Benchmarking large language models for cell typing in single-cell RNA-Seq

	Benchmarking large language models for cell typing in single-cell RNA-Seq
	Xiao, TX; Hua, DZ; Wang, YA; Lu, XM; Zhang, C
	2025
发表期刊	Brief. Bioinform.
ISSN	1467-5463
卷号	26 期号:6
摘要	Large language models (LLMs) show significant potential for cell type annotation in single-cell RNA sequencing (scRNA-seq), but a systematic framework for their application and a comprehensive performance comparison are lacking. Here, we systematically benchmarked seven leading LLM models and three traditional bioinformatics tools across 34 diverse human and mouse datasets. We establish that using marker genes selected by statistical significance and ranked by log(2) fold change optimizes annotation accuracy. Our benchmark reveals that LLMs profoundly outperform traditional methods, particularly in resolving fine-grained cell subtypes. A top tier of models, including Kimi-k2, GPT-5, Claude-4.1, and Grok-4, consistently delivered the highest accuracy. To harness their collective strength, we developed an elite ensemble strategy that achieves state-of-the-art performance. We encapsulated these findings into DeepCellSeek, an open-source R package and interactive web platform, to provide a validated, high-performance solution. This work provides a practical roadmap for leveraging LLMs in single-cell research and paves the way for their evolution into powerful discovery engines.
收录类别	SCIE
语种	英语
文献类型	期刊论文
条目标识符	http://ir.kiz.ac.cn/handle/152453/15014
专题	管理、支撑部门_大脑进化与生物信息学（张超）
推荐引用方式 GB/T 7714	Xiao, TX,Hua, DZ,Wang, YA,et al. Benchmarking large language models for cell typing in single-cell RNA-Seq[J]. Brief. Bioinform.,2025,26(6).
APA	Xiao, TX,Hua, DZ,Wang, YA,Lu, XM,&Zhang, C.(2025).Benchmarking large language models for cell typing in single-cell RNA-Seq.Brief. Bioinform.,26(6).
MLA	Xiao, TX,et al."Benchmarking large language models for cell typing in single-cell RNA-Seq".Brief. Bioinform. 26.6(2025).

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
2026070702.pdf（2292KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	请求全文