EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AbLWR: a context-aware listwise ranking framework for antibody-antigen binding affinity prediction via positive-unlabeled learning

Fan Xu iD, Zhi-An Huang iD, Haohuai He iD, Yidong Song iD, Wei Liu, Dongxu Zhang iD, Yao Hu iD, Jibin Wu iD, Kay Chen Tan iD

Bioinformatics · 02.11.2026 · 42 (11)

DOI: 10.1093/bioinformatics/btag793 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 23.10.2026. Verfasst von Fan Xu und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China. Hauptthemen laut MEDLINE: Computational Biology, Antibody Affinity, Machine Learning, Antigens. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Department of Science and Technology of Guangdong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Accurate prediction of antibody-antigen binding affinity is fundamental to therapeutic design and the rapid response to evolving pathogens. However, current computational approaches predominantly formulate this as a point-wise regression task. This paradigm struggles to discriminate subtle affinity differences among highly homologous variants and lacks the global context necessary to effectively prioritize top-tier candidates. Furthermore, the field is severely constrained by label sparsity. Although sequence data is abundant, experimentally verified affinities are scarce, leaving a massive pool of unverified antibody-antigen structural interactions unexploited by standard supervised paradigms. Results We propose AbLWR (Antibody-antigen binding affinity Listwise Ranking), a novel framework that reformulates the conventional affinity regression task as a listwise ranking problem to directly optimize candidate prioritization. To mitigate label sparsity, AbLWR incorporates a Positive-Unlabeled (PU) learning mechanism, leveraging a dual-level contrastive objective and meta-optimized label refinement to distill robust structural representations from vast unlabeled data. To accommodate antigenic variation, we employ a homologous antigen sampling strategy coupled with a Multi-Head Self-Attention (MHSA) module, which explicitly models inter-sample dependencies within training lists to capture subtle affinity nuances. Extensive evaluations demonstrate that AbLWR significantly outperforms state-of-the-art sequence-, structure-, and complex-based baselines. It improves the Full Rank Accuracy (FRA) by approximately 8% compared to the strongest baseline in randomized cross-validation, and exhibits strong robustness in out-of-distribution scenarios involving distinct antigen and antibody clusters. Case studies on Influenza Viruses and Human Interleukin-33 further validate its practical utility. Specifically, AbLWR successfully tracks affinity drops caused by antigenic drift and immediately captures optimal binders in simulated wet-lab screening. Availability Source code and datasets are freely available at https://github.com/Josie-xufan/AbLWR.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computational BiologyAntibody AffinityMachine LearningAntigensSoftwareHumansAlgorithmsImmunoinformatics

Substanzen

Antigens

Autor:innen und Institutionen

  • Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China.
  • Department of Computer Science, City University of Hong Kong (Dongguan), Dongguan, Guangdong 523808, China.
  • Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China.
  • School of Statistics and Data Science, Nankai University, Tianjin 300071, China.
  • School of Public Health, Xiamen University, Xiamen, Fujian 361102, China.

ORCID-Profile: Fan Xu, Zhi-An Huang, Haohuai He, Yidong Song, Dongxu Zhang, Yao Hu, Jibin Wu, Kay Chen Tan

Förderung

  • National Natural Science Foundation of China
  • Guangdong Basic and Applied Basic Research Foundation
  • Department of Science and Technology of Guangdong Province
  • Guangdong and Hong Kong Universities '1+1+1' Joint Research Collaboration Scheme
  • Seed Project under City University of Hong Kong (Dongguan) Technology and Innovation Center
  • Grant PolyU
  • Research Grants Council of the Hong Kong SAR
  • Guangdong and Hong Kong Universities ‘1+1+1’ Joint Research Collaboration Scheme

Zitieren

APA

Xu, F., Huang, Z. A., He, H., Song, Y., Liu, W., Zhang, D., Hu, Y., Wu, J., & Tan, K. C. (2026). AbLWR: a context-aware listwise ranking framework for antibody-antigen binding affinity prediction via positive-unlabeled learning. Bioinformatics, 42(11). https://doi.org/10.1093/bioinformatics/btag793

Vancouver

Xu F, Huang ZA, He H, Song Y, Liu W, Zhang D, et al. AbLWR: a context-aware listwise ranking framework for antibody-antigen binding affinity prediction via positive-unlabeled learning. Bioinformatics. 2026;42(11). doi:10.1093/bioinformatics/btag793

BibTeX
@article{Xu2026,
  author = {Xu, Fan and Huang, Zhi-An and He, Haohuai and Song, Yidong and Liu, Wei and Zhang, Dongxu and Hu, Yao and Wu, Jibin and Tan, Kay Chen},
  title = {AbLWR: a context-aware listwise ranking framework for antibody-antigen binding affinity prediction via positive-unlabeled learning},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {11},
  doi = {10.1093/bioinformatics/btag793}
}
Kostenlos starten →