Machine learning is poised to accelerate and de-risk drug development, but its effectiveness is hindered by limited and low-quality data. To address these challenges, we explore strategies such as active learning, data pairing, and the integration of machine learning with physical simulations. We highlight case studies where such approaches allowed us to more accurately predict complex ADMET endpoints and to design nanoformulations with large potential to enable the creation of safer and more effective therapies.
Learning Objectives:
Understand current opportunities and future challenges in machine learning for drug discovery and delivery
Learn about different machine learning approaches and Drug-Excipient nanoparticle technologies
Gain insights into case studies for machine learning in drug development
