EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Rapid Species-Level Classification of Urinary Pathogens from Raw LC-MS/MS Signals Using Machine Learning

Simon J Pelletier iD, Antoine Lacombe-Rastoll, Florence Roux-Dalvai, Mickaël Leclercq iD, Clarisse Gotti, Eve Bérubé, Pascaline Bories iD, Marie-Ève Thibeault, Dorte B Bekker-Jensen, Nicolai Bache, Maciej Bromirski, Sandra Isabel und 2 weitere

Analytical Chemistry · 2026

DOI: 10.1021/acs.analchem.6c02725 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Analytical Chemistry, 2026. Verfasst von Simon J Pelletier und 13 weiteren Autor:innen. Beteiligte Einrichtung: Computational Biology Laboratory, CHU de Québec-Université Laval Research Center, Québec City, QuebecG1V 4G2, Canada. Hauptthemen laut MEDLINE: Machine Learning, Urinary Tract Infections. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Thermo Fisher Scientific, Genome Quebec, Evosep Biosystems.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Urinary tract infections are among the most common infections in humans, yet their diagnosis still depends on time-consuming workflows based on microbial culture, followed by MALDI-TOF mass spectrometry. Although LC-MS/MS offers the sensitivity and specificity needed to bypass culture, conventional pipelines depend on lengthy analyses and peptide/protein identification steps, limiting the throughput and hindering its adoption in clinical settings. Here, we introduce a direct, identification-free LC-MS/MS workflow that analyzes raw ion signal and produces species-level microbial identification in about 5 min after preparation, fast enough to meet clinical throughput requirements. Our machine learning-enabled raw-signal pipeline bypasses peptide identification entirely, preserving information and eliminating the traditional interpretation stack. Across 15 independent analytical batches covering 28 clinically relevant pathogens, the method achieved high-confidence classification (MCC = 0.86). Applied to 206 clinical urine specimens across three batches, the approach reached 91% accuracy at clinically actionable microbial loads (greater than 105 CFU/mL) and, critically, 0 false positives in control specimens. The performance was lower for specimens below this threshold. These results show that raw LC-MS/MS spectra contain sufficient biological information for direct microbial diagnosis, establishing an analytical framework for clinical mass spectrometry. This proof-of-concept demonstrates that rapid, culture-free, fast microbial identification is achievable and positions raw signal inference as a promising direction for next-generation diagnostic mass spectrometry.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningUrinary Tract InfectionsTandem Mass SpectrometryHumansLiquid Chromatography-Mass SpectrometryChromatography, Liquid

Autor:innen und Institutionen

  • Computational Biology Laboratory, CHU de Québec-Université Laval Research Center, Québec City, QuebecG1V 4G2, Canada.
  • Proteomics Platform, CHU de Québec-Université Laval Research Center, Québec City, QuebecG1V 4G2, Canada.
  • Centre de Recherche en Infectiologie de l'Université Laval, Axe Maladies Infectieuses et Immunitaires, Centre de Recherche du CHU de Québec-UniversitéLaval, Québec City, QuebecG1V 4G2, Canada.
  • Evosep Biosystems, OdenseDK-5230, Denmark.
  • ThermoFisher Scientific, Bremen28199, Germany.
  • Université Côte d'Azur, Inria, CNRS, I3S, Nice06903, France.

ORCID-Profile: Simon J Pelletier, Mickaël Leclercq, Pascaline Bories

Förderung

  • Thermo Fisher Scientific
  • Genome Quebec
  • Evosep Biosystems

Zitieren

APA

Pelletier, S. J., Lacombe-Rastoll, A., Roux-Dalvai, F., Leclercq, M., Gotti, C., Bérubé, E., Bories, P., Thibeault, M. È., Bekker-Jensen, D. B., Bache, N., Bromirski, M., Isabel, S., Precioso, F., & Droit, A. (2026). Rapid Species-Level Classification of Urinary Pathogens from Raw LC-MS/MS Signals Using Machine Learning. Analytical Chemistry. https://doi.org/10.1021/acs.analchem.6c02725

Vancouver

Pelletier SJ, Lacombe-Rastoll A, Roux-Dalvai F, Leclercq M, Gotti C, Bérubé E, et al. Rapid Species-Level Classification of Urinary Pathogens from Raw LC-MS/MS Signals Using Machine Learning. Analytical Chemistry. 2026. doi:10.1021/acs.analchem.6c02725

BibTeX
@article{Pelletier2026,
  author = {Pelletier, Simon J and Lacombe-Rastoll, Antoine and Roux-Dalvai, Florence and Leclercq, Mickaël and Gotti, Clarisse and Bérubé, Eve and Bories, Pascaline and Thibeault, Marie-Ève and Bekker-Jensen, Dorte B and Bache, Nicolai and Bromirski, Maciej and Isabel, Sandra and Precioso, Frederic and Droit, Arnaud},
  title = {Rapid Species-Level Classification of Urinary Pathogens from Raw LC-MS/MS Signals Using Machine Learning},
  journal = {Analytical Chemistry},
  year = {2026},
  doi = {10.1021/acs.analchem.6c02725}
}
Kostenlos starten →