Swarms of Large Language Model Agents for Protein Sequence Design with Experimental Validation

2025-11-27

AI Summary

Existing de novo protein design methods face limitations in flexibility, scalability, and target-directed control. To address these challenges, this work introduces a decentralized large language model (LLM) agent swarm framework. Each agent operates in parallel per residue position, integrating local interaction modeling, iterative feedback mechanisms, and position-specific architecture to enable context-aware sequence generation—without fine-tuning, structural templates, or multiple sequence alignments (MSAs). Joint optimization via structural metrics, conservation analysis, and embedding-space evaluation enables rapid, GPU-hour-scale design of target secondary structures—including α-helices and coils. Experiments demonstrate high sequence convergence and structural validity. This work presents the first LLM-driven, end-to-end, target-directed de novo protein design approach leveraging swarm intelligence, establishing a paradigm shift toward scalable, controllable, and template-free protein engineering.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Multiagent Systems: Mechanism Design

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• 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

Abstract

Designing proteins de novo with tailored structural, physicochemical, and functional properties remains a grand challenge in biotechnology, medicine, and materials science, due to the vastness of sequence space and the complex coupling between sequence, structure, and function. Current state-of-the-art generative methods, such as protein language models (PLMs) and diffusion-based architectures, often require extensive fine-tuning, task-specific data, or model reconfiguration to support objective-directed design, thereby limiting their flexibility and scalability. To overcome these limitations, we present a decentralized, agent-based framework inspired by swarm intelligence for de novo protein design. In this approach, multiple large language model (LLM) agents operate in parallel, each assigned to a specific residue position. These agents iteratively propose context-aware mutations by integrating design objectives, local neighborhood interactions, and memory and feedback from previous iterations. This position-wise, decentralized coordination enables emergent design of diverse, well-defined sequences without reliance on motif scaffolds or multiple sequence alignments, validated with experiments on proteins with alpha helix and coil structures. Through analyses of residue conservation, structure-based metrics, and sequence convergence and embeddings, we demonstrate that the framework exhibits emergent behaviors and effective navigation of the protein fitness landscape. Our method achieves efficient, objective-directed designs within a few GPU-hours and operates entirely without fine-tuning or specialized training, offering a generalizable and adaptable solution for protein design. Beyond proteins, the approach lays the groundwork for collective LLM-driven design across biomolecular systems and other scientific discovery tasks.

Problem

• Designing proteins with tailored properties is challenging due to vast sequence space.
• Current generative methods lack flexibility and scalability for objective-directed protein design.
• The paper introduces a decentralized LLM agent framework for de novo protein design.

Innovation

• Decentralized LLM agents propose mutations iteratively
• Agents integrate design objectives and local interactions
• No fine-tuning needed, operates within few GPU-hours