Claire Fuller Reed

PhD thesis: Automated Chemical Synthesis Enabled by Digital Molecular Technologies

My PhD project focuses on using machine learning to gain insight and control over the properties of fluorophores constructed by supramolecular host-guest interactions. These complexes offer high quantum yields and a vast, tuneable design space, making them promising candidates for a variety of photocatalytic applications. My project also falls under the Automated Chemical Synthesis Enabled by Digital Molecular Technologies (SynTech) CDT program.

Who or what inspired you to pursue your research interests?

I have always had an interest in mathematics and the natural sciences. I gravitated towards chemistry because of its extensive overlap with other scientific disciplines, making it a diverse and enriching area to study. While conducting research in organic synthesis in my undergraduate research group, I first became interested in machine learning for its predictive capabilities and potential to optimize synthesis pathways more efficiently. I am fortunate to have had wonderful mentors in chemistry, mathematics, and computer science who encouraged me to venture outside my comfort zone in my endeavour to unite these interests.