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 between normal and tumor tissues based on the pair-wise gene expression ratio.

YeeLeng Yap1, XueWu Zhang, M T Ling

  • 1HKU-Pasteur Research Centre, Dexter H,C, Man Building, 8 Sassoon Road Pokfulam, HongKong, China. daniely@hkusua.hku.hk

BMC Cancer
|October 8, 2004
PubMed
Summary

This study introduces a novel gene expression ratio transformation to enhance cancer classification. The method improves signal-to-noise ratio, uncovering reliable cancer markers for better tumor identification and diagnosis.

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

A Triple-Signal Output Lateral Flow Platform Leveraging CRISPR/Cas12a and Nanozyme Cascades for Ultra-Sensitive Aflatoxin B1 Detection.

ACS sensors·2026
Same author

Whole-genome sequencing and probiotic potential analysis of Enterococcus durans B21 isolated from Tibetan kefir.

Microbiological research·2026
Same author

Integration of chemical fingerprinting and multi-pathway pharmacological validation to evaluate the sleep-promoting efficacy of Ziziphus jujuba leaves from diverse origins.

Journal of the science of food and agriculture·2026
Same author

On-site monitoring of juice spoilage: a POCT immunosensor based on sponge-like sensing interface for alicyclobacillus acidoterrestris detection.

Food research international (Ottawa, Ont.)·2026
Same author

Multi-Omics Integration to Investigate the Effects of Variety and Origin on Volatile and Non-Volatile Metabolites in Melons.

Foods (Basel, Switzerland)·2026
Same author

WAS-Mamba: 3D Medical Image Segmentation via Windowed Attention State Space Model.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Area of Science:

  • Genomics
  • Bioinformatics
  • Cancer Research

Background:

  • Accurate cancer classification is vital for effective treatment.
  • Existing gene expression profiling methods often lack reliable cancer signals.
  • Improving tumor classification precision remains a significant challenge.

Purpose of the Study:

  • To develop a data transformation method for gene expression profiles.
  • To enhance the signal-to-noise ratio in gene expression datasets.
  • To identify novel cancer-related signals for improved tumor classification.

Main Methods:

  • A data transformation procedure converting single gene expression to pair-wise gene expression ratios was proposed.
  • Internal dataset consistency was leveraged to improve signal-to-noise ratio.

Related Experiment Videos

  • Feature partitioning using gene annotation was employed for classification analysis.

    • Main Results:

    • The transformation successfully reduced coefficient of variation (CV) in colon cancer data from 45.3% to 16.5%.
    • Classification efficiency for colon cancer improved from 87.1% to 93.5% using the transformed data.
    • Over 90% of top discriminating features showed significant improvement post-transformation, indicating reliable cancer signals.

    Conclusions:

    • Pair-wise gene expression ratio transformation enhances classification accuracy when CV is lowered and correlation with tissue phenotype is improved.
    • This method effectively identifies reliable cancer markers through gene expression ratios, aiding in precise cancer diagnosis.