AUTHOR=Liu Wei , Tang Jia-Wei , Mou Jing-Yi , Lyu Jing-Wen , Di Yu-Wei , Liao Ya-Long , Luo Yan-Fei , Li Zheng-Kang , Wu Xiang , Wang Liang 

TITLE=Rapid discrimination of Shigella spp. and Escherichia coli via label-free surface enhanced Raman spectroscopy coupled with machine learning algorithms

JOURNAL=Frontiers in Microbiology

VOLUME=14

YEAR=2023

URL=https://www.frontiersin.org/journals/microbiology/articles/10.3389/fmicb.2023.1101357

DOI=10.3389/fmicb.2023.1101357

ISSN=1664-302X

ABSTRACT=<p><italic>Shigella</italic> and enterotoxigenic <italic>Escherichia coli</italic> (ETEC) are major bacterial pathogens of diarrheal disease that is the second leading cause of childhood mortality globally. Currently, it is well known that <italic>Shigella</italic> spp., and <italic>E</italic>. <italic>coli</italic> are very closely related with many common characteristics. Evolutionarily speaking, <italic>Shigella</italic> spp., are positioned within the phylogenetic tree of <italic>E</italic>. <italic>coli</italic>. Therefore, discrimination of <italic>Shigella</italic> spp., from <italic>E</italic>. <italic>coli</italic> is very difficult. Many methods have been developed with the aim of differentiating the two species, which include but not limited to biochemical tests, nucleic acids amplification, and mass spectrometry, etc. However, these methods suffer from high false positive rates and complicated operation procedures, which requires the development of novel methods for accurate and rapid identification of <italic>Shigella</italic> spp., and <italic>E</italic>. <italic>coli</italic>. As a low-cost and non-invasive method, surface enhanced Raman spectroscopy (SERS) is currently under intensive study for its diagnostic potential in bacterial pathogens, which is worthy of further investigation for its application in bacterial discrimination. In this study, we focused on clinically isolated <italic>E</italic>. <italic>coli</italic> strains and <italic>Shigella</italic> species (spp.), that is, <italic>S</italic>. <italic>dysenteriae</italic>, <italic>S</italic>. <italic>boydii</italic>, <italic>S</italic>. <italic>flexneri</italic>, and <italic>S</italic>. <italic>sonnei</italic>, based on which SERS spectra were generated and characteristic peaks for <italic>Shigella</italic> spp., and <italic>E</italic>. <italic>coli</italic> were identified, revealing unique molecular components in the two bacterial groups. Further comparative analysis of machine learning algorithms showed that, the Convolutional Neural Network (CNN) achieved the best performance and robustness in bacterial discrimination capacity when compared with Random Forest (RF) and Support Vector Machine (SVM) algorithms. Taken together, this study confirmed that SERS paired with machine learning could achieve high accuracy in discriminating <italic>Shigella</italic> spp., from <italic>E</italic>. <italic>coli</italic>, which facilitated its application potential for diarrheal prevention and control in clinical settings.
<fig position="float" id="g006"><caption><p>Graphical abstract</p></caption><graphic xlink:href="fmicb-14-1101357-g006.tif" xmlns:xlink="http://www.w3.org/1999/xlink" /></fig></p>