AgentDrug: 利用大语言模型在代理工作流中进行零样本分子编辑
AgentDrug: Utilizing Large Language Models in An Agentic Workflow for Zero-Shot Molecular Editing
AI总结:
AgentDrug通过代理工作流利用大语言模型,在分子编辑任务中实现更高准确性,特别是在单属性和多属性编辑任务中表现出显著性能提升。
摘要:
分子编辑——对给定分子进行修改以改善所需性质——是药物发现中的基本任务。虽然LLMs有潜力通过自然语言驱动编辑来解决此任务,但直接提示方法在准确性上有限。在本工作中,我们提出了AgentDrug,一种利用LLMs在结构化细化过程中实现显著更高准确性的代理工作流。AgentDrug定义了一个嵌套的细化循环:内循环使用来自化学信息学工具包的反馈来验证分子结构,而外循环则通过通用反馈和基于梯度的目标来引导LLM,使分子朝着性质改进方向发展。我们评估了AgentDrug在单属性和多属性编辑的基准测试中,分别在宽松和严格阈值下。结果表明,与先前方法相比,性能有显著提升。使用Qwen-2.5-3B模型,AgentDrug在六个单属性任务上将准确性提高了20.7%(宽松)和16.8%(严格),在八个多属性任务上分别提高了7.0%和5.3%。使用更大模型Qwen-2.5-7B,AgentDrug在六个单属性目标上进一步将准确性提高了28.9%(宽松)和29.0%(严格),在八个多属性目标上分别提高了14.9%(宽松)和13.2%(严格)。
英文摘要:
Molecular editing-modifying a given molecule to improve desired properties-is a fundamental task in drug discovery. While LLMs hold the potential to solve this task using natural language to drive the editing, straightforward prompting achieves limited accuracy. In this work, we propose AgentDrug, an agentic workflow that leverages LLMs in a structured refinement process to achieve significantly higher accuracy. AgentDrug defines a nested refinement loop: the inner loop uses feedback from cheminformatics toolkits to validate molecular structures, while the outer loop guides the LLM with generic feedback and a gradient-based objective to steer the molecule toward property improvement. We evaluate AgentDrug on benchmarks with both single- and multi-property editing under loose and strict thresholds. Results demonstrate significant performance gains over previous methods. With Qwen-2.5-3B, AgentDrug improves accuracy by 20.7% (loose) and 16.8% (strict) on six single-property tasks, and by 7.0% and 5.3% on eight multi-property tasks. With larger model Qwen-2.5-7B, AgentDrug further improves accuracy on 6 single-property objectives by 28.9% (loose) and 29.0% (strict), and on 8 multi-property objectives by 14.9% (loose) and 13.2% (strict).
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。