EUVIMEDEUVIMED entdecken
Crossref

Analysis of high-molecular-weight proteins using MALDI-TOF MS and machine learning for the differentiation of clinically relevant Clostridioides difficile ribotypes

Ana Candela, David Rodriguez-Temporal, Mario Blázquez-Sánchez, Manuel J Arroyo, Mercedes Marín, Luis Alcalá, Germán Bou, Belén Rodríguez-Sánchez, Marina Oviaño

European Journal of Clinical Microbiology & Infectious Diseases · 2025-02 · 44 (2) · 417-425

DOI: 10.1007/s10096-024-05023-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Clinical Microbiology & Infectious Diseases, online erschienen am 17.12.2024. Verfasst von Ana Candela und 8 weiteren Autor:innen. Beteiligte Einrichtung: Clinical Microbiology Department, Complexo Hospitalario Universitario A Coruña, Institute of Biomedical Research A Coruña (INIBIC), A Coruña, Spain. …. Hauptthemen laut MEDLINE: Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization, Clostridioides difficile, Ribotyping, Machine Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: Instituto de Salud Carlos III.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: Clostridioides difficile is the main cause of antibiotic related diarrhea and some ribotypes (RT), such as RT027, RT181 or RT078, are considered high risk clones. A fast and reliable approach for C. difficile ribotyping is needed for a correct clinical approach. This study analyses high-molecular-weight proteins for C. difficile ribotyping with MALDI-TOF MS. METHODS: Sixty-nine isolates representative of the most common ribotypes in Europe were analyzed in the 17,000-65,000 m/z region and classified into 4 categories (RT027, RT181, RT078 and 'Other RTs'). Five supervised Machine Learning algorithms were tested for this purpose: K-Nearest Neighbors, Support Vector Machine, Partial Least Squares-Discriminant Analysis, Random Forest (RF) and Light-Gradient Boosting Machine (GBM). RESULTS: All algorithms yielded cross-validation results > 70%, being RF and Light-GBM the best performing, with 88% of agreement. Area under the ROC curve of these two algorithms was > 0.9. RT078 was correctly classified with 100% accuracy and isolates from the RT181 category could not be differentiated from RT027. CONCLUSIONS: This study shows the possibility of rapid discrimination of relevant C. difficile ribotypes by using MALDI-TOF MS. This methodology reduces the time, costs and laboriousness of current reference methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spectrometry, Mass, Matrix-Assisted Laser Desorption-IonizationClostridioides difficileRibotypingMachine LearningClostridium InfectionsBacterial ProteinsHumansMolecular WeightEuropeAlgorithms

Stichwörter der Autor:innen

Clostridioides difficileMALDI-TOF MSMachine learningRibotyping

Substanzen

Bacterial Proteins

Autor:innen und Institutionen

  • Clinical Microbiology Department, Complexo Hospitalario Universitario A Coruña, Institute of Biomedical Research A Coruña (INIBIC), A Coruña, Spain. acandelagon@gmail.com.
  • Clinical Microbiology and Infectious Diseases Department, Hospital General Universitario Gregorio Marañón and Instituto de Investigación Sanitaria Gregorio Marañón (IiSGM), Madrid, Spain. david.rodriguez@iisgm.com.
  • Clinical Microbiology and Infectious Diseases Department, Hospital General Universitario Gregorio Marañón and Instituto de Investigación Sanitaria Gregorio Marañón (IiSGM), Madrid, Spain.
  • Clover Bioanalytical Software, Av. del Conocimiento, 41, Granada, 18016, Spain.
  • CIBER de Enfermedades Respiratorias (CIBERES CB06/06/0058), Madrid, 28007, Spain.
  • Clinical Microbiology Department, Complexo Hospitalario Universitario A Coruña, Institute of Biomedical Research A Coruña (INIBIC), A Coruña, Spain.

Förderung

  • Instituto de Salud Carlos III

Zitieren

APA

Candela, A., Rodriguez-Temporal, D., Blázquez-Sánchez, M., Arroyo, M. J., Marín, M., Alcalá, L., Bou, G., Rodríguez-Sánchez, B., & Oviaño, M. (2025). Analysis of high-molecular-weight proteins using MALDI-TOF MS and machine learning for the differentiation of clinically relevant Clostridioides difficile ribotypes. European Journal of Clinical Microbiology & Infectious Diseases, 44(2), 417-425. https://doi.org/10.1007/s10096-024-05023-2

Vancouver

Candela A, Rodriguez-Temporal D, Blázquez-Sánchez M, Arroyo MJ, Marín M, Alcalá L, et al. Analysis of high-molecular-weight proteins using MALDI-TOF MS and machine learning for the differentiation of clinically relevant Clostridioides difficile ribotypes. European Journal of Clinical Microbiology & Infectious Diseases. 2025;44(2):417-425. doi:10.1007/s10096-024-05023-2

BibTeX
@article{Candela2025,
  author = {Candela, Ana and Rodriguez-Temporal, David and Blázquez-Sánchez, Mario and Arroyo, Manuel J and Marín, Mercedes and Alcalá, Luis and Bou, Germán and Rodríguez-Sánchez, Belén and Oviaño, Marina},
  title = {Analysis of high-molecular-weight proteins using MALDI-TOF MS and machine learning for the differentiation of clinically relevant Clostridioides difficile ribotypes},
  journal = {European Journal of Clinical Microbiology & Infectious Diseases},
  year = {2025},
  volume = {44},
  number = {2},
  pages = {417--425},
  doi = {10.1007/s10096-024-05023-2}
}
Kostenlos starten →