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

Staged heterogeneity learning to identify conformational B-cell epitopes from antigen sequences.

Jing Ren1,2, Jiangning Song3,4, John Ellis5

  • 1Advanced Analytics Institute, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia.

BMC Genomics
|April 1, 2017
PubMed
Summary

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

NicheTrans: spatial-aware cross-omics translation.

Nature methods·2026
Same author

Causal effects of wildfire PM<sub>2.5</sub> on hospital costs and length of stay in Brazil.

Nature communications·2026
Same author

Comprehensive review and assessment of multi-species splicing variant prediction: task-specific deep learning models and genomic foundation models.

Briefings in bioinformatics·2026
Same author

Genetic contributors to postoperative delirium and their implications for dementia outcomes.

Anesthesiology·2026
Same author

Corrigendum to "Identification of a novel antimicrobial peptide Gp-AMP1 with broad-spectrum and exceptional stability from deep-sea mussel Gigantidas platifrons" [Food Chem. 501 (2026) 147576].

Food chemistry·2026
Same author

EvoRMD: integrating biological context and evolutionary RNA language models for interpretable prediction of RNA modifications.

Genome biology·2026

A novel staged heterogeneity learning method effectively identifies conformational B-cell epitopes from antigen sequences. This sequence-based approach significantly improves prediction accuracy and broadens applicability for vaccine development.

Area of Science:

  • Immunoinformatics
  • Computational Biology
  • Machine Learning

Background:

  • Identifying conformational B-cell epitopes is challenging due to the heterogeneity of antigen-antibody interactions across species and data sources.
  • Existing methods struggle with this heterogeneity, limiting their applicability and accuracy in epitope prediction.
  • This complexity confounds research efforts in understanding immune responses and developing targeted therapies.

Purpose of the Study:

  • To develop a widely applicable learning algorithm for identifying conformational B-cell epitopes.
  • To address the significant heterogeneity challenges in antigen-antibody interactions.
  • To improve the accuracy and transferability of epitope prediction models.

Main Methods:

  • Proposed a staged heterogeneity learning method to learn data characteristics and heterogeneity in phases.
Keywords:
B-cell epitopeConformational epitopeEpitope predictionSequence-basedStaged heterogeneity learning

Related Experiment Videos

  • Utilized computationally defined epitopes in the first stage to learn general epitope patterns.
  • Employed experimentally determined epitopes in the second stage to learn heterogeneous complementarity.
  • Developed an algorithm to cluster predicted antigenic residues into conformational B-cell epitopes.

    • Main Results:

    • The staged heterogeneity learning method demonstrated significantly improved transferability for handling heterogeneous data.
    • The sequence-based method achieved outstanding performance, approximately doubling the accuracy of existing sequence-based and structure-based predictors.
    • The model was successfully tested on datasets with both computationally and experimentally defined epitopes.

    Conclusions:

    • The proposed sequence-based method offers broader applications by relying solely on antigen sequence information.
    • This approach has strong potential for real-world applications, particularly in vaccine development.
    • The method effectively overcomes heterogeneity challenges, leading to superior epitope prediction performance.