Giving Simulated Cells a Voice: Evolving Prompt-to-Intervention Models for Cellular Control
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_ | 1866908504144478208 |
|---|---|
| author | Le, Nam H. Erikson, Patrick Zhang, Yanbo Levin, Michael Bongard, Josh |
| author_facet | Le, Nam H. Erikson, Patrick Zhang, Yanbo Levin, Michael Bongard, Josh |
| contents | Guiding biological systems toward desired states, such as morphogenetic outcomes, remains a fundamental challenge with far-reaching implications for medicine and synthetic biology. While large language models (LLMs) have enabled natural language as an interface for interpretable control in AI systems, their use as mediators for steering biological or cellular dynamics remains largely unexplored.
In this work, we present a functional pipeline that translates natural language prompts into spatial vector fields capable of directing simulated cellular collectives. Our approach combines a large language model with an evolvable neural controller (Prompt-to-Intervention, or P2I), optimized via evolutionary strategies to generate behaviors such as clustering or scattering in a simulated 2D environment.
We demonstrate that even with constrained vocabulary and simplified cell models, evolved P2I networks can successfully align cellular dynamics with user-defined goals expressed in plain language. This work offers a complete loop from language input to simulated bioelectric-like intervention to behavioral output, providing a foundation for future systems capable of natural language-driven cellular control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_02766 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Giving Simulated Cells a Voice: Evolving Prompt-to-Intervention Models for Cellular Control Le, Nam H. Erikson, Patrick Zhang, Yanbo Levin, Michael Bongard, Josh Artificial Intelligence Neural and Evolutionary Computing Robotics Tissues and Organs Guiding biological systems toward desired states, such as morphogenetic outcomes, remains a fundamental challenge with far-reaching implications for medicine and synthetic biology. While large language models (LLMs) have enabled natural language as an interface for interpretable control in AI systems, their use as mediators for steering biological or cellular dynamics remains largely unexplored. In this work, we present a functional pipeline that translates natural language prompts into spatial vector fields capable of directing simulated cellular collectives. Our approach combines a large language model with an evolvable neural controller (Prompt-to-Intervention, or P2I), optimized via evolutionary strategies to generate behaviors such as clustering or scattering in a simulated 2D environment. We demonstrate that even with constrained vocabulary and simplified cell models, evolved P2I networks can successfully align cellular dynamics with user-defined goals expressed in plain language. This work offers a complete loop from language input to simulated bioelectric-like intervention to behavioral output, providing a foundation for future systems capable of natural language-driven cellular control. |
| title | Giving Simulated Cells a Voice: Evolving Prompt-to-Intervention Models for Cellular Control |
| topic | Artificial Intelligence Neural and Evolutionary Computing Robotics Tissues and Organs |
| url | https://arxiv.org/abs/2505.02766 |