SPACEL: deep learning-based characterization of spatial transcriptome architectures

• Published in: Nature communications Vol. 14; no. 1; pp. 7603 - 18
• Main Authors: Xu, Hao, Wang, Shuyan, Fang, Minghao, Luo, Songwen, Chen, Chunpeng, Wan, Siyuan, Wang, Rirui, Tang, Meifang, Xue, Tian, Li, Bin, Lin, Jun, Qu, Kun
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 22.11.2023; Nature Publishing Group; Nature Portfolio
• Subjects: 38; 631/114; 631/114/1314; 631/114/2397; 631/1647/48; 631/61/514; Algorithms; Alignment; Artificial neural networks; Coordinates; Data analysis; Data processing; Deconvolution; Deep Learning; Gene expression; Gene Expression Profiling; Humanities and Social Sciences; Information processing; Machine learning; Models, Statistical; multidisciplinary; Probabilistic models; Science; Science (multidisciplinary); Spatial analysis; Spatial discrimination learning; Spatial distribution; Toolkits; Transcriptome - genetics; Transcriptomes; Transcriptomics
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-023-43220-3

Spatial transcriptomics (ST) technologies detect mRNA expression in single cells/spots while preserving their two-dimensional (2D) spatial coordinates, allowing researchers to study the spatial distribution of the transcriptome in tissues; however, joint analysis of multiple ST slices and aligning them to construct a three-dimensional (3D) stack of the tissue still remain a challenge. Here, we introduce spatial architecture characterization by deep learning (SPACEL) for ST data analysis. SPACEL comprises three modules: Spoint embeds a multiple-layer perceptron with a probabilistic model to deconvolute cell type composition for each spot in a single ST slice; Splane employs a graph convolutional network approach and an adversarial learning algorithm to identify spatial domains that are transcriptomically and spatially coherent across multiple ST slices; and Scube automatically transforms the spatial coordinate systems of consecutive slices and stacks them together to construct a 3D architecture of the tissue. Comparisons against 19 state-of-the-art methods using both simulated and real ST datasets from various tissues and ST technologies demonstrate that SPACEL outperforms the others for cell type deconvolution, for spatial domain identification, and for 3D alignment, thus showcasing SPACEL as a valuable integrated toolkit for ST data processing and analysis. Spatial transcriptomics (ST) technologies detect transcript distribution in space. Here, authors present a deep learning based method SPACEL for cell type deconvolution, spatial domain identification and 3D alignment, showcasing it as a valuable toolkit for ST data analysis