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

Multiclass molecular cancer classification by kernel subspace methods with effective kernel parameter selection.

Satoshi Niijima1, Satoru Kuhara

  • 1Department of Bioinformatics, Graduate School of Systems Life Sciences, Kyushu University, Hakozaki 6-10-1, Higashi-ku, Fukuoka 812-8581, Japan. niijima@grt.kyushu-u.ac.jp

Journal of Bioinformatics and Computational Biology
|November 10, 2005
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

A multi-kingdom genetic barcoding system for precise clone isolation.

Nature biotechnology·2025
Same author

Identification and characterization of the suppressed lipid accumulation-related gene, SLA1, in the oleaginous yeast Lipomyces starkeyi.

Bioscience, biotechnology, and biochemistry·2024
Same author

INSTABILITY OF MESSENGER AND RIBOSOMAL RNA IN A GLUE-PROTEIN MUTANT OF Bombyx mori.

Development, growth & differentiation·2023
Same author

Development of a chub mackerel with less-aggressive fry stage by genome editing of arginine vasotocin receptor V1a2.

Scientific reports·2023
Same author

LsSpt23p is a regulator of triacylglycerol synthesis in the oleaginous yeast Lipomyces starkeyi.

Applied microbiology and biotechnology·2023
Same author

Prdm12 regulates inhibitory neuron differentiation in mouse embryonal carcinoma cells.

Cytotechnology·2022

The kernel subspace (KS) method shows high performance in multiclass cancer classification, comparable to support vector machines (SVMs). This study validates the KS method and proposes a useful kernel parameter selection criterion for cancer diagnosis.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Oncology

Background:

  • Microarray techniques offer insights into molecular cancer classification, crucial for diagnosis and treatment.
  • Supervised machine learning, particularly support vector machines (SVMs), is increasingly used for cancer classification with gene expression data.
  • Limited research exists on applying alternative kernel methods to cancer classification.

Purpose of the Study:

  • To apply and assess the validity of the kernel subspace (KS) method for multiclass cancer classification.
  • To compare the performance of the KS method against multiclass SVMs.
  • To propose an effective criterion for kernel parameter selection in the KS method.

Main Methods:

  • Application of the kernel subspace (KS) method to seven multiclass cancer datasets.

Related Experiment Videos

  • Comparative analysis of KS method performance against multiclass SVMs.
  • Development and evaluation of a novel criterion for kernel parameter selection.

    • Main Results:

    • The KS method demonstrated high performance in multiclass cancer classification.
    • KS method performance was found to be comparable to that of multiclass SVMs.
    • The proposed kernel parameter selection criterion proved effective for KS method computation.

    Conclusions:

    • The kernel subspace (KS) method is a valid and high-performing alternative for multiclass cancer classification.
    • The KS method offers comparable results to established methods like SVMs.
    • The developed parameter selection criterion enhances the utility of the KS method in cancer research.