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

Improved protein secondary structure prediction using support vector machine with a new encoding scheme and an

Hae-Jin Hu1, Yi Pan, Robert Harrison

  • 1Department of Computer Science, Georgia State University, Atlanta, GA 30303-4110, USA. jpark1808@earthlink.net

IEEE Transactions on Nanobioscience
|January 6, 2005
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

Post-Acute COVID Among California Workers' Compensation Claims Filed in 2020-2022.

Journal of occupational and environmental medicine·2026
Same author

Home improvement programs and deadly countertops: the need to protect workers.

Annals of the American Thoracic Society·2026
Same author

Porphyrin-based nanotechnology: a minimally invasive approach for drug delivery and cholesteatoma treatment.

Frontiers in surgery·2025
Same author

Respiratory injuries among California career firefighters, 2000-2019.

Annals of the American Thoracic Society·2025
Same author

WOEMA Position Paper and Call-to-Action: California Needs More Physicians Specializing in Occupational and Environmental Medicine (OEM).

Journal of occupational and environmental medicine·2025
Same author

Thallium Exposure Secondary to Commercial Kale Chip Consumption: California Case Highlights Opportunities for Improved Surveillance and Toxicological Understanding.

International journal of environmental research and public health·2025

This study enhances protein secondary structure prediction using Support Vector Machines (SVM) and novel encoding schemes. The optimized SVM approach achieved a 78.8% Q3 accuracy, surpassing existing methods.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning

Background:

  • Protein secondary structure prediction is crucial for understanding protein function.
  • Neural networks and Support Vector Machines (SVM) are current leading methods.
  • SVMs are effective for pattern recognition tasks.

Purpose of the Study:

  • To improve protein secondary structure prediction accuracy using SVM.
  • To explore and optimize various encoding schemes for SVM.
  • To develop and evaluate a novel tertiary classifier.

Main Methods:

  • Utilized Support Vector Machines (SVM) for secondary structure prediction.
  • Applied and optimized orthogonal matrix, hydrophobicity matrix, and BLOSUM62 substitution matrices.

Related Experiment Videos

  • Determined optimal window length for six SVM binary classifiers.
  • Introduced a new tertiary classifier combining one-versus-one binary classifiers.

    • Main Results:

    • Achieved a 2% accuracy increase with new encoding schemes compared to classical orthogonal matrices.
    • The novel tertiary classifier reached a Q3 prediction accuracy of 78.8%.
    • Outperformed the best previously reported results in the literature.

    Conclusions:

    • Optimized SVM with novel encoding schemes significantly improves secondary structure prediction.
    • The proposed tertiary classifier offers superior performance over existing methods.
    • This approach advances the field of bioinformatics and protein structure analysis.