EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

iProtDNA-SMOTE: Enhancing protein-DNA binding sites prediction through imbalanced graph neural networks

Ruiyan Huang iD, Wangren Qiu, Xuan Xiao, Weizhong Lin iD

PLOS One · 2025

DOI: 10.1371/journal.pone.0320817 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Ruiyan Huang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Jingdezhen Ceramic University, Jingdezhen Jiangxi, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, DNA, DNA-Binding Proteins, Computational Biology. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Education Department of Jiangxi Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Protein-DNA interactions play a crucial role in cellular biology, essential for maintaining life processes and regulating cellular functions. We propose a method called iProtDNA-SMOTE, which utilizes non-equilibrium graph neural networks along with pre-trained protein language models to predict DNA binding residues. This approach effectively addresses the class imbalance issue in predicting protein-DNA binding sites by leveraging unbalanced graph data, thus enhancing model’s generalization and specificity. We trained the model on two datasets, TR646 and TR573, and conducted a series of experiments to evaluate its performance. The model achieved AUC values of 0.850, 0.896, and 0.858 on the independent test datasets TE46, TE129, and TE181, respectively. These results indicate that iProtDNA-SMOTE outperforms existing methods in terms of accuracy and generalization for predicting DNA binding sites, offering reliable and effective predictions to minimize errors. The model has been thoroughly validated for its ability to predict protein-DNA binding sites with high reliability and precision. For the convenience of the scientific community, the benchmark datasets and codes are publicly available at https://github.com/primrosehry/iProtDNA-SMOTE .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerDNADNA-Binding ProteinsComputational BiologyBinding SitesProtein BindingAlgorithmsSoftwareDatabases, ProteinGraph Neural Networks

Substanzen

DNADNA-Binding Proteins

Autor:innen und Institutionen

  • School of Information Engineering, Jingdezhen Ceramic University, Jingdezhen Jiangxi, China.
  • School of Information Engineering, Jingxi Art & Ceramics Technology Institute, Jingdezhen Jiangxi, China.

ORCID-Profile: Ruiyan Huang, Weizhong Lin

Förderung

  • National Natural Science Foundation of China
  • Education Department of Jiangxi Province

Zitieren

APA

Huang, R., Qiu, W., Xiao, X., & Lin, W. (2025). iProtDNA-SMOTE: Enhancing protein-DNA binding sites prediction through imbalanced graph neural networks. PLOS One. https://doi.org/10.1371/journal.pone.0320817

Vancouver

Huang R, Qiu W, Xiao X, Lin W. iProtDNA-SMOTE: Enhancing protein-DNA binding sites prediction through imbalanced graph neural networks. PLOS One. 2025. doi:10.1371/journal.pone.0320817

BibTeX
@article{Huang2025,
  author = {Huang, Ruiyan and Qiu, Wangren and Xiao, Xuan and Lin, Weizhong},
  title = {iProtDNA-SMOTE: Enhancing protein-DNA binding sites prediction through imbalanced graph neural networks},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0320817}
}
Kostenlos starten →