TMCells: A topic-based probabilistic framework for interpretable metacell construction in single-cell data
Bioinformatics · 17.11.2026
DOI: 10.1093/bioinformatics/btag840 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 17.11.2026. Verfasst von Wenqi Qiu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics, Harbin Institute of Technology, Harbin 150000, China. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Motivation Metacells have emerged as an important analytical strategy for addressing the computational barriers posed by the scale and complexity of large-scale single-cell omics data, while preserving biologically relevant information and improving analytical interpretability. However, existing metacell inference methods usually have limited biological interpretability, rely on deterministic assignments that insufficiently capture continuous state transitions, and may lose potential biological signals due to prior feature selection or dimensionality reduction. Results We propose TMCells, an interpretable metacell identification algorithm based on a probabilistic generative framework. TMCells introduces the concept of topic modeling and uses a Gaussian mixture model as the prior for topic distribution, defining metacells as statistical distribution centers in the latent topic space. By modeling the cell generation process, TMCells enables the simultaneous learning of topic representations and metacell partitions in an end-to-end manner, capturing the continuity and uncertainty in cell state transitions. TMCells effectively identifies high-quality metacells, eliminating technical noise while preserving the original biological heterogeneity, thereby enhancing downstream analyses such as differential expression, rare cell type identification, and trajectory inference. Furthermore, TMCells provides an intuitive interpretation of cellular heterogeneity through latent topics associated with biologically meaningful regulatory programs, offering a generative perspective for dissecting regulatory dynamics during cell-state transitions. Availability and implementation The TMCells along with detailed documentation is freely available at https://github.com/Jinsl-lab/TMCells with DOI: 10.5281/zenodo.24198840. Supplementary Information Supplementary data are available at Bioinformatics online.
Autor:innen und Institutionen
- School of Mathematics, Harbin Institute of Technology, Harbin 150000, China.
- School of Automation (School of Artificial Intelligence), Beijing Information Sciene and Technology University, Beijing 100000, China.
Zitieren
APA
Qiu, W., Hua, J., Chen, J., Yan, Y., Li, Z., & Jin, S. (2026). TMCells: A topic-based probabilistic framework for interpretable metacell construction in single-cell data. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag840
Vancouver
Qiu W, Hua J, Chen J, Yan Y, Li Z, Jin S. TMCells: A topic-based probabilistic framework for interpretable metacell construction in single-cell data. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag840
BibTeX
@article{Qiu2026,
author = {Qiu, Wenqi and Hua, Jiao and Chen, Jing and Yan, Yushun and Li, Zhengyi and Jin, Shuilin},
title = {TMCells: A topic-based probabilistic framework for interpretable metacell construction in single-cell data},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag840}
}
EUVIMED