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 linear B-cell epitopes using string kernels.

Yasser El-Manzalawy1, Drena Dobbs, Vasant Honavar

  • 1Artificial Intelligence Laboratory, Iowa State University, Ames, IA 50010, USA. yasser@iastate.edu

Journal of Molecular Recognition : JMR
|May 23, 2008
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

EPR26-162: Distinct Clinical Profiles of Younger and Older Patients at Risk for Non-Small Cell Lung Cancer.

Journal of the National Comprehensive Cancer Network : JNCCN·2026
Same author

EPR26-162: Distinct Clinical Profiles of Younger and Older Patients at Risk for Non-Small Cell Lung Cancer.

Journal of the National Comprehensive Cancer Network : JNCCN·2026
Same author

Machine learning identifies clinical and sociodemographic factors contributing to post-COVID hospitalization and cardiovascular risk in patients with peripheral artery disease.

Scientific reports·2025
Same author

DGX: Uncovering General Behavior of Deep Graph Models With Model-Level Explanation.

IEEE transactions on computational biology and bioinformatics·2025
Same author

Female sex is associated with short-term mortality in coronary artery bypass grafting patients: A propensity-matched analysis.

Heliyon·2025
Same author

Atrial appendage closure is associated with increased risk for postoperative atrial fibrillation.

Journal of cardiothoracic surgery·2024
Same journal

Temperature Dependent Motions of N-Terminal Loop in PD-1 Determine the Affinity Towards Nivolumab.

Journal of molecular recognition : JMR·2026
Same journal

AFM Force Volume for Extracellular Vesicle Detection and Membrane Blebbing Analysis Through Mechanical Signature Mapping.

Journal of molecular recognition : JMR·2026
Same journal

Induced Circular Dichroism From the Binding of Achiral Bivalent Ligands to Transthyretin.

Journal of molecular recognition : JMR·2026
Same journal

Design of Multi-Epitope DIVA-Compatible Vaccine Candidate Against Canine Parvovirus 2.

Journal of molecular recognition : JMR·2026
Same journal

Artificial Intelligence Clustering Approach for Force Mapping Analysis of Polyacrylic Acid (PAA)/Polyethylene Oxide (PEO) Polymer Brushes for Biosensor Applications.

Journal of molecular recognition : JMR·2026
Same journal

RPA Combined With CRISPR/Cas12a for Rapid and Ultrasensitive Detection Dual-Gene of Methicillin-Resistant Staphylococcus aureus (MRSA).

Journal of molecular recognition : JMR·2026
See all related articles

We developed BCPred, a novel computational method for predicting linear B-cell epitopes. BCPred, utilizing a subsequence kernel, demonstrates superior performance over existing Support Vector Machine classifiers and other prediction tools.

Area of Science:

  • Immunoinformatics
  • Computational Biology
  • Vaccine Development

Background:

  • Accurate identification of B-cell epitopes is crucial for vaccine design, diagnostics, and antibody production.
  • Computational tools for predicting linear B-cell epitopes are highly sought after.

Purpose of the Study:

  • To evaluate Support Vector Machine (SVM) classifiers for predicting linear B-cell epitopes.
  • To propose a novel and improved computational method for B-cell epitope prediction.

Main Methods:

  • Evaluated SVM classifiers with five kernel methods using a homology-reduced dataset.
  • Developed BCPred using a subsequence kernel for B-cell epitope prediction.
  • Compared BCPred with AAP and ABCPred using unique B-cell epitope datasets.

Related Experiment Videos

Main Results:

  • BCPred achieved a superior predictive performance (AUC = 0.758) compared to 11 SVM classifiers and AAP (AUC = 0.7).
  • Analysis highlighted the importance of using homology-reduced datasets to avoid overestimating method performance.
  • BCPred demonstrated robust performance in predicting linear B-cell epitopes.

Conclusions:

  • BCPred is a novel and effective method for predicting linear B-cell epitopes.
  • Homology-reduced datasets are essential for reliable comparison of B-cell epitope prediction methods.
  • The BCPREDS web server provides public access to the developed method and datasets.