Global Context-aware Representation Learning for Spatially Resolved Transcriptomics

Spatially Resolved Transcriptomics (SRT) is a cutting-edge technique that captures the spatial context of cells within tissues, enabling the study of complex biological networks. Recent graph-based methods leverage both gene expression and spatial information to identify relevant spatial domains. However, these approaches fall short in obtaining meaningful spot representations, especially for spots near spatial domain boundaries, as they heavily emphasize adjacent spots that have minimal feature differences from an anchor node. To address this, we propose Spotscape, a novel framework that introduces the Similarity Telescope module to capture global relationships between multiple spots. Additionally, we propose a similarity scaling strategy to regulate the distances between intra- and inter-slice spots, facilitating effective multi-slice integration. Extensive experiments demonstrate the superiority of Spotscape in various downstream tasks, including single-slice and multi-slice scenarios.

Understanding how cells are organized and function within tissues is important for biology and medicine. Spatially Resolved Transcriptomics (SRT) is a new technology that measures gene activity in cells along with their exact locations inside tissues microenvironment. However, analyzing this complex data is challenging because cells near boundaries between tissue regions look very similar locally, making it hard to distinguish meaningful patterns.To solve this, we developed Spotscape, a new machine learning method that looks beyond immediate neighbors and captures global relationships between many cells at once. This helps to better identify distinct tissue regions and important gene expression patterns. Spotscape also integrates data from multiple tissue slices, overcoming technical differences that often confuse analysis.Our method outperforms existing approaches on various SRT datasets and reveals biologically meaningful insights. Spotscape is fast and scalable, making it useful for large and complex spatial transcriptomics studies. This work can advance biomedical research by providing more accurate tools to understand tissue organization and disease mechanisms.