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

Protein secondary structure prediction based on position-specific scoring matrices.

D T Jones1

  • 1Department of Biological Sciences, University of Warwick, Coventry, CV4 7AL, United Kingdom. jones@globin.bio.warwick.ac.uk

Journal of Molecular Biology
|September 24, 1999
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

Publisher Correction: Brain charts for the human lifespan.

Nature·2022
Same author

Brain charts for the human lifespan.

Nature·2022
Same author

Changes in Ventricular and Cortical Volumes following Shunt Placement in Patients with Idiopathic Normal Pressure Hydrocephalus.

AJNR. American journal of neuroradiology·2021
Same author

Studies on Clostridium acetobutylicum ginA promoters and antisense RNA.

Molecular microbiology·2017
Same author

Genomic profiling of Acute lymphoblastic leukemia in ataxia telangiectasia patients reveals tight link between ATM mutations and chromothripsis.

Leukemia·2017
Same author

A taxonomic index, with names of descriptive authorities of termite genera and species: an accompaniment to Biology of Termites: A Modern Synthesis (Bignell DE, Roisin Y, Lo N, Editors. 2011. Springer, Dordrecht. 576 pp.).

Journal of insect science (Online)·2014

A novel neural network method, PSIPRED, accurately predicts protein secondary structure. This protein structure prediction approach outperforms existing methods, achieving the highest published scores to date.

Area of Science:

  • Computational biology
  • Bioinformatics
  • Structural bioinformatics

Background:

  • Accurate prediction of protein secondary structure is crucial for understanding protein function and design.
  • Existing methods for protein secondary structure prediction have limitations in accuracy and scope.

Purpose of the Study:

  • To develop and evaluate a novel, highly accurate method for predicting protein secondary structure.
  • To benchmark the performance of the new method against established techniques.

Main Methods:

  • A two-stage neural network was employed, utilizing position-specific scoring matrices from PSI-BLAST.
  • The method, named PSIPRED, was rigorously tested using a dataset of 187 unique protein folds.
  • Three-way cross-validation was performed based on structural similarity to ensure robust evaluation.

Related Experiment Videos

Main Results:

  • PSIPRED achieved an average Q3 score between 76.5% and 78.3%, representing the highest published accuracy for secondary structure prediction.
  • The method demonstrated superior performance compared to other leading methods, including PHD, in benchmarking and CASP3 evaluations.
  • Blind testing during CASP3 confirmed the method's reliability and high predictive power.

Conclusions:

  • PSIPRED offers a significant advancement in protein secondary structure prediction accuracy.
  • The method's performance indicates its potential as a valuable tool in structural bioinformatics and protein design.
  • The high scores achieved suggest a reliable prediction capability for diverse protein structures.