Single-cell omics arena: evaluation of large language models for automatic cell-type annotations on single-cell omics data via RNA-seq bridging
Briefings in Bioinformatics · 2025
DOI: 10.1093/bib/bbaf622 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Junhao Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of California, Irvine, 6210 Donald Bren Hall, Irvine, CA 92697, United States. Hauptthemen laut MEDLINE: Single-Cell Analysis, RNA-Seq, Molecular Sequence Annotation, Sequence Analysis, RNA. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIDA NIH HHS, NHGRI NIH HHS, NIH HHS.
Abstract (Originalsprache)
The single-cell sequencing revolution enables simultaneous molecular profiling of various modalities across thousands of individual cells, allowing scientists to investigate the diverse functions of complex tissues. Among all the analysis steps, assigning individual cells to specific types is fundamental for understanding cellular heterogeneity. However, this process is labor-intensive and requires extensive expert knowledge. Recent advances in large language models (LLMs) have demonstrated their ability to automatically extract biological knowledge, such as marker genes, promoting efficient, and automated cell-type annotations. To evaluate the capability of modern LLMs in automating the cell-type identification process, we first introduce an automated cell-type annotation method with comprehensive benchmark: Single-cell Omics Arena). Specifically, we began by compiling 11 publicly available single-cell RNA sequencing (scRNA-seq) datasets and evaluating eight LLMs across 1226 cell-type annotation-related tasks. This effort established a foundation for automated cell-type annotation from scRNA-seq data using interpretable features such as gene names. Building upon this benchmark, we introduced domain-specific chain-of-thought prompting techniques to enhance the accuracy of cell-type annotation and facilitate the extraction of relevant biological insights. Finally, to accommodate non-interpretable features, we proposed to leverage a pretrained VAE-based cross-modality translation module to convert features such as epigenetic marks into interpretable representations, which enables the seamless extension of LLM-based cell-type annotation to non-RNA-based sequencing technologies. In summary, our benchmark provides key insights into automated cell-type annotation from scRNA-seq data and demonstrates the potential of cross-modality translation for handling non-interpretable features.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, University of California, Irvine, 6210 Donald Bren Hall, Irvine, CA 92697, United States.
- Department of Chemical and Biomolecular Engineering, University of California, Irvine, 5200 Engineering Hall, Irvine, CA 92697, United States.
ORCID-Profile: Junhao Liu, Siwei Xu, Yongxian Wu, Jing Zhang
Förderung
- NIDA NIH HHS
- NHGRI NIH HHS
- NIH HHS
- National Institutes of Health
Zitieren
APA
Liu, J., Xu, S., Wu, Y., & Zhang, J. (2025). Single-cell omics arena: evaluation of large language models for automatic cell-type annotations on single-cell omics data via RNA-seq bridging. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf622
Vancouver
Liu J, Xu S, Wu Y, Zhang J. Single-cell omics arena: evaluation of large language models for automatic cell-type annotations on single-cell omics data via RNA-seq bridging. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf622
BibTeX
@article{Liu2025,
author = {Liu, Junhao and Xu, Siwei and Wu, Yongxian and Zhang, Jing},
title = {Single-cell omics arena: evaluation of large language models for automatic cell-type annotations on single-cell omics data via RNA-seq bridging},
journal = {Briefings in Bioinformatics},
year = {2025},
doi = {10.1093/bib/bbaf622}
}
EUVIMED