(209c) Streamlining Small Molecule Design and Synthesis

This talk will cover recent progress in the application of data science and machine learning techniques to problems in synthetic chemistry as they relate to molecular discovery. The typical discovery paradigm is an iterative process of designing candidate compounds, synthesizing those compounds, and testing their performance, where each repeat of this cycle can require weeks or months. Time and cost constraints may necessitate selecting compounds on the basis of what are perceived as fast to synthesize, rather than what are most informative to assay. Data science and statistical learning offer unprecedented opportunities to systematize and streamline the process by which new functional small molecules are designed and synthesized. I will describe how historical reaction data can be used to inform decision-making in small molecule pathway design, for both retrosynthesis and forward reaction prediction, and how these techniques can be integrated with de novo molecular design to triage candidate compounds for testing.