EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Gene-Chronos: parameter-efficient developmental time inference using a pretrained single-cell foundation model

Yinbo Liu, Handi Gao, Tian Tian iD

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag469 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Yinbo Liu und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China. Hauptthemen laut MEDLINE: Single-Cell Analysis, Gene Expression Regulation, Developmental, Transcriptome. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Lei Jun Foundation Limited and the Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large-scale single-cell and spatial transcriptomic atlases enable the study of developmental processes at high resolution. However, most datasets capture only static snapshots of cells, making it difficult to infer continuous biological time from transcriptomic profiles. Existing temporal inference methods often show limited robustness across heterogeneous datasets, and recent single-cell foundation models, although powerful for representation learning, are not designed to capture continuous temporal relationships. We present Gene-Chronos, a parameter-efficient framework for developmental time inference built on a frozen pretrained Geneformer backbone. The model introduces learnable temporal prompt tokens and a temporal contrastive objective to extract time-informative signals and encourage temporally coherent organization of cell representations. Across multiple benchmark datasets spanning diverse species and developmental stages, Gene-Chronos outperforms existing approaches and demonstrates strong generalization to previously unseen samples. Attention-based analyses further identify genes associated with developmental progression, providing interpretable insights into temporal gene expression dynamics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single-Cell AnalysisGene Expression Regulation, DevelopmentalTranscriptomeAnimalsSingle-Cell Gene Expression AnalysisGene Expression ProfilingSpatial TranscriptomicsHumans

Stichwörter der Autor:innen

developmental time inferencesingle-cell transcriptomicsspatial transcriptomicstransfer generalization

Autor:innen und Institutionen

  • School of Computer Science, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China.
  • School of Artificial Intelligence, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China.
  • School of Mathematics and Statistics, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China.

ORCID-Profile: Tian Tian

Förderung

  • Lei Jun Foundation Limited and the Fundamental Research Funds for the Central Universities

Zitieren

APA

Liu, Y., Gao, H., & Tian, T. (2026). Gene-Chronos: parameter-efficient developmental time inference using a pretrained single-cell foundation model. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag469

Vancouver

Liu Y, Gao H, Tian T. Gene-Chronos: parameter-efficient developmental time inference using a pretrained single-cell foundation model. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag469

BibTeX
@article{Liu2026,
  author = {Liu, Yinbo and Gao, Handi and Tian, Tian},
  title = {Gene-Chronos: parameter-efficient developmental time inference using a pretrained single-cell foundation model},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag469}
}
Kostenlos starten →