EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

MambaCpG: an accurate model for single-cell DNA methylation status imputation using mamba

Qi Zhao, Ze Li, Qian Mao, Tingwei Chen, Yiran Zhang, Bingle Li, Zheng Zhao, Xiaoya Fan

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf360 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Qi Zhao und 7 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Information, Liaoning University, Chongshan Middle Road 66, 110036 Liaoning, China. Hauptthemen laut MEDLINE: DNA Methylation, Single-Cell Analysis, Software. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Fundamental Research Funds for Public Universities in Liaoning, National Natural Science Foundation of China, National Training Program of Innovation and Entrepreneurship for Undergraduates.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

DNA methylation is a key epigenetic modification involved in biological processes and disease development. The accurate analysis of DNA methylation site information is of significant biological importance. Despite advances in single-cell sequencing, data sparsity due to low cytosine-phosphate-guanine (CpG) coverage remains a challenge. To address this, we introduce MambaCpG, a single-cell DNA methylation state imputation model based on the Mamba block. MambaCpG integrates the methylation matrix and DNA sequence context and uses bidirectional Mamba blocks to obtain embeddings, effectively capturing the long-range dependencies between CpG sites within DNA methylation patterns. Experiments on seven datasets of various scales demonstrate that MambaCpG outperforms existing models on large, highly sparse datasets while showing competitive performance on smaller datasets. MambaCpG has lower parameter and memory requirements, making it suitable for practical applications. MambaCpG also reveals ultra-long-range dependencies and provides new insights into DNA methylation patterning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DNA MethylationSingle-Cell AnalysisSoftwareHumansCpG IslandsAlgorithmsSequence Analysis, DNAEpigenesis, GeneticComputational Biology

Stichwörter der Autor:innen

DNA methylation imputationMambaMambaCpGdeep learningsingle-cell

Autor:innen und Institutionen

  • Faculty of Information, Liaoning University, Chongshan Middle Road 66, 110036 Liaoning, China.
  • College of Medicine and Biological Information Engineering, Northeastern University, Wenhua Road 3, 110000 Liaoning, China.
  • College of Light Industry, Liaoning University, Chongshan Middle Road 66, 110036 Liaoning, China.
  • College of Artificial Intelligence, Dalian Maritime University, Linghai Road #1, 116026 Liaoning, China.
  • School of Software, Dalian University of Technology, No. 2 Linggong Road, 116024 Liaoning, China.

Förderung

  • Fundamental Research Funds for Public Universities in Liaoning
  • National Natural Science Foundation of China
  • National Training Program of Innovation and Entrepreneurship for Undergraduates

Zitieren

APA

Zhao, Q., Li, Z., Mao, Q., Chen, T., Zhang, Y., Li, B., Zhao, Z., & Fan, X. (2025). MambaCpG: an accurate model for single-cell DNA methylation status imputation using mamba. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf360

Vancouver

Zhao Q, Li Z, Mao Q, Chen T, Zhang Y, Li B, et al. MambaCpG: an accurate model for single-cell DNA methylation status imputation using mamba. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf360

BibTeX
@article{Zhao2025,
  author = {Zhao, Qi and Li, Ze and Mao, Qian and Chen, Tingwei and Zhang, Yiran and Li, Bingle and Zhao, Zheng and Fan, Xiaoya},
  title = {MambaCpG: an accurate model for single-cell DNA methylation status imputation using mamba},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf360}
}
Kostenlos starten →