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

Cluster analysis of gene expression data based on self-splitting and merging competitive learning.

Shuanhu Wu1, Alan Wee-Chung Liew, Hong Yan

  • 1Department of Computer Engineering and Information Technology, City University of Hong Kong, Kowloon, Hong Kong.

IEEE Transactions on Information Technology in Biomedicine : a Publication of the IEEE Engineering in Medicine and Biology Society
|April 2, 2004
PubMed
Summary

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

3D TractFormer: 3D Direct Volumetric White Matter Tract Segmentation with Hybrid Channel-Wise Transformer.

Sensors (Basel, Switzerland)·2026
Same author

A Hybrid Bidirectional Deep Learning Model Using HRV for Prediction of ICU Mortality Risk in TBI Patients.

Journal of healthcare informatics research·2025
Same author

Explainable multimodal hematology analysis for white blood cell classification and attribute prediction.

Computers in biology and medicine·2025
Same author

Identifying key physiological and clinical factors for traumatic brain injury patient management using network analysis and machine learning.

PloS one·2025
Same author

Galformer: a transformer with generative decoding and a hybrid loss function for multi-step stock market index prediction.

Scientific reports·2024
Same author

Integration of Multikinds Imputation With Covariance Adaptation Based on Evidence Theory.

IEEE transactions on neural networks and learning systems·2024

This study introduces a novel clustering framework for gene expression data. The new method accurately identifies natural gene clusters and determines the correct number of clusters, improving biological insights.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Cluster analysis of gene expression data is crucial for identifying biologically relevant gene groups.
  • Accurately finding natural clusters and determining the correct number of clusters remain significant challenges in gene expression analysis.

Purpose of the Study:

  • To propose a novel clustering framework addressing the challenges of natural cluster identification and number estimation in gene expression data.
  • To develop an algorithm that is robust to initialization and accurately determines the number of distinct clusters.

Main Methods:

  • Utilized the one-prototype-take-one-cluster (OPTOC) competitive learning paradigm.
  • Implemented a cluster splitting and merging strategy for estimating the number of clusters.

Related Experiment Videos

  • Applied the algorithm to both simulated and real yeast cell cycle gene expression data.

    • Main Results:

    • The proposed algorithm successfully identified natural clusters in simulated gene expression data.
    • The method accurately estimated the correct number of clusters in simulated datasets.
    • Performance on real yeast cell cycle data demonstrated effectiveness compared to existing algorithms.

    Conclusions:

    • The developed clustering framework effectively addresses key challenges in gene expression data analysis.
    • The algorithm provides a robust and accurate method for identifying gene clusters and their quantities.
    • This approach enhances the biological interpretation of gene expression patterns.