Exploring the Mosaic-like Tissue Architecture of Kidney Diseases Using Relation Equivariant Graph Neural Networks on Spatially Resolved Transcriptomics

Abstract

Emerging spatially resolved transcriptomics (SRT) technologies provide unprecedented opportunities to discover the spatial patterns of gene expression at the cellular or tissue levels. Currently, most existing computational tools on SRT are designed and tested on the ribbon-like brain cortex. Their present expressive power often makes it challenging to identify highly heterogeneous mosaic-like tissue architectures, such as tissues from kidney diseases. This demands heightened precision in discerning the cellular and morphological changes within renal tubules and their interstitial niches. We present an empowered graph deep learning framework, REGNN (Relation Equivariant Graph Neural Networks), for SRT data analyses on heterogeneous tissue structures. To increase expressive power in the SRT lattice using graph modeling, the proposed REGNN integrates equivariance to handle the rotational and translational symmetries of the spatial space, and Positional Encoding (PE) to identify and strengthen the relative spatial relations of the nodes uniformly distributed in the lattice. Our study finds that REGNN outperforms existing computational tools in identifying inherent mosaic-like heterogenous tissue architectures in kidney samples sourced from different kidney diseases using the 10X Visium platform. In case studies on acute kidney injury and chronic kidney diseases, the results identified by REGNN are also validated by experienced nephrology physicians. This proposed framework explores the expression patterns of highly heterogeneous tissues with an enhanced graph deep learning model, and paves the way to pinpoint underlying pathological mechanisms that contribute to the progression of complex diseases. REGNN is publicly available at https://github.com/Mraina99/REGNN.