Spatial transcriptomics enable us to dissect tissue heterogeneity and map out inter-cellular communications. Optimal integration of transcriptomics data and associated spatial information is essential towards fully exploiting the data. We present SEDR, an unsupervised spatially embedded deep representation of both transcript and spatial information. The SEDR pipeline uses a deep autoencoder to construct a low-dimensional latent representation of gene expression, which is then simultaneously embedded with the corresponding spatial information through a variational graph autoencoder. We applied SEDR on human dorsolateral prefrontal cortex data and achieved better clustering accuracy, and correctly retraced the prenatal cortex development order with trajectory analysis. We also found the SEDR representation to be eminently suited for batch integration. Applying SEDR to human breast cancer data, we discerned heterogeneous sub-regions within a visually homogenous tumor region, identifying a tumor core with pro-inflammatory microenvironment and an outer ring region enriched with tumor associated macrophages which drives an immune suppressive microenvironment.

Advances in spatial transcriptomics technologies has enabled gene expression profiling of tissues while retaining the spatial context. To effectively exploit the data, spatially informed analysis tools are required. Here, we present DeepST, a versatile graph contrastive self-supervised learning framework that incorporates spatial location information and gene expression profiles to accomplish three key tasks, spatial clustering, spatial transcriptomics (ST) data integration, and single-cell RNA-seq (scRNA-seq) transfer onto ST. DeepST combines graph neural networks (GNNs) with contrastive self-supervised learning to learn spot representations in the ST data, and an auto-encoder to extract informative features in the scRNA-seq data. Spatial contrastive self-supervised learning enables the learned spatial spot representation to be more informative and discriminative by minimizing the embedding distance between spatially adjacent spots and vice versa. With DeepST, we found biologically consistent clusters with greater accuracy than competing methods. We next demonstrated DeepST's ability to jointly analyze multiple tissue slices in both vertical and horizontal integration while correcting for batch effects. Lastly, we used DeepST to deconvolute cell types present in ST with scRNA-seq data, showing better performance than cell2location. We also demonstrated DeepST's accurate cell type mapping to recover immune cell distribution in the different regions of breast tumor tissue. DeepST is an easily usable and computationally efficient tool for capturing and dissecting the heterogeneity within ST data, enabling biologists to gain insights into the cellular states within tissues.

Spatial transcriptomics technologies generate gene expression profiles with spatial context, requiring spatially informed analysis tools for three key tasks, spatial clustering, multisample integration, and cell-type deconvolution. We present GraphST, a graph self-supervised contrastive learning method that fully exploits spatial transcriptomics data to outperform existing methods. It combines graph neural networks with self-supervised contrastive learning to learn informative and discriminative spot representations by minimizing the embedding distance between spatially adjacent spots and vice versa. We demonstrated GraphST on multiple tissue types and technology platforms. GraphST achieved 10% higher clustering accuracy and better delineated fine-grained tissue structures in brain and embryo tissues. GraphST is also the only method that can jointly analyze multiple tissue slices in vertical or horizontal integration while correcting batch effects. Lastly, GraphST demonstrated superior cell-type deconvolution to capture spatial niches like lymph node germinal centers and exhausted tumor infiltrating T cells in breast tumor tissue.