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

Confirmation of data mining based predictions of protein function.

Ross D King1, Paul H Wise, Amanda Clare

  • 1Department of Computer Science, University of Wales, Aberystwyth, Wales SY23 3DB, UK. rdk@aber.ac.uk

Bioinformatics (Oxford, England)
|February 7, 2004
PubMed
Summary

Data Mining Prediction (DMP) accurately predicted functions for Escherichia coli open reading frames (ORFs). These non-sequence similarity predictions were validated by updated genome data and experimental evidence, demonstrating their reliability.

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

Genome assemblies and annotations are not static and need support for tracking their evolution.

Briefings in bioinformatics·2026
Same author

Protecting Children From the Harms of Immigration Detention and Family Separation-Reply.

JAMA pediatrics·2026
Same author

Drug response profile-based machine learning enables strategic cell line and compound selection for drug development.

Bioinformatics (Oxford, England)·2026
Same author

Investigating uncharacterised genes in Saccharomyces cerevisiae using robot scientists.

Scientific reports·2026
Same author

Compressing Chemistry Reveals Functional Groups.

Journal of chemical information and modeling·2026
Same author

Safeguarding the Health of Children in Carceral Custody.

JAMA pediatrics·2026

Area of Science:

  • Bioinformatics
  • Genomics
  • Computational Biology

Background:

  • Assigning function to sequenced open reading frames (ORFs) is a key bioinformatics challenge.
  • Traditional methods rely on sequence similarity (SIM) like PSI-BLAST.
  • Alternative methods, such as Data Mining Prediction (DMP), are emerging.

Purpose of the Study:

  • To validate Data Mining Prediction (DMP) functional predictions for Escherichia coli open reading frames (ORFs) made in 2000/1.
  • To assess the accuracy and biological relevance of DMP compared to updated biological knowledge.
  • To introduce the Genepredictions database as a repository for protein functional predictions.

Main Methods:

  • Utilized updated Riley group genome annotation (20.02.02) for validation.

Related Experiment Videos

  • Reviewed scientific literature for direct experimental confirmation of ORF functions.
  • Employed Inductive Logic Programming and decision trees within the DMP framework, combining amino-acid attributes, predicted structure, and phylogenic patterns.

    • Main Results:

    • DMP predictions were confirmed by updated genome annotations and scientific literature.
    • Prediction accuracy ranged from 75-100% for voting rules, significantly exceeding random chance.
    • Twenty-one DMP predictions have been experimentally verified, with biologically plausible explanations.

    Conclusions:

    • Data Mining Prediction (DMP) offers a reliable, non-SIM based approach for assigning protein function.
    • DMP predictions are generalizable and validated by experimental data.
    • The Genepredictions database provides an open platform for sharing and accessing protein functional predictions.