Assessing GPT-4 for cell type annotation in single-cell RNA-seq analysis

Wenpin Hou; Zhicheng Ji

doi:10.1038/s41592-024-02235-4

Assessing GPT-4 for cell type annotation in single-cell RNA-seq analysis

Nat Methods. 2024 Mar 25. doi: 10.1038/s41592-024-02235-4. Online ahead of print.

Authors

Wenpin Hou¹, Zhicheng Ji²

Affiliations

¹ Department of Biostatistics, Columbia University Mailman School of Public Health, New York City, NY, USA. wh2526@cumc.columbia.edu.
² Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC, USA. zhicheng.ji@duke.edu.

PMID: 38528186
DOI: 10.1038/s41592-024-02235-4

Abstract

Here we demonstrate that the large language model GPT-4 can accurately annotate cell types using marker gene information in single-cell RNA sequencing analysis. When evaluated across hundreds of tissue and cell types, GPT-4 generates cell type annotations exhibiting strong concordance with manual annotations. This capability can considerably reduce the effort and expertise required for cell type annotation. Additionally, we have developed an R software package GPTCelltype for GPT-4's automated cell type annotation.