MS2MP: A Deep Learning Framework for Metabolic Pathway Prediction from MS/MS-Based Untargeted Metabolomics
Analytical Chemistry · 15.07.2025 · 97 (27) · 14200-14209
DOI: 10.1021/acs.analchem.4c06875 ↗Kurz gefasst
Fachartikel in der Zeitschrift Analytical Chemistry, online erschienen am 30.06.2025. Verfasst von Han Bao und 7 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Medical Proteomics, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, Dalian 116023, P. R. China. Hauptthemen laut MEDLINE: Metabolomics, Deep Learning, Metabolic Networks and Pathways. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Dalian Institute of Chemical Physics, Chinese Academy of Sciences, National Natural Science Foundation of China, Yulin Branch, Dalian National Laboratory For Clean Energy, Chinese Academy of Sciences.
Abstract (Originalsprache)
MS/MS-based untargeted metabolomics generates complex data, but pathway enrichment analysis is constrained by the low annotation rates of metabolic features. Here, we propose MS2MP, a novel deep learning-based framework for KEGG pathway prediction directly from untargeted tandem mass spectrometry (MS2), eliminating the need for prior metabolite annotation. MS2MP utilizes a graph neural network architecture to learn the complex relationships between spectral features and metabolic pathways, representing MS2 spectra as fragmentation tree graphs. Trained on 33,221 experimental MS2 spectra, MS2MP achieves robust predictive performance with a balanced accuracy of 94.1% in cross-validation and 87.8%-91.2% on three independent test sets. Notably, MS2MP achieves an "exact match" for 97-98 out of 161 tested metabolite standards across diverse experimental conditions, underscoring its reliability and adaptability. Subsequently, a novel MS2-based pathway enrichment method was developed. The established methods were applied to identify significantly perturbed pathways in transgenic maize. The results uncovered disruptions in phenylpropanoid biosynthesis and related downstream pathways, including those involved in amino acid and secondary metabolite metabolism, which were overlooked by the conventional annotation-based enrichment analysis method. To the best of our knowledge, MS2MP is the first computational tool capable of directly predicting metabolic pathways from MS2 spectra. By linking MS2-based untargeted metabolomics data to metabolic pathways, MS2MP enables more efficient pathway enrichment analysis, thereby accelerating biological discoveries and enhancing our understanding of complex metabolic networks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- State Key Laboratory of Medical Proteomics, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, Dalian 116023, P. R. China.
- University of Chinese Academy of Sciences, Beijing 100049, P. R. China.
- Liaoning Province Key Laboratory of Metabolomics, Dalian 116023, P. R. China.
ORCID-Profile: Xinxin Wang, Xin Lu, Guowang Xu
Förderung
- Dalian Institute of Chemical Physics, Chinese Academy of Sciences
- National Natural Science Foundation of China
- Yulin Branch, Dalian National Laboratory For Clean Energy, Chinese Academy of Sciences
Zitieren
APA
Bao, H., Zhang, X., Wang, X., Zhao, J., Zhao, X., Zhao, C., Lu, X., & Xu, G. (2025). MS2MP: A Deep Learning Framework for Metabolic Pathway Prediction from MS/MS-Based Untargeted Metabolomics. Analytical Chemistry, 97(27), 14200-14209. https://doi.org/10.1021/acs.analchem.4c06875
Vancouver
Bao H, Zhang X, Wang X, Zhao J, Zhao X, Zhao C, et al. MS2MP: A Deep Learning Framework for Metabolic Pathway Prediction from MS/MS-Based Untargeted Metabolomics. Analytical Chemistry. 2025;97(27):14200-14209. doi:10.1021/acs.analchem.4c06875
BibTeX
@article{Bao2025,
author = {Bao, Han and Zhang, Xiuqiong and Wang, Xinxin and Zhao, Jinhui and Zhao, Xinjie and Zhao, Chunxia and Lu, Xin and Xu, Guowang},
title = {MS2MP: A Deep Learning Framework for Metabolic Pathway Prediction from MS/MS-Based Untargeted Metabolomics},
journal = {Analytical Chemistry},
year = {2025},
volume = {97},
number = {27},
pages = {14200--14209},
doi = {10.1021/acs.analchem.4c06875}
}
EUVIMED