DeepPhosPPI: a deep learning framework with attention-CNN and transformer for predicting phosphorylation effects on protein–protein interactions
Briefings in Bioinformatics · 2025
DOI: 10.1093/bib/bbaf462 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Yinyin Gong und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410083, China. Hauptthemen laut MEDLINE: Deep Learning, Neural Networks, Computer, Computational Biology, Protein Interaction Mapping. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hunan Province of China, Natural Science Foundation of Chongqing.
Abstract (Originalsprache)
Protein phosphorylation regulates protein function and cellular signaling pathways, and is strongly associated with diseases, including neurodegenerative disorders and cancer. Phosphorylation plays a critical role in regulating protein activity and cellular signaling by modulating protein–protein interactions (PPIs). It alters binding affinities and interaction networks, thereby influencing biological processes and maintaining cellular homeostasis. Experimental validation of these effects is labor-intensive and expensive, highlighting the need for efficient computational approaches. We propose DeepPhosPPI, the first sequence-based deep learning framework for phosphorylation effects on PPIs prediction, which employs the pre-trained protein language model for feature embedding, with ProtBERT and ESM-2 as alternative backbone encoders. By combining attention-based convolutional neural network and Transformer models, DeepPhosPPI accurately predicts phosphorylation effects. The experimental results show that DeepPhosPPI consistently outperforms state-of-the-art methods in multiple tasks, including functional sites identification and regulatory effect classification.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410083, China.
- College of Computing and Data Science, Nanyang Technological University, 639798, Singapore.
- Research and Innovation Center for Convergence of Automobile and Cyberspace, Research Institute of Hunan University in Chongqing, Chongqing, 401120, China.
- Peng Cheng Laboratory, Shenzhen, 518066, China.
- Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN 46556, USA.
ORCID-Profile: Yinyin Gong, Danny Z Chen
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Hunan Province of China
- Natural Science Foundation of Chongqing
Zitieren
APA
Gong, Y., Li, R., Liu, Y., Wang, J., Chen, D. Z., & Kwoh, C. K. (2025). DeepPhosPPI: a deep learning framework with attention-CNN and transformer for predicting phosphorylation effects on protein–protein interactions. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf462
Vancouver
Gong Y, Li R, Liu Y, Wang J, Chen DZ, Kwoh CK. DeepPhosPPI: a deep learning framework with attention-CNN and transformer for predicting phosphorylation effects on protein–protein interactions. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf462
BibTeX
@article{Gong2025,
author = {Gong, Yinyin and Li, Rui and Liu, Yan and Wang, Jilong and Chen, Danny Z and Kwoh, Chee Keong},
title = {DeepPhosPPI: a deep learning framework with attention-CNN and transformer for predicting phosphorylation effects on protein–protein interactions},
journal = {Briefings in Bioinformatics},
year = {2025},
doi = {10.1093/bib/bbaf462}
}
EUVIMED