Explainable multiview framework for dissecting spatial relationships from highly multiplexed data
Top Cited Papers
Open Access
- 14 April 2022
- journal article
- research article
- Published by Springer Nature in Genome Biology
- Vol. 23 (1) , 1-31
Abstract
The advancement of highly multiplexed spatial technologies requires scalable methods that can leverage spatial information. We present MISTy, a flexible, scalable, and explainable machine learning framework for extracting relationships from any spatial omics data, from dozens to thousands of measured markers. MISTy builds multiple views focusing on different spatial or functional contexts to dissect different effects. We evaluated MISTy on in silico and breast cancer datasets measured by imaging mass cytometry and spatial transcriptomics. We estimated structural and functional interactions coming from different spatial contexts in breast cancer and demonstrated how to relate MISTy’s results to clinical features.Keywords
All Related Versions
Funding Information
- Ministrstvo za Izobraževanje, Znanost in Šport (C3330-17-529021)
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (P2ZHP3_181475)
- Damon Runyon Cancer Research Foundation (DRQ-03-20)
- Bundesministerium für Forschung, Technologie und Raumfahrt (01ZZ2004)
- Medizinische Fakultät Heidelberg der Universität Heidelberg
This publication has 46 references indexed in Scilit:
- The 3D OrbiSIMS—label-free metabolic imaging with subcellular lateral resolution and high mass-resolving powerNature Methods, 2017
- histoCAT: analysis of cell phenotypes and interactions in multiplex image cytometry dataNature Methods, 2017
- OmniPath: guidelines and gateway for literature-curated signaling pathway resourcesNature Methods, 2016
- Using Raman spectroscopy to characterize biological materialsNature Protocols, 2016
- MALDI Imaging mass spectrometry: current frontiers and perspectives in pathology research and practiceLaboratory Investigation, 2015
- Multiplexed ion beam imaging of human breast tumorsNature Medicine, 2014
- Highly multiplexed imaging of tumor tissues with subcellular resolution by mass cytometryNature Methods, 2014
- Ridge Regression in Prediction Problems: Automatic Choice of the Ridge ParameterGenetic Epidemiology, 2013
- Fast unfolding of communities in large networksJournal of Statistical Mechanics: Theory and Experiment, 2008
- Random ForestsMachine Learning, 2001