EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Identifying DNA methylation types and methylated base positions from bacteria using nanopore sequencing with multi-scale neural network

Zheng Chen, Peng Ni, Jianxin Wang iD

Bioinformatics · 2025

DOI: 10.1093/bioinformatics/btaf397 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von Zheng Chen und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Central South University, Changsha 410083, China. Hauptthemen laut MEDLINE: DNA Methylation, Nanopore Sequencing, Neural Networks, Computer, Bacteria. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Project of Xiangjiang Laboratory, National Natural Science Foundation of China Grant.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation DNA methylation plays important roles in various cellular physiological processes in bacteria. Nanopore sequencing has shown the ability to identify different types of DNA methylation from individual bacteria directly. However, existing methods for identifying bacterial methylomes showed inconsistent performances in different methylation motifs in bacteria and didn’t fully utilize the different scale information contained in nanopore signals. Results We propose a deep-learning method, called Nanoident, for de novo detection of DNA methylation types and methylated base positions in bacteria using Nanopore sequencing. For each targeted motif sequence, Nanoident utilizes five different features, including statistical features extracted from both the nanopore raw signals and the basecalling results of the motif. All the five features are processed by a multi-scale neural network in Nanoident, which extracts information from different receptive fields of the features. The Leave-One-Out Cross-Validation (LOOCV) on the dataset containing 7 bacteria samples with 46 methylation motifs shows that Nanoident achieves ∼10% improvement in accuracy than the previous method. Furthermore, Nanoident achieves ∼13% improvement in accuracy in an independent dataset, which contains 12 methylation motifs. Additionally, we optimize the pipeline for de novo methylation motif enrichment, enabling the discovery of novel methylation motifs. Availability and implementation The source code of Nanoident is freely available at https://github.com/cz-csu/Nanoident and https://doi.org/10.6084/m9.figshare.29252264.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DNA MethylationNanopore SequencingNeural Networks, ComputerBacteriaDNA, BacterialDeep LearningSequence Analysis, DNA

Substanzen

DNA, Bacterial

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Central South University, Changsha 410083, China.
  • Xiangjiang Laboratory, Changsha 410205, China.
  • Hunan Provincial Key Lab on Bioinformatics, Central South University, Changsha 410083, China.

ORCID-Profile: Jianxin Wang

Förderung

  • National Natural Science Foundation of China
  • Project of Xiangjiang Laboratory
  • National Natural Science Foundation of China Grant

Zitieren

APA

Chen, Z., Ni, P., & Wang, J. (2025). Identifying DNA methylation types and methylated base positions from bacteria using nanopore sequencing with multi-scale neural network. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf397

Vancouver

Chen Z, Ni P, Wang J. Identifying DNA methylation types and methylated base positions from bacteria using nanopore sequencing with multi-scale neural network. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf397

BibTeX
@article{Chen2025,
  author = {Chen, Zheng and Ni, Peng and Wang, Jianxin},
  title = {Identifying DNA methylation types and methylated base positions from bacteria using nanopore sequencing with multi-scale neural network},
  journal = {Bioinformatics},
  year = {2025},
  doi = {10.1093/bioinformatics/btaf397}
}
Kostenlos starten →