Automating MD simulations for Proteins using Large language Models: NAMD-Agent

2025-07-10

AI Summary

Preparing input files for protein molecular dynamics (MD) simulations is time-consuming and error-prone. This paper introduces the first end-to-end solution integrating a large language model (Gemini 2.0 Flash) with web automation, implemented via Python and Selenium to intelligently invoke and iteratively optimize the CHARMM Graphical User Interface (GUI), thereby generating high-fidelity NAMD input files automatically. Our key contributions are: (i) the first LLM-driven, GUI-based interactive parameter generation and self-correcting workflow requiring zero manual intervention; and (ii) an integrated post-processing module enabling parallel configuration of multi-protein systems. Experimental evaluation demonstrates over 80% reduction in simulation setup time, substantial mitigation of human-induced errors, and high robustness and scalability. The proposed framework delivers an efficient, fully automated, and standardized workflow for computational biophysics.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Molecular dynamics simulations are an essential tool in understanding protein structure, dynamics, and function at the atomic level. However, preparing high quality input files for MD simulations can be a time consuming and error prone process. In this work, we introduce an automated pipeline that leverages Large Language Models (LLMs), specifically Gemini 2.0 Flash, in conjunction with python scripting and Selenium based web automation to streamline the generation of MD input files. The pipeline exploits CHARMM GUI's comprehensive web-based interface for preparing simulation-ready inputs for NAMD. By integrating Gemini's code generation and iterative refinement capabilities, simulation scripts are automatically written, executed, and revised to navigate CHARMM GUI, extract appropriate parameters, and produce the required NAMD input files. Post processing is performed using additional software to further refine the simulation outputs, thereby enabling a complete and largely hands free workflow. Our results demonstrate that this approach reduces setup time, minimizes manual errors, and offers a scalable solution for handling multiple protein systems in parallel. This automated framework paves the way for broader application of LLMs in computational structural biology, offering a robust and adaptable platform for future developments in simulation automation.

Problem

• Automating MD simulation input file preparation for proteins
• Reducing time and errors in protein simulation setup
• Integrating LLMs to streamline NAMD input generation

Innovation

• Leverages LLMs for automating MD input file generation
• Integrates Gemini with Python and Selenium web automation
• Uses CHARMM GUI for simulation-ready NAMD inputs