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

Bayesian segmentation of protein secondary structure.

S C Schmidler1, J S Liu, D L Brutlag

  • 1Section on Medical Informatics, Stanford University School of Medicine, CA 94305, USA. Schmidler@SMI.stanford.edu

Journal of Computational Biology : a Journal of Computational Molecular Cell Biology
|July 13, 2000
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

[Current situation of surgical treatment of gallbladder polyps and some problems that should be paid attention to].

Zhonghua yi xue za zhi·2024
Same author

Information dissemination evolution under group feedback.

Chaos (Woodbury, N.Y.)·2023
Same author

A tera-electron volt afterglow from a narrow jet in an extremely bright gamma-ray burst.

Science (New York, N.Y.)·2023
Same author

[Burned-out testicular germ cell tumors: a clinicopathological analysis of three cases].

Zhonghua bing li xue za zhi = Chinese journal of pathology·2023
Same author

Constraints on Heavy Decaying Dark Matter from 570 Days of LHAASO Observations.

Physical review letters·2023
Same author

Spontaneous Ferromagnetism Induced Topological Transition in EuB_{6}.

Physical review letters·2022

This study introduces a novel Bayesian method for protein secondary structure prediction using structural segments. It achieves high accuracy by modeling protein structure relationships and improving predictions over traditional sliding window approaches.

Area of Science:

  • Computational Biology
  • Structural Bioinformatics
  • Biophysics

Background:

  • Traditional protein secondary structure prediction methods rely on local residue windows.
  • These methods have limitations in capturing complex protein structure relationships.

Purpose of the Study:

  • To develop a novel probabilistic model for protein secondary structure prediction.
  • To improve prediction accuracy by utilizing structural segments and Bayesian inference.

Main Methods:

  • Developed a probabilistic model based on structural segments (alpha-helices, beta-strands).
  • Formulated prediction as a Bayesian inference problem, incorporating structural features.
  • Employed dynamic programming for efficient calculation of posterior probabilities.

Related Experiment Videos

Main Results:

  • The proposed model achieved prediction accuracies comparable to the best existing methods.
  • Marginal posterior modes significantly improved predictive accuracy over optimal segmentation.
  • Provided reliable estimates of prediction uncertainty at each sequence position.

Conclusions:

  • The novel Bayesian approach offers a powerful framework for protein secondary structure prediction.
  • Explicit modeling of structural segments and their properties enhances accuracy.
  • Future work can extend the framework to include nonlocal interactions for further improvement.