A0975
Title: Joint dimension reduction and spatial clustering for spatial transcriptomics data analysis
Authors: Wei Liu - Sichuan University (China) [presenting]
Abstract: Dimension reduction and spatial clustering are usually performed sequentially; however, the low-dimensional embeddings estimated in the dimension-reduction step may not be relevant to the class labels inferred in the clustering step. A dimension-reduction spatial-clustering (DR-SC) computation method has been developed to perform dimension reduction and (spatial) clustering simultaneously within a unified framework. Joint analysis by DR-SC produces accurate (spatial) clustering results and ensures the effective extraction of biologically informative low-dimensional features. DR-SC applies to spatial clustering in spatial transcriptomics, which characterizes the spatial organization of the tissue by segregating it into multiple tissue structures. With comprehensive simulations and real data applications, it is shown that DR-SC outperforms existing clustering and spatial clustering methods: it extracts more biologically relevant features than conventional dimension reduction methods, improves clustering performance, and offers improved trajectory inference and visualization for downstream trajectory inference analyses.
