Back

Spatial-ID: a cell typing method for spatially resolved transcriptomics via transfer learning and spatial embedding

Shen, R.; Liu, L.; Wu, Z.; Zhang, Y.; Yuan, Z.; guo, j.; Yang, F.; Zhang, C.; Chen, B.; Liu, C.; Guo, J.; Fan, G.; Zhang, Y.; Li, Y.; Xu, X.; Yao, J.

2022-05-27 genomics
10.1101/2022.05.26.493527 bioRxiv
Show abstract

Spatially resolved transcriptomics (SRT) provides the opportunity to investigate the gene expression profiles and the spatial context of cells in naive state. Cell type annotation is a crucial task in the spatial transcriptome analysis of cell and tissue biology. In this study, we propose Spatial-ID, a supervision-based cell typing method, for high-throughput cell-level SRT datasets that integrates transfer learning and spatial embedding. Spatial-ID effectively incorporates the existing knowledge of reference scRNA-seq datasets and the spatial information of SRT datasets. A series of quantitative comparison experiments on public available SRT datasets demonstrate the superiority of Spatial-ID compared with other state-of-the-art methods. Besides, the application of Spatial-ID on a SRT dataset with 3D spatial dimension measured by Stereo-seq shows its advancement on the large field tissues with subcellular spatial resolution.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.