EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AntiBMPNN: Structure‐Guided Graph Neural Networks for Precision Antibody Engineering

Ze-Yu Sun, Jiayi Yuan, Divya Jaiswal, Jingxuan Ge, Tianjian Liang, Jiahui Wei, Jinghong Cao, Yulong Li, Xiaojie Chu, Yan Chen, Ying Xue, Wei Li und 2 weitere

Advanced Science · 2025-09 · 12 (35)

DOI: 10.1002/advs.202504278 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 27.06.2025. Verfasst von Ze-Yu Sun und 13 weiteren Autor:innen. Beteiligte Einrichtung: College of Pharmacology Sciences, Zhejiang University of Technology, Hangzhou, 310014, P. R. China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Protein Engineering, Antibodies. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAID NIH HHS, REACH: Research Enterprise to Advance a Cure for HIV, I4C 2.0: Immunotherapy for Cure.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Antibodies are crucial for medical applications, yet traditional methods for designing sequences are inefficient. This study introduces AntiBMPNN, an advanced deep‐learning framework that leverages an antibody‐specific 3D dataset, a fine‐tuned message‐passing neural network (MPNN), a frequency‐based scoring function, and AlphaFold 3 to achieve highly accurate antibody sequence design. AntiBMPNN surpasses ProteinMPNN with a perplexity of 1.5 and over 80% sequence recovery. Its scoring function, combined with AlphaFold 3, effectively prioritizes sequences based on structural recovery, positional stability, and biochemical or complex properties. Experimental validation highlights a 75% success rate in single‐point antibody design. AntiBMPNN consistently outperforms AbMPNN, AntiFold, and ProteinMPNN in designing complementarity determining regions (CDR) 1‐3, yielding stronger binding affinities. For CDR1 of huJ3 (anti‐HIV nanobody), it achieves a half maximal effective concentration (EC₅₀) of 9.2 nM (nanomolar), better than ProteinMPNN (135.2 nM) and AntiFold (59.3 nM), and comparable to AbMPNN (6.6 nM). For CDR2 of the D6 nanobody (targeting CD16), AntiBMPNN reaches 0.3 nM, outperforming AbMPNN (2.3 nM), AntiFold (0.7 nM), and ProteinMPNN (0.7 nM). In CDR3 of huJ3, it achieves 1.7 nM, surpassing AbMPNN (51.2 nM), with no detectable activity from AntiFold or ProteinMPNN. These findings confirm that AntiBMPNN‐designed sequences for J3 and D6 outperform the originals, highlighting its potential to improve therapeutic antibody design.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerProtein EngineeringAntibodiesComplementarity Determining RegionsDeep LearningHumansSingle-Domain AntibodiesGraph Neural Networks

Stichwörter der Autor:innen

deep learningmessage passing neuron networks (MPNNs)precision antibody engineeringsequence designs

Substanzen

Complementarity Determining RegionsAntibodiesSingle-Domain Antibodies

Autor:innen und Institutionen

  • College of Pharmacology Sciences, Zhejiang University of Technology, Hangzhou, 310014, P. R. China.
  • Department of Pharmaceutical Sciences, School of Pharmacy, University of Pittsburgh, Pittsburgh, PA, 15261, USA.
  • College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, 310058, China.
  • College of Chemistry and Environmental Engineering, Sichuan University of Science and Engineering, Zigong, 643000, P. R. China.
  • Department of Medicine, Center for AIDS Research, Division of Infectious Diseases, School of Medicine, University of Pittsburgh, Pittsburgh, PA, 15261, USA.
  • Faculty of Pharmaceutical Sciences, Shenzhen University of Advanced Technology, Shenzhen, 518107, P. R. China.

ORCID-Profile: Tingjun Hou

Förderung

  • NIAID NIH HHS
  • REACH: Research Enterprise to Advance a Cure for HIV
  • I4C 2.0: Immunotherapy for Cure
  • NIDA NIH HHS
  • National Institute of Development Administration

Zitieren

APA

Sun, Z. Y., Yuan, J., Jaiswal, D., Ge, J., Liang, T., Wei, J., Cao, J., Li, Y., Chu, X., Chen, Y., Xue, Y., Li, W., Hou, T., & Feng, Z. (2025). AntiBMPNN: Structure‐Guided Graph Neural Networks for Precision Antibody Engineering. Advanced Science, 12(35). https://doi.org/10.1002/advs.202504278

Vancouver

Sun ZY, Yuan J, Jaiswal D, Ge J, Liang T, Wei J, et al. AntiBMPNN: Structure‐Guided Graph Neural Networks for Precision Antibody Engineering. Advanced Science. 2025;12(35). doi:10.1002/advs.202504278

BibTeX
@article{Sun2025,
  author = {Sun, Ze-Yu and Yuan, Jiayi and Jaiswal, Divya and Ge, Jingxuan and Liang, Tianjian and Wei, Jiahui and Cao, Jinghong and Li, Yulong and Chu, Xiaojie and Chen, Yan and Xue, Ying and Li, Wei and Hou, Tingjun and Feng, Zhiwei},
  title = {AntiBMPNN: Structure‐Guided Graph Neural Networks for Precision Antibody Engineering},
  journal = {Advanced Science},
  year = {2025},
  volume = {12},
  number = {35},
  doi = {10.1002/advs.202504278}
}
Kostenlos starten →