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

Forecasting residue-residue contact prediction accuracy.

P P Wozniak1, B M Konopka1, J Xu2

  • 1Department of Biomedical Engineering, Faculty of Fundamental Problems of Technology, Wroclaw University of Science and Technology, Wroclaw, Poland.

Bioinformatics (Oxford, England)
|October 17, 2017
PubMed
Summary

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

Citius, Altius, Fortius.

Proteins·2020
Same author

Bio-knowledge-based filters improve residue-residue contact prediction accuracy.

Bioinformatics (Oxford, England)·2018
Same author

Correlated mutations select misfolded from properly folded proteins.

Bioinformatics (Oxford, England)·2017
Same author

Novel IRF6 Mutations Detected in Orofacial Cleft Patients by Targeted Massively Parallel Sequencing.

Journal of dental research·2016
Same author

GPCRdb: the G protein-coupled receptor database - an introduction.

British journal of pharmacology·2016
Same author

The role of the second and third extracellular loops of the adenosine A1 receptor in activation and allosteric modulation.

Biochemical pharmacology·2012

This study introduces a regression model to predict the accuracy of residue-residue contact predictions for proteins. This method improves upon Direct Coupling Analysis (DCA) by providing reliable accuracy estimates for individual proteins.

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Structural Biology

Background:

  • Current residue-residue contact prediction methods, primarily based on Direct Coupling Analysis (DCA) of multiple sequence alignments (MSAs), achieve an average accuracy of approximately 40% for the top predicted contacts.
  • The lack of reliable accuracy estimates for individual proteins hinders the effective use of these predictions in experimental research.

Purpose of the Study:

  • To develop a regression model capable of forecasting the accuracy of residue-residue contact predictions for individual proteins.
  • To provide end-users with a quantitative measure of confidence in predicted contacts to guide experimental validation.

Main Methods:

  • A regression model was designed using parameters describing the MSA, predicted secondary structure, predicted solvent accessibility, and contact prediction scores.

Related Experiment Videos

  • Two DCA methods, gplmDCA and PSICOV, were employed for contact prediction within the model development framework.

    • Main Results:

    • The developed regression model achieved an average error of 7 percentage points in forecasting contact prediction accuracy.
    • The model demonstrated applicability to meta-methods, as validated using RaptorX.

    Conclusions:

    • The developed model offers a significant improvement by providing accurate, protein-specific confidence scores for residue-residue contact predictions.
    • This tool enhances the utility of computational predictions in guiding experimental protein research by quantifying prediction reliability.