ABRefine: An Accurate Antibody Structure Refinement Method by Equivariant Graph Transformer with Rigid Body Constraint
Journal of Medicinal Chemistry · 11.06.2026 · 69 (11) · 12925-12940
DOI: 10.1021/acs.jmedchem.5c03435 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Medicinal Chemistry, online erschienen am 19.05.2026. Verfasst von Jinxian Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Artificial Intelligence, Fudan University, 2005 Songhu RD, 200438 Shanghai, China. Hauptthemen laut MEDLINE: Antibodies, Single-Domain Antibodies. Die Arbeit nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate antibody structural modeling is essential for therapeutic antibody development. However, even advanced artificial intelligence models such as AlphaFold2/3 struggle to precisely predict antibody structures due to the high flexibility of the complementarity-determining regions. Structure refinement methods can therefore play a critical role in improving the quality of predicted antibody conformations. In this paper, we present ABRefine, an end-to-end antibody structure refinement framework based on an equivariant graph transformer with rigid-body constraints. ABRefine directly predicts atomic coordinate shifts from initial structures while enforcing physically meaningful rigid-body consistency, enabling rapid and accurate refinement without conformational sampling. To our knowledge, ABRefine is also the first dedicated refinement method for nanobodies. Comprehensive evaluations on multiple antibody and nanobody benchmarks show that ABRefine outperforms existing refinement methods in both accuracy and efficiency, and notably enhances the structural quality of AlphaFold3 predictions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- College of Computer Science and Artificial Intelligence, Fudan University, 2005 Songhu RD, 200438 Shanghai, China.
- Lingang Laboratory, 2380 Hechuan RD, 201100 Shanghai, China.
- Changchun GeneScience Pharmaceuticals Co., Ltd., 130000 Changchun, China.
- Global Institute of Future Technology, Shanghai Jiao Tong University, 800 Dongchuan, 200240 Shanghai, China.
- School of Computer Science and Technology, Tongji University, 4800 Cao'an RD, 200618 Shanghai, China.
ORCID-Profile: Jinxian Wang
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Wang, J., Zhang, Z., Jing, X., Zheng, S., Guan, J., & Zhou, S. (2026). ABRefine: An Accurate Antibody Structure Refinement Method by Equivariant Graph Transformer with Rigid Body Constraint. Journal of Medicinal Chemistry, 69(11), 12925-12940. https://doi.org/10.1021/acs.jmedchem.5c03435
Vancouver
Wang J, Zhang Z, Jing X, Zheng S, Guan J, Zhou S. ABRefine: An Accurate Antibody Structure Refinement Method by Equivariant Graph Transformer with Rigid Body Constraint. Journal of Medicinal Chemistry. 2026;69(11):12925-12940. doi:10.1021/acs.jmedchem.5c03435
BibTeX
@article{Wang2026,
author = {Wang, Jinxian and Zhang, Ziqiao and Jing, Xiaoyang and Zheng, Shuangjia and Guan, Jihong and Zhou, Shuigeng},
title = {ABRefine: An Accurate Antibody Structure Refinement Method by Equivariant Graph Transformer with Rigid Body Constraint},
journal = {Journal of Medicinal Chemistry},
year = {2026},
volume = {69},
number = {11},
pages = {12925--12940},
doi = {10.1021/acs.jmedchem.5c03435}
}
EUVIMED