EUVIMEDObjevte EUVIMED
Open access

HAIRpred : Prediction of human antibody interacting residues in an antigen from its primary structure

Ruchir Sahni iD, Nishant Kumar iD, Gajendra P S Raghava iD

Protein Science · 2025

DOI: 10.1002/pro.70212 ↗

At a glance

Journal article in Protein Science, 2025. Written by Ruchir Sahni and 2 co-authors. Institution: Department of Computational Biology, Indraprastha Institute of Information Technology Delhi, New Delhi, India. Major MEDLINE topics: Epitopes, B-Lymphocyte, Software, Antigens, Antigen-Antibody Complex. Cited 3 times so far (Crossref); 48 references. The full text is freely available in PubMed Central. Funded by: Department of Biotechnology, Ministry of Science and Technology, India.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

In the past, several methods have been developed for predicting conformational B‐cell epitopes in antigens that are not specific to any host. Our primary analysis of antibody–antigen complexes indicated a need to develop host‐specific B‐cell epitopes. In this study, we present a novel approach to predict conformational B‐cell epitopes specific to human hosts by focusing on human antibody interacting residues in antigens. We trained, tested, and evaluated our models on 277 complexes of human antibody–antigen complexes. Initially, we employed machine learning models based on the one hot encoding sequence profile of antigens, achieving a maximum area under the receiver operating characteristic curve (AUROC) of 0.61. The performance of the model improved significantly with the AUROC increasing from 0.61 to 0.67 when evolutionary profiles were used instead of one hot encoding profile. Models developed using embeddings from fine‐tuned protein language models reached an AUROC of 0.61. Additionally, models utilizing predicted surface relative solvent accessibility achieved an AUROC of 0.67. Our ensemble model, which combined relative surface accessibility with evolutionary profiles, achieved the highest precision with an AUROC of 0.72. All models in this study were trained using fivefold cross‐validation on a training dataset and evaluated on an independent dataset not used for training or validation. Our method outperforms existing approaches on the independent dataset. Furthermore, we used the SHAP eXplainable AI (XAI) method to interpret the importance of elements in features contributing to the predictions made by our models. To support the scientific community, we have developed a standalone software and web server, HAIRpred, for predicting human antibody interacting residues in proteins ( https://webs.iiitd.edu.in/raghava/hairpred/ ).

Subjects

MeSH terms (MEDLINE)

Epitopes, B-LymphocyteSoftwareAntigensAntigen-Antibody ComplexHumansMachine LearningModels, Molecular

Author keywords

B‐cell epitopesantibody interacting residuesantibody–antigen interactionmachine learningprotein language models

Substances

Epitopes, B-LymphocyteAntigensAntigen-Antibody Complex

Authors and institutions

  • Department of Computational Biology, Indraprastha Institute of Information Technology Delhi, New Delhi, India.
  • Indian Institute of Science Education and Research (IISER) Pune, Pune, India.

ORCID profiles: Ruchir Sahni, Nishant Kumar, Gajendra P S Raghava

Funding

  • Department of Biotechnology, Ministry of Science and Technology, India

Cite

APA

Sahni, R., Kumar, N., & Raghava, G. P. S. (2025). HAIRpred : Prediction of human antibody interacting residues in an antigen from its primary structure. Protein Science. https://doi.org/10.1002/pro.70212

Vancouver

Sahni R, Kumar N, Raghava GPS. HAIRpred : Prediction of human antibody interacting residues in an antigen from its primary structure. Protein Science. 2025. doi:10.1002/pro.70212

BibTeX
@article{Sahni2025,
  author = {Sahni, Ruchir and Kumar, Nishant and Raghava, Gajendra P S},
  title = {HAIRpred : Prediction of human antibody interacting residues in an antigen from its primary structure},
  journal = {Protein Science},
  year = {2025},
  doi = {10.1002/pro.70212}
}
Start for free →