PLMABFW: A deep learning framework for predicting Antibody–Antigen interactions using protein language model
Journal of Bioinformatics and Computational Biology · 2025
DOI: 10.1142/s0219720025500209 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Bioinformatics and Computational Biology, 2025. Verfasst von Yongbing Chen und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Technology, and Center of AI for Science, Northeast Normal University, Changchun, China. Hauptthemen laut MEDLINE: Deep Learning, SARS-CoV-2, Antibodies, Neutralizing, Antibodies, Viral. Die Arbeit nennt 26 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
The emergence of SARS-CoV-2 has highlighted the need for computational methods to identify neutralizing antibodies. Existing sequence-based tools for predicting antigen—antibody interactions struggle to effectively identify antibodies capable of neutralizing different variants due to high sequence similarity among SARS-CoV-2 strains and the similarity in the framework regions (FWRs) of antibodies. To address this challenge, particularly the issue of high sequence similarity among homologous antigens that impedes accurate prediction of antigen–antibody interactions, we developed a deep learning framework named PLMABFW. It differentiates homologous antigens using encoding techniques and network architecture design. It employs pre-trained protein language models ESM-2 for antigens and AntiBERTy for antibodies to encode sequences and capture additional features. The framework also incorporates both antigen features and their transposed versions to enhance antigen information capture. To validate the performance of PLMABFW, we collected a SARS-CoV-2 neutralization dataset. PLMABFW outperformed existing neutralizing antibody prediction tools (AbAgIntPre, DeepAAI) and docking tools (HDOCK, LSTM-PHV) in predicting neutralizing antibodies for homologous antigens. Furthermore, it effectively learned the interactions between the antibody’s CDR-H3 region and antigens via a partial masking strategy. The model code is available on GitHub for customization and adaptation to diverse research needs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Information Science and Technology, and Center of AI for Science, Northeast Normal University, Changchun, China.
- Changchun Veterinary Research Institute, Chinese Academy of Agricultural Sciences, State Key Laboratory of Pathogen and Biosecurity, Changchun, China.
- Key Laboratory of Jilin Province for Zoonosis Prevention and Control, Changchun, China.
- Department of Gastrointestinal Colorectal and Anal Surgery, China-Japan Union Hospital of Jilin University, Changchun, China.
ORCID-Profile: Yongbing Chen, Qianyi Jia, Xinyue Jia, Zhiguo Fu, Pingping Sun, Bo Li, Zilin Ren
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Chen, Y., Jia, Q., Jia, X., Fu, Z., Sun, P., Li, B., & Ren, Z. (2025). PLMABFW: A deep learning framework for predicting Antibody–Antigen interactions using protein language model. Journal of Bioinformatics and Computational Biology. https://doi.org/10.1142/s0219720025500209
Vancouver
Chen Y, Jia Q, Jia X, Fu Z, Sun P, Li B, et al. PLMABFW: A deep learning framework for predicting Antibody–Antigen interactions using protein language model. Journal of Bioinformatics and Computational Biology. 2025. doi:10.1142/s0219720025500209
BibTeX
@article{Chen2025,
author = {Chen, Yongbing and Jia, Qianyi and Jia, Xinyue and Fu, Zhiguo and Sun, Pingping and Li, Bo and Ren, Zilin},
title = {PLMABFW: A deep learning framework for predicting Antibody–Antigen interactions using protein language model},
journal = {Journal of Bioinformatics and Computational Biology},
year = {2025},
doi = {10.1142/s0219720025500209}
}
EUVIMED