EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Interpretable Graph-Regularized Optimal Transport Framework for Diagonal Single-Cell Integrative Analysis

Zexuan Wang iD, Qipeng Zhan, Shu Yang iD, Zhuoping Zhou, Mengyuan Kan iD, Tianhuan Zhai, Li Shen iD

GigaScience · 2026

DOI: 10.1093/gigascience/giag012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift GigaScience, 2026. Verfasst von Zexuan Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Graduate Group in Applied Mathematics and Computational Science, University of Pennsylvania, 209 S. 33rd Street Philadelphia, PA 19104-6395, USA. Hauptthemen laut MEDLINE: Single-Cell Analysis, Computational Biology. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIA NIH HHS, NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background Recent advancements in single-cell omics technologies have enabled detailed characterization of cellular processes. However, coassay sequencing technologies remain limited, resulting in un-paired single-cell omics datasets with differing feature dimensions Finding we present GROTIA (Graph-Regularized Optimal Transport Framework for Diagonal Single-Cell Integrative Analysis), a computational method to align multi-omics datasets without requiring any prior correspondence information. GROTIA achieves global alignment through optimal transport while preserving local relationships via graph regularization. Additionally, our approach provides interpretability by deriving domain-specific feature importance from partial derivatives, highlighting key biological markers. Moreover, the transport plan between modalities can be leveraged for post-integration clustering, enabling a data-driven approach to discover novel cell subpopulations Conclusions We demonstrate GROTIA’s superior performance on four simulated and four real-world datasets, surpassing state-of-the-art unsupervised alignment methods and confirming the biological significance of the top features identified in each domain.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single-Cell AnalysisComputational BiologyAlgorithmsMultiomicsHumansClustering AlgorithmsSoftware

Stichwörter der Autor:innen

data integrationgraph Laplacianinterpretablemulti-omicsoptimal transportsingle cell

Autor:innen und Institutionen

  • Graduate Group in Applied Mathematics and Computational Science, University of Pennsylvania, 209 S. 33rd Street Philadelphia, PA 19104-6395, USA.
  • Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA.

ORCID-Profile: Zexuan Wang, Shu Yang, Mengyuan Kan, Li Shen

Förderung

  • NIA NIH HHS
  • NIH HHS

Zitieren

APA

Wang, Z., Zhan, Q., Yang, S., Zhou, Z., Kan, M., Zhai, T., & Shen, L. (2026). An Interpretable Graph-Regularized Optimal Transport Framework for Diagonal Single-Cell Integrative Analysis. GigaScience. https://doi.org/10.1093/gigascience/giag012

Vancouver

Wang Z, Zhan Q, Yang S, Zhou Z, Kan M, Zhai T, et al. An Interpretable Graph-Regularized Optimal Transport Framework for Diagonal Single-Cell Integrative Analysis. GigaScience. 2026. doi:10.1093/gigascience/giag012

BibTeX
@article{Wang2026,
  author = {Wang, Zexuan and Zhan, Qipeng and Yang, Shu and Zhou, Zhuoping and Kan, Mengyuan and Zhai, Tianhuan and Shen, Li},
  title = {An Interpretable Graph-Regularized Optimal Transport Framework for Diagonal Single-Cell Integrative Analysis},
  journal = {GigaScience},
  year = {2026},
  doi = {10.1093/gigascience/giag012}
}
Kostenlos starten →