CellForge: Agentic Design of Virtual Cell Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Xiangru, Yu, Zhuoyun, Chen, Jiapeng, Cui, Yan, Shao, Daniel, Wang, Weixu, Wu, Fang, Zhuang, Yuchen, Shi, Wenqi, Huang, Zhi, Cohan, Arman, Lin, Xihong, Theis, Fabian, Krishnaswamy, Smita, Gerstein, Mark
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912878235222016
author Tang, Xiangru
Yu, Zhuoyun
Chen, Jiapeng
Cui, Yan
Shao, Daniel
Wang, Weixu
Wu, Fang
Zhuang, Yuchen
Shi, Wenqi
Huang, Zhi
Cohan, Arman
Lin, Xihong
Theis, Fabian
Krishnaswamy, Smita
Gerstein, Mark
author_facet Tang, Xiangru
Yu, Zhuoyun
Chen, Jiapeng
Cui, Yan
Shao, Daniel
Wang, Weixu
Wu, Fang
Zhuang, Yuchen
Shi, Wenqi
Huang, Zhi
Cohan, Arman
Lin, Xihong
Theis, Fabian
Krishnaswamy, Smita
Gerstein, Mark
contents Virtual cell modeling aims to predict cellular responses to diverse perturbations but faces challenges from biological complexity, multimodal data heterogeneity, and the need for interdisciplinary expertise. We introduce CellForge, a multi-agent framework that autonomously designs and synthesizes neural network architectures tailored to specific single-cell datasets and perturbation tasks. Given raw multi-omics data and task descriptions, CellForge discovers candidate architectures through collaborative reasoning among specialized agents, then generates executable implementations. Our core contribution is the framework itself: showing that multi-agent collaboration mechanisms - rather than manual human design or single-LLM prompting - can autonomously produce executable, high-quality computational methods. This approach goes beyond conventional hyperparameter tuning by enabling entirely new architectural components such as trajectory-aware encoders and perturbation diffusion modules to emerge from agentic deliberation. We evaluate CellForge on six datasets spanning gene knockouts, drug treatments, and cytokine stimulations across multiple modalities (scRNA-seq, scATAC-seq, CITE-seq). The results demonstrate that the models generated by CellForge are highly competitive with established baselines, while revealing systematic patterns of architectural innovation. CellForge highlights the scientific value of multi-agent frameworks: collaboration among specialized agents enables genuine methodological innovation and executable solutions that single agents or human experts cannot achieve. This represents a paradigm shift toward autonomous scientific method development in computational biology. Code is available at https://github.com/gersteinlab/CellForge.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02276
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CellForge: Agentic Design of Virtual Cell Models
Tang, Xiangru
Yu, Zhuoyun
Chen, Jiapeng
Cui, Yan
Shao, Daniel
Wang, Weixu
Wu, Fang
Zhuang, Yuchen
Shi, Wenqi
Huang, Zhi
Cohan, Arman
Lin, Xihong
Theis, Fabian
Krishnaswamy, Smita
Gerstein, Mark
Machine Learning
Artificial Intelligence
Computation and Language
Quantitative Methods
Virtual cell modeling aims to predict cellular responses to diverse perturbations but faces challenges from biological complexity, multimodal data heterogeneity, and the need for interdisciplinary expertise. We introduce CellForge, a multi-agent framework that autonomously designs and synthesizes neural network architectures tailored to specific single-cell datasets and perturbation tasks. Given raw multi-omics data and task descriptions, CellForge discovers candidate architectures through collaborative reasoning among specialized agents, then generates executable implementations. Our core contribution is the framework itself: showing that multi-agent collaboration mechanisms - rather than manual human design or single-LLM prompting - can autonomously produce executable, high-quality computational methods. This approach goes beyond conventional hyperparameter tuning by enabling entirely new architectural components such as trajectory-aware encoders and perturbation diffusion modules to emerge from agentic deliberation. We evaluate CellForge on six datasets spanning gene knockouts, drug treatments, and cytokine stimulations across multiple modalities (scRNA-seq, scATAC-seq, CITE-seq). The results demonstrate that the models generated by CellForge are highly competitive with established baselines, while revealing systematic patterns of architectural innovation. CellForge highlights the scientific value of multi-agent frameworks: collaboration among specialized agents enables genuine methodological innovation and executable solutions that single agents or human experts cannot achieve. This represents a paradigm shift toward autonomous scientific method development in computational biology. Code is available at https://github.com/gersteinlab/CellForge.
title CellForge: Agentic Design of Virtual Cell Models
topic Machine Learning
Artificial Intelligence
Computation and Language
Quantitative Methods
url https://arxiv.org/abs/2508.02276