There’s no question that artificial intelligence (AI) is now embedded in the drug discovery process at a growing number of companies. Machine learning, deep learning, and generative AI can help scientists generate structures for new drug candidates and explore protein-ligand binding before starting any experiments in a wet lab.

Use cases for AI in drug discovery are still evolving, and AI-powered drug ideation still must overcome many hurdles before it becomes commonplace and reliable. This C&EN white paper provides the latest on how AI supports drug discovery.

Key objectives:

• Machine learning (ML) and deep learning (DL) and methods for virtual screening of protein-ligand interactions
• Combining ML or DL with physics-based modeling techniques, such as free energy perturbation calculations, to assess ligand-protein binding
• Designing new molecules with generative AI
• Incorporating predictive ADMET at early stages of drug design
• Advancing algorithms with robust benchmarking and higher-quality training data