3D-MSNet: a point cloud-based deep learning model for untargeted feature detection and quantification in profile LC-HRMS data.

Journal: Bioinformatics (Oxford, England)
PMID: 37071700

Abstract

MOTIVATION: Liquid chromatography coupled with high-resolution mass spectrometry is widely used in composition profiling in untargeted metabolomics research. While retaining complete sample information, mass spectrometry (MS) data naturally have the characteristics of high dimensionality, high complexity, and huge data volume. In mainstream quantification methods, none of the existing methods can perform direct 3D analysis on lossless profile MS signals. All software simplify calculations by dimensionality reduction or lossy grid transformation, ignoring the full 3D signal distribution of MS data and resulting in inaccurate feature detection and quantification.

Authors

  • Ruimin Wang
    State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China.
  • Miaoshan Lu
    School of Engineering, Westlake University, Hangzhou, Zhejiang Province 310030, China.
  • Shaowei An
    Fudan University, Shanghai 200433, China.
  • Jinyin Wang
    Shandong First Medical University & Shandong Academy of Medical Sciences, Jinan, Shandong Province 250021, China.
  • Changbin Yu
    Shandong First Medical University & Shandong Academy of Medical Sciences, Jinan, Shandong Province 250021, China.

Keywords

External Resources

Popular Topics
Recent Journals