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 Bayesian network model for protein fold and remote homologue recognition.

A Raval1, Z Ghahramani, D L Wild

  • 1Keck Graduate Institute of Applied Life Sciences, 535 Watson Drive, Claremont, CA 91711, USA.

Bioinformatics (Oxford, England)
|June 21, 2002
PubMed
Summary

This study introduces a novel Bayesian network for protein classification, outperforming hidden Markov models. It integrates amino acid sequence, secondary structure, and residue accessibility for improved protein fold and superfamily identification.

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

Real-world use of PSMA imaging in metastatic castration-sensitive prostate cancer: Findings from the CAPRI-3 registry.

European journal of nuclear medicine and molecular imaging·2026
Same author

A study on subcutaneous infection model of colibacillosis in broilers: Selected immunological and hematological aspects.

Veterinary and animal science·2025
Same author

Patient practices regarding topical drugs and a 'nudge' to prevent topical steroid abuse.

Clinical and experimental dermatology·2020
Same author

Outcome Determinants of Patients with Traumatic Pelvic Fractures: A Cohort Study in a Level I Trauma Center in Southern Iran.

Malaysian orthopaedic journal·2018
Same author

Fda Cdx Category Medication Use During Pregnancy in the United States.

Value in health : the journal of the International Society for Pharmacoeconomics and Outcomes Research·2016
Same author

Measurement of the relative prompt production rate of <i>χ</i><sub>c2</sub> and <i>χ</i><sub>c1</sub> in pp collisions at [Formula: see text].

The European physical journal. C, Particles and fields·2015

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Structural Biology

Background:

  • Bayesian networks offer a probabilistic graphical framework, encompassing hidden Markov models.
  • Hidden Markov models show promise for protein fold and superfamily classification using sequence or structure data.

Purpose of the Study:

  • To develop and evaluate a novel Bayesian network for simultaneous learning of protein sequence, secondary structure, and residue accessibility.
  • To improve protein superfamily classification accuracy compared to existing methods.

Main Methods:

  • Implemented a Bayesian network model incorporating amino acid sequence, secondary structure, and residue accessibility.
  • Utilized a confusion matrix to account for errors in predicted secondary structure.
  • Trained and validated the model using data from the Structural Classification of Proteins (SCOP) database.

Related Experiment Videos

Main Results:

  • The developed Bayesian network achieved superior performance in classifying proteins of known structural superfamily.
  • Cross-validation demonstrated better accuracy compared to hidden Markov models trained solely on amino acid sequences.
  • The model effectively integrates multiple data types for enhanced classification.

Conclusions:

  • The novel Bayesian network approach provides a more accurate method for protein superfamily classification.
  • Simultaneous learning of diverse protein features enhances classification efficacy.
  • This framework holds potential for advancing protein structure prediction and analysis.