Agentic system improves drug formulation success rates significantly
Evidence-Grounded Agentic Formulation Development in an Autonomous Laboratory
Machine Learning
Summary
Making better drug formulations is hard and takes a lot of experiments. The authors created Andromeda 2, an intelligent system that plans and runs experiments using past data and lab automation. It found many more good drug mixes for a challenging medicine paclitaxel than previous methods. This system also uses existing lab data to boost results. Overall, it speeds up finding effective drug formulations.
What this means in practice
- •For pharmaceutical formulation teams: Accelerate the development of oral drug formulations with better performance by using an autonomous system that plans and executes experiments with past lab data.
- •For automated lab operators: Integrate structured experimental evidence into automated lab workflows to improve the success rate and quality of self-emulsifying drug formulations.
Authors
Michael M. Craig, Riley J. Hickman, Yingshan Ma, Rémi Piché-Taillefer, Christine Allen, Pauric Bannigan
Abstract
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%.