PhageMind: generalized strain-level phage host range prediction via meta-learning
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag262 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Yang Shen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, City University of Hong Kong, Hong Kong (SAR), China. Hauptthemen laut MEDLINE: Bacteriophages, Host Specificity, Computational Biology, Bacteria. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hong Kong Research Grants Council, General Research Fund, City University of Hong Kong.
Abstract (Originalsprache)
Motivation Bacteriophages (phages) are key regulators of bacterial populations and hold great promise for applications such as phage therapy, biocontrol, and industrial fermentation. The success of these applications depends on accurately determining phage host range, which is often specific at the strain level rather than the species level. However, existing computational approaches face major limitations: many rely on genus-specific features that do not generalize across taxa, while others require large amounts of training data that are unavailable for most bacterial lineages. These challenges create a critical need for methods that can accurately predict strain-level phage–host interactions across diverse bacterial genera, particularly under data-limited conditions. Results We present PhageMind, a learning framework designed to address this challenge by enabling efficient transfer of knowledge across bacterial genera. PhageMind is trained to identify shared principles of phage–bacterium interactions from well-studied systems and to rapidly adapt these principles to new genera using only a small number of known interactions. To reflect the biological basis of infection, we represent phage–host relationships using a knowledge graph that explicitly incorporates phage tail fiber proteins and bacterial O-antigen biosynthesis gene clusters, and we use this representation to guide interaction prediction. Across four bacterial genera (Escherichia, Klebsiella, Vibrio, and Alteromonas), PhageMind achieves high prediction accuracy and shows strong adaptability to new lineages. In particular, in leave-one-genus-out evaluations, the model maintains robust performance when only limited reference data are available, demonstrating its potential as a scalable and practical tool for studying phage–host interactions across the global phageome. Availability and implementation The source code of PhageMind is available via: https://github.com/YangSH-ac/PhageMind.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Electrical Engineering, City University of Hong Kong, Hong Kong (SAR), China.
- School of Oceanography and Earth Sciences, Tongji University, Shanghai 200092, P.R. China.
- State Key Laboratory of Marine Environmental Science, College of Ocean and Earth Sciences, Xiamen University, Xiamen 361005, China.
- Archaeal Biology Center, Synthetic Biology Research Center, Shenzhen Key Laboratory of Marine Microbiome Engineering, Key Laboratory of Marine Microbiome Engineering of Guangdong Higher Education Institutes, Institute f…
- Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong (SAR), China.
ORCID-Profile: Rui Zhang, Yanni Sun, Jiayu Shang
Förderung
- Hong Kong Research Grants Council
- General Research Fund
- City University of Hong Kong
- National Natural Science Foundation of China
- Shenzhen Science and Technology Program
Zitieren
APA
Shen, Y., Shi, K., Yu, C., Zhang, R., Sun, Y., & Shang, J. (2026). PhageMind: generalized strain-level phage host range prediction via meta-learning. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag262
Vancouver
Shen Y, Shi K, Yu C, Zhang R, Sun Y, Shang J. PhageMind: generalized strain-level phage host range prediction via meta-learning. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag262
BibTeX
@article{Shen2026,
author = {Shen, Yang and Shi, Keming and Yu, Chen and Zhang, Rui and Sun, Yanni and Shang, Jiayu},
title = {PhageMind: generalized strain-level phage host range prediction via meta-learning},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag262}
}
EUVIMED