EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A KAN-based hybrid deep neural networks for accurate identification of transcription factor binding sites

Guodong He, Jiahao Ye, Huijun Hao, Wei Chen iD

PLOS One · 2025

DOI: 10.1371/journal.pone.0322978 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Guodong He und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Wenzhou Business College, Wenzhou, Zhejiang, PR China. Hauptthemen laut MEDLINE: Transcription Factors, Neural Networks, Computer, Computational Biology. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wenzhou Business College Research Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Predicting protein-DNA binding sites in vivo is a challenging but urgent task in many fields such as drug design and development. Most promoters contain many transcription factor (TF) binding sites, yet only a few have been identified through time-consuming biochemical experiments. To address this challenge, numerous computational approaches have been proposed to predict TF binding sites from DNA sequences. However, current deep learning methods often face issues such as gradient vanishing as the model depth increases, leading to suboptimal feature extraction.

Results

We propose a model called CBR-KAN (where C represents Convolutional Neural Network (CNN), B represents Bidirectional Long Short Term Memory (BiLSTM), and R represents Residual Mechanism) to predict transcription factor binding sites. Specifically, we designed a multi-scale convolution module (ConvBlock1, 2, 3) combined with BiLSTM network, introduced KAN network to replace traditional multilayer perceptron, and promoted model optimization through residual connections. Testing on 50 common ChIP seq benchmark datasets shows that CBR-KAN outperforms other state-of-the-art methods such as DeepBind, DanQ, DeepD2V, and DeepSEA in predicting TF binding sites.

Conclusions

The CBR-KAN model significantly improves prediction accuracy for transcription factor binding sites by effectively integrating multiple neural network architectures and mechanisms. This approach not only enhances feature extraction but also stabilizes training and boosts generalization capabilities. The promising results on multiple key performance indicators demonstrate the potential of CBR-KAN in bioinformatics applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Transcription FactorsNeural Networks, ComputerComputational BiologyBinding SitesDeep LearningProtein BindingAlgorithmsHumansPromoter Regions, Genetic

Substanzen

Transcription Factors

Autor:innen und Institutionen

  • School of Information Engineering, Wenzhou Business College, Wenzhou, Zhejiang, PR China.

ORCID-Profile: Wei Chen

Förderung

  • Wenzhou Business College Research Project

Zitieren

APA

He, G., Ye, J., Hao, H., & Chen, W. (2025). A KAN-based hybrid deep neural networks for accurate identification of transcription factor binding sites. PLOS One. https://doi.org/10.1371/journal.pone.0322978

Vancouver

He G, Ye J, Hao H, Chen W. A KAN-based hybrid deep neural networks for accurate identification of transcription factor binding sites. PLOS One. 2025. doi:10.1371/journal.pone.0322978

BibTeX
@article{He2025,
  author = {He, Guodong and Ye, Jiahao and Hao, Huijun and Chen, Wei},
  title = {A KAN-based hybrid deep neural networks for accurate identification of transcription factor binding sites},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0322978}
}
Kostenlos starten →