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 Video

Updated: Jul 16, 2026

Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells
11:26

Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells

Published on: May 22, 2017

Functionally Guided Graph Learning for Robust Cross-Patient Cell-Type Annotation in Single-Cell RNA Sequencing.

Yue-Chao Li1, Meng-Meng Wei2, Xin-Fei Wang3

  • 1School of Computer Science, Northwestern Polytechnical University, Shaanxi 710129, China.

Journal of Chemical Information and Modeling
|July 15, 2026
PubMed
Summary

Related Concept Videos

RNA-seq03:21

RNA-seq

RNA sequencing, or RNA-Seq, is a high-throughput sequencing technology used to study the transcriptome of a cell. Transcriptomics helps to interpret the functional elements of a genome and identify the molecular constituents of an organism. Additionally, it also helps in understanding the development of an organism and the occurrence of diseases. 
Before the discovery of RNA-seq, microarray-based methods and Sanger sequencing were used for transcriptome analysis. However, while microarray-based...

You might also read

Related Articles

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

Sort by
Same author

Inferring circRNA-Disease Associations via Sparse Topological Representation Learning and Dual-View Decoding.

International journal of molecular sciences·2026
Same author

Enhancing X-ray Image Classification through Heterogeneous Federated Learning with Natural Image-Augmented Models.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

SARGE: A novel framework for miRNA-mRNA interaction prediction combining jumping knowledge aggregation with multi-layer graph attention network.

International journal of biological macromolecules·2026
Same author

TIME: A Taylor-Inspired Mixed-Effects Model for IDH Prediction.

IEEE transactions on bio-medical engineering·2026
Same author

scALGSL: Active Learning and Graph Structure Learning for Cell Type Annotation From Single-Cell RNA-seq Data.

IEEE transactions on computational biology and bioinformatics·2026
Same author

FD-MSGL: Drug Repositioning via Frequency-Domain Multi-Source Synergistic Graph Learning.

IEEE journal of biomedical and health informatics·2026

PathoGraph enhances single-cell RNA sequencing analysis by using functional gene pathway data to improve cell-type annotation across different patients, overcoming challenges from biological variability.

Area of Science:

  • Computational Biology
  • Genomics
  • Bioinformatics

Background:

  • Cross-patient cell-type annotation in single-cell RNA sequencing (scRNA-seq) is hindered by significant interpatient heterogeneity and shifting cellular contexts.
  • Existing annotation methods often rely on expression similarity or graph construction, which can lead to unstable knowledge transfer and spurious cell connections.

Purpose of the Study:

  • To develop a robust framework, PathoGraph, for accurate cross-patient cell-type annotation in scRNA-seq data.
  • To improve the reliability of cell-type identification across diverse patient samples by integrating functional biological information.

Main Methods:

  • PathoGraph employs a functionally guided graph learning framework integrating KEGG pathway-based biosemantic graph structure learning.
  • It refines patient-specific cell graphs using pathway-derived functional profiles to ensure biologically coherent neighborhoods and reduce noise.

Related Experiment Videos

Last Updated: Jul 16, 2026

Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells
11:26

Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells

Published on: May 22, 2017

  • A cross-patient representation adaptation mechanism aligns cell embeddings between reference and query patients for reliable annotation transfer.

    • Main Results:

    • PathoGraph demonstrated stable and competitive annotation performance across three different cancer datasets (leukemia, breast invasive carcinoma, colorectal cancer), achieving an average accuracy of 84.28% and F1-score of 84.08% over 32 tasks.
    • Ablation studies confirmed the critical role of the biosemantic graph learning module, with its removal reducing average accuracy to 83.48%.
    • Functional relevance analyses indicated that PathoGraph captures biologically meaningful cell-cell interactions beyond simple expression similarity.

    Conclusions:

    • PathoGraph provides a robust and effective solution for cross-patient cell-type annotation in scRNA-seq data by leveraging functional graph learning.
    • The framework successfully addresses interpatient heterogeneity, leading to more stable and biologically relevant annotations, crucial for translational research in oncology and immunology.