Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 5, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

SpaHNR: a spatial domain identification method via sparse attention-based hierarchical node representation and

Wei Peng^1,2, Zhihao Ping³, Wei Dai^3,4

¹Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, 650050, China. weipeng1980@gmail.com.

BMC Bioinformatics

|July 3, 2026

Summary

Related Concept Videos

Depth Perception and Spatial Vision

Depth Perception and Spatial Vision

Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Evaluation of red CdTe and near infrared CdHgTe quantum dots by fluorescent imaging.

Journal of nanoscience and nanotechnology·2008

Same author

Exploring feasibility of multicolored CdTe quantum dots for in vitro and in vivo fluorescent imaging.

Journal of nanoscience and nanotechnology·2008

Same author

[Effects of Dahuang Zhechong Pill on expressions of tissue inhibitor of metalloproteinase-1 and plasminogen activator inhibitor-1 in rats with glomerulosclerosis].

Zhong xi yi jie he xue bao = Journal of Chinese integrative medicine·2008

Same author

[Construction and expression of a fusion protein containing extracellular domain of human Delta-like1 and Fc fragment of human IgG1 in the Pichia pastoris].

Xi bao yu fen zi mian yi xue za zhi = Chinese journal of cellular and molecular immunology·2008

Same author

[Preparation and characterization of the monoclonal antibodies to PTD-bcr/abl].

Xi bao yu fen zi mian yi xue za zhi = Chinese journal of cellular and molecular immunology·2008

Same author

Prostaglandin F2alpha induces the normoxic activation of the hypoxia-inducible factor-1 transcription factor in differentiating 3T3-L1 preadipocytes: Potential role in the regulation of adipogenesis.

Journal of cellular biochemistry·2008

This summary is machine-generated.

SpaHNR, a novel deep learning method, identifies spatial domains in tissues by analyzing hierarchical structures in spatial transcriptomics data. It improves understanding of tissue organization and disease mechanisms.

Area of Science:

Computational Biology
Genomics
Bioinformatics

Background:

Deep learning on spatial transcriptomics data reveals tissue organization and gene expression.
Understanding spatial organization is key for dissecting biological processes and disease mechanisms.
Existing methods often overlook the hierarchical structure of biological tissues.

Purpose of the Study:

Develop a novel method, SpaHNR, for spatial domain identification that utilizes the multi-layered structure of tissues.
Integrate diverse data types including tissue images, gene expression, spatial coordinates, and cell communications.
Capture multi-scale feature information for enhanced spatial domain delineation.

Main Methods:

SpaHNR uses Sparse Attention-based Hierarchical Node Representation and multi-view contrastive learning.

Keywords:

Hierarchical node representation Multi-view contrastive learning Self-supervised learning Spatial domain identification Spatial transcriptomics

Related Experiment Videos

Last Updated: Jul 5, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Spots are treated as nodes, with two views constructed by integrating image, gene expression, spatial, and cell communication data.

Graph Convolutional Networks (GCNs) and a hierarchical node fusion module generate multi-scale representations.

Model trained using gene expression reconstruction and cross-view contrastive loss.

Spatial domains identified using Leiden clustering on fine-to-coarse node assignment matrix features.

Main Results:

SpaHNR effectively integrates spatial location, gene expression, tissue images, and cell communication data.
Hierarchical representation learning and contrastive learning enhance spatial domain identification.
Evaluations on human and mouse datasets show SpaHNR outperforms state-of-the-art methods.
The method successfully delineates spatial domains by capturing multi-scale features.

Conclusions:

SpaHNR significantly improves spatial domain identification in spatial transcriptomics data.
The method's ability to leverage hierarchical structures and multi-view learning offers potential for analyzing complex tissue architectures.
SpaHNR demonstrates a powerful approach for advancing our understanding of tissue organization and disease.