ETH Meets San Francisco

The challenges of discovering new pharmaceutical therapies present a multi-dimensional problem. Identifying viable drug candidates requires optimization ¨C in parallel ¨C of both efficacy and safety. In the midst of The Fourth Industrial Revolution, much excitement surrounds the potential of AI to further digital healthcare. How might we define ¡°intelligent behavior¡± in the context of drug discovery? Essentially, an intelligent agent ¨C either man or machine ¨C demonstrates an ability to solve problems, to learn from experience, and to deal with new situations. With regard to these three central criteria, certain machine learning modalities, specifically autonomous adaptive systems, may constitute instances of AI.

Recent advances in adaptive robotic systems, automated chemical syntheses, and biological testing, as well as AI systems, improve a design hypothesis through feedback analysis. Such systems provide the basis for introducing greater automation potentially accelerating timeframes for compound discovery, optimization, and more effective chemical space searches. However, such approaches also raise considerable conceptual, technical, and organizational challenges, as well as hype and skepticism. Rapid feedback cycles require not only the customization of instrumentation, but also the adjustment of work processes. Establishing this concept in pharmaceutical discovery may require significant investment in terms of money and (re)organization of not only laboratory structures and processes, but also mindsets. It will be necessary to evaluate the feasibility of fully autonomous molecular design with the aid of computers and robotic devices. At the same time analyzing which aspects of compound generation are best left to a chemically savvy artificial intelligence brain or a skilled human mind.

This symposium brings together leading experts who will unveil concepts, approaches, and technologies that medicinal chemists could robustly implement in the near future. They will also critically analyze the opportunities and challenges for a more widespread application.