Enhancing cross-domain protein and peptide interaction with retrained deep learning models
Briefings in Bioinformatics · 2025
DOI: 10.1093/bib/bbaf544 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Xin Cao und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Data Science, The Chinese University of Hong Kong, Shenzhen 518172, China. Hauptthemen laut MEDLINE: Deep Learning, SARS-CoV-2, Peptides, Viral Proteins. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Academician Expert Workstation in Yunnan Province, National Natural Science Foundation of China.
Abstract (Originalsprache)
Accumulating evidence has shown that protein–peptide interactions (PPepIs) are critical for understanding biological processes and developing peptide-based therapeutics. While deep learning-based protein–protein interaction (PPI) prediction showed promise, it suffers from poor generalization and overfitting problems. This study addresses these challenges by focusing training on short proteins containing much less redundant noninteracting sequence. To avoid artificial PPI, only the experimentally validated PPI pairs from STRING database were used to construct the PPI training dataset. We integrated protein sequence and structure information and presented a multilevel deep learning framework. Training on short-protein datasets yielded higher accuracy and computational efficiency compared with training on long-protein datasets. Moreover, we applied the model to delineate human protein and SARS-CoV-2 virus PPI networks. Notably, we screened PPepIs of current drug peptides with human proteins and SARS-CoV-2 viral proteins, identifying numerous potential side effect or new therapeutic targets. Together, our retrained model could be extensively applied to delineate PPepI network, contribute to peptide drug target identification and side effect analysis, and also provide ample resource for viral infection investigations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Data Science, The Chinese University of Hong Kong, Shenzhen 518172, China.
- School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen 518172, China.
- State Key Laboratory of Agricultural Microbiology, Huazhong Agricultural University, Wuhan 430070, China.
- College of Veterinary Medicine, Huazhong Agricultural University, Wuhan 430070, China.
- Center for Cell Lineage Technology and Engineering, Guangzhou Institutes of Biomedicine and Health, Chinese Academy of Sciences, Guangzhou 510530, China.
- College of Information, Huazhong Agricultural University, Wuhan 430070, China.
ORCID-Profile: Xin Cao, Jingquan Li, Fanpeng Meng, Bing Yang, Yanyan Zou
Förderung
- Academician Expert Workstation in Yunnan Province
- National Natural Science Foundation of China
Zitieren
APA
Cao, X., Li, J., Meng, F., Yang, B., & Zou, Y. (2025). Enhancing cross-domain protein and peptide interaction with retrained deep learning models. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf544
Vancouver
Cao X, Li J, Meng F, Yang B, Zou Y. Enhancing cross-domain protein and peptide interaction with retrained deep learning models. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf544
BibTeX
@article{Cao2025,
author = {Cao, Xin and Li, Jingquan and Meng, Fanpeng and Yang, Bing and Zou, Yanyan},
title = {Enhancing cross-domain protein and peptide interaction with retrained deep learning models},
journal = {Briefings in Bioinformatics},
year = {2025},
doi = {10.1093/bib/bbaf544}
}
EUVIMED