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

Applying Support Vector Machines for Gene Ontology based gene function prediction.

Arunachalam Vinayagam1, Rainer König, Jutta Moormann

  • 1Department of Molecular Biophysics, Deutsches Krebsforschungszentrum (DKFZ), TP3, Im Neuenheimer Feld 580, Heidelberg, D-69120, Germany. A.Vinayagam@dkfz-heidelberg.de

BMC Bioinformatics
|August 31, 2004
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

Medical history predicts phenome-wide disease onset and enables the rapid response to emerging health threats.

Nature communications·2025
Same author

The commitment of the human cell atlas to humanity.

Nature communications·2024
Same author

Sainsc: A Computational Tool for Segmentation-Free Analysis of In Situ Capture Data.

Small methods·2024
Same author

Senescent Syncytiotrophoblast Secretion During Early Onset Preeclampsia.

Hypertension (Dallas, Tex. : 1979)·2024
Same author

The European Health Data Space can be a boost for research beyond borders.

Nature medicine·2024
Same author

An open-source framework for end-to-end analysis of electronic health record data.

Nature medicine·2024

We developed an automated gene function annotation system using Support Vector Machines (SVM) and Gene Ontology (GO) terms. This system provides reliable, accurate, and confident predictions for large-scale sequencing projects.

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • High-throughput sequencing necessitates rapid and accurate gene product function assignment.
  • Existing annotation methods have limitations in scope, formality, and confidence estimation.

Purpose of the Study:

  • To develop a comprehensive, automated system for large-scale gene sequence annotation.
  • To address limitations of current annotation methods by providing formal predictions with confidence estimates.

Main Methods:

  • Utilized multiple Support Vector Machines (SVM) for classification of gene product functions.
  • Employed Gene Ontology (GO) terms for standardized annotation.
  • Performed organism-wise cross-validation to establish confidence estimates.

Related Experiment Videos

Main Results:

  • Achieved an average precision of 80% for 74% of test sequences.
  • Demonstrated organism-independent prediction performance, comparable to manual annotations.
  • Provided over twice the number of contigs with good quality annotation for Xenopus laevis compared to existing methods, including confidence values.

Conclusions:

  • Presented a fully automated annotation system overcoming common challenges using GO and SVM.
  • Successfully applied the system to Xenopus laevis, providing extensive functional annotation.
  • Results are publicly available, facilitating further research.