Abstract
Computational analysis is crucial to capitalize on the wealth of spatio-molecular information generated by mass spectrometry imaging (MSI) experiments. Currently, the spatial information available in MSI data is often under-utilized, due to the challenges of in-depth spatial pattern extraction. The advent of deep learning has greatly facilitated such complex spatial analysis. In this work, we use a pre-trained neural network to extract high-level features from ion images in MSI data, and test whether this improves downstream data analysis. The resulting neural network interpretation of ion images, coined neural ion images, is used to cluster ion images based on spatial expressions. We evaluate the impact of neural ion images on two ion image clustering pipelines, namely DBSCAN clustering, combined with UMAP-based dimensionality reduction, and k-means clustering. In both pipelines, we compare regular and neural ion images from two different MSI datasets. All tested pipelines could extract underlying spatial patterns, but the neural network-based pipelines provided better assignment of ion images, with more fine-grained clusters, and greater consistency in the spatial structures assigned to individual clusters. Additionally, we introduce the relative isotope ratio metric to quantitatively evaluate clustering quality. The resulting scores show that isotopical m/z values are more often clustered together in the neural network-based pipeline, indicating improved clustering outcomes. The usefulness of neural ion images extends beyond clustering towards a generic framework to incorporate spatial information into any MSI-focused machine learning pipeline, both supervised and unsupervised.Graphical abstract
Highlights
Mass spectrometry imaging (MSI) is a powerful, label-free molecular imaging technology that enables mapping the Published in the topical collection Mass Spectrometry Imaging 2.0 with guest editors Shane R
We focus on assessing the merits of neural ion images for the unsupervised task of clustering, i.e., grouping together, ion images based on their spatial expression
We set out this work with the observation that the spatial information available in MSI is often under-utilized in its computational analysis, in part due to the fact that it is nontrivial to translate the complex spatial pattern recognition that humans perform on a daily basis into simple algorithms
Summary
Mass spectrometry imaging (MSI) is a powerful, label-free molecular imaging technology that enables mapping the Published in the topical collection Mass Spectrometry Imaging 2.0 with guest editors Shane R. While a number of different MSI variants exist [11], in general MSI operates by first overlaying the tissue with a virtual rectangular grid, and collecting a mass spectrum at each grid location. Each of these collected mass spectra is a histogram of biomolecular ions counts, partitioned by their mass-to-charge values (m/z), within a target mass-tocharge range. MSI experiments result in a three-dimensional data cube, with spatial coordinates (x and y) and a m/z axis containing the spectral information. Ion images are constructed by plotting the intensities for a single mass bin (m/z value) for each acquired pixel, i.e., (x, y) grid location in the tissue
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
