AGCLD: an adaptive graph contrastive learning method with denoising for spatial domain identification
Briefings in Bioinformatics · 03.07.2026 · 27 (4)
DOI: 10.1093/bib/bbag385 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 14.07.2026. Verfasst von Yating Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence, Hainan Normal University, No. 99 Longkun South Road, Qiongshan District, Haikou 571158, Hainan, China. Hauptthemen laut MEDLINE: Single-Cell Analysis, Machine Learning. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hainan Province, Research Project on Education and Teaching Reform in Higher Education Institutions in Hainan Province.
Abstract (Originalsprache)
Single-cell spatial multi-omics technologies enable the simultaneous acquisition of multimodal molecular profiles and spatial location information in situ, providing a novel perspective for spatial domain identification and functional characterization of tissues. However, existing methods still suffer from several limitations, including insufficient denoising capability for single-cell data, reliance on static graph structures, and inadequate exploitation of the complementary relationships between spatial information and molecular features. To address these challenges, we propose AGCLD, an adaptive graph contrastive learning method with denoising for spatial domain identification. Specifically, a modality-specific denoising variational autoencoder is first employed to learn robust latent representations, thereby effectively mitigating noise interference. A differentiable graph generator is then introduced to adaptively construct spatial adjacency graphs and expression similarity graphs, alleviating the bias introduced by fixed neighborhood assumptions. Finally, AGCLD utilizes a dual-graph attention network to encode the spatial adjacency and expression similarity graphs, yielding spatial and feature embeddings, and incorporates a contrastive learning mechanism to align the dual-view representations, thereby enhancing representation consistency. Extensive experiments on five spatial multi-omics datasets demonstrate that AGCLD outperforms state-of-the-art methods, including SpatialGlue, in spatial domain identification tasks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Artificial Intelligence, Hainan Normal University, No. 99 Longkun South Road, Qiongshan District, Haikou 571158, Hainan, China.
- Key Laboratory of Data Science and Smart Education, Ministry of Education, Hainan Normal University, No. 99 Longkun South Road, Qiongshan District, Haikou 571158, Hainan, China.
- Haikou Key Laboratory of Intelligent Analysis and Secure Sharing of Tropical Biodiversity Data, Hainan Normal University, No. 99 Longkun South Road, Qiongshan District, Haikou 571158, Hainan, China.
- School of Life Science and Technology, University of Electronic Science and Technology of China, No. 4, Section 2, North Jianshe Road, Chengdu 610054, China.
ORCID-Profile: Yating Li, Xinyue Yu, Hao Zhang, Hao Lin, Bo Liu, Haixia Long
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Hainan Province
- Research Project on Education and Teaching Reform in Higher Education Institutions in Hainan Province
- Talent Research Startup Foundation of Hainan Normal University
Zitieren
APA
Li, Y., Yu, X., Zhang, H., Lin, H., Liu, B., & Long, H. (2026). AGCLD: an adaptive graph contrastive learning method with denoising for spatial domain identification. Briefings in Bioinformatics, 27(4). https://doi.org/10.1093/bib/bbag385
Vancouver
Li Y, Yu X, Zhang H, Lin H, Liu B, Long H. AGCLD: an adaptive graph contrastive learning method with denoising for spatial domain identification. Briefings in Bioinformatics. 2026;27(4). doi:10.1093/bib/bbag385
BibTeX
@article{Li2026,
author = {Li, Yating and Yu, Xinyue and Zhang, Hao and Lin, Hao and Liu, Bo and Long, Haixia},
title = {AGCLD: an adaptive graph contrastive learning method with denoising for spatial domain identification},
journal = {Briefings in Bioinformatics},
year = {2026},
volume = {27},
number = {4},
doi = {10.1093/bib/bbag385}
}
EUVIMED