A0716
Title: Spatial transcriptomics deconvolution using deep neural networks with adversarial discriminative domain adaptation
Authors: Jingsi Ming - East China Normal University (China) [presenting]
Abstract: The rapid advancement of spatial transcriptomics has substantially improved the understanding of spatial architecture and gene expression heterogeneity within tissues. However, many spatial transcriptomics techniques can not reach single-cell resolution, instead measuring gene expression profiles from mixtures of potentially heterogeneous cell types. AddaGCN is proposed, a robust deconvolution method to infer cell type composition from spatial transcriptomic data. AddaGCN leverages graph convolutional networks to incorporate spatial information and employ an adversarial discriminative domain adaptation approach to mitigate batch effects between spatial and single-cell reference data. Comprehensive real data analyses demonstrate AddaGCN's flexibility to diverse datasets generated by various technology platforms and underscore its superior performance and robustness in cell-type deconvolution compared to other methods.
