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

Microarray learning with ABC.

Dhammika Amaratunga1, Javier Cabrera, Vladimir Kovtun

  • 1Johnson & Johnson Pharmaceutical Research & Development LLC, Raritan, NJ 08869-0602, USA. damaratu@prdus.jnj.com

Biostatistics (Oxford, England)
|June 19, 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

Root growth promotion by <i>Penicillium melinii</i> : mechanistic insights and agricultural applications.

bioRxiv : the preprint server for biology·2026
Same author

Root and microbiome synergy in plant heat stress resilience: epigenetic regulation as a frontier for future research.

Journal of experimental botany·2025
Same author

Development of multiple microbiome biomarkers using penalized regression methods.

Journal of applied microbiology·2025
Same author

Corrigendum to "Integrated genomic, proteomic and cognitive assessment in Duchenne Muscular Dystrophy suggest astrocyte centric pathology" [Heliyon Volume 9, Issue 8, August 2023, Article e18530].

Heliyon·2025
Same author

Novel machine learning approach to differential cell flow cytometry analysis based on projection pursuit.

Journal of biopharmaceutical statistics·2025
Same author

Quasi-Empirical Bayes methods for parameter estimation involving many small samples.

Journal of biopharmaceutical statistics·2025

This study introduces a novel unsupervised classification method for DNA microarray data, overcoming limitations of standard clustering algorithms. The new approach, ABC dissimilarities, significantly improves the accuracy of sample clustering and data visualization.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Standard clustering algorithms struggle with DNA microarray data due to high dimensionality (more genes than samples).
  • Noise and complex correlations among genes in microarray data hinder accurate cluster identification.
  • Existing methods like gene filtering or dimension reduction are insufficient for robust clustering.

Purpose of the Study:

  • To develop a novel unsupervised classification method for DNA microarray data.
  • To address the challenges posed by high-dimensional gene expression data in clustering.
  • To improve the accuracy and reliability of sample classification in genomic studies.

Main Methods:

  • Proposed a new method based on aggregating results from randomly resampled data (samples and genes).

Related Experiment Videos

  • Introduced a resampling procedure to prioritize informative genes and minimize noise.
  • Generated 'ABC dissimilarities' by aggregating clusters from data ensembles.
  • Utilized Ward's procedure and multidimensional scaling with ABC dissimilarities for cluster analysis and visualization.

    • Main Results:

    • The proposed ABC dissimilarities method demonstrated significantly superior performance compared to existing clustering methods.
    • Extensive comparisons using actual DNA microarray data validated the effectiveness of the new approach.
    • The method successfully identified true clusters despite the noisy and high-dimensional nature of the data.

    Conclusions:

    • ABC dissimilarities offer a robust and accurate solution for unsupervised classification of DNA microarray data.
    • The novel resampling and aggregation strategy effectively handles the unique challenges of genomic data.
    • This method enhances the ability to perform meaningful cluster analysis and visualization on gene expression data.