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

An evolution based classifier for prediction of protein interfaces without using protein structures.

I Res1, I Mihalek, O Lichtarge

  • 1Department of Molecular and Human Genetics, Baylor College of Medicine, One Baylor Plaza, Houston, TX 77030, USA.

Bioinformatics (Oxford, England)
|February 25, 2005
PubMed
Summary

Predicting protein-protein interactions from sequence is crucial due to limited structural data. This study introduces a novel method using evolutionary information with support vector machines to identify interacting residues, achieving 64% accuracy.

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

Mutations in RIT1 cause Noonan syndrome - additional functional evidence and expanding the clinical phenotype.

Clinical genetics·2015
Same author

Sequence and structure continuity of evolutionary importance improves protein functional site discovery and annotation.

Protein science : a publication of the Protein Society·2010
Same author

Background frequencies for residue variability estimates: BLOSUM revisited.

BMC bioinformatics·2007
Same author

On itinerant water molecules and detectability of protein-protein interfaces through comparative analysis of homologues.

Journal of molecular biology·2007
Same author

Evolutionary trace report_maker: a new type of service for comparative analysis of proteins.

Bioinformatics (Oxford, England)·2006
Same author

Evolutionary and structural feedback on selection of sequences for comparative analysis of proteins.

Proteins·2006

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Structural Biology

Background:

  • The scarcity of experimentally determined protein structures necessitates computational methods for predicting protein function and interactions.
  • Identifying residues involved in protein-protein interactions (PPIs) from sequence alone is a significant challenge in bioinformatics.

Purpose of the Study:

  • To develop and evaluate a computational method for predicting residues involved in protein-protein interactions using only amino acid sequence information.
  • To improve the accuracy of PPI site prediction by incorporating evolutionary information.

Main Methods:

  • Support vector machines (SVMs) were employed for residue classification.
  • Sequence-derived features, including evolutionary importance rankings, were utilized as input for the SVM model.

Related Experiment Videos

  • Leave-one-out cross-validation was performed to assess prediction performance.

    • Main Results:

    • The developed method successfully classifies protein residues into interface and non-interface categories.
    • The incorporation of evolutionary information significantly enhanced classification accuracy compared to sequence information alone.
    • A prediction accuracy of 64% was achieved, demonstrating the effectiveness of the approach.

    Conclusions:

    • Computational prediction of protein-protein interaction sites from sequence is feasible and can be improved with evolutionary data.
    • The proposed method offers a valuable tool for understanding protein interactions in the absence of structural data.
    • Further research can explore additional features and machine learning algorithms to enhance prediction accuracy.