Salvato in:
Dettagli Bibliografici
Autori principali: Mao, Yuren, Mi, Yu, Liu, Peigen, Zhang, Mengfei, Liu, Hanqing, Gao, Yunjun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2504.04698
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913780488732672
author Mao, Yuren
Mi, Yu
Liu, Peigen
Zhang, Mengfei
Liu, Hanqing
Gao, Yunjun
author_facet Mao, Yuren
Mi, Yu
Liu, Peigen
Zhang, Mengfei
Liu, Hanqing
Gao, Yunjun
contents Cell type annotation is critical for understanding cellular heterogeneity. Based on single-cell RNA-seq data and deep learning models, good progress has been made in annotating a fixed number of cell types within a specific tissue. However, universal cell annotation, which can generalize across tissues, discover novel cell types, and extend to novel cell types, remains less explored. To fill this gap, this paper proposes scAgent, a universal cell annotation framework based on Large Language Models (LLMs). scAgent can identify cell types and discover novel cell types in diverse tissues; furthermore, it is data efficient to learn novel cell types. Experimental studies in 160 cell types and 35 tissues demonstrate the superior performance of scAgent in general cell-type annotation, novel cell discovery, and extensibility to novel cell type.
format Preprint
id arxiv_https___arxiv_org_abs_2504_04698
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle scAgent: Universal Single-Cell Annotation via a LLM Agent
Mao, Yuren
Mi, Yu
Liu, Peigen
Zhang, Mengfei
Liu, Hanqing
Gao, Yunjun
Computation and Language
Cell type annotation is critical for understanding cellular heterogeneity. Based on single-cell RNA-seq data and deep learning models, good progress has been made in annotating a fixed number of cell types within a specific tissue. However, universal cell annotation, which can generalize across tissues, discover novel cell types, and extend to novel cell types, remains less explored. To fill this gap, this paper proposes scAgent, a universal cell annotation framework based on Large Language Models (LLMs). scAgent can identify cell types and discover novel cell types in diverse tissues; furthermore, it is data efficient to learn novel cell types. Experimental studies in 160 cell types and 35 tissues demonstrate the superior performance of scAgent in general cell-type annotation, novel cell discovery, and extensibility to novel cell type.
title scAgent: Universal Single-Cell Annotation via a LLM Agent
topic Computation and Language
url https://arxiv.org/abs/2504.04698