Spatial domain identification method based on multi-view graph convolutional network and contrastive learning
PLOS Computational Biology · 17.10.2025 · 21 (10) · e1013369
DOI: 10.1371/journal.pcbi.1013369 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 17.10.2025. Verfasst von Xikeng Liang und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics, Harbin Institute of Technology, Harbin, China. Hauptthemen laut MEDLINE: Deep Learning, Gene Expression Profiling, Single-Cell Analysis. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, The Natural Science Foundation of Heilongjiang Province, China, Postdoctoral Fellowship Program of CPSF.
Abstract (Originalsprache)
Spatial transcriptomics is a rapidly developing field of single-cell genomics that quantitatively measures gene expression while providing spatial information within tissues. A key challenge in spatial transcriptomics is identifying spatially structured domains, which involves analyzing transcriptomic data to find clusters of cells with similar expression patterns and their spatial distribution. To address these challenges, we propose a novel deep-learning method called DMGCN for domain identification. The process begins with preprocessing that constructs two types of graphs: a spatial graph based on Euclidean distance and a feature graph based on Cosine distance. These graphs represent spatial positions and gene expressions, respectively. The embeddings of both graphs are generated using a multi-view graph convolutional encoder with an attention mechanism, enabling separate and co-convolution of the graphs, as well as corrupted feature convolution for contrastive learning. Finally, a fully connected network (FCN) decoder is employed to generate domain labels and reconstruct gene expressions for downstream analysis. Experimental results demonstrate that DMGCN consistently outperforms state-of-the-art methods in various tasks, including spatial clustering, trajectory inference, and gene expression broadcasting.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Mathematics, Harbin Institute of Technology, Harbin, China.
- V.I. Romanovsky Institute of Mathematics, Uzbekistan Academy of Sciences, Tashkent, Uzbekistan.
ORCID-Profile: Jing Qi, Shuilin Jin
Förderung
- National Natural Science Foundation of China
- The Natural Science Foundation of Heilongjiang Province, China
- Postdoctoral Fellowship Program of CPSF
- Natural Science Foundation of Heilongjiang Province
- Heilongjiang Postdoctoral Foundation
Zitieren
APA
Liang, X., Xiao, S., Ba, L., Feng, Y., Ma, Z., Adilova, F., Qi, J., & Jin, S. (2025). Spatial domain identification method based on multi-view graph convolutional network and contrastive learning. PLOS Computational Biology, 21(10), e1013369. https://doi.org/10.1371/journal.pcbi.1013369
Vancouver
Liang X, Xiao S, Ba L, Feng Y, Ma Z, Adilova F, et al. Spatial domain identification method based on multi-view graph convolutional network and contrastive learning. PLOS Computational Biology. 2025;21(10):e1013369. doi:10.1371/journal.pcbi.1013369
BibTeX
@article{Liang2025,
author = {Liang, Xikeng and Xiao, Shutong and Ba, Lu and Feng, Yuhui and Ma, Zhicheng and Adilova, Fatima and Qi, Jing and Jin, Shuilin},
title = {Spatial domain identification method based on multi-view graph convolutional network and contrastive learning},
journal = {PLOS Computational Biology},
year = {2025},
volume = {21},
number = {10},
pages = {e1013369},
doi = {10.1371/journal.pcbi.1013369}
}
EUVIMED