High-speed diagnosis of bacterial pathogens at the single cell level by Raman microspectroscopy with machine learning filters and denoising autoencoders

Xu, J., Yi, X., Jin, G., Peng, D., Fan, G., Xu, X., Chen, X., Yin, H. , Cooper, J. M. and Huang, W. E. (2022) High-speed diagnosis of bacterial pathogens at the single cell level by Raman microspectroscopy with machine learning filters and denoising autoencoders. ACS Chemical Biology, 17(2), pp. 376-385. (doi: 10.1021/acschembio.1c00834) (PMID:35026119)

[img] Text
263331.pdf - Accepted Version

2MB
[img] Text
263331Suppl.pdf - Supplemental Material

825kB

Abstract

Accurate and rapid identification of infectious bacteria is important in medicine. Raman microspectroscopy holds great promise in performing label-free identification at the single-cell level. However, due to the naturally weak Raman signal, it is a challenge to build extensive databases and achieve both accurate and fast identification. Here, we used signal-to-noise ratio (SNR) as a standard indicator for Raman data quality and performed bacterial identification using 11, 141 single-cell Raman spectra from nine bacterial strains. Subsequently, using two machine learning methods, a simple filter, and a neural network-based denoising autoencoder (DAE), we demonstrated 92% (simple filter using 1 s/cell spectra) and 84% (DAE using 0.1 s/cell spectra) identification accuracy. Our machine learning-aided Raman analysis paves the way for high-speed Raman microspectroscopic clinical diagnostics.

Item Type:Articles
Additional Information:J.X., H.Y., J.M.C., and W.E.H. thank the Innovate UK (project reference number 104984). X.Y., G.J., D.P., G.F., X.X., and X.C. are grateful for the grants received from the National Key Research and Development Project (2018YFE0101800), Shanghai Municipal Science and Technology Commission (18411950601). J.X., J.W., and W.E.H. also thank the Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences for financial support.
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Cooper, Professor Jonathan and Yin, Professor Huabing
Authors: Xu, J., Yi, X., Jin, G., Peng, D., Fan, G., Xu, X., Chen, X., Yin, H., Cooper, J. M., and Huang, W. E.
College/School:College of Science and Engineering > School of Engineering > Biomedical Engineering
Journal Name:ACS Chemical Biology
Publisher:American Chemical Society
ISSN:1554-8929
ISSN (Online):1554-8937
Published Online:13 January 2022
Copyright Holders:Copyright © 2022 American Chemical Society
First Published:First published in ACS Chemical Biology 17(2): 376-385
Publisher Policy:Reproduced in accordance with the publisher copyright policy

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
304354An integrated microfluidic single cell Raman technology for rapid diagnosis of pathogens and their antibiotic resistanceHuabing YinInnovate UK (INNOVATE)104984ENG - Biomedical Engineering