EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SeekRBP: Leveraging Sequence-Structure Integration with Reinforcement Learning for Receptor-Binding Protein Identification

Xiling Luo, Le Ou-Yang, Yang Shen, Jiaojiao Guan, Dehan Cai, Jun Zhang, Guoliang Xing, Yanni Sun, Jiayu Shang

Bioinformatics · 10.11.2026

DOI: 10.1093/bioinformatics/btag813 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 10.11.2026. Verfasst von Xiling Luo und 8 weiteren Autor:innen. Beteiligte Einrichtung: Guangdong Provincial Key Laboratory of Wastewater Information Analysis and Early Warning, Beijing Normal University, Zhuhai, China. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Receptor-binding proteins (RBPs) initiate viral infection and determine host specificity, serving as key targets for phage engineering and therapy. However, the identification of RBPs is complicated by their extreme sequence divergence, which often renders traditional homology-based alignment methods ineffective. While machine learning offers a promising alternative, such approaches struggle with severe class imbalance and the difficulty of selecting informative negative samples from heterogeneous tail proteins. Existing methods often fail to balance learning from these “hard negatives” while maintaining generalization. Results We present SeekRBP, a sequence–structure framework that models negative sampling as a sequential decision-making problem. By employing a multi-armed bandit strategy, SeekRBP dynamically prioritizes informative non-RBP sequences based on real-time training feedback, complemented by a multimodal fusion of protein language and structural embeddings. Benchmarking demonstrates that SeekRBP consistently outperforms static sampling strategies. Furthermore, a case study on Vibrio phages validates that SeekRBP effectively identifies RBPs to improve host prediction, highlighting its potential for large-scale annotation and synthetic biology applications. Availability The source code of SeekRBP is available via: https://github.com/Saillxl/SeekRBP.

Autor:innen und Institutionen

  • Guangdong Provincial Key Laboratory of Wastewater Information Analysis and Early Warning, Beijing Normal University, Zhuhai, China.
  • Department of Electrical Engineering, City University of Hong Kong, Hong Kong (SAR), China.
  • MoE Key Lab of Artificial Intelligence, AI Institute, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China.
  • SMBU-MSU-BIT Joint Laboratory on Bioinformatics and Engineering Biology, Shenzhen MSU-BIT University, Shenzhen, China.
  • Department of Information Engineering, Chinese University of Hong Kong, Hong Kong (SAR), China.

Zitieren

APA

Luo, X., Ou-Yang, L., Shen, Y., Guan, J., Cai, D., Zhang, J., Xing, G., Sun, Y., & Shang, J. (2026). SeekRBP: Leveraging Sequence-Structure Integration with Reinforcement Learning for Receptor-Binding Protein Identification. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag813

Vancouver

Luo X, Ou-Yang L, Shen Y, Guan J, Cai D, Zhang J, et al. SeekRBP: Leveraging Sequence-Structure Integration with Reinforcement Learning for Receptor-Binding Protein Identification. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag813

BibTeX
@article{Luo2026,
  author = {Luo, Xiling and Ou-Yang, Le and Shen, Yang and Guan, Jiaojiao and Cai, Dehan and Zhang, Jun and Xing, Guoliang and Sun, Yanni and Shang, Jiayu},
  title = {SeekRBP: Leveraging Sequence-Structure Integration with Reinforcement Learning for Receptor-Binding Protein Identification},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag813}
}
Kostenlos starten →