Jove
Visualize
Contact Us

Related Experiment Videos

SamCluster: an integrated scheme for automatic discovery of sample classes using gene expression profile.

Wuju Li1, Ming Fan, Momiao Xiong

  • 1Beijing Institute of Basic Medical Sciences, PO Box 130(3), People's Republic of China. wujuli@yahoo.com

Bioinformatics (Oxford, England)
|May 2, 2003
PubMed
Summary

This study introduces SamCluster, an efficient method for discovering sample classes from gene expression profiles. The approach integrates feature selection with hierarchical clustering, significantly improving classification accuracy.

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

Characteristics of gut microbiota structure and composition in diabetic patients from the Chaoshan region of China.

Journal of medical microbiology·2026
Same author

Efficacy of Jishi Shuanghua Granules in preventing radiation-induced esophagitis in non-small cell lung cancer patients undergoing concurrent chemoradiotherapy: protocol for a multicenter, randomized, double-blind, placebo-controlled trial.

Frontiers in medicine·2026
Same author

Modified sini powder for the management of postoperative depression in non-small cell lung cancer patients: a multicenter, randomized, double-blind, placebo-controlled trial protocol.

Frontiers in pharmacology·2026
Same author

Characteristics of dermal fibroblasts and their biotherapeutic value in musculoskeletal system diseases.

Frontiers in bioengineering and biotechnology·2026
Same author

Brain and knee joint degeneration following anterior cruciate ligament injury in a mouse model of Alzheimer's disease.

JBMR plus·2026
Same author

Soil Fungal Communities' Characteristics of the <i>Lamiophlomis rotata</i> Root-Zone to Altitude and Their Relationship with Environmental Factors.

Microorganisms·2026
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

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Gene expression profiling is crucial for sample classification.
  • Traditional feature selection methods are well-established for prediction but less explored for pattern discovery in clustering.
  • Developing effective feature selection for clustering is essential for uncovering biological patterns.

Purpose of the Study:

  • To present an integrated scheme and software (SamCluster) for automatic discovery of sample classes using gene expression data.
  • To incorporate feature selection algorithms (CV and t-test) into hierarchical clustering for enhanced pattern discovery.
  • To evaluate the performance of the proposed method on real-world gene expression datasets.

Main Methods:

  • An integrated scheme combining coefficient of variation (CV) and t-test based feature selection with hierarchical clustering.

Related Experiment Videos

  • Iterative selection of differentially expressed genes based on pre-specified thresholds and p-values.
  • Construction of consensus sample classes and identification of optimal classes based on minimum distance.

    • Main Results:

    • The SamCluster scheme demonstrated high accuracy in classifying samples across four datasets (COLON, LEUKEMIA72, LEUKEMIA38, OVARIAN), with minimal misclassifications (0-5 samples).
    • The integrated feature selection effectively identified relevant genes for robust sample class discovery.
    • The method successfully discovered stable sample classes through iterative clustering and consensus building.

    Conclusions:

    • SamCluster is an efficient and accurate method for sample class discovery from gene expression profiles.
    • The integration of feature selection with hierarchical clustering significantly improves the performance of pattern discovery algorithms.
    • The developed scheme provides a valuable tool for analyzing gene expression data and identifying distinct biological subgroups.