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

Classification of protein quaternary structure with support vector machine.

Shao-Wu Zhang1, Quan Pan, Hong-Cai Zhang

  • 1Department of Automatic Control, Northwestern Polytechnical University, Xi'an 710072, People's Republic of China. shaowuzhang@hotmail.com

Bioinformatics (Oxford, England)
|December 12, 2003
PubMed
Summary

This study introduces a new method using support vector machine (SVM) to classify protein quaternary structures from primary sequences. The approach accurately predicts protein structures, aiding biological research.

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

Hepatic TGFβ1 signaling impairs insulin sensitivity via inducing insulin receptor substrate 1 degradation.

Metabolism: clinical and experimental·2026
Same author

Temporal gene expression profiling reveals the protective mechanism of APIP in atrial fibrillation following myocardial infarction.

Biochimica et biophysica acta. Molecular basis of disease·2026
Same author

Exciton-driven two-step charge transfer in MoS<sub>2</sub>-WSe<sub>2</sub> heterostructures revealed by valley-resolved broadband pump-probe spectroscopy.

Physical chemistry chemical physics : PCCP·2026
Same author

Super Cost-Effective and Scalable Imine-Based Sorbent With Field Attraction and In Situ Fixation for Efficient Capture of Diverse Iodine Species under Industrial Conditions.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Highly Effective Energy Redistribution and Vertical Electron Transfer in Reduced Graphene Oxide/Au Composite Ultrathin Electrodes.

The journal of physical chemistry letters·2026
Same author

Supplementary filling seedlings in secondary Pinus massoniana forests changed the structure of soil bacterial communities.

Scientific reports·2026

Area of Science:

  • Computational Biology
  • Structural Bioinformatics
  • Machine Learning in Biology

Background:

  • The growing number of protein sequences outpaces structural determination, necessitating automated classification methods.
  • Classifying protein quaternary structure from primary sequences offers valuable biological insights.
  • There is a need for reliable, automated systems for protein structure classification.

Purpose of the Study:

  • To develop effective methods for attribute extraction from protein primary sequences.
  • To create an algorithm for classifying protein quaternary structure based on primary sequences.
  • To investigate the utility of Support Vector Machine (SVM) for this classification task.

Main Methods:

  • Employed Support Vector Machine (SVM) and covariant discriminant algorithms.

Related Experiment Videos

  • Utilized amino acid composition and auto-correlation functions based on amino acid indices.
  • Analyzed 472 amino acid indices, selecting four optimal ones to create five datasets (COMP, FASG, NISK, WOLS, KYTJ).

    • Main Results:

    • SVM achieved high accuracies (78.5-87.5%) across different datasets in jackknife tests.
    • SVM performance was significantly higher (13-20%) than the covariant discriminant algorithm.
    • The developed methods outperformed previous approaches in feature extraction for predicting quaternary structure.

    Conclusions:

    • Support Vector Machine (SVM) is effective for discriminating protein homodimers from non-homodimers using primary sequences.
    • The selected protein sequence descriptors accurately reflect quaternary structure information.
    • This automated classification approach provides a reliable tool for structural bioinformatics.