EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AbAgKer: a unified semi-supervised framework for antigen-antibody binding affinity and kinetics prediction

Gang Luo, Junkai Wang, Sizhe Zhang, Zhilin Zhu iD, Zhangli Lu, Min Li iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag606 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Gang Luo und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Central South University, Changsha 410083, China. Hauptthemen laut MEDLINE: Antibody Affinity, Software, Antigen-Antibody Complex, Computational Biology. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Hunan Provincial Natural Science Foundation Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation The rapid advancement of generative artificial intelligence has enabled the high-throughput design of therapeutic antibody candidates. However, the precise evaluation of these candidates remains a significant challenge due to the scarcity of high-quality activity data and the structural flexibility of antibody complementarity-determining regions (CDRs). Results To address these challenges, we propose AbAgKer, an antibody screening model leveraging pre-trained representations and biological prior guidance for antigen-antibody affinity and kinetics prediction. Specifically, we design a biological prior-guided feature fusion framework that integrates pseudo-structural epitope knowledge and CDR-specific attention mechanisms via a mixture-of-experts architecture to effectively capture complex binding landscapes. To mitigate data scarcity, we employ a semi-supervised learning strategy for data self-distillation, which significantly enhances affinity prediction performance. Additionally, we demonstrate that the interaction representations learned by AbAgKer can be effectively transferred to the data-scarce task of predicting dissociation rates via few-shot learning. Extensive experiments demonstrate that AbAgKer outperforms baseline models and exhibits strong generalization capabilities in antibody screening and drug residence time analysis. Availability and implementation The source code and dataset are available at https://github.com/CSUBioGroup/AbAgKer and https://doi.org/10.5281/zenodo.19691211.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Antibody AffinitySoftwareAntigen-Antibody ComplexComputational BiologyAntigen-Antibody ReactionsAntibodiesAntigensSupervised Machine LearningKineticsComplementarity Determining RegionsGenerative Artificial Intelligence

Substanzen

Antigen-Antibody ComplexComplementarity Determining RegionsAntibodiesAntigens

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Central South University, Changsha 410083, China.

ORCID-Profile: Zhilin Zhu, Min Li

Förderung

  • National Natural Science Foundation of China
  • Hunan Provincial Natural Science Foundation Project

Zitieren

APA

Luo, G., Wang, J., Zhang, S., Zhu, Z., Lu, Z., & Li, M. (2026). AbAgKer: a unified semi-supervised framework for antigen-antibody binding affinity and kinetics prediction. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag606

Vancouver

Luo G, Wang J, Zhang S, Zhu Z, Lu Z, Li M. AbAgKer: a unified semi-supervised framework for antigen-antibody binding affinity and kinetics prediction. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag606

BibTeX
@article{Luo2026,
  author = {Luo, Gang and Wang, Junkai and Zhang, Sizhe and Zhu, Zhilin and Lu, Zhangli and Li, Min},
  title = {AbAgKer: a unified semi-supervised framework for antigen-antibody binding affinity and kinetics prediction},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag606}
}
Kostenlos starten →