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

Efficient generalized matrix approximations for biomarker discovery and visualization in gene expression data.

Wenyuan Li1, Yanxiong Peng, Hung-Chung Huang

  • 1Department of Computer Science, University of Texas at Dallas, Richardson, TX 75083, USA.

Computational Systems Bioinformatics. Computational Systems Bioinformatics Conference
|March 21, 2007
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

Efficacy of Non-Invasive Brain Stimulation in Alzheimer's Disease: An Umbrella Review of Meta-Analyses.

Neuroscience and biobehavioral reviews·2026
Same author

Gut microbiota-induced elevation of succinate exacerbates diabetic myocardial ischemia/reperfusion injury by promoting macrophage polarization.

Frontiers in immunology·2026
Same author

Evaluation of Preoperative Tamsulosin Use in Ureteroscopic Holmium Laser Lithotripsy for Elderly Patients with Ureteral Stones.

Journal of visualized experiments : JoVE·2026
Same author

Characterization of gut microbiome signatures in metabolic dysfunction associated steatotic liver disease.

NPJ biofilms and microbiomes·2026
Same author

Methylation plus alpha-fetoprotein blood test for early detection of HCC in at-risk populations.

Hepatology communications·2026
Same author

Ore forming process of magmatic nickel-copper-cobalt sulfide deposits in China.

Fundamental research·2026

This study introduces a novel method for biomarker discovery by integrating differential gene expression with multiple sample classes. This approach enhances sample classification accuracy and provides effective data visualization.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Real-life gene expression data often features multiple sample classes, categorized as normal or diseased.
  • Traditional feature selection methods treat classes equally, ignoring differential gene regulation.
  • Specific gene selection methods focus on differential expression but overlook multiple class characteristics.

Purpose of the Study:

  • To improve biomarker discovery by leveraging both differential gene expression and multiple sample class information.
  • To develop a method that considers the ordinal nature of sample classes and their regulatory patterns.
  • To enhance the accuracy and interpretability of gene expression data analysis.

Main Methods:

  • Employing 1-rank generalized matrix approximations (GMA) to simultaneously analyze differential expressions and multiple classes.

Related Experiment Videos

  • Developing an algorithm based on GMA for compact biomarker identification.
  • Utilizing domain knowledge (differential expression) and data characteristics (multiple classes) in the analysis.

    • Main Results:

    • The proposed method significantly improves sample classification accuracy compared to traditional approaches.
    • The GMA framework provides effective visualization for analyzing both genes and samples.
    • A novel algorithm successfully identifies compact biomarkers by reducing redundancy.

    Conclusions:

    • Integrating differential gene expression with multiple sample class information offers a more powerful approach to biomarker discovery.
    • Generalized Matrix Approximations provide a robust framework for analyzing complex gene expression data.
    • The developed method enhances both predictive accuracy and analytical interpretability in genomics research.