Benchmarking antibody modeling tools across structure prediction, docking, and paratope–epitope interface analysis
Bioinformatics Advances · 07.01.2026 · 6 (1)
DOI: 10.1093/bioadv/vbag223 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics Advances, online erschienen am 11.08.2026. Verfasst von Zeyuan Yu und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, Anhui 230026, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
Motivation Computational antibody engineering requires reliable prediction of antibody variable-fragment structures, antigen–antibody complexes, and binding interfaces. However, publicly available tools for these tasks have rarely been compared across the complete workflow under a controlled and statistically grounded design. Results We evaluated ImmuneBuilder, IgFold, AlphaFold3, GRAMM, and dyMEAN on 50 non-redundant humanized antibody–antigen complexes using multiple retained predictions and paired statistical testing. All three antibody structure predictors were accurate, with AlphaFold3 performing best overall and for the third complementarity-determining region of the heavy chain. AlphaFold3 also substantially outperformed GRAMM and dyMEAN in complex prediction, producing medium- or high-quality binding interfaces for 46% of the complexes, although overall interface accuracy remained limited. When docking was reliable, AlphaFold3 accurately recovered epitope and paratope residues, salt bridges, and non-bonded contacts, but reproduced hydrogen bonds and fine-grained contact strengths less consistently. These findings provide practical guidance for selecting tools across antibody-modeling workflows and identify persistent limitations in fine-grained interface prediction. Availability and implementation Data, structural predictions, evaluation results, and analysis code are available from Zenodo under record 20710876.
Autor:innen und Institutionen
- School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, Anhui 230026, China.
- College of Biotechnology, Jiangsu University of Science and Technology, Zhenjiang, Jiangsu 212100, China.
- School of Pharmacy, Qingdao University, Qingdao, Shandong 266071, China.
- State Key Laboratory of National Security Specially Needed Medicines, Beijing 100000, China.
ORCID-Profile: Zeyuan Yu
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Yu, Z., Wu, J., Ning, Z., Qiao, C., Wang, J., Li, X., Liu, C., Chen, G., Feng, J., & Yu, J. (2026). Benchmarking antibody modeling tools across structure prediction, docking, and paratope–epitope interface analysis. Bioinformatics Advances, 6(1). https://doi.org/10.1093/bioadv/vbag223
Vancouver
Yu Z, Wu J, Ning Z, Qiao C, Wang J, Li X, et al. Benchmarking antibody modeling tools across structure prediction, docking, and paratope–epitope interface analysis. Bioinformatics Advances. 2026;6(1). doi:10.1093/bioadv/vbag223
BibTeX
@article{Yu2026,
author = {Yu, Zeyuan and Wu, Jilei and Ning, Ziyao and Qiao, Chunxia and Wang, Jing and Li, Xinying and Liu, Chenghua and Chen, Guojiang and Feng, Jiannan and Yu, Jijun},
title = {Benchmarking antibody modeling tools across structure prediction, docking, and paratope–epitope interface analysis},
journal = {Bioinformatics Advances},
year = {2026},
volume = {6},
number = {1},
doi = {10.1093/bioadv/vbag223}
}
EUVIMED