3D reconstruction of spatial transcriptomics with spatial pattern enhanced graph convolutional neural network

Spatially resolved transcriptomics (SRT) is a promising new technology that enables simultaneous analysis of gene expression and spatial information for biomedical research. However, the existing statistical and deep learning algorithms used for analyzing SRT data rely solely on two-dimensional (2D) spatial coordinates, which limits their ability to accurately identify spatial domains, spatially variable genes, cell-to-cell communications, and developmental trajectories in a three-dimensional (3D) spatial manner. To address these limitations, we introduced Spa3D, which utilized the anti-leakage Fourier transform and graph convolutional neural network model to reconstruct 3D-based spatial structures from multiple 2D SRT slices. We demonstrate that Spa3D is appliable to analyze data from various SRT technology platforms and outperforms state-of-art methods by: (I) improving spatial domain identification through 3D reconstruction, (II) elucidating cell-cell communication landscape in the 3D cellular organization, (III) modeling of organ-level tempo-spatial development patterns in a 3D fashion, and (IV) annotating 3D spatial trajectory that are not captured by 2D spatial coordinates. Key pointsO_LIMost existing spatial omics analysis methods rely on 2D data, limiting their ability to capture full spatial and developmental tissue complexity C_LIO_LISpa3D incorporates physical z-axis distances, enabling accurate 3D modeling even when adjacent slices vary in tissue structure and composition C_LIO_LISpa3D reconstructs true 3D spatial structures from 2D SRT slices using graph convolutional networks and anti-leakage Fourier transforms C_LIO_LISpa3D enhances spatial domain detection, revealing detailed cell-cell communication and organ-level development patterns across multiple spatial omics platforms C_LIO_LISpa3D enables novel biological discoveries by revealing spatial features and trajectories not detectable using traditional 2D transcriptomic analysis approaches C_LI