Jackson Burns

MIT Department: Chemical Engineering
Faculty Mentor: Prof. Conner Coley
Undergraduate Institution: University of Delaware
Website: Website, LinkedIn, Twitter
Research Poster
Lightning Talk


Hello and thanks for viewing my intern profile! My name is Jackson Burns and I am a rising senior at the University of Delaware studying chemical engineering and computer science. At my home institution I focus on the development of novel chemical transformations related to transition metal-catalyzed coupling under the guidance of Prof. Don Watson. Here at MIT I am working with Prof. Connor Coley on autonomous optimization — integrating machine learning and robotics into a typical chemistry workflow. Outside of class I enjoy reading, playing chess, and rock climbing.


2021 Abstract

Predicting Small Molecule Substrate Reactivity via Data Mining and
Machine Learning

Jackson Burns1, Priyanka Raghavan2, Connor Coley2
1Department of Chemical Engineering, University of Delaware
2Department of Chemical Engineering, Massachusetts Institute of Technology

Rapid development of pharmaceutical reagents is of the utmost interest for our collective health. Small molecule pharmaceuticals in particular are highly sought-after chemicals. Unfortunately the synthesis of these species can take months to discover and optimize because of a reliance on human-driven experimentation. Machine learning (ML) can be used to accelerate this process by building models to predict reaction conditions and yield and guide experimentation. Existing literature contains massive volumes of data for said ML but it is not being used effectively at scale. Using a database of published chemical reactions, over 300 unique transformations involving samarium iodide from more than 200 separate publications are identified and used to build an accurate ML model. This family of reactions is of particular interest due to its complex relationship to solvent, which is not well-modeled using current approaches. Each reaction is parameterized into machine-interpretable representations using molecular fingerprints and common DFT parameters like Fukui values and partial charges generated using a pre-trained neural network. The resulting model will enable chemists to optimize their reactions using literature precedent more rapidly. This approach could also be used to automate chemical space exploration by allowing a computer to predict conditions for and then set up its own experiments. The ML model created is pre-trained and can be distributed as-is for researchers interested in samarium iodide chemistry and will also be extended to more diverse chemistries in the near future.