Timothy Cernak
University of Michigan, MI·Chemistry·Early-career
Medicines, polymers, agrochemicals and battery materials all depend on chemical reactions, yet chemists still struggle to predict whether a given reaction will work. Better predictions need large public collections of reaction data and algorithms that learn from them.
- Fields
Chemistry
Computer Science
- Topics
organic synthesis
chemical synthesis
high-throughput experimentation
- Grants
- 1 known grant, through Feb 2028
What they work on
- Use graph theory, including adjacency matrix mapping of known total syntheses of terpenes, alkaloids and pharmaceuticals, to identify reaction types that do not yet exist but would be valuable for synthesis.
- Develop new reactions that form carbon–oxygen bonds from amine and carboxylic acid building blocks, combining robotic high-throughput experimentation (HTE) with machine learning.
- Advance miniaturized HTE at the hardware and software level and build machine learning models of chemical reactivity, releasing thousands of machine-readable reaction data points to the public.
- Plan multistep syntheses of pharmaceuticals and alkaloids such as stemoamide and gelsemine with AI-based retrosynthetic algorithms, then validate the proposed routes experimentally.
More about the research
This project combines robotic chemistry and data science to make reaction outcomes more predictable, even for complex target molecules.
Why it matters
More reliable ways to predict and plan chemical reactions could speed the discovery and production of medicines, polymers, agrochemicals and energy storage materials. Publicly released, machine-readable reaction data will give other researchers material to train and test predictive models. New reaction types could add tools for building complex molecules.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Douglas Frantz
Washington University in St Louis, MO·Chemistry
Discover and design metal-based catalysts that selectively form either C–O or C–N bonds when alkylating N,O-heterocycles, taming their ambident reactivity.
Sarah Reisman
California Institute of Technology, CA·Chemistry
Develop a photoredox-catalyzed radical-polar crossover annulation (RPCA), a light-driven ring-forming reaction, to build the bridged bicyclo[3.2.1]octane core of the polyketide natural product enterocin.
Patrick Walsh
University of Pennsylvania, PA·Chemistry
Develop enantioselective nickel-catalyzed cross-electrophile coupling, which joins sulfur electrophiles with aryl or alkyl halides, to make diaryl and alkyl aryl sulfoxides enriched in one mirror-image form.
The school
University of Michigan: 124 labs on PI Pages, $2.1B a year on research, 963 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.