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 peptides binding to MHC class II molecules using multi-objective evolutionary algorithms.

Menaka Rajapakse1, Bertil Schmidt, Lin Feng

  • 1Institute for Infocomm Research, 21 Heng Mui Keng Terrace, 119613 Singapore. menaka@i2r.a-star.edu.sg

BMC Bioinformatics
|November 23, 2007
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

Accelign: a GPU-based library for accelerating pairwise sequence alignment.

BMC bioinformatics·2026
Same author

gpuPairHMM: High-Speed Pair-HMM Forward Algorithm for DNA Variant Calling on GPUs.

IEEE transactions on computational biology and bioinformatics·2026
Same author

RMapAlign3N: fast mapping of 3N-Reads.

Bioinformatics advances·2025
Same author

GPU-accelerated homology search with MMseqs2.

Nature methods·2025
Same author

Corrigendum to Studying Privacy Aspects of Learned Knowledge Bases in the Context of Synthetic and Medical Data.

Studies in health technology and informatics·2025
Same author

RabbitTrim: An Efficient and Versatile Trimmer on Multi-Core Platforms.

IEEE transactions on computational biology and bioinformatics·2025
Same journal

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026
Same journal

NAP: an open source pipeline for cross-domain microbiome profiling using Nanopore sequencing-derived amplicon data.

BMC bioinformatics·2026
Same journal

SurvGME: an R package for survival analysis with graphical and measurement error models.

BMC bioinformatics·2026
Same journal

SimMapNet: a Bayesian framework for gene regulatory network inference using gene ontology similarities as external hint.

BMC bioinformatics·2026
Same journal

Dual channel drug-drug interactions extraction based on cross attention.

BMC bioinformatics·2026
Same journal

FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron-sulfur proteins.

BMC bioinformatics·2026
See all related articles

Predicting peptide binding to Major Histocompatibility Complex (MHC) class II molecules is vital for vaccine development. New multi-objective evolutionary algorithms (MOEA) improve prediction accuracy for MHC class II binding peptides, outperforming previous methods.

Area of Science:

  • Immunoinformatics
  • Computational Biology
  • Molecular Immunology

Background:

  • Peptide binding to Major Histocompatibility Complex (MHC) class II molecules is critical for initiating and regulating immune responses.
  • Predicting these peptide-MHC interactions aids in identifying potential vaccine candidates.
  • Challenges in prediction arise from variable peptide lengths, core binding site locations, and promiscuous MHC molecules binding numerous low-affinity peptides.

Purpose of the Study:

  • To develop and evaluate two novel multi-objective evolutionary algorithms (MOEA) for predicting peptides that bind to MHC class II molecules.
  • To address the complexities of predicting binding motifs for promiscuous MHC class II molecules like I-Ag7.
  • To compare the performance of the proposed MOEA approaches against existing methods.

Related Experiment Videos

Main Methods:

  • Two MOEA-based approaches were developed: one for self-discovery of motifs using binder and non-binder data, and another for guided-discovery incorporating experimentally determined motifs.
  • The methods were applied to predict peptides binding to the MHC class II I-Ag7 molecule.
  • Cross-validation and validation on publicly available benchmark datasets (HLA-DRB1*0401 and mixed mouse/HLA alleles) were performed.

Main Results:

  • The proposed MOEA methods demonstrated superior generalization abilities and accuracy compared to earlier approaches for the I-Ag7 molecule.
  • Validation on benchmark datasets showed that the methods outperformed previous techniques on most datasets.
  • The results indicate the suitability of the proposed methods for predicting peptides binding to various MHC class II molecules.

Conclusions:

  • Two MOEA-based algorithms, one for self-discovery and one for guided-discovery of motifs, were successfully developed for predicting binding peptides to the I-Ag7 molecule.
  • The MOEA algorithms exhibited improved performance over existing methods for predicting binding sites on I-Ag7 and other MHC class II alleles.
  • The developed methods show broad applicability for identifying binding motifs across a wide range of MHC class II alleles.