A1773
Title: Cross-modal denoising and integration of spatial multi-omics data with CANDIES
Authors: Mingxuan Cai - City University of Hong Kong (Hong Kong) [presenting]
Abstract: Spatial multi-omics data offer a powerful framework for integrating diverse molecular profiles while maintaining the spatial organization of cells. However, inherent variations in data quality and noise levels across different modalities pose significant challenges to accurate integration and analyses. CANDIES is introduced as a method that leverages a conditional diffusion model and contrastive learning to effectively denoise and integrate spatial multi-omics data. With its innovative model and algorithm designs, CANDIES enhances the quality of spatial multi-omics data and yields a unified and comprehensive joint representation, thereby enabling many downstream analyses. Extensive evaluations on diverse synthetic and real datasets, including MISAR-seq data from the mouse brain, spatial CITE-seq data from human skin biopsy tissue, spatial Mux-seq and spatial ATAC-RNA-seq data from the mouse embryo, and 10x Visium data from human lymph nodes, demonstrate that CANDIES shows superior performance on various downstream tasks, including denoising, spatial domain identification, spatiotemporal trajectory reconstruction, and spatial association mapping for complex human traits. In particular, CANDIES representations can be integrated with the rich resources from genome-wide association studies (GWASs), allowing the spatial domains to be linked with complex human traits, yielding spatially resolved interpretations of complex traits in their relevant tissues.
