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

Constrained clusters of gene expression profiles with pathological features.

Jun Sese1, Yukinori Kurokawa, Morito Monden

  • 1Undergraduate Program for Bioinformatics and Systems Biology, Graduate School of Frontier Sciences, University of Tokyo, Bunkyo, Tokyo, Japan. sesejun@gi.k.u-tokyo.ac.jp

Bioinformatics (Oxford, England)
|June 26, 2004
PubMed
Summary
This summary is machine-generated.

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

Convergence and divergence of DNA methylation and gene expression patterns in neopolyploid Arabidopsis kamchatica.

Nature communications·2026
Same author

Comparing artificial intelligence and physician performance in predicting IDH mutation status in glioma.

NPJ digital medicine·2026
Same author

Individual Variability in Physiological Responses and Psychological Conditions Associated With Methamphetamine Use: Pilot Ecological Momentary Assessment Study Using a Wearable Device and Self-Monitoring Mobile App.

JMIR formative research·2026
Same author

A likelihood ratio test for detecting shifts in homeolog expression ratios in allopolyploids.

The New phytologist·2025
Same author

Pleural invasion of peripheral cT1 lung cancer by deep learning analysis of thoracoscopic images: a retrospective pilot study.

Journal of thoracic disease·2025
Same author

Identification of epistatic SNP combinations in rheumatoid arthritis using LAMPLINK and Japanese cohorts.

Journal of human genetics·2024

Itemset constrained clustering (IC-Clustering) identifies gene expression patterns linked to disease features. This novel method accurately labels clusters with pathological characteristics, outperforming traditional k-means analysis in liver cancer studies.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Gene expression profiles offer insights into cellular status and disease variations.
  • Current clustering methods may miss genes associated with pathological features due to independent analysis steps.
  • Identifying gene expression clusters linked to pathological features is crucial for disease understanding.

Purpose of the Study:

  • To develop a novel technique for identifying gene expression clusters associated with pathological features.
  • To improve the accuracy of disease subtyping using gene expression data.

Main Methods:

  • Introduced 'itemset constrained clustering' (IC-Clustering) to optimize cluster analysis.
  • IC-Clustering maximizes interclass variance under constraints of common feature expression.

Related Experiment Videos

  • Applied the method to liver cancer datasets.

    • Main Results:

    • IC-Clustering successfully identified informative gene expression clusters.
    • Clusters were automatically annotated with relevant pathological features (e.g., 'tumor', 'normal liver function').
    • The k-means method failed to detect these clinically relevant clusters.

    Conclusions:

    • IC-Clustering is an effective method for discovering gene expression clusters with pathological significance.
    • This technique enhances the interpretability of gene expression data for disease classification.
    • IC-Clustering offers an advantage over standard methods like k-means for analyzing complex biological data.