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 accuracy of protein secondary structure prediction using structural alignment.

Scott Montgomerie1, Shan Sundararaj, Warren J Gallin

  • 1Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2E8, Canada. montgomerie@shaw.ca

BMC Bioinformatics
|June 16, 2006
PubMed
Summary

This study introduces PROTEUS, a novel method for protein secondary structure prediction that integrates sequence and structure databases. PROTEUS achieves over 80% accuracy, significantly outperforming existing methods.

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

Fluxomics in precision nutrition: integrating dynamic metabolic profiling with multiomics.

Nutrition (Burbank, Los Angeles County, Calif.)·2026
Same author

Identification of High-Performing Blood Metabolite Biomarkers of Lung Cancer in a Chinese Population.

Phenomics (Cham, Switzerland)·2026
Same author

Automated, targeted, NMR spectral profiling of human breast milk.

Metabolomics : Official journal of the Metabolomic Society·2026
Same author

Serum metabolomic profiling reveals LysoPC/PC depletion as a potential biomarker to detect avian reoviral infection in neonatal broiler chickens.

Frontiers in cellular and infection microbiology·2026
Same author

The NMR Exchange Format (NEF): Specification and Applications.

bioRxiv : the preprint server for biology·2026
Same author

A scoring system for validity assessment of biomarkers of food intake.

Critical reviews in food science and nutrition·2026

Area of Science:

  • Computational Biology
  • Structural Bioinformatics
  • Machine Learning

Background:

  • Protein secondary structure prediction accuracy has reached ~75% (Q3).
  • Existing methods primarily rely on sequence-based comparisons.
  • The Protein Data Bank offers a vast resource for structure-based analysis.

Purpose of the Study:

  • To improve protein secondary structure prediction accuracy.
  • To develop a method incorporating structure database comparisons.
  • To enhance prediction by combining sequence and structure information.

Main Methods:

  • Developed a structure-based sequence alignment method.
  • Mapped known homologue structures onto query sequences.
  • Integrated structural alignment with sequence-based methods and a consensus system (jury-of-experts).

Related Experiment Videos

Main Results:

  • Achieved an average Q3 score of 81.3% on a sequence-unique test set.
  • Demonstrated a 4-5% improvement over existing methods.
  • Reached nearly 88% Q3 accuracy on non-sequence-unique test sets.

Conclusions:

  • Protein secondary structure prediction accuracy routinely exceeds 80% using integrated sequence and structure databases.
  • The PROTEUS program and web server are available for prediction tasks.
  • PROTEUS facilitates high-throughput and batch analyses via local downloads.