DynaMate: An Autonomous Agent for Protein-Ligand Molecular Dynamics Simulations

2025-12-10

AI Summary

Molecular dynamics (MD) simulations are widely used in drug discovery, yet their adoption is hindered by high technical barriers—including system parameterization, input preparation, and software configuration—limiting efficiency and reproducibility. Method: We propose the first modular, multi-agent framework for end-to-end automation of protein–ligand MD workflows, pioneering the integration of embodied agents into this domain. The framework synergistically combines LLM-driven autonomous planning, dynamic tool invocation, web-based literature retrieval, PaperQA-enhanced scientific document understanding, and self-correcting mechanisms, while seamlessly interfacing with AMBER/GROMACS and MM/PB(GB)SA free-energy calculation pipelines. Contribution/Results: Evaluated on 12 multiscale benchmark systems, the framework achieves 100% end-to-end success, automatically diagnosing and rectifying runtime errors, and delivering structural analyses and binding free-energy estimates. It markedly improves modeling efficiency, robustness, and reproducibility.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Force field-based molecular dynamics (MD) simulations are indispensable for probing the structure, dynamics, and functions of biomolecular systems, including proteins and protein-ligand complexes. Despite their broad utility in drug discovery and protein engineering, the technical complexity of MD setup, encompassing parameterization, input preparation, and software configuration, remains a major barrier for widespread and efficient usage. Agentic LLMs have demonstrated their capacity to autonomously execute multi-step scientific processes, and to date, they have not successfully been used to automate protein-ligand MD workflows. Here, we present DynaMate, a modular multi-agent framework that autonomously designs and executes complete MD workflows for both protein and protein-ligand systems, and offers free energy binding affinity calculations with the MM/PB(GB)SA method. The framework integrates dynamic tool use, web search, PaperQA, and a self-correcting behavior. DynaMate comprises three specialized modules, interacting to plan the experiment, perform the simulation, and analyze the results. We evaluated its performance across twelve benchmark systems of varying complexity, assessing success rate, efficiency, and adaptability. DynaMate reliably performed full MD simulations, corrected runtime errors through iterative reasoning, and produced meaningful analyses of protein-ligand interactions. This automated framework paves the way toward standardized, scalable, and time-efficient molecular modeling pipelines for future biomolecular and drug design applications.

Problem

• Automates complex molecular dynamics simulation workflows
• Reduces technical barriers in protein-ligand interaction studies
• Enables autonomous error correction and result analysis

Innovation

• Autonomous multi-agent framework for molecular dynamics simulations
• Integrates dynamic tools, web search, and self-correcting behavior
• Automates protein-ligand MD workflows with free energy calculations