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

Molecular classification of multiple tumor types.

C H Yeang1, S Ramaswamy, P Tamayo

  • 1Center for Genome Research, MIT Whitehead Institute, One Kendall Square, Cambridge, MA 02139, USA. chyeang@mit.edu

Bioinformatics (Oxford, England)
|July 27, 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

Resistance training partially restores age-related differences in skeletal muscle amino acid transporters - secondary analysis from two randomized controlled trials.

The journal of nutrition, health & aging·2026
Same author

Assessing MRI interpretability of the orbit, paranasal sinuses, and nasopharynx in cochlear implant patients.

Frontiers in neurology·2025
Same author

Post mortem cadaveric and imaging mapping analysis of the influence of cochlear implants on cMRI assessment regarding implant positioning and artifact formation.

European archives of oto-rhino-laryngology : official journal of the European Federation of Oto-Rhino-Laryngological Societies (EUFOS) : affiliated with the German Society for Oto-Rhino-Laryngology - Head and Neck Surgery·2024
Same author

Contrasting magma chemistry in the Candelaria IOCG district caused by changing tectonic regimes.

Scientific reports·2024
Same author

Risk factors for the development of secondary intracranial hypertension in acute cerebral venous thrombosis.

Neuroradiology·2022
Same author

The lipid composition of the in situ pellicle.

Archives of oral biology·2022

Classifying multiple tumor types using gene expression data is feasible. The one-vs-all support vector machine achieved the best cross-validation and test error rates for cancer diagnosis.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Gene expression patterns effectively distinguish some tumor types.
  • Simultaneous classification across diverse tumor types remains understudied.

Purpose of the Study:

  • To investigate the feasibility of multi-tumor type classification using gene expression data.
  • To evaluate different classification algorithms and combination strategies.

Main Methods:

  • Generated a combined gene expression dataset from 190 samples across 14 tumor classes.
  • Applied three binary classifiers (k-nearest neighbors, weighted voting, support vector machines) with three combination scenarios (one-vs-all, all-pairs, hierarchical partitioning).

Main Results:

Related Experiment Videos

  • Achieved a cross-validation error rate of 18.75% and a test error rate of 21.74%.
  • The one-vs-all support vector machine algorithm yielded the best performance.

Conclusions:

  • Demonstrated the feasibility of classifying multiple tumor types simultaneously using gene expression data.
  • Results suggest potential for clinically useful cancer diagnosis tools.