.png){kind=icon}
.png){kind=icon}
Return
Advances and Challenges in Cell Type Annotation for Spatial Transcriptomics
.png){kind=icon}
PRE
AI
DOI：10.1007/s11831-026-10614-7.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The task of cell type annotation is essential in the overall analysis workflow of spatial transcriptomics data. Although a variety of methods have been proposed for cell type annotation in spatial transcriptomics, each has certain limitations. Therefore, it is necessary to systematically summarize and review these methods, so that researchers can apply them according to their specific needs or gain insights to guide the development of future spatial transcriptomics cell type annotation approaches. This review takes cell type annotation methods developed for different spatial transcriptomics technologies as the entry point and provides a detailed overview of each method applicable to the two types of technologies from three perspectives: the time of proposal, the implementation approach, and the strengths and limitations. Furthermore, it introduces an innovative classification of these methods based on whether they require single-cell transcriptomic reference data, offering a more refined and comprehensive summary of spatial transcriptomics cell type annotation methods for researchers in the field. This review serves as a resource for researchers applying or developing cell type annotation methods in spatial transcriptomics. This review summarizes several methods specifically developed for cell type annotation in spatial transcriptomics, from the perspective of different types of spatial transcriptomics technologies. This review provides guidance for researchers selecting cell type annotation methods based on spatial technology, and offers insights to developers designing new spatial transcriptomics annotation models. This review presents an innovative classification of spatial transcriptomics cell type annotation methods based on whether or not they rely on single-cell transcriptomic reference data, offering a more comprehensive and structured guide for researchers in the field. As spatial transcriptomics advances, cell type annotation methods are evolving, with key developments focusing on integrating multi-omics data and leveraging machine learning and deep learning models.
Journal
IF:
12.1
Papers:
1.8K
Citations:
1.2W
Organization
View more organizations