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

Knowledge-assisted recognition of cluster boundaries in gene expression data.

Yoshifumi Okada1, Takehiko Sahara, Hikaru Mitsubayashi

  • 1Satellite Venture Business Laboratory, Muroran Institute of Technology, 27-1 Mizumoto-cho, Muroran, Hokkaido 050-8585, Japan. okada@mail.svbl.muroran-it.ac.jp

Artificial Intelligence in Medicine
|August 2, 2005
PubMed
Summary

This study introduces a novel algorithm that integrates gene function annotations with hierarchical clustering to improve gene expression analysis. The method accurately identifies biological processes and enhances cluster interpretation, outperforming traditional techniques.

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

A lightweight deep learning architecture for automatic shrimp disease classification.

Scientific reports·2026
Same author

Enzyme cycling method using hypoxanthine-guanine phosphoribosyltransferase: a highly sensitive assay for pyrophosphate.

Analytical methods : advancing methods and applications·2025
Same author

Identification and characterization of xyloglucan-degradation related α-1,2-l-fucosidase in Aspergillus oryzae.

Journal of bioscience and bioengineering·2024
Same author

Three-dimensional wall-thickness distributions of unruptured intracranial aneurysms characterized by micro-computed tomography.

Biomechanics and modeling in mechanobiology·2024
Same author

Accessory fragment migration in a professional baseball player with bipartite patella: A case report.

International journal of surgery case reports·2023
Same author

Molecular evolution of Cypridina noctiluca secretory luciferase for production of spectrum-shifted luminescence-emitting mutants and their application in nuclear receptor-reporter assays.

Photochemistry and photobiology·2023

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • DNA microarray technology enables parallel gene expression analysis across multiple conditions.
  • Gene expression data analysis requires classifying genes with similar patterns for exploring genetic networks and disease diagnosis.
  • Traditional hierarchical clustering methods lack biological interpretability and require laborious manual effort for understanding gene functions within clusters.

Purpose of the Study:

  • To develop a novel algorithm for gene expression data analysis that integrates functional annotations to determine cluster boundaries.
  • To improve the biological interpretation of gene clusters derived from gene expression profiles.

Main Methods:

  • Hierarchical clustering of gene expression profiles.

Related Experiment Videos

  • Determination of cluster boundaries using the Variance Inflation Factor of Gene Function Vectors.
  • Automatic identification of functionally independent gene agglomerations on a dendrogram.
  • Annotation of clusters based on dominant gene functions.

    • Main Results:

    • The algorithm successfully identified distinct biological processes, including cell cycle phases (Early G1, Late G1, S, G2, M) in yeast.
    • Novel functional annotation information was obtained, surpassing traditional hierarchical clustering methods.
    • The algorithm demonstrated high validity when compared to K-means, self-organizing map, and AutoClass using cluster validity indices.

    Conclusions:

    • The proposed algorithm enhances the biological interpretation of gene expression data by incorporating functional annotations.
    • This approach provides a more insightful understanding of biological processes compared to conventional clustering techniques.
    • The algorithm is a valuable tool for analyzing gene expression datasets and discovering hidden biological functions.