用多智能体大模型安全高效设计脂质，提升基因递送效果
LipoAgent: Coordinating Fine-Tuned LLM Agents for Safer Lipid Design
- 分阶段预测：先判断毒性再预测效率，符合临床筛选逻辑
- 相比现有模型，转染效率预测平均提升32%
- 虚拟筛选结果经实验验证，可直接指导真实实验设计
脂质纳米颗粒（LNPs）是核酸递送最成熟的平台之一，但设计兼具高效性与生物安全性的脂质仍存在重大瓶颈。实际筛选中，毒性是决定性约束：若脂质有毒，则其效率预测无临床意义。我们提出LipoAgent，一种面向脂质设计的安全感知多智能体大模型框架。该框架结合领域特定微调与条件预测目标，强制将毒性作为效率预测的前提，并通过轻量级人类监督下的多智能体协同验证进一步提升可靠性。在多个基础模型上，LipoAgent相较于其他报道的脂质设计模型，平均实现32%的mRNA转染效率预测提升。湿实验验证表明，虚拟筛选排名能可靠转化为真实的生物转染结果。代码已公开于https://github.com/SAI-Lab-NYU/LipoAgent.git。
原文摘要 · Abstract (English)
Lipid nanoparticles (LNPs) are among the most clinically mature platforms for nucleic acid delivery, yet designing lipids that are both effective and biologically safe remains a major bottleneck. In practical screening, toxicity is a decision-level constraint: if a lipid is toxic, its efficiency prediction is clinically irrelevant. We propose LipoAgent, a safety-aware multi-agent LLM framework for lipid discovery. LipoAgent combines domain-specific finetuning with a conditional prediction objective that enforces toxicity as a prerequisite for efficiency prediction, and further improves reliability via multi-agent verification with lightweight human oversight when disagreement persists. Across multiple foundation models, LipoAgent achieves an average 32% relative improvement in mRNA transfection efficiency prediction compared with other reported models for lipid design. Wet-lab validation confirms that virtual screening rankings reliably translate to biological transfection outcomes. The code is publicly available at https://github.com/SAI-Lab-NYU/LipoAgent.git.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。