Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

CausalTCC: causal temporal contrastive learning for automated Alzheimer's disease biomarker discovery with bio-electrical signals.

Journal of neural engineering·2026
Same author

STELLA: a spatial transcriptomics framework for microenvironment decoding using dynamic graph neural networks.

Science China. Life sciences·2026
Same author

Leveraging TROPOMI red solar-induced chlorophyll fluorescence for enhanced detection of harmful algal blooms in turbid coastal waters.

Marine pollution bulletin·2026
Same author

PRISM: A structure-guided computational approach for identifying RNA-targeting small molecules by integrating 3D conformational and chemical information.

European journal of medicinal chemistry·2026
Same author

HopWD-DTA: a novel framework for drug-target affinity prediction fusing multi-hop neighborhoods and deep features.

Journal of molecular modeling·2026
Same author

Optimized CNN-based facial analysis for depression detection: Managing mental disorder in education.

Brain research bulletin·2026
Same journal

Genomic insights into the probiotic potential of dairy-associated Saccharomyces cerevisiae WUT3 and WUT151 strains.

Functional & integrative genomics·2026
Same journal

Integrative analysis of circ_DLGAP4, lncRNA KCNQ1OT1, and the miR-9/SOX7 interaction network in chronic kidney disease progression: a case-control study.

Functional & integrative genomics·2026
Same journal

Multi-omics integration identifies macrophage senescence driven by the RUNX1-P53 axis as a key mechanism in diabetic foot ulcer.

Functional & integrative genomics·2026
Same journal

Positive regulatory role of EuWRKY1 in the biosynthesis of Eucommia ulmoides rubber.

Functional & integrative genomics·2026
Same journal

Environmental enrichment modulates, but does not normalize, aging-associated immune transcriptional programs after ischemic stroke.

Functional & integrative genomics·2026
Same journal

A hypoxia-responsive migrasome-related lncRNA signature predicts prognosis and suggests the MSC-AS1/ITGA5 axis as a potential therapeutic target in head and neck squamous cell carcinoma.

Functional & integrative genomics·2026
See all related articles

Related Experiment Video

Updated: Jul 7, 2026

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

A multi-scale graph frequency network for structural and functional region analysis in spatial transcriptomics.

Ruoyan Dai1, Zhenghui Wang1, Zhiwei Zhang1

  • 1Academy of Artificial Intelligence, Beijing Institute of Petrochemical Technology, Beijing, 102617, China.

Functional & Integrative Genomics
|July 5, 2026
PubMed
Summary
This summary is machine-generated.

Spatial Graph Frequency Network (SGFN) is a new deep learning method for analyzing spatial transcriptomics data. It effectively models gene expression and tissue structure, revealing biological insights in various tissues.

Keywords:
Cell type deconvolutionContrastive learningFrequency domain analysisGraph neural networksSpatial domain identificationSpatial transcriptomicsTissue microenvironment

More Related Videos

Mining Spatial Transcriptomics Datasets using DeepSpaceDB
10:16

Mining Spatial Transcriptomics Datasets using DeepSpaceDB

Published on: September 5, 2025

Recording and Analyzing Multimodal Large-Scale Neuronal Ensemble Dynamics on CMOS-Integrated High-Density Microelectrode Array
09:44

Recording and Analyzing Multimodal Large-Scale Neuronal Ensemble Dynamics on CMOS-Integrated High-Density Microelectrode Array

Published on: March 8, 2024

Related Experiment Videos

Last Updated: Jul 7, 2026

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Mining Spatial Transcriptomics Datasets using DeepSpaceDB
10:16

Mining Spatial Transcriptomics Datasets using DeepSpaceDB

Published on: September 5, 2025

Recording and Analyzing Multimodal Large-Scale Neuronal Ensemble Dynamics on CMOS-Integrated High-Density Microelectrode Array
09:44

Recording and Analyzing Multimodal Large-Scale Neuronal Ensemble Dynamics on CMOS-Integrated High-Density Microelectrode Array

Published on: March 8, 2024

Area of Science:

  • Computational Biology
  • Genomics
  • Bioinformatics

Background:

  • Spatial transcriptomics offers insights into tissue organization but faces analytical challenges due to complex spatial dependencies and multi-scale architectures.
  • Effective computational frameworks are needed to jointly model spatial topology and molecular features for accurate biological interpretation.

Purpose of the Study:

  • To introduce the Spatial Graph Frequency Network (SGFN), a novel deep learning framework designed to enhance the analysis of spatial transcriptomics data.
  • To develop a method that integrates graph signal processing, graph attention, and contrastive learning for modeling spatial topology and molecular features.

Main Methods:

  • SGFN utilizes a frequency-domain enhancement module that decomposes spatial graphs into multi-scale spectral components via Laplacian eigenbasis.
  • The framework incorporates adaptive wavelet denoising for improved signal processing when applicable.
  • It integrates graph signal processing, graph attention, and contrastive learning for joint modeling of spatial and molecular data.

Main Results:

  • SGFN demonstrated superior or competitive performance across diverse biological systems, including human brain, breast cancer, and embryonic development datasets.
  • The method successfully identified biologically coherent spatial or functional regions in unlabeled datasets, supported by marker-gene and pathway enrichment analyses.
  • SGFN accurately reconstructed human cortical layer architecture, delineated tumor modules, and revealed developmental spatiotemporal trajectories.

Conclusions:

  • SGFN provides a unified computational framework for decoding tissue organization and molecular heterogeneity using spatial transcriptomics data.
  • The integration of interpretable frequency-domain representations with data-driven learning advances the understanding of spatial systems in development, physiology, and pathology.
  • This framework facilitates deeper insights into the spatial organization of gene expression within intact tissues.