Automated identification of <i>Salmonella</i> serotype using MALDI-TOF mass spectrometry and machine learning techniques
<i>Salmonella</i> serotyping is vital for outbreak tracking and clinical guidance, but traditional methods are slow and laborious. This study combines matrix-assisted laser desorption ionization-time of flight mass spectrometry with machine learning (XGBoost) to enable rapid, accurate, and cost-effective serotyping. The streamlined model performed excellently in validation and was deployed as a user-friendly Streamlit app, enhancing usability. This innovation simplifies workflows, reduces diagnostic time, and supports scalable use in clinical and public health settings, improving outbreak response and epidemiological research.
Authors
- Mingming Zhou (ORCID: https://orcid.org/0000-0002-7826-3543)
- Yuanyuan Xu (ORCID: https://orcid.org/0000-0003-2354-9453)
- Jintao Xia (ORCID: https://orcid.org/0000-0003-2334-7595)
- Wenjun Cao (ORCID: https://orcid.org/0000-0001-6383-9012)
- Chunhong Liu (ORCID: https://orcid.org/0000-0001-7364-0568)
- Jianing Wu (ORCID: https://orcid.org/0000-0003-0902-4466)
- Mengyu Zhang (ORCID: https://orcid.org/0000-0001-9375-6664)
- Shengjie Li (ORCID: https://orcid.org/0000-0002-6443-740X)
- Yingzhu Li (ORCID: https://orcid.org/0000-0001-8525-4066)
- Jun Ren (ORCID: https://orcid.org/0009-0003-1095-3016)
Institutions
- Eye & ENT Hospital of Fudan University (CN)
- National Clinical Research (US)
- China Coal Technology and Engineering Group Corp (China) (CN)
- Zhejiang University (CN)
Publication Details
- Journal
- Journal of Clinical Microbiology
- Published
- 2025-06-11
- DOI
- https://doi.org/10.1128/jcm.00037-25
- Citations
- 4
- Primary Topic
- Bacterial Identification and Susceptibility Testing
- Type
- article
- Field-Weighted Citation Impact
- 5.27
Funders
- National Natural Science Foundation of China