期刊
TALANTA
卷 234, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.talanta.2021.122640
关键词
Bacterial identification; Yersinia pestis; Yersinia pseudotuberculosis; Plague; Multivariate analysis
资金
- National Natural Science Foundation of China [81160354]
- General Program of Yunnan Provincial Science and Technology Department [2018FB030]
- Training Plan for Medical Subject Leaders in Yunnan [D-2019002]
- Jianguo Xu Academician Workstation [2018IC155]
This study established a complete MALDI-TOF MS data pipeline and identified a Y. pestis-specific biomarker, achieving nearly perfect separation between Y. pseudotuberculosis and Y. pestis with a separation accuracy of 0.999 using an LDA model. The new computing method paves the way for automatic differentiation between the two highly similar bacterial species.
Separating Yersinia pseudotuberculosis and Yersinia pestis is an important issue in plague diagnosis but can be extremely difficult because of the high similarity between the two species. MALDI-TOF MS has grown as a diagnostic tool with great potential in bacterial identification. Its application in this field is largely enhanced by multivariate analysis, especially in extracting subtle spectral differences. In this study, we built a complete MALDI-TOF MS data pipeline and found a Y. pestis-specific biomarker at 3063 Da closely related to Y. pestis plasminogen activation factor. Based on this, we achieved almost perfect separation between Y. pseudotuberculosis and Y. pestis (AUC = 0.999) using a supervised linear discriminant analysis (LDA) model. This is significantly better than the conventionally applied unsupervised spectral similarity comparison methods, such as hierarchical clustering analysis (HCA), which gave a separation accuracy of 75.0%. This new computing method paves the way for automatic differentiation between the two highly similar bacterial species with high separation accuracy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据