Integrative evidence-knowledge marker selection enhances LLM-based cell type annotation in single-cell RNA-seq analysis

BioData Mining

卷:19

Research

Jiyeong Shin¹  Soyoung Jeong^2,3  Hyun Je Kim^2,4,5  Minsik Oh¹ 

[1] Department of Artificial Intelligence, Myongji University, Seoul, Republic of Korea

[2] Genomic Medicine Institute, Seoul National University Medical Research Center, Seoul, Republic of Korea

[3] Cancer Research Institute, Seoul National University College of Medicine, Seoul, Republic of Korea

[4] Department of Biomedical Sciences, Seoul National University Graduate School, Seoul, Republic of Korea

[5] Interdisciplinary Program in Artificial Intelligence (IPAI), Seoul National University, Seoul, Republic of Korea

关键词: Single-cell RNA-seq;    Large language model;    Cell type annotation;    Information integration;    Marker gene;   

DOI  :  10.1186/s13040-026-00593-7

 received in 2026-03-10, accepted in 2026-08-01,  发布年份 2026

来源: Springer

【 摘 要 】

BackgroundCell type annotation is essential for gaining biological insight from single-cell RNA sequencing data, yet manual labeling remains time-consuming and difficult to reproduce. Various computational approaches have been developed to automate this process, and recent studies suggest that large language models can infer cell types with promising accuracy in single-cell analysis. However, most workflows still rely on cluster-specific markers derived from gene expression alone or manual curation. As a result, marker selection can be sensitive to statistical criteria and dataset-dependent bias, which may lead to the selection of less informative genes or missing important markers, while providing limited biological context.ResultsTo address this limitation, we introduce CELLIA, an LLM-based workflow for automated and robust cell type annotation. CELLIA employs an integrative evidence-knowledge marker selection strategy that combines statistical differential expression criteria with curated tissue-specific marker resources to identify informative marker genes. In benchmarking analyses of 102 cell types, this approach improved agreement with manual annotations. In addition, CELLIA achieved higher agreement in subtype-level analyses of closely related immune populations and was further evaluated in a non-immune stromal subtype setting, covering 25 cell types in total.ConclusionBy integrating evidence-knowledge from gene expression with curated biological prior knowledge, CELLIA provides a more stable marker selection and improves the reliability of LLM-cell type annotation.

【 授权许可】

CC BY-NC-ND   
© The Author(s) 2026

【 图 表 】

Fig. 8

Fig. 2

Fig. 1