Large Language Models Meet Virtual Cell: A Survey
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911199754452992 |
|---|---|
| author | Li, Krinos Xiao, Xianglu Deng, Shenglong He, Lucas Zhong, Zijun Zou, Yuanjie Zhan, Zhonghao Hui, Zheng Bao, Weiye Yang, Guang |
| author_facet | Li, Krinos Xiao, Xianglu Deng, Shenglong He, Lucas Zhong, Zijun Zou, Yuanjie Zhan, Zhonghao Hui, Zheng Bao, Weiye Yang, Guang |
| contents | Large language models (LLMs) are transforming cellular biology by enabling the development of "virtual cells"--computational systems that represent, predict, and reason about cellular states and behaviors. This work provides a comprehensive review of LLMs for virtual cell modeling. We propose a unified taxonomy that organizes existing methods into two paradigms: LLMs as Oracles, for direct cellular modeling, and LLMs as Agents, for orchestrating complex scientific tasks. We identify three core tasks--cellular representation, perturbation prediction, and gene regulation inference--and review their associated models, datasets, evaluation benchmarks, as well as the critical challenges in scalability, generalizability, and interpretability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07706 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Large Language Models Meet Virtual Cell: A Survey Li, Krinos Xiao, Xianglu Deng, Shenglong He, Lucas Zhong, Zijun Zou, Yuanjie Zhan, Zhonghao Hui, Zheng Bao, Weiye Yang, Guang Computation and Language Computational Engineering, Finance, and Science Machine Learning Cell Behavior Large language models (LLMs) are transforming cellular biology by enabling the development of "virtual cells"--computational systems that represent, predict, and reason about cellular states and behaviors. This work provides a comprehensive review of LLMs for virtual cell modeling. We propose a unified taxonomy that organizes existing methods into two paradigms: LLMs as Oracles, for direct cellular modeling, and LLMs as Agents, for orchestrating complex scientific tasks. We identify three core tasks--cellular representation, perturbation prediction, and gene regulation inference--and review their associated models, datasets, evaluation benchmarks, as well as the critical challenges in scalability, generalizability, and interpretability. |
| title | Large Language Models Meet Virtual Cell: A Survey |
| topic | Computation and Language Computational Engineering, Finance, and Science Machine Learning Cell Behavior |
| url | https://arxiv.org/abs/2510.07706 |