EUVIMEDEUVIMED entdecken
Crossref

ComicGTN infers disease-associated rare cell states from single-cell multiomic data using DNA sequence–augmented graph transformer networks

Boran Yang, Jiao Hua, Guanghua Zhou, Yuhui Feng, Jing Qi, Yiyuan Guo, Danshu Sheng, Shuilin Jin

Genome Research · 2026-08 · 36 (8) · 1652-1667

DOI: 10.1101/gr.281661.125 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Genome Research, online erschienen am 17.07.2026. Verfasst von Boran Yang und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics, Harbin Institute of Technology, Harbin 150000, China. Hauptthemen laut MEDLINE: Single-Cell Analysis, Sequence Analysis, DNA. Die Arbeit nennt 81 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Heilongjiang Province, Key Research and Development Program of Heilongjiang.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single-cell multiomic technology makes it possible to profile both the transcriptome and epigenome within individual cells. The detection of rare cell states from such data is crucial for exploring novel disease biomarkers with clinical potential. However, existing methods typically focus on the gene and peak counts while ignoring the underlying genomic sequence at accessible sites. Here, we propose ComicGTN, an innovative computational framework that integrates single-cell multiomic data with DNA sequence information via enhanced graph transformer networks to accurately identify rare cell clusters. ComicGTN consistently outperforms nine state-of-the-art methods in identifying rare cells across multiple complex scenarios. In mouse breast cancer data, ComicGTN detects several functionally distinct immune subpopulations. In cerebral cortex of epilepsy patients, it uncovers oligodendrocytes undergoing particular differentiation states. For polycystic kidney disease patient–derived organoids, ComicGTN elaborates pathological pathways in a captured rare glomerular subgroup. Overall, ComicGTN accelerates the localization of disease-associated rare cell populations, facilitating the derivation of clinical insights in development and disease progression.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single-Cell AnalysisSequence Analysis, DNAHumansAnimalsMiceMultiomicsSingle-Cell Gene Expression AnalysisEpilepsyGraph Neural NetworksPolycystic Kidney DiseasesFemaleTranscriptome

Autor:innen und Institutionen

  • School of Mathematics, Harbin Institute of Technology, Harbin 150000, China.
  • Department of Ophthalmology, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China.
  • School of Mathematics, Harbin Institute of Technology, Harbin 150000, China; jinsl@hit.edu.cn shengds@hit.edu.cn.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Heilongjiang Province
  • Key Research and Development Program of Heilongjiang
  • Science and Technology Program of XPCC
  • Fundamental Research Funds for the Central Universities
  • General Postdoctoral Funding Program of Heilongjiang Province
  • Science and Technology Innovation Talent Program for Advanced Manufacturing of Harbin City
  • State Key Laboratory of Advanced Welding and Joining, Harbin Institute of Technology

Zitieren

APA

Yang, B., Hua, J., Zhou, G., Feng, Y., Qi, J., Guo, Y., Sheng, D., & Jin, S. (2026). ComicGTN infers disease-associated rare cell states from single-cell multiomic data using DNA sequence–augmented graph transformer networks. Genome Research, 36(8), 1652-1667. https://doi.org/10.1101/gr.281661.125

Vancouver

Yang B, Hua J, Zhou G, Feng Y, Qi J, Guo Y, et al. ComicGTN infers disease-associated rare cell states from single-cell multiomic data using DNA sequence–augmented graph transformer networks. Genome Research. 2026;36(8):1652-1667. doi:10.1101/gr.281661.125

BibTeX
@article{Yang2026,
  author = {Yang, Boran and Hua, Jiao and Zhou, Guanghua and Feng, Yuhui and Qi, Jing and Guo, Yiyuan and Sheng, Danshu and Jin, Shuilin},
  title = {ComicGTN infers disease-associated rare cell states from single-cell multiomic data using DNA sequence–augmented graph transformer networks},
  journal = {Genome Research},
  year = {2026},
  volume = {36},
  number = {8},
  pages = {1652--1667},
  doi = {10.1101/gr.281661.125}
}
Kostenlos starten →