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

Improving the performance of DomainParser for structural domain partition using neural network.

Jun-tao Guo1, Dong Xu, Dongsup Kim

  • 1Protein Informatics Group, Life Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37830-6480, USA.

Nucleic Acids Research
|February 1, 2003
PubMed
Summary

This study introduces a new neural network method to automatically identify the correct number of structural domains in proteins. This improves protein domain decomposition accuracy, aiding protein folding and function studies.

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

MUFOLD-DB: a processed protein structure database for protein structure prediction and analysis.

BMC genomics·2015
Same author

Advances in translational bioinformatics facilitate revealing the landscape of complex disease mechanisms.

BMC bioinformatics·2015
Same author

The I-TASSER Suite: protein structure and function prediction.

Nature methods·2014
Same author

Genome-wide expression analysis of soybean NF-Y genes reveals potential function in development and drought response.

Molecular genetics and genomics : MGG·2014
Same author

Classification of lung cancer using ensemble-based feature selection and machine learning methods.

Molecular bioSystems·2014
Same author

Resveratrol possesses protective effects in a pristane-induced lupus mouse model.

PloS one·2014

Area of Science:

  • Protein structure analysis
  • Computational biology
  • Bioinformatics

Background:

  • Structural domains are fundamental units in protein folding, evolution, and function.
  • Automatic protein domain decomposition remains a significant challenge in structural biology.
  • Previous methods like DomainParser struggle when the number of domains is unknown.

Purpose of the Study:

  • To develop an accurate method for automatic protein domain decomposition.
  • To improve the prediction of the most probable number of domains in protein structures.
  • To enhance the accuracy of computational protein structure analysis.

Main Methods:

  • Utilized various structural information, including hydrophobic moment profiles.
  • Developed a neural network model trained to discriminate correct from incorrect domain partitions.

Related Experiment Videos

  • Integrated this method with existing network flow algorithms for domain partitioning.

    • Main Results:

    • The new method effectively assesses the probable number of domains in protein structures.
    • Achieved a higher decomposition accuracy of 81.9% compared to previous methods (74.5%).
    • Outperformed earlier approaches on a dataset of 1317 protein chains when compared to SCOP database annotations.

    Conclusions:

    • The developed neural network-based approach significantly enhances automatic protein domain decomposition.
    • This advancement offers a more reliable tool for analyzing protein structures and their functions.
    • Improves upon existing computational methods for understanding protein architecture.