CellTypeAgent: Trustworthy cell type annotation with Large Language Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Jiawen, Zhang, Jianghao, Yao, Huaxiu, Li, Yun
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912374205710336
author Chen, Jiawen
Zhang, Jianghao
Yao, Huaxiu
Li, Yun
author_facet Chen, Jiawen
Zhang, Jianghao
Yao, Huaxiu
Li, Yun
contents Cell type annotation is a critical yet laborious step in single-cell RNA sequencing analysis. We present a trustworthy large language model (LLM)-agent, CellTypeAgent, which integrates LLMs with verification from relevant databases. CellTypeAgent achieves higher accuracy than existing methods while mitigating hallucinations. We evaluated CellTypeAgent across nine real datasets involving 303 cell types from 36 tissues. This combined approach holds promise for more efficient and reliable cell type annotation.
format Preprint
id arxiv_https___arxiv_org_abs_2505_08844
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CellTypeAgent: Trustworthy cell type annotation with Large Language Models
Chen, Jiawen
Zhang, Jianghao
Yao, Huaxiu
Li, Yun
Genomics
Artificial Intelligence
68T20
I.2.1
Cell type annotation is a critical yet laborious step in single-cell RNA sequencing analysis. We present a trustworthy large language model (LLM)-agent, CellTypeAgent, which integrates LLMs with verification from relevant databases. CellTypeAgent achieves higher accuracy than existing methods while mitigating hallucinations. We evaluated CellTypeAgent across nine real datasets involving 303 cell types from 36 tissues. This combined approach holds promise for more efficient and reliable cell type annotation.
title CellTypeAgent: Trustworthy cell type annotation with Large Language Models
topic Genomics
Artificial Intelligence
68T20
I.2.1
url https://arxiv.org/abs/2505.08844