Revealing Tissue Heterogeneity and Spatial Dark Genes from Spatially Resolved Transcriptomics by Multiview Graph Networks

Abstract

Spatially resolved transcriptomics (SRT) is capable of comprehensively characterizing gene expression patterns and providing an unbiased image of spatial composition. To fully understand the organizational complexity and tumor immune escape mechanism, we propose stMGATF, a multiview graph attention fusion model that integrates gene expression, histological images, spatial location, and gene association. To better extract information, stMGATF exploits SimCLRv2 for visual feature exaction and employs edge feature enhanced graph attention networks for the learning potential embedding of each view. A global attention mechanism is used to adaptively integrate 3 views to obtain low-dimensional representation. Applied to diverse SRT datasets, stMGATF is robust and outperforms other methods in detecting spatial domains and denoising data even with different resolutions and platforms. In particular, stMGATF contributes to the elucidation of tissue heterogeneity and extraction of 3-dimensional expression domains. Importantly, considering the associations between genes in tumors, stMGATF can identify the spatial dark genes ignored by traditional methods, which can be used to predict tumor-driving transcription factors and reveal tumor immune escape mechanisms, providing theoretical evidence for the development of new immunotherapeutic strategies.

Uncovering the Pre-Deterioration State during Disease Progression Based on Sample-Specific Causality Network Entropy (SCNE)

“…The detection of critical signals for abrupt deterioration is pivotal in the majority of complex diseases. However, the application of existing critical-state detection methods to bulk RNA-sequencing data with limited sample sizes or single-cell data is constrained by the substantial noise inherent in the data [ 36 ]. In this research, we present a robust computational method at the specific sample level, called SCNE, that is capable of constructing a sample-specific causality network for each individual and efficiently identifying critical points or pre-deterioration states associated with disease deterioration.…”