Integrating Large Language Models For Monte Carlo Simulation of Chemical Reaction Networks

2025-03-27

AI Summary

Manual construction of kinetic parameters for chemical reaction networks is time-consuming and requires domain expertise. Method: We propose the first end-to-end large language model (LLM)-driven framework that automatically parses natural-language reaction descriptions, generates structured kinetic models, and executes stochastic Monte Carlo simulations—enabled by prompt engineering and output constraints to ensure semantic fidelity, with seamless integration into COPASI. Results: Evaluated across diverse biochemical networks, our method reconstructs dynamical behaviors matching hand-crafted models with <5% error, substantially lowering modeling barriers. Contribution: This work establishes the first fully automated, closed-loop pipeline from natural language to executable stochastic simulation. Crucially, it also identifies fundamental limitations of LLMs in generalizing complex nonlinear rate laws—a key insight for advancing AI-augmented systems biology modeling.

Technology Category

• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Chemical reaction network is an important method for modeling and exploring complex biological processes, bio-chemical interactions and the behavior of different dynamics in system biology. But, formulating such reaction kinetics takes considerable time. In this paper, we leverage the efficiency of modern large language models to automate the stochastic monte carlo simulation of chemical reaction networks and enable the simulation through the reaction description provided in the form of natural languages. We also integrate this process into widely used simulation tool Copasi to further give the edge and ease to the modelers and researchers. In this work, we show the efficacy and limitations of the modern large language models to parse and create reaction kinetics for modelling complex chemical reaction processes.

Problem

• Automating Monte Carlo simulation of chemical reaction networks
• Enabling simulation via natural language reaction descriptions
• Integrating LLMs into Copasi for easier modeling

Innovation

• Leverage large language models for automation
• Enable natural language reaction descriptions
• Integrate with Copasi simulation tool