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

Randomized maps for assessing the reliability of patients clusters in DNA microarray data analyses.

Alberto Bertoni1, Giorgio Valentini

  • 1DSI, Dipartimento di Scienze dell' Informazione, Università degli Studi di Milano, Via Comelico 39, Milano, Italy.

Artificial Intelligence in Medicine
|May 25, 2006
PubMed
Summary

This study introduces a novel method for assessing the reliability of clusters in DNA microarray data. The approach uses random projections to validate cluster stability, aiding in the discovery of new disease subtypes.

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

MiRInter-Trans: a transformer-based framework for microRNA interaction prediction.

Bioinformatics advances·2026
Same author

On the state of protein function prediction: a report on the fourth CAFA challenge.

bioRxiv : the preprint server for biology·2026
Same author

Computational understanding of non-coding RNA pairwise interactions.

Frontiers in artificial intelligence·2026
Same author

Systematic benchmarking demonstrates large language models have not reached the diagnostic accuracy of traditional rare-disease decision support tools.

European journal of human genetics : EJHG·2026
Same author

Leveraging generative AI to assist biocuration of medical actions for rare disease.

Bioinformatics advances·2025
Same author

RNA knowledge-graph analysis through homogeneous embedding methods.

Bioinformatics advances·2025

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Clustering DNA microarray data can reveal disease subtypes.
  • Assessing the reliability of identified clusters is crucial but challenging.
  • Existing methods struggle with high-dimensional biological data.

Purpose of the Study:

  • To develop and validate novel cluster-stability measures for DNA microarray data.
  • To enhance the reliability assessment of clustering algorithms in bioinformatics.
  • To support the discovery of new disease classifications at the molecular level.

Main Methods:

  • Applied random projections based on Johnson-Lindenstrauss theory to high-dimensional gene expression data.
  • Estimated cluster stability by comparing clusters in original and projected lower-dimensional subspaces.

Related Experiment Videos

  • Utilized bootstrapping and noise injection techniques for cluster validity.

    • Main Results:

    • Demonstrated accurate prediction of cluster number and reliability using synthetic data.
    • Successfully applied stability measures to DNA microarray data from lymphoma and melanoma patients.
    • Showcased the ability to identify stable patient clusters and potential new disease subtypes.

    Conclusions:

    • The proposed stability measures effectively validate clusters derived from DNA microarray data.
    • Randomized map-based stability assessment aids in discovering reliable molecular-level disease subtypes.
    • This approach supports bio-medical researchers in identifying robust patient subgroups.