GatorSC: multi-scale cell and gene graphs with mixture-of-experts fusion for single-cell transcriptomics
Briefings in Bioinformatics · 04.05.2026 · 27 (3)
DOI: 10.1093/bib/bbag330 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 17.06.2026. Verfasst von Yuxi Liu und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics and Health Data Science, Indiana University School of Medicine, Indianapolis, 410 W 10th St, IN 46202, United States. Hauptthemen laut MEDLINE: Single-Cell Analysis, Transcriptome, Software, Gene Expression Profiling. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIH HHS, NIA NIH HHS, Australia National Health and Medical Research Council (NHMRC) Investigator Fellowship.
Abstract (Originalsprache)
Single-cell RNA sequencing (scRNA-seq) enables high-resolution characterization of cellular heterogeneity, but its rich, complementary structure across cells and genes remains underexploited, especially in the presence of technical noise and sparsity. Effectively leveraging this multi-scale structure is essentially an information fusion problem that requires integrating heterogeneous graph-based views of cells and genes into robust low-dimensional representations. In this paper, we introduce GatorSC, a unified representation learning framework that models scRNA-seq data through multi-scale cell and gene graphs and fuses them with a mixture-of-experts architecture. GatorSC constructs a global cell–cell graph, a global gene–gene graph, and a local gene–gene graph derived from neighborhood-specific subgraphs, and learns graph neural network embeddings that are adaptively fused by a gating network. To learn noise-robust and structure-preserving embeddings without labels, we couple graph reconstruction and graph contrastive learning in a unified self-supervised objective applied to both cell- and gene-level graphs. We evaluate GatorSC on 19 publicly available scRNA-seq datasets covering diverse tissues, species, and sequencing platforms. Experiments showed that GatorSC consistently outperforms state-of-the-art deep generative, graph-based, and contrastive methods for cell clustering, gene expression imputation, and cell-type annotation. The learned embeddings are used for accurate trajectory inference, recovery of canonical marker gene programs, and cell-type-specific pathway signatures in an Alzheimer’s disease single-nucleus dataset. GatorSC provides a flexible foundation for comprehensive single-cell transcriptomic analysis and can be readily extended to multi-omic and spatial modalities.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biostatistics and Health Data Science, Indiana University School of Medicine, Indianapolis, 410 W 10th St, IN 46202, United States.
- College of Life Sciences, Northwest A&F University, No. 3 Taicheng Road, Yangling, Shaanxi 712100, China.
- Department of Computer Science, The University of North Carolina at Chapel Hill, 232 S Columbia St, NC 27599, United States.
- Department of Computer Science, University of Central Florida, 4000 Central Florida Blvd., FL 32816, United States.
- School of Computer Science and Engineering, Faculty of Engineering, University of New South Wales, High St, Kensington, NSW 2052, Australia.
- School of Computing and Information Technology, Faculty of Engineering and Information Sciences, University of Wollongong, Wollongong, NSW 2522, Australia.
Förderung
- NIH HHS
- NIA NIH HHS
- Australia National Health and Medical Research Council (NHMRC) Investigator Fellowship
- National Institutes of Health
Zitieren
APA
Liu, Y., Zhang, Z., Qiu, M., Wang, S., Salim, F. D., Shen, J., Chen, T., Razzak, I., Li, F., & Bian, J. (2026). GatorSC: multi-scale cell and gene graphs with mixture-of-experts fusion for single-cell transcriptomics. Briefings in Bioinformatics, 27(3). https://doi.org/10.1093/bib/bbag330
Vancouver
Liu Y, Zhang Z, Qiu M, Wang S, Salim FD, Shen J, et al. GatorSC: multi-scale cell and gene graphs with mixture-of-experts fusion for single-cell transcriptomics. Briefings in Bioinformatics. 2026;27(3). doi:10.1093/bib/bbag330
BibTeX
@article{Liu2026,
author = {Liu, Yuxi and Zhang, Zhenhao and Qiu, Mufan and Wang, Song and Salim, Flora D and Shen, Jun and Chen, Tianlong and Razzak, Imran and Li, Fuyi and Bian, Jiang},
title = {GatorSC: multi-scale cell and gene graphs with mixture-of-experts fusion for single-cell transcriptomics},
journal = {Briefings in Bioinformatics},
year = {2026},
volume = {27},
number = {3},
doi = {10.1093/bib/bbag330}
}
EUVIMED