Explainable multiview framework for dissecting spatial relationships from highly multiplexed data

• Verfasst von: Tanevski, Jovan [VerfasserIn]
• Verfasst von: Ramirez Flores, Ricardo O. [VerfasserIn]
• Verfasst von: Gabor, Attila [VerfasserIn]
• Verfasst von: Schapiro, Denis [VerfasserIn]
• Verfasst von: Sáez Rodríguez, Julio [VerfasserIn]
• Titel: Explainable multiview framework for dissecting spatial relationships from highly multiplexed data
• Verf.angabe: Jovan Tanevski, Ricardo Omar Ramirez Flores, Attila Gabor, Denis Schapiro and Julio Saez-Rodriguez
• E-Jahr: 2022
• Jahr: 14 April 2022
• Umfang: 31 S.
• Fussnoten: Gesehen am 17.05.2022
• Titel Quelle: Enthalten in: Genome biology
• Ort Quelle: London : BioMed Central, 2000
• Jahr Quelle: 2022
• Band/Heft Quelle: 23(2022), Artikel-ID 97, Seite 1-31
• ISSN Quelle: 1474-760X
• DOI: doi:10.1186/s13059-022-02663-5
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Intercellular signaling
• Sach-SW: Machine learning
• Sach-SW: Multiplexed data
• Sach-SW: Spatial omics
• K10plus-PPN: 1802139761
• K10plus-PPN:
  Universitätsbibliothek
• Lokale URL UB: Zum Volltext

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.