Accurate identification of living Bacillus spores using laser tweezers Raman spectroscopy and deep learning

Fusheng Du; Lin He; Xiaoxu Lu; Yong-Qing Li; Yufeng Yuan

doi:10.1016/j.saa.2022.122216

Accurate identification of living Bacillus spores using laser tweezers Raman spectroscopy and deep learning

Spectrochim Acta A Mol Biomol Spectrosc. 2023 Mar 15:289:122216. doi: 10.1016/j.saa.2022.122216. Epub 2022 Dec 7.

Authors

Fusheng Du¹, Lin He², Xiaoxu Lu³, Yong-Qing Li⁴, Yufeng Yuan⁵

Affiliations

¹ School of Electronic Engineering and Intelligentization, Dongguan University of Technology, Dongguan, Guangdong 523808, China; School of Information and Optoelectronic Science and Engineering, South China Normal University, Guangzhou, Guangdong 510631, China.
² School of Electronic Engineering and Intelligentization, Dongguan University of Technology, Dongguan, Guangdong 523808, China.
³ School of Information and Optoelectronic Science and Engineering, South China Normal University, Guangzhou, Guangdong 510631, China.
⁴ School of Electronic Engineering and Intelligentization, Dongguan University of Technology, Dongguan, Guangdong 523808, China; Department of Physics, East Carolina University, Greenville, NC 27858-4353, USA.
⁵ School of Electronic Engineering and Intelligentization, Dongguan University of Technology, Dongguan, Guangdong 523808, China. Electronic address: yufengyuan@dgut.edu.cn.

PMID: 36527970
DOI: 10.1016/j.saa.2022.122216

Abstract

Accurately, rapidly, and noninvasively identifying Bacillus spores can greatly contribute to controlling a plenty of infectious diseases. Laser tweezers Raman spectroscopy (LTRS) has confirmed to be a powerful tool for studying Bacillus spores at a single cell level. In this study, we constructed a single-cell Raman spectra dataset of living Bacillus spores and utilized deep learning approach to accurately, nondestructively identify Bacillus spores. The trained convolutional neural network (CNN) could efficiently extract tiny Raman spectra features of five spore species, and provide a prediction accuracy of specie identification as high as 100 %. Moreover, the spectral feature differences in three Raman bands at 660, 826, and 1017 cm^-1 were confirmed to mostly contribute to producing such high prediction accuracy. In addition, optimal CNN model was employed to monitor and identify sporulation process at different metabolic phases in one growth cycle. The obtained average prediction accuracy of metabolic phase identification was approximately 88 %. It can be foreseen that, LTRS combined with CNN approach have great potential for accurately identifying spore species and metabolic phases at a single cell level, and can be gradually extended to perform identification for many unculturable bacteria growing in soil, water, and food.

Keywords: Bacillus spore classification; Deep learning; Laser tweezers Raman spectroscopy; Metabolic phase identification; Single cell level.

MeSH terms

Bacillus*
Deep Learning*
Optical Tweezers
Spectrum Analysis, Raman / methods
Spores, Bacterial / chemistry