Explainable multiview framework for dissecting spatial relationships from highly multiplexed data
Heidelberg University · University Hospital Heidelberg · +5 more institutions
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…
Citation impact
- FWCI
- 20.88
- Percentile
- 100%
- References
- 50
Authors
5- JTJovan TanevskiCorresponding
Heidelberg University, University Hospital Heidelberg, Jožef Stefan Institute
- RORicardo O. Ramirez Flores
Heidelberg University, University Hospital Heidelberg
- AGAttila Gábor
Heidelberg University, University Hospital Heidelberg
- DSDenis Schapiro
Broad Institute, Harvard University, Heidelberg University, University Hospital Heidelberg, Center for Systems Biology
- JSJulio Sáez-Rodríguez
Heidelberg University, University Hospital Heidelberg, RWTH Aachen University
Topics & keywords
- Leverage (statistics)
- Spatial analysis
- Scalability
- Biology
- Computational biology
- Computer science
- Human breast
- Artificial intelligence
- Good health and well-being
Funding
- DRDamon Runyon Cancer Research FoundationAward: DRQ-03-20
- ECEuropean Commission
- SNSchweizerischer Nationalfonds zur Förderung der Wissenschaftlichen ForschungAward: P2ZHP3_181475
- BFBundesministerium für Bildung und ForschungAwards: BMBF 01ZZ2004, 01ZZ2004
- MZMinistrstvo za Izobraževanje, Znanost in ŠportAward: C3330-17-529021