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

Pcons: a neural-network-based consensus predictor that improves fold recognition.

J Lundström1, L Rychlewski, J Bujnicki

  • 1Stockholm Bioinformatics Center, Stockholm University, SE 10691 Stockholm, Sweden.

Protein Science : a Publication of the Protein Society
|October 18, 2001
PubMed
Summary

Pcons, a neural-network consensus predictor, improves protein fold recognition by combining predictions from multiple servers. This method enhances accuracy and specificity compared to individual servers, aiding protein structure prediction.

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

pyconsFold: a fast and easy tool for modeling and docking using distance predictions.

Bioinformatics (Oxford, England)·2021
Same author

The SubCons webserver: A user friendly web interface for state-of-the-art subcellular localization prediction.

Protein science : a publication of the Protein Society·2017
Same author

SubCons: a new ensemble method for improved human subcellular localization predictions.

Bioinformatics (Oxford, England)·2017
Same author

Expanding the set of rhodococcal Baeyer-Villiger monooxygenases by high-throughput cloning, expression and substrate screening.

Applied microbiology and biotechnology·2012
Same author

CAFASP2: the second critical assessment of fully automated structure prediction methods.

Proteins·2002
Same author

LiveBench-2: large-scale automated evaluation of protein structure prediction servers.

Proteins·2002

Area of Science:

  • Computational biology
  • Structural bioinformatics
  • Machine learning in bioinformatics

Background:

  • Numerous protein fold recognition methods exist, utilizing diverse algorithms and data.
  • Evaluating these methods through benchmarks and real-world data reveals that combining diverse approaches can enhance prediction accuracy.

Purpose of the Study:

  • To develop and evaluate Pcons, a neural-network-based consensus predictor for protein fold recognition.
  • To improve the accuracy and specificity of protein structure prediction by intelligently combining predictions from multiple servers.

Main Methods:

  • Pcons integrates predictions from six different protein structure prediction servers.
  • It uses a neural network to translate server confidence scores into uniform accuracy values.

Related Experiment Videos

  • Pcons analyzes the similarity between models generated by different servers for final selection.

    • Main Results:

    • Pcons outperforms individual prediction servers, achieving 8-10% more correct predictions on newly solved proteins.
    • The specificity of Pcons is significantly higher than that of any single server.
    • Analysis indicates that model similarity measurement is key to Pcons's improved performance.

    Conclusions:

    • Pcons effectively enhances protein fold recognition accuracy and specificity by consensus prediction.
    • The method demonstrates the power of combining diverse prediction strategies.
    • Pcons is available to the academic community via a web server for protein structure prediction.