EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Evaluating the Utilities of Foundation Models in Single‐Cell Data Analysis

Tianyu Liu iD, Kexing Li, Yuge Wang, Hongyu Li, Hongyu Zhao iD

Advanced Science · 2026-05 · 13 (27)

DOI: 10.1002/advs.202514490 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 23.03.2026. Verfasst von Tianyu Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Interdepartmental Program in Computational Biology & Bioinformatics, Yale University, Connecticut, USA. Hauptthemen laut MEDLINE: Single-Cell Analysis, Data Analysis. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 154 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHGRI NIH HHS, NIH HHS, NIGMS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Foundation Models (FMs) have made significant strides in both industrial and scientific domains. In this paper, we evaluate the performance of FMs for single‐cell sequencing data analysis through comprehensive experiments across eight downstream tasks pertinent to single‐cell data. Overall, the top FMs include scGPT, Geneformer, and CellFM by considering model performances and user accessibility among ten single‐cell FMs. However, by comparing these FMs with task‐specific methods, we found that single‐cell FMs may not consistently excel than task‐specific methods in all tasks, which challenges the necessity of developing foundation models for single‐cell analysis. In addition, we evaluated the effects of hyperparameters, initial settings, and stability for training single‐cell FMs based on a proposed scEval framework, and provide guidelines for pre‐training and fine‐tuning to enhance the performances of single‐cell FMs. Our work summarizes the current state of single‐cell FMs, points to their constraints and avenues for future development, and offers a freely available evaluation pipeline to benchmark new models and improve method development.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single-Cell AnalysisData AnalysisHumans

Stichwörter der Autor:innen

benchmarkdeep learningfoundation modellarge language modelsingle‐cell data

Autor:innen und Institutionen

  • Interdepartmental Program in Computational Biology & Bioinformatics, Yale University, Connecticut, USA.
  • Department of Biostatistics, Yale University, Connecticut, USA.

ORCID-Profile: Tianyu Liu, Hongyu Zhao

Förderung

  • NHGRI NIH HHS
  • NIH HHS
  • NIGMS NIH HHS
  • NCI NIH HHS
  • National Institutes of Health

Zitieren

APA

Liu, T., Li, K., Wang, Y., Li, H., & Zhao, H. (2026). Evaluating the Utilities of Foundation Models in Single‐Cell Data Analysis. Advanced Science, 13(27). https://doi.org/10.1002/advs.202514490

Vancouver

Liu T, Li K, Wang Y, Li H, Zhao H. Evaluating the Utilities of Foundation Models in Single‐Cell Data Analysis. Advanced Science. 2026;13(27). doi:10.1002/advs.202514490

BibTeX
@article{Liu2026,
  author = {Liu, Tianyu and Li, Kexing and Wang, Yuge and Li, Hongyu and Zhao, Hongyu},
  title = {Evaluating the Utilities of Foundation Models in Single‐Cell Data Analysis},
  journal = {Advanced Science},
  year = {2026},
  volume = {13},
  number = {27},
  doi = {10.1002/advs.202514490}
}
Kostenlos starten →