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

Reducing false positives in molecular pattern recognition.

Xijin Ge1, Shuichi Tsutsumi, Hiroyuki Aburatani

  • 1Genome Science Division, Research Center for Advanced Science and Technology, The University of Tokyo, 4-6-1 Komaba, Meguro-ku, Tokyo 153-8904, Japan. xge@genome.rcast.u-tokyo.ac.jp

Genome Informatics. International Conference on Genome Informatics
|February 12, 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

Multiancestry genomic and transcriptomic analysis of gastric cancer.

Nature genetics·2023
Same author

LMNA Mutations and Right Heart Failure in Patients With Cardiomyopathy and With Left Ventricular Assist Devices.

Journal of cardiac failure·2023
Same author

Loss of viral genome with altered immune microenvironment during tumour progression of Epstein-Barr virus-associated gastric carcinoma.

The Journal of pathology·2023
Same author

Cross-ancestry genome-wide analysis of atrial fibrillation unveils disease biology and enables cardioembolic risk prediction.

Nature genetics·2023
Same author

Tandemly repeated genes promote RNAi-mediated heterochromatin formation via an antisilencing factor, Epe1, in fission yeast.

Genes & development·2023
Same author

Clinical utility of Todai OncoPanel in the setting of approved comprehensive cancer genomic profiling tests in Japan.

Cancer science·2023
Same journal

Linear regression models predicting strength of transcriptional activity of promoters.

Genome informatics. International Conference on Genome Informatics·2012
Same journal

Sign: large-scale gene network estimation environment for high performance computing.

Genome informatics. International Conference on Genome Informatics·2012
Same journal

Docking-calculation-based method for predicting protein-RNA interactions.

Genome informatics. International Conference on Genome Informatics·2012
Same journal

Mechanism of cell cycle disruption by multiple p53 pulses.

Genome informatics. International Conference on Genome Informatics·2012
Same journal

Database for crude drugs and Kampo medicine.

Genome informatics. International Conference on Genome Informatics·2012
Same journal

A dynamic programming algorithm to predict synthesis processes of tree-structured compounds with graph grammar.

Genome informatics. International Conference on Genome Informatics·2011
See all related articles

To accurately classify cancer subtypes using gene expression, the prototype matching (PM) method shows lower false positive rates than k-nearest neighbor (KNN) and support vector machine (SVM). A new cluster-and-select gene selection technique enhances classification reliability.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Accurate cancer subtype classification is crucial for effective treatment.
  • Gene expression profiling is a powerful tool for identifying new cancer subtypes.
  • Misclassification of unknown subtypes as known ones can lead to treatment errors.

Purpose of the Study:

  • To evaluate the false positive error rates of various classification algorithms for cancer subtypes.
  • To develop a robust gene selection method for improved classification accuracy.
  • To assess the reliability of a novel cluster-and-select gene selection technique.

Main Methods:

  • A 'null test' was performed using independent samples not belonging to training datasets.
  • Evaluated k-nearest neighbor (KNN), support vector machine (SVM), and prototype matching (PM) algorithms.

Related Experiment Videos

  • Developed and applied a cluster-and-select gene selection technique using the Kruskal-Wallis H test.

    • Main Results:

    • KNN and SVM exhibited high false positive rates with fewer than 100 genes, which decreased with more genes.
    • Prototype matching (PM) demonstrated significantly lower false positive rates.
    • The cluster-and-select method, combined with confidence measures, improved robustness without sacrificing sensitivity.

    Conclusions:

    • Prototype matching (PM) offers a more reliable approach for cancer subtype classification compared to KNN and SVM, especially with limited genes.
    • The proposed cluster-and-select gene selection technique enhances classification accuracy and reliability.
    • This study provides a robust framework for identifying novel cancer subtypes through gene expression analysis.