Automating De Novo Protein Design via LLM-Based Multi-agent Systems
Document Type
Conference Proceeding
Publication Date
Summer 7-2-2026
Abstract
Designing de novo proteins, synthetic proteins with functions not found in nature, is a complex and resource-intensive process. Traditional methods face limitations due to high computational costs, manual intervention, and inefficient exploration of the vast protein sequence space. This work presents Protogenix, a modular multi-agent system powered by large language models (LLMs) to automate the protein design pipeline. The system leverages tools such as Chroma, OmegaFold, and Anisotropic Network Model (ANM) analysis to handle generation, structure prediction, and mechanical analysis. Through LangGraph and Retrieval-Augmented Generation (RAG), agents collaborate asynchronously, enabling efficient planning, execution, and refinement. This architecture reduces human oversight and accelerates protein design, democratizing access to cutting-edge computational biology tools. Protogenix achieved RMSD values as low as 1.2 Å, pLDDT scores above 89, and 95% success after revision, outperforming or matching baselines like ProtAgents and Baker Lab in flexibility, automation, and cost-efficiency.
Recommended Citation
Abdelaziz, Konouz; Pester, Andreas; Andres, Frederic; and Mostafa, Noha, "Automating De Novo Protein Design via LLM-Based Multi-agent Systems" (2026). Mechanical Engineering. 292.
https://buescholar.bue.edu.eg/mech_eng/292