Study on Identification of Non-Tuberculosis Mycobacteria Based on Single-Cell Raman Spectroscopy
RUAN Zhen1, ZHU Peng-fei3, ZHANG Lei3, CHEN Rong-ze3, LI Xun-rong3, FU Xiao-ting3, HUANG Zheng-gu4, ZHOU Gang4, JI Yue-tong5, LIAO Pu1, 2*
1. Key Laboratory of Diagnostic Medicine, Ministry of Education; School of Laboratory Medicine, Chongqing Medical University, Chongqing 400016, China
2. Department of Laboratory Medicine, Chongqing General Hospital, Chongqing 400013, China
3. Single-Cell Center, Qingdao Institute of Bioenergy and Bioprocess Technology, Chinese Academy of Sciences, Qingdao 266101, China
4. Center Lab, Chongqing Public Health Medical Center, Chongqing 400036, China
5. Qingdao Single-Cell Biotechnology Co., Ltd., Qingdao 266101, China
Abstract：Non-tuberculosis mycobacteria (NTM) are the collection of mycobacteria other than Mycobacterium tuberculosis complex (MTC) and Mycobacterium leprosy. The clinical symptoms of NTM are very similar to MTC infection, yet their treatments are different, thus rapid and accurate identification methods of NTM are urgently needed. Single-cell Raman Spectroscopy (SCRS) is label-free, and independent of cultivation, thus it is deemed a rapid and efficient technology with low cost. Here we propose an SCRS based method to identify NTM based on confocal SCRS. We selected six common NTM species in the clinic, Mycobacterium abscessus, Mycobacterium gordonae, Mycobacterium fortuitum, Mycobacterium fortuitum, Mycobacterium avium and Mycobacterium kansasii. The unsupervised low-dimensional visualization t-distribution random neighborhood embedding method for the data structures proved the separability of data in the low-dimensional space. Performance of six commonly classifiers, including Support Vector Machine (SVM), K-Nearest Neighbor method (KNN), Partial Least Square-Discriminate Analysis (PLS-DA), Random Forests (RF), Linear Discriminant Analysis (LDA) and XG Boost was compared, with SVM and LDA achieving an accuracy of 99.4% and 98.8% respectively in NTMs classification. SVM offers 100% classification accuracy for every species, except Mycobacterium kansasii which is slightly lower (97.96%, 48/49), while LDA offers 100% accuracy for each species except Mycobacterium abscessus (95.65%; 22/23) and Mycobacterium gordonae(96.30%, 26/27). Therefore, SCRS combined with SVM can accurately classify NTMs and thus provide a new tool for the rapid diagnosis of NTM.
[1] Tortoli E, Fedrizzi T, Meehan C J, et al. Infection, Genetics and Evolution, 2017, 56: 19.
[2] Baldwin S L, Larsen S E, Ordway D, et al. PLOS Neglected Tropical Diseases, 2019, 13(2): e0007083.
[3] Huang W C, Yu M C, Huang Y W. Journal of the Formosan Medical Association, 2020, 119: 532.
[4] WANG Li-xia, CHENG Shi-ming, CHEN Ming-ting, et al(王黎霞, 成诗明, 陈明亭, 等). Chinese Journal of Antituberculosis（中国防痨杂志）, 2012，(8): 485.
[5] Mcgrath E E, Anderson P B. The Lancet, 2007, 370(9581): 28.
[6] Griffith D E, Aksamit T, Brown-Elliott B A, et al. American Journal of Respiratory and Critical Care Medicine, 2007, 175(4): 367.
[7] Brown-Elliott B A, Nash K A, Wallace R J Jr. Clinical Microbiology Reviews, 2012, 25(3): 545.
[8] Seagar A L, Prendergast C, Emmanuel F X, et al. Journal of Medical Microbiology, 2008, 57: 605.
[9] Kim S, Park E M, Kwon O J, et al. The International Journal of Tuberculosis and Lung Disease, 2008, 12(11): 1344.
[10] LIANG Hao-yue, CHENG Xue-lian, YANG Wan-zhu, et al(梁昊岳, 程雪莲, 杨晚竹, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(12): 3670.
[11] RUAN Zhen, ZHU Peng-fei, FU Xiao-ting, et al(阮 真, 朱鹏飞, 付晓婷，等). Microbiology China（微生物学通报）. doi：10.13344/j.microbiol.china.200703.
[12] Petry R, Schmitt M, Popp J. Chemphyschem, 2003, 4(1): 14.
[13] Montanari L B, Martins C H G, De Mello C A, et al. Journal of Water and Health, 2018, 16(2): 311.
[14] Harz M, Kiehntopf M, Stockel S, et al. Journal of Biophotonics, 2009, 2(1-2): 70.
[15] Jorgensen J H, Pfaller M A. Manual of Clinical Microbiology. American Society for Microbiology, 2015.
[16] He Y, Wang X, Ma B, et al. Biotechnology Advances, 2019, 37(6): 107388.
[17] Xu T, Gong Y, Su X, et al. Small, 2020, 16(30): e2001172.
