Explainable multiview framework for dissecting spatial relationships from highly multiplexed data

Genome biology, vol. 23, pp. 97

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.

Authors 5

1. Jovan Tanevski

   Heidelberg University · University Hospital Heidelberg · Jožef Stefan Institute · Jožef Stefan International Postgraduate School

   Affiliation as printed

   Department of Knowledge Technologies, Jožef Stefan Institute, Ljubljana, Slovenia

   Institute for Computational Biomedicine, Faculty of Medicine, Heidelberg University and Heidelberg University Hospital, Heidelberg, Germany

2. Ricardo O. Ramirez Flores

   Heidelberg University · University Hospital Heidelberg

   Affiliation as printed

   Institute for Computational Biomedicine, Faculty of Medicine, Heidelberg University and Heidelberg University Hospital, Heidelberg, Germany

3. Attila Gábor

   Heidelberg University · University Hospital Heidelberg

   Affiliation as printed

   Institute for Computational Biomedicine, Faculty of Medicine, Heidelberg University and Heidelberg University Hospital, Heidelberg, Germany

4. Denis Schapiro

   Broad Institute · Harvard University · Heidelberg University · University Hospital Heidelberg · Klarman Cell Observatory

   Affiliation as printed

   Institute for Computational Biomedicine, Faculty of Medicine, Heidelberg University and Heidelberg University Hospital, Heidelberg, Germany

   Institute of Pathology, Faculty of Medicine, Heidelberg University and Heidelberg University Hospital, Heidelberg, Germany

   Klarman Cell Observatory, Broad Institute of MIT and Harvard, Cambridge, MA, USA

   Laboratory of Systems Pharmacology, Harvard Medical School, Boston, MA, USA

5. Julio Sáez-Rodríguez corresponding Aachen Joint Research Centre for Computational Biomedicine (JRC-COMBINE) Faculty of Medicine

   Heidelberg University · University Hospital Heidelberg · RWTH Aachen University

   Affiliation as printed

   Institute for Computational Biomedicine, Faculty of Medicine, Heidelberg University and Heidelberg University Hospital, Heidelberg, Germany. pub.saez@uni-heidelberg.de

   Joint Research Centre for Computational Biomedicine (JRC-COMBINE), Faculty of Medicine, RWTH Aachen University, Aachen, Germany. pub.saez@uni-heidelberg.de

   Institute for Computational Biomedicine, Faculty of Medicine, Heidelberg University and Heidelberg University Hospital, Heidelberg, Germany