EUVIMEDEUVIMED entdecken
Open Access

MetaboAnnotate: An AI-powered Multiagent Framework for Integrating Annotation Tools for Untargeted Metabolomics

Yan Zhou Chen, Brandon Mukadziwashe, Frederick Zhang, Soha Hassoun iD

Analytical Chemistry · 08.09.2026 · 98 (35) · 25617-25625

DOI: 10.1021/acs.analchem.6c01717 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Analytical Chemistry, online erschienen am 27.08.2026. Verfasst von Yan Zhou Chen und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Tufts University, Medford, Massachusetts02155, United States. Hauptthemen laut MEDLINE: Metabolomics, Software. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS, National Institute of General Medical Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Metabolite annotation remains a major bottleneck in untargeted metabolomics, limiting biological interpretation of large-scale mass spectrometry data sets. Although substantial advances have been made through spectral libraries, machine learning–based annotation models, and community benchmarking efforts, many recently developed tools remain difficult to incorporate into routine workflows because they are distributed as research-oriented software with complex dependencies and nonstandard interfaces. Here, we present MetaboAnnotate, a web-based framework that uses a large language model (LLM) in a multiagent system to orchestrate multiple metabolite annotation tools through a unified natural-language interface. The system enables users to submit MS/MS spectra and execute multitool annotation workflows without local installation or programming expertise. The current implementation integrates complementary methods, including SIRIUS, FLARE, JESTR, and DiffMS. Evaluation on the CASMI 2016 and CASMI 2022 benchmarks shows that agreement among independent annotation tools substantially reduces false discovery rates and improves annotation accuracy. Application to a fecal metabolomics data set further demonstrates the utility of multitool consensus for identifying high-confidence putative metabolites. MetaboAnnotate is available at: https://hassounlab.cs.tufts.edu/MetaboAnnotate/

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MetabolomicsSoftwareLarge Language ModelsTandem Mass SpectrometryFecesInternet

Autor:innen und Institutionen

  • Department of Computer Science, Tufts University, Medford, Massachusetts02155, United States.
  • Department of Chemical and Biological Engineering, Tufts University, Medford, Massachusetts02155, United States.

ORCID-Profile: Soha Hassoun

Förderung

  • NIGMS NIH HHS
  • National Institute of General Medical Sciences

Zitieren

APA

Zhou Chen, Y., Mukadziwashe, B., Zhang, F., & Hassoun, S. (2026). MetaboAnnotate: An AI-powered Multiagent Framework for Integrating Annotation Tools for Untargeted Metabolomics. Analytical Chemistry, 98(35), 25617-25625. https://doi.org/10.1021/acs.analchem.6c01717

Vancouver

Zhou Chen Y, Mukadziwashe B, Zhang F, Hassoun S. MetaboAnnotate: An AI-powered Multiagent Framework for Integrating Annotation Tools for Untargeted Metabolomics. Analytical Chemistry. 2026;98(35):25617-25625. doi:10.1021/acs.analchem.6c01717

BibTeX
@article{ZhouChen2026,
  author = {Zhou Chen, Yan and Mukadziwashe, Brandon and Zhang, Frederick and Hassoun, Soha},
  title = {MetaboAnnotate: An AI-powered Multiagent Framework for Integrating Annotation Tools for Untargeted Metabolomics},
  journal = {Analytical Chemistry},
  year = {2026},
  volume = {98},
  number = {35},
  pages = {25617--25625},
  doi = {10.1021/acs.analchem.6c01717}
}
Kostenlos starten →