PhosF3C: a feature fusion architecture with fine-tuned protein language model and conformer for prediction of general phosphorylation site
Briefings in Bioinformatics · 2025
DOI: 10.1093/bib/bbaf242 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Yuhuan Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Cuiying Honors College, Lanzhou University, 222 South Tianshui Road, 730000 Lanzhou, China. Hauptthemen laut MEDLINE: Proteins, Software, Computational Biology. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Protein phosphorylation, a key post-translational modification, provides essential insight into protein properties, making its prediction highly significant. Using the emerging capabilities of large language models (LLMs), we apply Low-Rank Adaptation (LoRA) fine-tuning to ESM2, a powerful protein large language model, to efficiently extract features with minimal computational resources, optimizing task-specific text alignment. Additionally, we integrate the conformer architecture with the feature coupling unit to enhance local and global feature exchange, further improving prediction accuracy. Our model achieves state-of-the-art performance, obtaining area under the curve scores of 79.5%, 76.3%, and 71.4% at the S, T, and Y sites of the general data sets. Based on the powerful feature extraction capabilities of LLMs, we conduct a series of analyses on protein representations, including studies on their structure, sequence, and various chemical properties [such as hydrophobicity (GRAVY), surface charge, and isoelectric point]. We propose a test method called linear regression tomography which is a top-down method using representation to explore the model’s feature extraction capabilities. Our resources, including data and code, are publicly accessible at https://github.com/SkywalkerLuke/PhosF3C
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Cuiying Honors College, Lanzhou University, 222 South Tianshui Road, 730000 Lanzhou, China.
- Department of Computer Science, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon Tong, Hong Kong 999077, China.
- Department of Computer Science, City University of Hong Kong (Dongguan), No. 8, Kaohsiung Road, Songshan Lake High-Tech Industrial Development Zone, 523808, Dongguan, China.
- New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), 95 Zhongguancun East Road, 100190, B…
- School of Mathematics and Statistics, Lanzhou University, 222 South Tianshui Road, 730000 Lanzhou, China.
- Xi'an Jiaotong University, No. 76 West Yanta Road, Xi'an, Shaanxi, 710061, P.R. China.
Zitieren
APA
Liu, Y., Wang, X., Zhong, H., Zhai, J., Gong, X., & Lu, T. (2025). PhosF3C: a feature fusion architecture with fine-tuned protein language model and conformer for prediction of general phosphorylation site. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf242
Vancouver
Liu Y, Wang X, Zhong H, Zhai J, Gong X, Lu T. PhosF3C: a feature fusion architecture with fine-tuned protein language model and conformer for prediction of general phosphorylation site. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf242
BibTeX
@article{Liu2025,
author = {Liu, Yuhuan and Wang, Xueying and Zhong, Haitian and Zhai, Jixiu and Gong, Xiaojuan and Lu, Tianchi},
title = {PhosF3C: a feature fusion architecture with fine-tuned protein language model and conformer for prediction of general phosphorylation site},
journal = {Briefings in Bioinformatics},
year = {2025},
doi = {10.1093/bib/bbaf242}
}
EUVIMED