Deep learning-based pseudo-mass spectrometry imaging analysis for precision medicine

Xiaotao Shen; Wei Shao; Chuchu Wang; Liang Liang; Songjie Chen; Sai Zhang; Mirabela Rusu; Michael P Snyder

doi:10.1093/bib/bbac331

Deep learning-based pseudo-mass spectrometry imaging analysis for precision medicine

Brief Bioinform. 2022 Sep 20;23(5):bbac331. doi: 10.1093/bib/bbac331.

Authors

Xiaotao Shen^{1

2}, Wei Shao³, Chuchu Wang⁴, Liang Liang^{1

2}, Songjie Chen^{1

2}, Sai Zhang^{1

2}, Mirabela Rusu³, Michael P Snyder^{1

2}

Affiliations

¹ Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA.
² Stanford Center for Genomics and Personalized Medicine, Stanford, CA, USA.
³ Department of Radiology, Stanford University School of Medicine, Stanford, CA, USA.
⁴ Howard Hughes Medical Institute, Stanford University, Stanford, CA 94305, USA.

PMID: 35947990
DOI: 10.1093/bib/bbac331

Abstract

Liquid chromatography-mass spectrometry (LC-MS)-based untargeted metabolomics provides systematic profiling of metabolic. Yet, its applications in precision medicine (disease diagnosis) have been limited by several challenges, including metabolite identification, information loss and low reproducibility. Here, we present the deep-learning-based Pseudo-Mass Spectrometry Imaging (deepPseudoMSI) project (https://www.deeppseudomsi.org/), which converts LC-MS raw data to pseudo-MS images and then processes them by deep learning for precision medicine, such as disease diagnosis. Extensive tests based on real data demonstrated the superiority of deepPseudoMSI over traditional approaches and the capacity of our method to achieve an accurate individualized diagnosis. Our framework lays the foundation for future metabolic-based precision medicine.

Keywords: deep-learning; diagnosis; pseudo-mass spectrometry imaging.

MeSH terms

Chromatography, Liquid / methods
Deep Learning*
Mass Spectrometry / methods
Metabolomics / methods
Precision Medicine
Reproducibility of Results