自主实验室中基于证据的智能体配方开发

中文摘要 AI 辅助

自乳化药物递送系统（SEDDS）可提高难溶性药物的口服生物利用度，但识别高性能配方仍需要大量实验。我们提出了Andromeda 2，一个智能体系统，它基于结构化的内部实验证据进行推理，并调用计算和实验工具来设计并执行连续的配方批次。在匹配预算下使用小型化自动化实验室，我们将其与Andromeda 1（一种已在数十个实际开发项目中部署的概率优化模型）以及湿实验室实验设计（DoE）活动进行了基准比较。对于紫杉醇，Andromeda 2实现了50%的高性能命中率，而Andromeda 1为17%，DoE为2%；Andromeda 2识别出12种满足全部四项目标产品概况（TPP）目标的配方，而Andromeda 1和DoE分别为6种和0种。中位AUC_{10-240}分别为70.1、12.0和3.5 mg·min/mL，而Andromeda 2与Andromeda 1的最大AUC相当。一个选定的全TPP配方在首次FaSSIF测量中实现了表观有效紫杉醇载药量为19±5% w/w，比已发表的紫杉醇S-SEDDS报道的5.7% w/w载药量高约3.3倍。一项受控消融实验表明，访问结构化内部实验证据使平均AUC提高了34%。

英文摘要

Self-emulsifying drug delivery systems (SEDDS) can improve the oral bioavailability of poorly soluble drugs, but identifying high-performing formulations remains experimentally intensive. We present Andromeda 2, an agentic system that reasons over structured in-house experimental evidence and invokes computational and experimental tools to design and execute successive formulation batches. Using a miniaturized automated laboratory at a matched budget, we benchmark it against Andromeda 1, a probabilistic optimization model deployed across dozens of live development projects, and a wet-lab design-of-experiments (DoE) campaign. For paclitaxel, Andromeda 2 achieved a 50% high-performance hit rate versus 17% for Andromeda 1 and 2% for DoE, and identified 12 formulations meeting all four target product profile (TPP) objectives versus 6 and 0, respectively. Median $AUC_{10-240}$ was 70.1, 12.0, and 3.5 mg$\cdot$min/mL, while maximum AUC was comparable between Andromeda 2 and Andromeda 1. A selected full-TPP formulation achieved an apparent effective paclitaxel loading of $19 \pm 5\%$ w/w at the first FaSSIF measurement, approximately 3.3-fold higher than the 5.7% w/w loading reported for a published paclitaxel S-SEDDS. A controlled ablation showed that access to structured in-house experimental evidence increased mean AUC by 34%.

发表机构

• Intrepid Labs（无畏实验室）

机构由 AI 辅助整理，请以论文原文为准。