Spateo: multidimensional spatiotemporal modeling of single-cell spatial transcriptomics

Qiu, Xiaojie; Zhu, Daniel Y.; Yao, Jiajun; Jing, Zehua; Zuo, Lulu; Wang, Mingyue; Min, Kyung Hoi; Pan, Hailin; Wang, Shuai; Liao, Sha; Lai, Yiwei; Hao, Shijie; Lu, Yuancheng; Hill, Matthew C.; Martin-Rufino, Jorge D.; Weng, Chen; Riera-Escandell, Anna Maria; Chen, Mengnan; Wu, Liang; Zhang, Yong; Wei, Xiaoyü; Li, Mei; Huang, Xin; Xiang, Rong; Yang, Zhuoxuan; Liu, Chao; Xia, Tianyi; Liang, Y.; Xu, Jin; Hu, Qinan; Hu, Yuhui; Zhu, Hongmei; Li, Yuxiang; Chen, Ao; Esteban, Miguel A.; Gu, Ying; Lauffenburger, Douglas A.; Xu, Xun; Liu, Longqi; Weissman, Jonathan S.; Liu, Shiping; Bai, Yinqi

doi:10.1101/2022.12.07.519417

Cited by 24 publications

(29 citation statements)

References 148 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The watershed method, implemented using the spateo package 30 , was utilized for segmentation based on nuclei staining images with some modifications. Firstly, the masks of nuclei were identified using both global and local adaptive thresholding techniques.…”

Section: Watershed Segmentationmentioning

confidence: 99%

Bering:joint cell segmentation and annotation for spatial transcriptomics with transferred graph embeddings

Jin,

Zhang,

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

Single-cell spatial transcriptomics such as in-situ hybridization or sequencing technologies can provide subcellular resolution that enables the identification of individual cell identities, locations, and a deep understanding of subcellular mechanisms. However, accurate segmentation and annotation that allows individual cell boundaries to be determined remains a major challenge that limits all the above and downstream insights. Current machine learning methods heavily rely on nuclei or cell body staining, resulting in the significant loss of both transcriptome depth and the limited ability to learn latent representations of spatial colocalization relationships. Here, we propose Bering, a graph deep learning model that leverages transcript colocalization relationships for joint noise-aware cell segmentation and molecular annotation in 2D and 3D spatial transcriptomics data. Graph embeddings for the cell annotation are transferred as a component of multi-modal input for cell segmentation, which is employed to enrich gene relationships throughout the process. To evaluate performance, we benchmarked Bering with state-of-the-art methods and observed significant improvement in cell segmentation accuracies and numbers of detected transcripts across various spatial technologies and tissues. To streamline segmentation processes, we constructed expansive pre-trained models, which yield high segmentation accuracy in new data through transfer learning and self-distillation, demonstrating the generalizability of Bering.

show abstract

Section: Watershed Segmentationmentioning

confidence: 99%

Bering:joint cell segmentation and annotation for spatial transcriptomics with transferred graph embeddings

Jin,

Zhang,

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The nuclei ssDNA images were used to calculate the cell boundaries by the cell segmentation algorithm spateo 97 (https://github.com/aristoteleo/spateorelease). The grey images of nuclei ssDNA were converted to binary images using the calculated Gaussian-weighted threshold.…”

Section: Cell Segmentationmentioning

confidence: 99%

Spatiotemporal transcriptome atlas of human embryos after gastrulation

Pan

Lin

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

The spatial and and temporal atlas of gene expression in the human embryo at early gestation is critical in understanding embryo development, organogenesis, and disease origins. We obtained the spatiotemporal transcriptome from 90 sagittal sections of 16 whole human embryos from 3 to 8 post-conception weeks by Stereo-seq with high resolution and ultra-large field, establishing the development trajectory/regulatory profiling of 49 organs. We uncovered the organ-specific regulons as potential lineage-determining factors and identified the new regulatory networks during heart and brain development. The atlas refines the key organs/cell types vulnerable to virus infection and genetic disorders, and, reveals the dynamics of allelic gene expression in specific organs at different stages. These results present the first comprehensive delineation of the spatiotemporal transcriptomic dynamics of human organogenesis.

show abstract

“…Here, we expanded our previous spatiotemporal transcriptomic atlas of Drosophila to cover its developmental lifespan from embryo to pupa. Using Stereo-seq and Spateo , a computational pipeline designed to analyze single-cell multi-modal spatial transcriptomic data 14 , we reconstructed 3D transcriptomes at single cell spatial resolution. We further complemented embryo single-cell Stereo-seq (scStereo-seq) data with single-cell RNA sequencing (scRNA-seq) and single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq) data to create a multi-omics atlas of Drosophila embryos that includes transcriptomic and epigenomic information within an ultra-high-resolution spatial context.…”

Section: Introductionmentioning

confidence: 99%

A single-cell 3D spatiotemporal multi-omics atlas fromDrosophilaembryogenesis to metamorphosis

Wang,

Hu,

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

The development of a multicellular organism is a highly intricate process tightly regulated by numerous genes and pathways in both spatial and temporal manners. Here, we present Flysta3D, a comprehensive multi-omics atlas of the model organism Drosophila, spanning its developmental lifespan from embryo to pupa. Our datasets encompass 3D single-cell spatial transcriptomic, single-cell transcriptomic, and single-cell chromatin accessibility information. By integrating these multi-dimensional data, we constructed cell state trajectories that uncover the detailed profiles of tissue development. With a focus on the central nervous system (CNS) and midgut, we dissected the spatiotemporal dynamics of gene regulatory networks, cell type diversity, and morphological changes from a multi-omics perspective. This extensive atlas provides an unprecedentedly rich resource and serves as a systematic platform for studying Drosophila development with integrated single-cell data at an ultra-high spatiotemporal resolution.

show abstract

Spateo: multidimensional spatiotemporal modeling of single-cell spatial transcriptomics

Cited by 24 publications

References 148 publications

Bering:joint cell segmentation and annotation for spatial transcriptomics with transferred graph embeddings

Bering:joint cell segmentation and annotation for spatial transcriptomics with transferred graph embeddings

Spatiotemporal transcriptome atlas of human embryos after gastrulation

A single-cell 3D spatiotemporal multi-omics atlas fromDrosophilaembryogenesis to metamorphosis

Contact Info

Product

Resources

About