EUVIMEDOpdag EUVIMED
Open access · CC BY-NC 4.0

Pocket restraints guided by B‐cell epitope prediction improve Chai‐1 antibody–antigen structure modeling

Joakim Nøddeskov Clifford iD, Morten Nielsen

Protein Science · 2026

DOI: 10.1002/pro.70730 ↗

At a glance

Journal article in Protein Science, 2026. Written by Joakim Nøddeskov Clifford and 1 co-authors. Institution: Department of Health Technology, Technical University of Denmark, Kongens Lyngby, Denmark. Major MEDLINE topics: Epitopes, B-Lymphocyte, Antigen-Antibody Complex, Software. Cited 2 times so far (Crossref); 38 references. The full text is freely available (open access, CC BY-NC 4.0). Funded by: NIAID NIH HHS, National Institute of Allergy and Infectious Diseases.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

The accurate prediction of antibody–antigen (AbAg) complexes is a key challenge for computational immunology, with applications in therapeutic antibody design and diagnostics. Current deep learning methods have the potential to generate high‐confidence AbAg structures. However, these methods often fail to predict the correct AbAg structure, placing the antibody incorrectly on the antigen and converge on repeatedly predicting the same redundant binding mode. Here, we present BepiPocket and DiscoPocket, two simple approaches that integrate B‐cell epitope prediction tools to guide antibody‐epitope restraints during Chai‐1 structure prediction. On a dataset of 1628 AbAg complexes, we demonstrate that using the sequence‐based predictor BepiPred‐3.0 (BepiPocket) and the structure‐based predictor DiscoTope‐3.0 (DiscoPocket) substantially improved both the accuracy and diversity of predicted AbAg complexes compared to standard Chai‐1 modeling with random seed variation. The software for both BepiPocket and DiscoPocket algorithms is freely available at https://github.com/mnielLab/BepiPocket .

Subjects

MeSH terms (MEDLINE)

Epitopes, B-LymphocyteAntigen-Antibody ComplexSoftwareModels, MolecularImmunoinformaticsHumansPrediction Algorithms

Author keywords

B‐cell epitope predictionantibodiesantigensdeep learningmachine learningprotein structure prediction

Substances

Epitopes, B-LymphocyteAntigen-Antibody Complex

Authors and institutions

  • Department of Health Technology, Technical University of Denmark, Kongens Lyngby, Denmark.

ORCID profiles: Joakim Nøddeskov Clifford

Funding

  • NIAID NIH HHS
  • National Institute of Allergy and Infectious Diseases

Cite

APA

Clifford, J. N., & Nielsen, M. (2026). Pocket restraints guided by B‐cell epitope prediction improve Chai‐1 antibody–antigen structure modeling. Protein Science. https://doi.org/10.1002/pro.70730

Vancouver

Clifford JN, Nielsen M. Pocket restraints guided by B‐cell epitope prediction improve Chai‐1 antibody–antigen structure modeling. Protein Science. 2026. doi:10.1002/pro.70730

BibTeX
@article{Clifford2026,
  author = {Clifford, Joakim Nøddeskov and Nielsen, Morten},
  title = {Pocket restraints guided by B‐cell epitope prediction improve Chai‐1 antibody–antigen structure modeling},
  journal = {Protein Science},
  year = {2026},
  doi = {10.1002/pro.70730}
}
Start for free →