Large language models are universal biomedical simulators

Abstract Computational simulation of biological processes can be a valuable tool in accelerating biomedical research, but usually requires extensive domain knowledge and manual adaptation. Recently, large language models (LLMs) such as GPT-4 have proven surprisingly successful for a wide range of tasks by generating human language at a very large scale. Here we explore the potential of leveraging LLMs as simulators of biological systems. We establish proof-of-concept of a text-based simulator, SimulateGPT, that uses LLM reasoning. We demonstrate good prediction performance for various biomedical applications, without requiring explicit domain knowledge or manual tuning. LLMs thus enable a new class of versatile and broadly applicable biological simulators. This text-based simulation paradigm is well-suited for modeling and understanding complex living systems that are difficult to describe with physics-based first-principles simulation, but for which extensive knowledge and context is available as written text.