Self-organizing maps: A versatile tool for the automatic analysis of untargeted imaging datasets

Authors

  • Pietro Franceschi,

    Corresponding author
    1. Biostatistics and Data Management, IASMA Research and Innovation Centre, Fondazione E. Mach, Trento, Italy
    • Correspondence: Dr. Pietro Franceschi, Biostatistics and Data Management, IASMA Research and Innovation Centre, Fondazione E. Mach, Via E. Mach 1, I-38010 S. Michele all'Adige, Trento, Italy

      E-mail: pietro.franceschi@fmach.it

    Search for more papers by this author
  • Ron Wehrens

    1. Biostatistics and Data Management, IASMA Research and Innovation Centre, Fondazione E. Mach, Trento, Italy
    Search for more papers by this author

  • Colour Online: See the article online to view Figs. 1–5 in colour.

Abstract

MS-based imaging approaches allow for location-specific identification of chemical components in biological samples, opening up possibilities of much more detailed understanding of biological processes and mechanisms. Data analysis, however, is challenging, mainly because of the sheer size of such datasets. This article presents a novel approach based on self-organizing maps, extending previous work in order to be able to handle the large number of variables present in high-resolution mass spectra. The key idea is to generate prototype images, representing spatial distributions of ions, rather than prototypical mass spectra. This allows for a two-stage approach, first generating typical spatial distributions and associated m/z bins, and later analyzing the interesting bins in more detail using accurate masses. The possibilities and advantages of the new approach are illustrated on an in-house dataset of apple slices.

Ancillary