Spatial transcriptomics (ST) helps us understand cell interactions, developmental processes, and disease progression within tissues by analyzing gene expression while preserv ing spatial information on tissue sections. However, the spatial distribution patterns of the same cell population may differ in different slice samples, and a single slice is difficult to adapt to spatial changes, making multi-slice integration methods a research hotspot in recent years. Traditional graph convolution relies on a fixed graph structure, whose adjacency relationships remain fixed during training. It cannot be adaptively updated according to feature changes and is difficult to reflect the spatial distribution differences between different slices. Dynamic graph convolutional neural networks (DGCNN), on the other hand, adaptively update based on node embeddings or features during training to capture complex spatial relationships. Therefore, we propose DGAE, a framework based on DGCNN for multi-slice ST data alignment and data enhancement. DGAE consists of two modules: DGAEₐlign and DGAEᵣecog. DGAEₐlign combines K-nearest neighbor (KNN) and r-radius to build a hybrid graph, and integrates the spatial information of different slices to achieve accurate spatial alignment. DGAEᵣecog aggregates the information of adjacent slices into the target slice for data enhancement, achieving effective transmission of information between different slices. Experimental results show that DGAE outperforms existing methods in multi-slice ST data alignment and also demonstrates superior performance in data enhancement tasks. In addition, DGAE has shown well adaptability and stability in spatial domain recognition, denoising and disease research, demonstrating the wide applicability and scalability of DGAE as a method for multi-slice ST data alignment and data enhancement.
Li et al. (2026) studied this question.