In cooperation with the Einstein Center Digital Future the Schering Stiftung presents a scientific lecture by this year’s Ernst Schering Prize laureate Professor Gisbert Schneider.

Molecular design may be regarded as a pattern recognition process. In this context, certain machine learning methods have emerged as an enabling technology for modern drug discovery. These models aim to mimic a chemist’s pattern recognition skills by learning from domain–specific data. Part of the appeal of applying “artificial intelligence” (AI) to drug design lies in the potential to develop autonomous models that navigate vast molecular datasets and prioritize alternatives. This concept of drug discovery represents at least a partial transfer of decision power to an AI, and could be viewed as synergistic with human intelligence; that is, a domain-specific implicit AI that would augment the capabilities of chemists in molecular design and selection. More ambitiously, the ultimate challenge for drug design with AI is to autonomously generate new chemical entities with the desired properties from scratch (“de novo”). This approach largely eliminates the need for the often prohibitively costly, serendipitous experimental chemical compound testing. I will present knowledge-based and data–driven methods for de novo molecule generation and pharmacological activity prediction, emphasizing ligand-based approaches that have proven useful and reliable in “little–data” scenarios. Selected prospective case studies will be presented, ranging from targeted molecular design to fully automated design-make-test-analyze cycles.

The lecture is aimed at a scientific audience.