EUVIMEDEUVIMED entdecken
Crossref

PreVFs-RG: A Deep Hybrid Model for Identifying Virulence Factors Based on Residual Block and Gated Recurrent Unit

Shengli Zhang, Yuanyuan Jing

IEEE/ACM Transactions on Computational Biology and Bioinformatics · 2023

DOI: 10.1109/tcbb.2022.3223038 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2023. Verfasst von Shengli Zhang und 1 weiteren Autor:innen. Hauptthemen laut MEDLINE: Neural Networks, Computer, Virulence Factors. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Basic Research Program of Shaanxi, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Many infectious diseases are caused by bacterial pathogens. The pathogenic mechanisms of bacterial pathogens are complex and it is usually caused by virulence factors (VFs) in many cases. Whether VFs exist is the main difference between the genomes of pathogenic and non-pathogenic bacteria. Therefore, identification of VFs is of great significance for exploring the pathogenesis of infectious diseases. In this paper, we develop a new model for predicting VFs based on multiple features and deep learning. Firstly, we used kmer, Dipeptide deviation from expected mean (DDE) and Amino acid composition (AAC) to extract features. And the deep model is constructed by integrating residual block and gated recurrent unit (GRU). Residual neural network is a kind of jump connection network to avoid gradient explosion or gradient disappearance, which is used to train deeper networks. Two residual blocks, which are separated by Relu activation function and Batch Normalization(BN) layer are used. Finally, the combined features processed by resnet are input into the recurrent structure GRU, and important information is filtered out through reset gate and update gate. The results of the proposed model are better than those of the existing methods by 10-fold cross-validation, and the accuracy is 93.81% and 95.43%, respectively. It shows that the deep hybrid model for identifying virulence factors based on residual block and gate recurrent unit is effective and feasible. The codes and datasets are accessible at https://github.com/VFs625/PreVFs-RG.git.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerVirulence FactorsBacteriaDeep LearningBacterial Infections

Substanzen

Virulence Factors

Förderung

  • National Natural Science Foundation of China
  • Natural Science Basic Research Program of Shaanxi
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Zhang, S., & Jing, Y. (2023). PreVFs-RG: A Deep Hybrid Model for Identifying Virulence Factors Based on Residual Block and Gated Recurrent Unit. IEEE/ACM Transactions on Computational Biology and Bioinformatics. https://doi.org/10.1109/tcbb.2022.3223038

Vancouver

Zhang S, Jing Y. PreVFs-RG: A Deep Hybrid Model for Identifying Virulence Factors Based on Residual Block and Gated Recurrent Unit. IEEE/ACM Transactions on Computational Biology and Bioinformatics. 2023. doi:10.1109/tcbb.2022.3223038

BibTeX
@article{Zhang2023,
  author = {Zhang, Shengli and Jing, Yuanyuan},
  title = {PreVFs-RG: A Deep Hybrid Model for Identifying Virulence Factors Based on Residual Block and Gated Recurrent Unit},
  journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics},
  year = {2023},
  doi = {10.1109/tcbb.2022.3223038}
}
Kostenlos starten →