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

Predicting enzyme class from protein structure using Bayesian classification.

Luiz C Borro1, Stanley R M Oliveira, Michel E B Yamagishi

  • 1Embrapa Information Technology, André Tosello, 209, Caixa Postal 6041, 13083-886 Campinas, SP, Brazil.

Genetics and Molecular Research : GMR
|June 7, 2006
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

Protein exosites as drug targets: from structural topology to therapeutic modality.

Drug discovery today·2026
Same author

STINGAllo: a web server for high-throughput prediction of allosteric site-forming residues using internal protein nanoenvironment descriptors.

Briefings in bioinformatics·2025
Same author

Plasminogen Activator Inhibitors in Thrombosis: Structural Analysis and Potential Natural Inhibitors.

ACS omega·2025
Same author

Phage display-derived peptides as molecular probes for predicting Staphylococcal Exfoliative Toxin-Desmoglein 1 interactions.

International journal of biological macromolecules·2025
Same author

Learning to utilize internal protein 3D nanoenvironment descriptors in predicting CRISPR-Cas9 off-target activity.

NAR genomics and bioinformatics·2025
Same author

Protein allosteric site identification using machine learning and per amino acid residue reported internal protein nanoenvironment descriptors.

Computational and structural biotechnology journal·2024

Predicting enzyme class from protein structure is difficult. Our new method combines statistical and data-mining approaches, outperforming existing techniques with a 45% accuracy for enzyme classification.

Area of Science:

  • Biochemistry and bioinformatics
  • Computational biology
  • Enzymology

Background:

  • Enzyme classification is crucial for understanding biological functions.
  • Predicting enzyme class from protein structure parameters remains a significant challenge in bioinformatics.
  • Existing methods for enzyme class prediction have limitations.

Purpose of the Study:

  • To develop a novel method for predicting enzyme class using protein structure parameters.
  • To combine statistical and data-mining techniques for improved prediction accuracy.
  • To evaluate the performance of the developed method against existing literature approaches.

Main Methods:

  • A hybrid approach integrating statistical and data-mining methods was employed.
  • The method utilizes protein structure parameters as input features.

Related Experiment Videos

  • Implementation is designed to be straightforward and mathematically robust.

    • Main Results:

    • The developed method achieved a prediction accuracy of 45% for enzyme class.
    • Comparative analysis demonstrated that the new method outperforms existing prediction techniques.
    • The hybrid approach shows promise in addressing the challenge of enzyme classification.

    Conclusions:

    • The novel hybrid method offers a viable approach for predicting enzyme class from protein structure.
    • Despite achieving 45% accuracy, the method demonstrates superior performance over current literature methods.
    • Further research may refine this approach for enhanced enzyme classification accuracy.