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

Multi-class cancer classification using multinomial probit regression with Bayesian gene selection.

X Zhou1, X Wang, E R Dougherty

  • 1Department of Electrical Engineering, Texas A&M University, College Station, TX 77843, USA.

Systems Biology
|September 22, 2006
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

Ratio-based decisions and the quantitative analysis of cDNA microarray images.

Journal of biomedical optics·2012
Same author

Multiscale denoising of biological data: a comparative analysis.

IEEE/ACM transactions on computational biology and bioinformatics·2012
Same author

Inference of Boolean networks under constraint on bidirectional gene relationships.

IET systems biology·2009
Same author

Small sample issues for microarray-based classification.

Comparative and functional genomics·2008
Same author

On approximate stochastic control in genetic regulatory networks.

IET systems biology·2008
Same author

Genomic profiles and predictive biological networks in oxidant-induced atherogenesis.

Physiological genomics·2003

This study introduces novel Bayesian gene selection methods for multi-class cancer classification using gene expression data. These advanced techniques accurately identify key genes influencing specific cancers, achieving high recognition accuracies.

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Gene expression data analysis is crucial for understanding complex diseases like cancer.
  • Accurate multi-class cancer classification requires effective methods for identifying relevant genes.
  • Existing classification methods may not optimally identify genes specific to different cancer types.

Purpose of the Study:

  • To develop and evaluate novel Bayesian gene selection schemes for multi-class cancer classification.
  • To compare two distinct Bayesian gene selection strategies: using different strongest genes versus the same strongest genes for all regressions.
  • To enhance the efficiency of Bayesian gene selection through fast implementation techniques.

Main Methods:

  • Utilizing the multinomial probit regression model integrated with Bayesian gene selection.

Related Experiment Videos

  • Proposing two distinct Bayesian gene selection schemes: one adaptive and one common.
  • Implementing fast computational techniques, including gene preselection and QR decomposition for recursive error estimation.

    • Main Results:

    • The proposed methods successfully identified important genes associated with specific cancer types across diverse datasets.
    • Selected genes demonstrated strong biological relevance, aligning with existing knowledge.
    • The Bayesian gene selection approaches achieved high recognition accuracies in multi-class cancer classification tasks.

    Conclusions:

    • The developed Bayesian gene selection methods offer a powerful tool for multi-class cancer classification from gene expression data.
    • These methods provide biologically meaningful insights into gene-cancer associations.
    • The proposed techniques significantly improve classification accuracy and gene identification compared to existing approaches.