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

Dimension reduction strategies for analyzing global gene expression data with a response.

Francesca Chiaromonte1, Jessica Martinelli

  • 1Department of Statistics, Penn State University, University Park, PA 16802, USA. chiaro@stat.psu.edu

Mathematical Biosciences
|February 28, 2002
PubMed
Summary

This study introduces a dimension reduction strategy for analyzing gene expression data, addressing the challenge of too many genes and too few samples. The method helps build accurate regression models and identify key genes for disease classification, such as in leukemia.

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

Variation and selection at predicted G-quadruplexes across the human pangenome.

bioRxiv : the preprint server for biology·2026
Same author

Substitution Spectrum and Selection at G-quadruplexes in Great Ape Telomere-to-Telomere Genomes.

Genome biology and evolution·2026
Same author

Mammalian mitochondrial DNA accumulates insertions and deletions with age in energetically demanding tissues.

Molecular biology and evolution·2026
Same author

Allele Frequency Selection and No Age-Related Increase in Human Oocyte Mitochondrial Mutations.

Obstetrical & gynecological survey·2026
Same author

Contrasting pre-vaccine COVID-19 waves in Italy through functional data analysis.

Scientific reports·2025
Same author

Comparative analysis of single-stranded and non-canonical DNA formation in human and other ape cells with telomere-to-telomere genomes.

bioRxiv : the preprint server for biology·2025

Area of Science:

  • Genetics
  • Biostatistics
  • Bioinformatics

Background:

  • Global gene expression analysis using microarrays presents significant statistical and modeling challenges.
  • High-dimensional data with numerous genes (predictors) and limited samples (observations) create an under-resolution problem.
  • Gene expression data is often used for response prediction and relevant gene identification.

Purpose of the Study:

  • To present a dimension reduction strategy for high-dimensional gene expression data.
  • To overcome the under-resolution problem in regression settings.
  • To enable robust regression modeling and relevant gene selection.

Main Methods:

  • Developed a dimension reduction strategy focusing on linear combinations of gene expression profiles.

Related Experiment Videos

  • Applied standard regression techniques to the reduced dimension data for model building and validation.
  • Utilized randomization-based comparison to a 'chance scenario' for ranking and selecting relevant genes.

    • Main Results:

    • The dimension reduction strategy effectively addresses the under-resolution issue in gene expression data analysis.
    • The approach facilitates the construction and validation of predictive regression models.
    • The method successfully identified relevant genes by comparing against a randomized background.
    • Applied successfully to publicly available leukemia classification data.

    Conclusions:

    • The proposed dimension reduction strategy is effective for analyzing high-dimensional gene expression data.
    • This approach enables accurate prediction and identification of key genes in biological and medical research.
    • The method offers a robust framework for tackling under-resolution in genetics and biostatistics.
    • Demonstrated utility in a real-world application for leukemia classification.