Explainable multiview framework for dissecting spatial relationships from highly multiplexed data

TLDR

Highly multiplexed spatial technologies demand scalable methods that exploit spatial information. The authors introduce MISTy, a flexible, scalable, explainable machine‑learning framework for extracting relationships from any spatial omics data. MISTy constructs multiple spatial or functional views to dissect distinct effects and was evaluated on in silico simulations and breast cancer imaging mass cytometry and spatial transcriptomics datasets. Using MISTy, the authors estimated structural and functional interactions in breast cancer from distinct spatial contexts and linked these results to clinical features.

Abstract

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.