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

Feature (gene) selection in gene expression-based tumor classification.

M Xiong1, W Li, J Zhao

  • 1Human Genetics Center, University of Texas--Houston Health Science Center, Houston, Texas 77225, USA. mxiong@utsph.sph.uth.tmc.edu

Molecular Genetics and Metabolism
|July 20, 2001
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

Identification of allele-specific KIV-2 repeats and impact on Lp(a) measurements for cardiovascular disease risk.

bioRxiv : the preprint server for biology·2023
Same author

Genome-wide analysis of mitochondrial DNA copy number reveals loci implicated in nucleotide metabolism, platelet activation, and megakaryocyte proliferation.

Human genetics·2021
Same author

Large trans-ethnic meta-analysis identifies AKR1C4 as a novel gene associated with age at menarche.

Human reproduction (Oxford, England)·2021
Same author

The Alzheimer's Disease Sequencing Project: Study design and sample selection.

Neurology. Genetics·2017
Same author

Metabolomics and cognition in African American adults in midlife: the atherosclerosis risk in communities study.

Translational psychiatry·2017
Same author

Whole-Exome Sequencing Identifies Novel Variants for Tooth Agenesis.

Journal of dental research·2017
Same journal

Accessibility and harmonization of biochemical tests for diagnosis and monitoring of Porphyrias in the United States: Recommendations by members of the American Porphyrias Expert Collaborative (APEX).

Molecular genetics and metabolism·2026
Same journal

Participants with long-chain 3-hydroxy-acylCoA dehydrogenase deficiency (LCHADD)/trifunctional protein deficiency (TFPD) report consistent low-fat diet intake over time.

Molecular genetics and metabolism·2026
Same journal

Expanding the clinical and molecular spectrum of NGLY1 deficiency: A multicenter cohort.

Molecular genetics and metabolism·2026
Same journal

Driving treatment for females with X-linked adrenoleukodystrophy.

Molecular genetics and metabolism·2026
Same journal

High dietary fat causes muscle structural breakdown, mitochondrial dysfunction, and contractile deficits in the absence of carnitine palmitoyltransferase 2.

Molecular genetics and metabolism·2026
Same journal

Ketogenic diet therapy in pyruvate dehydrogenase deficiency: Global clinical practice from literature and survey data.

Molecular genetics and metabolism·2026
See all related articles

Gene selection effectively reduces the number of genes for accurate tumor classification. Using just 2-3 genes achieves over 90% accuracy, offering a cost-effective and clinically applicable approach for molecular tumor diagnosis.

Area of Science:

  • Bioinformatics
  • Molecular Biology
  • Oncology

Background:

  • Tumor classification is shifting from morphology to molecular profiling.
  • Gene expression profiles offer richer data than traditional methods.
  • Selecting relevant genes is crucial for accurate molecular classification.

Purpose of the Study:

  • To discuss criteria and techniques for gene selection in tumor classification.
  • To demonstrate the effectiveness of selecting a small gene subset for high accuracy.
  • To present stepwise Fisher's linear discriminant function as a practical method.

Main Methods:

  • Analysis of gene expression profiles across colon, breast, and leukemia samples.
  • Application of gene selection techniques to identify informative gene subsets.

Related Experiment Videos

  • Utilizing stepwise Fisher's linear discriminant function for classification.

    • Main Results:

    • Classification accuracy exceeding 90% was achieved using only 2-3 selected genes.
    • Demonstrated feasibility across diverse cancer types (colon, breast, leukemia).
    • Stepwise Fisher's linear discriminant function proved effective for gene expression-based classification.

    Conclusions:

    • Gene selection is a powerful, cost-effective dimensionality reduction technique for tumor classification.
    • A small set of genes can serve as biomarkers or potential drug targets.
    • This approach is simpler and more clinically adaptable than other dimensionality reduction methods.