MAC-AMP: A Closed-Loop Multi-Agent Collaboration System for Multi-Objective Antimicrobial Peptide Design

2026-02-16

AI Summary

This work addresses the longstanding challenge in antimicrobial peptide (AMP) design—balancing high antimicrobial activity, low toxicity, and structural novelty while ensuring interpretability and flexible scoring. To this end, the authors propose the first large language model–based closed-loop multi-agent collaboration framework, which autonomously generates novel AMPs from only a task description and a few examples. By simulating peer review and incorporating adaptive reinforcement learning, the system achieves cross-domain transferability for the first time in AMP design, while maintaining an interpretable decision-making process. Experimental results demonstrate that the generated peptides significantly outperform those from existing generative models across key metrics, including antimicrobial efficacy, low cytotoxicity, structural reliability, and sequence novelty.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation
• Multiagent Systems: Adversarial Agents

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

To address the global health threat of antimicrobial resistance, antimicrobial peptides (AMP) are being explored for their potent and promising ability to fight resistant pathogens. While artificial intelligence (AI) is being employed to advance AMP discovery and design, most AMP design models struggle to balance key goals like activity, toxicity, and novelty, using rigid or unclear scoring methods that make results hard to interpret and optimize. As the capabilities of Large Language Models (LLM) advance and evolve swiftly, we turn to AI multi-agent collaboration based on such models (multi-agent LLMs), which show rapidly rising potential in complex scientific design scenarios. Based on this, we introduce MAC-AMP, a closed-loop multi-agent collaboration (MAC) system for multi-objective AMP design. The system implements a fully autonomous simulated peer review-adaptive reinforcement learning framework that requires only a task description and example dataset to design novel AMPs. The novelty of our work lies in introducing a closed-loop multi-agent system for AMP design, with cross-domain transferability, that supports multi-objective optimization while remaining explainable rather than a'black box'. Experiments show that MAC-AMP outperforms other AMP generative models by effectively optimizing AMP generation for multiple key molecular properties, demonstrating exceptional results in antibacterial activity, AMP likeliness, toxicity compliance, and structural reliability.

Problem

• antimicrobial peptide design
• multi-objective optimization
• activity-toxicity balance
• interpretability
• antimicrobial resistance

Innovation

• multi-agent LLMs
• closed-loop collaboration
• multi-objective optimization
• explainable AI
• antimicrobial peptide design