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

Predicting protein subcellular locations using hierarchical ensemble of Bayesian classifiers based on Markov chains.

Alla Bulashevska1, Roland Eils

  • 1Theoretical Bioinformatics Department, German Cancer Research Center, Im Neuenheimer Feld 280, 69120 Heidelberg, Germany. A.Bulashevska@dkfz.de

BMC Bioinformatics
|June 16, 2006
PubMed
Summary

A new method, HensBC, accurately predicts protein subcellular location using only amino acid sequences. This recursive ensemble classifier improves prediction accuracy, especially for imbalanced datasets.

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

Small language models in medicine.

Nature biomedical engineering·2026
Same author

Large language models are powerful electronic health record encoders.

NPJ digital medicine·2026
Same author

Rethinking healthcare data interoperability in the age of large language models.

Med (New York, N.Y.)·2026
Same author

CLUES A Comprehensive Workflow for Integrating Geospatial Data in Biomedical Research.

Nature communications·2026
Same author

Single-Cell and Spatial Omics: Methods and Applications.

MedComm·2026
Same author

BRAF<sup>V600E</sup> patient derived colon cancer organoids identify biomarkers of response to EGFR and BRAF inhibition and replicate clinical data.

Journal of experimental & clinical cancer research : CR·2026

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Proteomics

Background:

  • Protein subcellular location is crucial for its function.
  • Predicting location from amino acid sequence alone is valuable.
  • Existing methods require further accuracy improvements.

Purpose of the Study:

  • Develop a novel method for predicting protein subcellular location.
  • Enhance prediction accuracy using only primary sequence information.

Main Methods:

  • Introduced HensBC, a recursive algorithm.
  • Utilized a hierarchical ensemble of Bayesian classifiers.
  • Employed Markov chain models for classification.

Main Results:

  • HensBC demonstrated high accuracy in predicting subcellular location.

Related Experiment Videos

  • The method improved predictions for classes with limited training data.
  • Effective for imbalanced datasets.

    • Conclusions:

    • HensBC accurately predicts protein subcellular location from primary sequence.
    • The recursive ensemble methodology is effective for classifier learning.
    • Computationally efficient and competitive with existing methods.