Event

Title: Developing Data Science Tools for Synthetic Chemists

Matthew S. Sigman

Department of Chemistry, University of Utah, Salt Lake City, UT (USA)

The optimization of catalytic reactions for organic synthesis is difficult as the interplay between the catalyst structure, reaction conditions, and substrates involved is a complex multidimensional problem. In other words, it is difficult to ascertain the pattern within the noise to offer a complete picture of how to optimize and/or interpret why a certain set of conditions are required for a particular reaction. Therefore, we have aimed to develop several data science and machine learning tools that assist in designing the proper experiments to facilitate the analysis of structure function relationships while also providing platforms for reaction optimization. Specifically, we have used new methods to develop descriptors for complex molecular architectures as well as data science methods to discern how these catalysts interact with a range of substrate types. This lecture will outline how we have put into practice a workflow that integrates data science tools, physical organic chemistry, and experiments with a focus on new case studies on a broad array of chemical processes.