(2ab) Enzymatic Synthesis and Metabolism of Small Molecules

Enzymes, Nature’s specific and efficient catalysts, assemble chemically complex natural products from simple, abundant, and renewable starting materials. They are also an important tool in a process chemist’s toolkit as they catalyze selective transformations under mild conditions in a safe and sustainable fashion. In addition to small molecule synthesis, enzymes in the human body can chemically alter, or metabolize, pharmaceutical drugs. Some drugs, called prodrugs, are administered in an inactive form, which is metabolized into an active form. The resulting active metabolites produce the desired therapeutic effects. To harness the value offered by enzymes, predictive models that are capable of generalizing known enzyme chemistry to (a) propose retrosynthetic routes to a given target (b) identify reactive sites and chemical modifications of a drug are valuable to process chemists and drug development scientists, respectively. The increasing availability of reaction corpora and algorithms for efficient search will enable development of such tools.

At the interface of biochemistry, data science, and machine learning, our group will focus on addressing the methodological challenges associated with enzymatic synthesis and metabolism of small molecules.

What this looks like in terms of research includes efforts to:

*develop generalizable enzymatic retrosynthesis models

*computationally identify and/or generate candidate enzyme sequences to catalyze desired transformations

*develop computational models to predict drug metabolism

*develop experimental platforms to validate computational enzyme catalysis predictions

By developing solutions to these research challenges, our long-term objectives are to:

*accelerate the identification and development of biocatalytic processes

*enhance understanding of small molecule drug metabolism

*leverage AI-driven platforms to discover new enzymes with desired catalytic activity

Teaching Interests

My chemical engineering training at University of Minnesota, Stanford University, and MIT has prepared me to teach any course in chemical engineering at the undergraduate and graduate levels. Through my teaching experience, I have gained expertise in teaching introductory, undergraduate chemical engineering courses including mass and energy balances. Through my research experience, I have gained expertise in biochemistry, computational chemistry, and machine learning. I would be well suited to teach any courses within these areas. Additionally, I would be excited to develop an elective titled ‘Machine learning in Chemical Engineering’, through which students will learn about recent advances in machine learning methods and gain hands-on experience training models in python. The course will also explore how these upcoming tools can be used to efficiently solve traditional chemical engineering problems such as biocatalytic process development and metabolic reaction catalysis. At the end of this course, students will be equipped to apply machine learning techniques in their future jobs or graduate research.