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 Experiment Videos

AGCLD: an adaptive graph contrastive learning method with denoising for spatial domain identification.

Yating Li1,2,3, Xinyue Yu1,2,3, Hao Zhang1,2,3

  • 1School of Artificial Intelligence, Hainan Normal University, No. 99 Longkun South Road, Qiongshan District, Haikou 571158, Hainan, China.

Briefings in Bioinformatics
|July 14, 2026
PubMed
Summary

Related Concept Videos

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
Deconvolution01:20

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

You might also read

Related Articles

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

Sort by
Same author

EssTFNet: integration of adaptive time-frequency and DNA language models for interpretable human essential gene prediction.

Briefings in bioinformatics·2026
Same author

Identification and Prognostic Analysis of Immune-Related Genes Co-Regulated by Key Histone Modifications in Breast Cancer.

Current issues in molecular biology·2026
Same author

Prediction of Digestible and Metabolizable Energy in Swine Feed Using Machine Learning.

ACS omega·2026
Same author

ac4C modification sites prediction in human mRNA: a complete review.

Briefings in bioinformatics·2026
Same author

Artificial intelligence-powered prediction of diabetic complications: from clinical data to molecular omics.

Briefings in bioinformatics·2026
Same author

Single-Cell Multi-Omics in Type 2 Diabetes Mellitus: Revealing Cellular Heterogeneity and Mechanistic Insights.

International journal of molecular sciences·2025

This study introduces AGCLD, an adaptive graph contrastive learning method with denoising, to improve spatial domain identification in single-cell spatial multi-omics. AGCLD enhances tissue analysis by overcoming limitations in current denoising and graph structure methods.

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Genomics

Background:

  • Single-cell spatial multi-omics provides insights into tissue architecture and function.
  • Existing methods struggle with data denoising, static graph structures, and integrating spatial-molecular data.
  • There is a need for advanced computational tools to analyze complex spatial multi-omics data.

Purpose of the Study:

  • To develop an adaptive graph contrastive learning method with denoising for improved spatial domain identification.
  • To address limitations in current single-cell spatial multi-omics analysis techniques.
  • To enhance the understanding of tissue organization through accurate spatial domain identification.

Main Methods:

  • Implemented a modality-specific denoising variational autoencoder for robust latent representations.
Keywords:
adaptive graphcontrastive learningmulti-head self-attentionsingle-cellspatial multi-omics

Related Experiment Videos

  • Introduced a differentiable graph generator for adaptive construction of spatial and expression similarity graphs.
  • Utilized a dual-graph attention network with contrastive learning to integrate spatial and molecular information.

    • Main Results:

    • AGCLD effectively denoises single-cell spatial multi-omics data, improving latent representation quality.
    • Adaptive graph generation overcomes limitations of static graph structures in spatial analysis.
    • The method demonstrated superior performance in spatial domain identification across five datasets compared to state-of-the-art approaches like SpatialGlue.

    Conclusions:

    • AGCLD offers a significant advancement in spatial domain identification for single-cell spatial multi-omics.
    • The proposed method effectively integrates spatial and molecular features, enhancing biological insights.
    • AGCLD provides a robust framework for analyzing complex tissue microenvironments.