Related Experiment Video
Updated: Jul 2, 2026
09:11
Revealing Neural Circuit Topography in Multi-Color
Published on: November 14, 2011
Histology-informed spatial domain identification through multi-view graph convolutional networks
Huihui Zhang1,2, Jiaxing Chang1,3, Zirong Li1
1Shenzhen Branch, Guangdong Laboratory of Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen, China.
Plos Computational Biology
|June 1, 2026
Summary
We developed STESH, a novel spatial transcriptomics clustering method. It integrates gene expression, spatial data, and histology to accurately identify spatial domains, outperforming existing methods.
Area of Science:
- Genomics
- Computational Biology
- Bioinformatics
Background:
- Spatial transcriptomics enables gene expression analysis within tissue context.
- Integrating gene expression, spatial location, and histology is crucial but challenging.
- Current methods struggle to effectively combine these diverse data types for accurate spatial domain identification.
Purpose of the Study:
- To develop a robust method for spatial domain identification in spatial transcriptomics.
- To improve the integration of gene expression, spatial, and histological data.
- To enhance the accuracy of clustering in spatial transcriptomics analysis.
Main Methods:
- STESH (Spatial Transcriptomics clustering method) combines Expression, Spatial information, and Histology.
- Utilizes a convolutional neural network for histological feature extraction.
- Employs a multi-view graph convolutional network with a decoder and attention mechanism.
Main Results:
- STESH demonstrated superior clustering accuracy across multiple tissue types and platforms.
- Outperformed ten state-of-the-art spatial transcriptomics methods.
- Achieved highest scores in adjusted Rand index, normalized mutual information, and Fowlkes-Mallows index.
Conclusions:
- STESH effectively integrates multi-modal data for accurate spatial domain identification.
- The method offers a significant advancement in spatial transcriptomics analysis.
- STESH provides a powerful tool for researchers studying tissue architecture and gene expression patterns.
