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

Classification of microarrays to nearest centroids.

Alan R Dabney1

  • 1Department of Biostatistics, University of Washington, Seattle, 98195, USA. adabney@u.washington.edu

Bioinformatics (Oxford, England)
|September 22, 2005
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

Using clinical and thrombus characteristics to predict the etiology of ischemic stroke: An analysis of the INSIGHT registry.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2026
Same author

SECNVs: A Simulator of Copy Number Variants and Whole-Exome Sequences From Reference Genomes.

Frontiers in genetics·2020
Same author

Author Correction: RNA-seq of serial kidney biopsies obtained during progression of chronic kidney disease from dogs with X-linked hereditary nephropathy.

Scientific reports·2020
Same author

RNA-seq of serial kidney biopsies obtained during progression of chronic kidney disease from dogs with X-linked hereditary nephropathy.

Scientific reports·2017
Same author

Predicting "heart age" using electrocardiography.

Journal of personalized medicine·2015
Same author

Normalization and missing value imputation for label-free LC-MS analysis.

BMC bioinformatics·2012

Classification to Nearest Centroids (ClaNC) offers a simpler, more accurate alternative to Prediction Analysis of Microarrays (PAM). ClaNC reduces misclassification error by using standard t-statistics and avoiding centroid shrinkage for improved biological sample classification.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Microarray-based classification of biological samples is a critical area of research.
  • Nearest centroid classification methods, like Prediction Analysis of Microarrays (PAM), have shown promise due to their accuracy and interpretability.
  • Simpler classification approaches are sought to potentially improve upon existing complex methods.

Purpose of the Study:

  • To assess the performance of classification methods simpler than PAM.
  • To introduce and evaluate a novel classification method, Classification to Nearest Centroids (ClaNC).
  • To compare the efficacy of ClaNC against PAM in terms of misclassification error.

Main Methods:

  • Genes are ranked using standard t-statistics.

Related Experiment Videos

  • Centroids are not shrunk, maintaining their original values.
  • A class-specific gene-selection procedure is implemented.
  • ClaNC is developed as a traditional nearest centroid classifier utilizing specially selected genes.

    • Main Results:

    • Modified t-statistics and shrunken centroids in PAM can increase misclassification error compared to simpler methods.
    • ClaNC demonstrates significantly lower error rates than PAM for a comparable number of active genes.
    • ClaNC is presented as a simpler and more interpretable classification approach.

    Conclusions:

    • ClaNC offers a more accurate and interpretable alternative for microarray-based biological sample classification.
    • The proposed method challenges the necessity of complex statistical adjustments like centroid shrinkage in PAM.
    • Freely available software for ClaNC facilitates its application in biological research.