"Machine learning in chemistry and beyond" (ChE-651) seminar by Rocío Mercado "Exploring new frontiers in drug discovery using deep generative models"

Artificial intelligence (AI) is transforming our approach to biomolecular engineering. In the drug discovery sector, the development of generative and predictive tools that can quickly learn from biochemical data is pushing the frontiers of how we discover and repurpose drugs through de novo molecular design. De novo design – the concept of designing molecules with desired properties from scratch so as to minimize experimental screening – is poised to allow scientists to more efficiently traverse chemical space in search of optimal molecules, and delegate error-prone decisions to computers via the use of predictive and generative computational models. In drug development, de novo design methods can aid medicinal chemists in the design and selection of drug candidates, with the added advantage that they can learn from datasets of billions of molecules in minutes and be constantly updated with new data. In this talk I will introduce molecular deep generative models (DGMs) and their utility in de novo design. DGMs use deep neural networks to build new molecules in silico, and work by proposing node-by-node modifications to an initial graph structure to generate compounds predicted to achieve a certain property profile. Such models can be applied to a range of therapeutic modalities; here I will focus on the design of small molecule protein binders and heterobifunctional degraders. I will end by touching on the importance of interdisciplinary communication for the development of new advances in this field, as well as discussing the importance and impact of open-source work.