A machine learning framework for classifying lipids in untargeted metabolomics using mass-to-charge ratios and retention times
Our results demonstrate that metabolites can be classified as "lipid", "non-lipid" using only m/z and RT from untargeted LC-MS data, without requiring MS2 spectra. Although this study focused on lipid classification, the approach shows potential for broader application, which warrants further investigation across diverse compound classes, detection methods, and chromatographic conditions.
Authors
- Hayley D. Ackerman (ORCID: https://orcid.org/0000-0002-1094-7949)
- John M. Koomen (ORCID: https://orcid.org/0000-0002-3818-1762)
- Dalia Ercan (ORCID: https://orcid.org/0000-0002-2425-0691)
- Eric A. Welsh (ORCID: https://orcid.org/0000-0002-9302-3855)
- Brooke L. Fridley (ORCID: https://orcid.org/0000-0001-7739-7956)
- Elsa R. Flores (ORCID: https://orcid.org/0000-0002-6173-2403)
- Christelle Colin (ORCID: https://orcid.org/0000-0002-8118-9591)
- Kevin O. Hicks (ORCID: https://orcid.org/0000-0002-0998-8786)
- Julián Ávila-Pacheco (ORCID: https://orcid.org/0000-0001-9388-3946)
- Vanessa Rubio (ORCID: https://orcid.org/0000-0003-1214-4397)
- Yonatan Ayalew Mekonnen (ORCID: https://orcid.org/0000-0002-7430-9428)
- Clary B. Clish (ORCID: https://orcid.org/0000-0001-8259-9245)
- Oana A. Zeleznik (ORCID: https://orcid.org/0000-0002-8705-1163)
- Isis Narváez-Bandera (ORCID: https://orcid.org/0000-0001-7320-618X)
- Paul A. Stewart (ORCID: https://orcid.org/0000-0003-0882-308X)
- Lancia Darville (ORCID: https://orcid.org/0000-0002-9793-3741)
- Nancy Gillis (ORCID: https://orcid.org/0000-0002-7744-8490)
- Min Liu (ORCID: https://orcid.org/0000-0001-5183-1187)
Institutions
- Broad Institute (US)
- Brigham and Women's Hospital (US)
- Children's Mercy Hospital (US)
- Harvard University (US)
- University of Utah (US)
- Huntsman Cancer Institute (US)
- Moffitt Cancer Center (US)
- Molecular Oncology (United States) (US)
Publication Details
- Journal
- Metabolomics
- Published
- 2025-10-18
- DOI
- https://doi.org/10.1007/s11306-025-02343-y
- Citations
- 1
- Primary Topic
- Metabolomics and Mass Spectrometry Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.81
Funders
- Cancer Research Institute
- University of Utah
- Moffitt Cancer Center
- Huntsman Cancer Foundation
- Huntsman Cancer Institute
- National Institutes of Health
- National Cancer Institute