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

Benchmarking AI scientists for omics data-driven biological discovery.

Bioinformatics (Oxford, England)·2026
Same author

A multi-modal diffusion model with dual-cross-attention for multi-omics data generation and translation.

Nature communications·2026
Same author

A generic reference defined by consensus peaks for single-cell ATAC-seq data analysis.

Nature communications·2026
Same author

hECA v2.0: an AI-ready ensemble cell atlas of single-cell RNA and ATAC sequencing data.

Scientific data·2025
Same author

ERNIE-RNA: an RNA language model with structure-enhanced representations.

Nature communications·2025
Same author

Computational methods and data resources for predicting tumor neoantigens.

Briefings in bioinformatics·2025

Related Experiment Video

Updated: Jul 12, 2025

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

792

Latent feature extraction with a prior-based self-attention framework for spatial transcriptomics.

Zhen Li1, Xiaoyang Chen1, Xuegong Zhang1

  • 1Ministry of Education Key Laboratory of Bioinformatics, Bioinformatics Division at the Beijing National Research Center for Information Science and Technology, Center for Synthetic and Systems Biology, Department of Automation, Tsinghua University, Beijing 100084, China.

Genome Research
|October 30, 2023
PubMed
Summary
This summary is machine-generated.

PAST, a new framework for spatial transcriptomics (ST), effectively characterizes spatial domains by integrating prior information and self-attention mechanisms. This method enhances downstream analyses and enables novel applications like automatic annotation using reference data.

More Related Videos

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection
09:19

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection

Published on: July 6, 2022

4.9K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K

Related Experiment Videos

Last Updated: Jul 12, 2025

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

792
Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection
09:19

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection

Published on: July 6, 2022

4.9K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K

Area of Science:

  • Genomics
  • Computational Biology
  • Bioinformatics

Background:

  • Spatial transcriptomics (ST) is rapidly advancing, necessitating robust methods for spatial domain characterization.
  • Accurate spatial domain identification is critical for downstream ST data analysis and biological interpretation.

Purpose of the Study:

  • To introduce a novel prior-based self-attention framework for spatial transcriptomics (PAST).
  • To enhance the characterization of spatial domains and facilitate downstream analyses in ST data.

Main Methods:

  • PAST utilizes a variational graph convolutional autoencoder.
  • It integrates prior information via a Bayesian neural network and captures spatial patterns using a self-attention mechanism.
  • A ripple walk sampler strategy ensures scalable application.

Main Results:

  • PAST effectively characterizes spatial domains across diverse ST datasets.
  • The framework facilitates ST visualization, spatial trajectory inference, and pseudotime analysis.
  • PAST demonstrates advantages in multislice joint embedding and automatic annotation of spatial domains.

Conclusions:

  • PAST is the first ST method to integrate reference data for ST data analysis.
  • This approach expands the applicability of ST technology by enabling customized reference data integration.
  • PAST opens new avenues for deciphering complex spatial transcriptomic data.