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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Removal of Soluble Nitrogen From Surimi Wash Water by Protein Recovery Using Lactic Acid for Safe Discharge.

Journal of food scienceĀ·2026
Same author

Selection process for recruitment in anaesthesiology: Time to revamp?

Indian journal of anaesthesiaĀ·2026
Same author

Beyond adoption: integrating TTAT and user-centric design for mHealth service continuance.

Journal of health organization and managementĀ·2026
Same author

Relationship Between Patient State Index and Richmond Agitation Sedation Scale for Sedation in Critically Ill Patients: An Observational Analytical Study.

Turkish journal of anaesthesiology and reanimationĀ·2026
Same author

Resistance-guided isolation and identification of antibiotic-resistant bacteria from bull semen: exploring alternatives to antibiotics in semen extenders.

Tropical animal health and productionĀ·2026
Same author

A multiscale interpretability framework for identifying actionable road network features to mitigate congestion in highly congested cities.

Scientific reportsĀ·2026

Related Experiment Video

Updated: Jun 9, 2025

Immunopeptidomics: Isolation of Mouse and Human MHC Class I- and II-Associated Peptides for Mass Spectrometry Analysis
09:32

Immunopeptidomics: Isolation of Mouse and Human MHC Class I- and II-Associated Peptides for Mass Spectrometry Analysis

Published on: October 15, 2021

11.7K

HLA-DR4Pred2: An improved method for predicting HLA-DRB1*04:01 binders.

Sumeet Patiyal1, Anjali Dhall1, Nishant Kumar1

  • 1Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi 110020, India.

Methods (San Diego, Calif.)
|October 21, 2024
PubMed
Summary

HLA-DR4Pred2 accurately predicts HLA-DRB1*04:01 binders using a large dataset and machine learning. This tool aids in developing immunotherapies and vaccines for associated diseases like COVID-19.

Keywords:
Antigen bindersBLAST searchHLA-DRB1*04:01ImmunotherapyMachine LearningPrediction Method

More Related Videos

Personalized Peptide Arrays for Detection of HLA Alloantibodies in Organ Transplantation
08:07

Personalized Peptide Arrays for Detection of HLA Alloantibodies in Organ Transplantation

Published on: September 6, 2017

10.1K
A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes
07:59

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

Published on: March 25, 2014

14.9K

Related Experiment Videos

Last Updated: Jun 9, 2025

Immunopeptidomics: Isolation of Mouse and Human MHC Class I- and II-Associated Peptides for Mass Spectrometry Analysis
09:32

Immunopeptidomics: Isolation of Mouse and Human MHC Class I- and II-Associated Peptides for Mass Spectrometry Analysis

Published on: October 15, 2021

11.7K
Personalized Peptide Arrays for Detection of HLA Alloantibodies in Organ Transplantation
08:07

Personalized Peptide Arrays for Detection of HLA Alloantibodies in Organ Transplantation

Published on: September 6, 2017

10.1K
A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes
07:59

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

Published on: March 25, 2014

14.9K

Area of Science:

  • Immunoinformatics
  • Computational Biology
  • Machine Learning in Immunology

Background:

  • The HLA-DRB1*04:01 allele is implicated in various diseases, including autoimmune disorders and COVID-19.
  • Accurate prediction of peptide binding to HLA-DRB1*04:01 is crucial for developing targeted immunotherapies and vaccines.
  • Existing prediction methods are often limited by small training datasets, impacting their predictive power.

Purpose of the Study:

  • To develop an improved computational tool, HLA-DR4Pred2, for predicting HLA-DRB1*04:01 binding peptides.
  • To leverage a significantly larger dataset compared to previous methods for enhanced model training.
  • To provide a user-friendly tool for researchers to predict, design, and virtually scan HLA-DRB1*04:01 binding peptides.

Main Methods:

  • Development of HLA-DR4Pred2 using a large dataset of 12,676 binders and an equal number of non-binders.
  • Training and optimization using five-fold cross-validation on 80% of the data, with evaluation on the remaining 20%.
  • Application of various machine learning techniques, including composition and binary profile features, with performance evaluation using AUROC.

Main Results:

  • The HLA-DR4Pred2 model achieved a maximum AUROC of 0.90 using composition features and 0.87 using binary profile features.
  • Combining composition-based models with BLAST search improved AUROC to 0.93.
  • Models trained on a realistic dataset (12,676 binders, 86,300 non-binders) reached a maximum AUROC of 0.99.
  • The proposed method demonstrated superior performance compared to existing methods on an independent dataset.

Conclusions:

  • HLA-DR4Pred2 significantly advances the prediction of HLA-DRB1*04:01 binding peptides, outperforming previous methods.
  • The developed tool and webserver facilitate the design and virtual screening of peptides for immunotherapy and vaccine development.
  • A publicly available Python package enhances accessibility for the research community.