EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

scHG: A supercell framework with high-order graph learning enables scalable multi-omics analysis

Yixiang Huang, Yuan Gan, Xinqi Gong iD

PLOS Computational Biology · 06.05.2026 · 22 (5) · e1013851

DOI: 10.1371/journal.pcbi.1013851 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 06.05.2026. Verfasst von Yixiang Huang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics, Renmin University of China, Beijing, China. Hauptthemen laut MEDLINE: Multiomics, Computational Biology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Technologies Research and Development Program, National Natural Science Foundation of China, Shenzhen Hospital, Southern Medical University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-omics profiling—spanning proteomics, transcriptomics, and additional omics data types—is rapidly advancing, providing increasingly detailed maps of cellular identity and function. Yet, identifying rare cell populations while maintaining computational tractability remains a major challenge in large-scale multi-omics clustering. Here, we introduce the supercell paradigm, in which expression-coherent cells are grouped into intermediate units that preserve weak but biologically meaningful local structure across omics layers, thereby improving sensitivity to rare populations that are often masked at the conventional cluster level. Supercells are constructed using angle-aware similarity metrics and second-order co-occurrence neighbors, with impurity cells pruned by degree centrality. Building on this idea, we develop scHG, a high-order graph learning framework with an omics-weighted optimizer that adaptively balances contributions from gene expression, surface proteins, and chromatin accessibility while remaining scalable on large datasets through sparse matrix optimization and iterative graph refinement. Across six benchmark datasets (up to 30672 cells), scHG consistently outperforms state-of-the-art methods, improving mean ARI and NMI by 3.97% and 3.54%, respectively, while reducing runtime by 26.40%. Beyond overall clustering accuracy, scHG resolves fine-grained heterogeneity within conventionally defined T-cell populations and, importantly, uncovers rare populations—including dendritic-cell populations and NK-like B cells—that remain hidden under standard clustering pipelines. These results demonstrate that supercells provide not only an efficient intermediate representation for large-scale multi-omics integration, but also a practical mechanism for rare-cell detection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MultiomicsComputational BiologyProteomicsAlgorithmsClustering AlgorithmsHumansGene Expression ProfilingCluster AnalysisAnimalsMachine Learning

Autor:innen und Institutionen

  • School of Mathematics, Renmin University of China, Beijing, China.

ORCID-Profile: Xinqi Gong

Förderung

  • Key Technologies Research and Development Program
  • National Natural Science Foundation of China
  • Shenzhen Hospital, Southern Medical University
  • Strategic Scientist Leadership Program, Renmin University of China
  • Public Computing Cloud, Renmin University of China
  • Big Data and Responsible Artificial Intelligence for National Governance, Renmin University of China

Zitieren

APA

Huang, Y., Gan, Y., & Gong, X. (2026). scHG: A supercell framework with high-order graph learning enables scalable multi-omics analysis. PLOS Computational Biology, 22(5), e1013851. https://doi.org/10.1371/journal.pcbi.1013851

Vancouver

Huang Y, Gan Y, Gong X. scHG: A supercell framework with high-order graph learning enables scalable multi-omics analysis. PLOS Computational Biology. 2026;22(5):e1013851. doi:10.1371/journal.pcbi.1013851

BibTeX
@article{Huang2026,
  author = {Huang, Yixiang and Gan, Yuan and Gong, Xinqi},
  title = {scHG: A supercell framework with high-order graph learning enables scalable multi-omics analysis},
  journal = {PLOS Computational Biology},
  year = {2026},
  volume = {22},
  number = {5},
  pages = {e1013851},
  doi = {10.1371/journal.pcbi.1013851}
}
Kostenlos starten →