A1496
Title: Clustering spatial transcriptomics data with dirichlet process mixture of random spanning trees
Authors: Bani Mallick - Texas A&M University (United States) [presenting]
Abstract: Spatial transcriptomics has gained tremendous popularity as it allows researchers to map gene expression directly onto tissue architecture, preserving spatial context and providing high-resolution insights into cellular interactions and biological processes within their native environments. We introduce a novel Bayesian nonparametric framework, the Dirichlet process mixture of random spanning trees, designed to detect an unknown number of possibly non-convex clusters in possibly non-convex spatial domains. The model's two-layer partitioning effectively addresses challenges posed by the intricate spatial organization of tissue samples, such as non-convex clusters and irregular spatial boundaries of the samples. Simulation studies show that this method achieves superior clustering accuracy compared to existing methods. We apply our method to our motivating mouse colonic dataset during healing from inflammatory damage, revealing meaningful clusters associated with different stages of tissue repair.
