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

Foundation Models for Liquid Chromatography–High-Resolution Mass Spectrometry: A New Era beyond Labeled Datasets

Andrea Junior Carnoli iD, Federico Padilla-Gonzalez iD, Leonieke M van den Bulk iD, Daan Korporaal, Martin Alewijn, Marco H Blokland iD, Bas H M van der Velden

Analytical Chemistry · 11.08.2026 · 98 (31) · 22586-22594

DOI: 10.1021/acs.analchem.6c01825 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Analytical Chemistry, online erschienen am 30.07.2026. Verfasst von Andrea Junior Carnoli und 6 weiteren Autor:innen. Beteiligte Einrichtung: Wageningen Food Safety Research (WFSR), Part of Wageningen University and Research, Wageningen6700 GE, The Netherlands. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Ministerie van Landbouw, Natuur en Voedselkwaliteit.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Liquid chromatography coupled to high-resolution mass spectrometry (LC–HRMS) is a widely used analytical technique for characterizing the chemical composition of organic samples. Due to its high sensitivity and ability to detect thousands of chemical features in a single run, untargeted LC–HRMS experiments generate highly complex and data-rich datasets that typically require advanced computational methods, including machine learning, for meaningful interpretation. While traditional machine learning approaches have been applied to LC–HRMS data, their performance remains limited for complex tasks. Deep learning has demonstrated improved performance, but both machine and deep learning are often constrained by the complexity and scarcity of labeled LC–HRMS data. Foundation models present a promising new horizon for LC–HRMS data analysis, given their ability to learn transferable representations from large-scale unlabeled data and adapt efficiently to downstream tasks with limited labeled samples. Recent studies have shown that foundation models can outperform conventional machine learning approaches in chemical annotation and molecular property prediction. We envision that foundation models for LC–HRMS data will benefit from the expansion of curated sample repositories and spectral libraries, developing privacy-preserving training strategies, enabling simultaneous modeling of multiple LC–HRMS data types, and improving model explainability.

Autor:innen und Institutionen

  • Wageningen Food Safety Research (WFSR), Part of Wageningen University and Research, Wageningen6700 GE, The Netherlands.

ORCID-Profile: Andrea Junior Carnoli, Federico Padilla-Gonzalez, Leonieke M van den Bulk, Marco H Blokland

Förderung

  • Ministerie van Landbouw, Natuur en Voedselkwaliteit

Zitieren

APA

Carnoli, A. J., Padilla-Gonzalez, F., van den Bulk, L. M., Korporaal, D., Alewijn, M., Blokland, M. H., & van der Velden, B. H. M. (2026). Foundation Models for Liquid Chromatography–High-Resolution Mass Spectrometry: A New Era beyond Labeled Datasets. Analytical Chemistry, 98(31), 22586-22594. https://doi.org/10.1021/acs.analchem.6c01825

Vancouver

Carnoli AJ, Padilla-Gonzalez F, van den Bulk LM, Korporaal D, Alewijn M, Blokland MH, et al. Foundation Models for Liquid Chromatography–High-Resolution Mass Spectrometry: A New Era beyond Labeled Datasets. Analytical Chemistry. 2026;98(31):22586-22594. doi:10.1021/acs.analchem.6c01825

BibTeX
@article{Carnoli2026,
  author = {Carnoli, Andrea Junior and Padilla-Gonzalez, Federico and van den Bulk, Leonieke M and Korporaal, Daan and Alewijn, Martin and Blokland, Marco H and van der Velden, Bas H M},
  title = {Foundation Models for Liquid Chromatography–High-Resolution Mass Spectrometry: A New Era beyond Labeled Datasets},
  journal = {Analytical Chemistry},
  year = {2026},
  volume = {98},
  number = {31},
  pages = {22586--22594},
  doi = {10.1021/acs.analchem.6c01825}
}
Kostenlos starten →