensuring high-quality products. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes. © 2024 The Autho

FAQs

Why is rapid detection of Oceanobacillus species in Daqu starter important?

Because the microbial community in open-environment fermentation fluctuates, rapid identification helps ensure the quality of the final baijiu products.

How were six Oceanobacillus species detected in the study?

Oceanobacillus caeni, O. kimchii, O. iheyensis, O. sojae, O. oncorhynchi subsp. Oncorhynchi, and O. profundus were detected across Daqu samples using amplicon sequencing and isolation by pure culture.

Which machine-learning model performed best, and how was it validated?

Support vector machine (SVM) achieved the highest accuracy. Validation used a synthetic microbial community with varying Oceanobacillus proportions, showing a mean error under 1% and agreement with amplicon sequencing via PLS regression.

Aug 5, 2026

Upload by Emma Wilson