EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GT-Mamba: a Topology-Aware Graph-State space model for robust and interpretable epigenetic age prediction

Han Wang iD, Hui Wang, Yanting Tong, Yuanyuan Liu, Qu Jing, Guan Ning Lin iD, Li Zhang iD

Bioinformatics · 02.07.2026 · 42 (7)

DOI: 10.1093/bioinformatics/btag401 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 16.06.2026. Verfasst von Han Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Technology, Institute of Computational Biology, Northeast Normal University, Changchun 130117, China. Hauptthemen laut MEDLINE: Epigenesis, Genetic, Epigenomics, Software. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Jilin Scientific and Technological Development Program, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Current epigenetic clocks face a trade-off between predictive accuracy and biological interpretability, often relying on dataset-specific correction to generalize across cohorts. We propose GT-Mamba, a novel architecture that integrates a Structure-Aware Graph Transformer with the Mamba state space model. This design captures CpG topological correlations and genome-wide long-range dependencies. Results GT-Mamba demonstrates strong out-of-the-box robustness across heterogeneous independent validation cohorts, achieving a weighted average MAE of 4.43 years. Notably, it effectively generalizes to EPIC 850k arrays despite partial feature missingness, and maintains consistent performance across homologous age distribution shifts (MAE 2.94 years in a young cohort). Ablation studies confirm that graph topology contributes to improved robustness against noise. Mechanistic analysis suggests that the model captures methylation patterns associated with both developmental and functional processes. Availability Source code and pre-trained models are freely available at https://github.com/NENUBioCompute/GT-Mamba and archived on Zenodo (DOI: 10.5281/zenodo.19703155).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Epigenesis, GeneticEpigenomicsSoftwareDNA MethylationHumansCpG IslandsAlgorithms

Autor:innen und Institutionen

  • School of Information Science and Technology, Institute of Computational Biology, Northeast Normal University, Changchun 130117, China.
  • School of Biomedical Engineering Excellence, China Pharmaceutical University, Nanjing 211198, China.
  • College of Computer Science and Technology, Jilin University, Changchun 130012, China.
  • College of Computer Science and Engineering, Changchun University of Technology, Changchun 130051, China.

ORCID-Profile: Han Wang, Guan Ning Lin, Li Zhang

Förderung

  • National Natural Science Foundation of China
  • Jilin Scientific and Technological Development Program
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Wang, H., Wang, H., Tong, Y., Liu, Y., Jing, Q., Lin, G. N., & Zhang, L. (2026). GT-Mamba: a Topology-Aware Graph-State space model for robust and interpretable epigenetic age prediction. Bioinformatics, 42(7). https://doi.org/10.1093/bioinformatics/btag401

Vancouver

Wang H, Wang H, Tong Y, Liu Y, Jing Q, Lin GN, et al. GT-Mamba: a Topology-Aware Graph-State space model for robust and interpretable epigenetic age prediction. Bioinformatics. 2026;42(7). doi:10.1093/bioinformatics/btag401

BibTeX
@article{Wang2026,
  author = {Wang, Han and Wang, Hui and Tong, Yanting and Liu, Yuanyuan and Jing, Qu and Lin, Guan Ning and Zhang, Li},
  title = {GT-Mamba: a Topology-Aware Graph-State space model for robust and interpretable epigenetic age prediction},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {7},
  doi = {10.1093/bioinformatics/btag401}
}
Kostenlos starten →