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

A simple and fast secondary structure prediction method using hidden neural networks.

Kuang Lin1, Victor A Simossis, Willam R Taylor

  • 1Division of Mathematical Biology, The National Institute for Medical Research The Ridgeway, Mill Hill, London NW7 1AA, UK. kxlin@nimr.mrc.ac.uk

Bioinformatics (Oxford, England)
|September 21, 2004
PubMed
Summary

We developed YASPIN, a novel protein secondary structure prediction method. YASPIN achieves comparable accuracy to top methods and excels in predicting strand structures.

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

An Accurate Genetic Colocalisation Method for the HLA Locus.

HLA·2026
Same author

Genetics of skeletal proportions across two different populations.

American journal of human genetics·2026
Same author

Multi-ancestry polygenic risk scores for the prediction of type 2 diabetes and complications in diverse ancestries.

The lancet. Diabetes & endocrinology·2026
Same author

Genetics of skeletal proportions across two different populations.

American journal of human genetics·2026
Same author

Phenome-Wide Associations of Polygenic Scores for Schizophrenia and Major Depression in 100,000 Chinese Adults.

Biological psychiatry global open science·2026
Same author

Family-GWAS reveals effects of environment and mating on genetic associations.

medRxiv : the preprint server for health sciences·2025

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Structural Bioinformatics

Background:

  • Accurate protein secondary structure prediction is crucial for understanding protein function and structure.
  • Current state-of-the-art methods often involve complex pipelines or multiple models.

Purpose of the Study:

  • To introduce YASPIN, a novel method for predicting protein secondary structure.
  • To evaluate YASPIN's performance against existing leading prediction tools.

Main Methods:

  • YASPIN employs a single neural network for 7-state local structure prediction.
  • A hidden Markov model is utilized to optimize the neural network's output.
  • The method was benchmarked against PHDpsi, PROFsec, SSPro2, JNET, and PSIPRED.

Related Experiment Videos

Main Results:

  • YASPIN demonstrates overall prediction accuracy comparable to top-performing methods on the EVA5 dataset.
  • The method achieves high accuracy in Q3 and SOV scores, particularly for strand prediction.
  • Performance was assessed using Q3, SOV, and Matthew's correlation coefficients.

Conclusions:

  • YASPIN offers a competitive and efficient approach to protein secondary structure prediction.
  • The method provides valuable information, especially for predicting strand elements.
  • YASPIN is publicly available online for researchers.