Cargando…

Explainable multiview framework for dissecting spatial relationships from highly multiplexed data

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 measure...

Descripción completa

Detalles Bibliográficos
Autores principales: Tanevski, Jovan, Flores, Ricardo Omar Ramirez, Gabor, Attila, Schapiro, Denis, Saez-Rodriguez, Julio
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9011939/
https://www.ncbi.nlm.nih.gov/pubmed/35422018
http://dx.doi.org/10.1186/s13059-022-02663-5
Descripción
Sumario: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. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s13059-022-02663-5.