B1923
Title: iIMPACT: Integrating image and molecular-based profiles to analyze and cluster spatial transcriptomics data
Authors: Xi Jiang - Southern Methodist University (United States)
Qiwei Li - The University of Texas at Dallas (United States) [presenting]
Guanghua Xiao - University of Texas Southwestern Medical Center (United States)
Lin Xu - University of Texas Southwestern Medical Center (United States)
Abstract: The breakthrough in spatial transcriptomics (ST) has enabled comprehensive molecular characterization at the cellular level while preserving spatial information. Meanwhile, pathology imaging powered by artificial intelligence enables the histology characterization of single cells. Understanding the spatial organization of cells and their heterogeneous gene expression profiles will provide deeper biological insights. To address these two problems, we develop iIMPACT, a multi-stage method to cluster and analyze ST data. The first stage is an interpretable Bayesian mixture model, which combines a Gaussian component to model the molecular profile and a multinomial component for cell abundances, and incorporates the spatial information by a Markov random field prior. After region segmentation, we develop a zero-inflated generalized linear regression model under the Bayesian framework to study the association between the cellular pattern and gene expression. Applying our method to a publicly available breast cancer dataset, we found that iIMPACT outperforms existing clustering methods in terms of segmentation accuracy and generates the most biologically meaningful cancer-related genes.