A comprehensive overview of graph neural network-based approaches to clustering for spatial transcriptomics.

ABSTRACT: Spatial transcriptomics technologies enable researchers to accurately quantify and localize messenger ribonucleic acid (mRNA) transcripts at a high resolution while preserving their spatial context. The identification of spatial domains, or the task of spatial clustering, plays a crucial role in investigating data on spatial transcriptomes. One promising approach for classifying spatial domains involves the use of graph neural networks (GNNs) by leveraging gene expressions, spatial locations, and histological images. This study provided a comprehensive overview of the most recent GNN-based methods of spatial clustering methods for the analysis of data on spatial transcriptomics. We extensively evaluated the performance of current methods on prevalent datasets of spatial transcriptomics by

SUBMITTER: Liu T 

PROVIDER: S-EPMC10714345 | biostudies-literature | 2024 Dec

REPOSITORIES: biostudies-literature