NOV 15, 2020 8:06 AM PST

Chemical reactivity flowcharts assist chemists in interpreting reaction outcomes

New research published in Organic Letters from Purdue University scientists presents the design and development of chemical reactivity flowcharts that assist chemists in interpreting reaction outcomes. The flowcharts are trained by machine learning models.

"Developing new and fast reactions is essential for chemical library design in drug discovery," said Gaurav Chopra, an assistant professor of analytical and physical chemistry in Purdue's College of Science. "We have developed a new, fast and one-pot multicomponent reaction (MCR) of N-sulfonylimines that was used as a representative case for generating training data for machine learning models, predicting reaction outcomes, and testing new reactions in a blind prospective manner.

"We expect this work to pave the way in changing the current paradigm by developing accurate, human-understandable machine learning models to interpret reaction outcomes that will augment the creativity and efficiency of human chemists to discover new chemical reactions and enhance organic and process chemistry pipelines."

The exciting part of this innovation is that it does not require large-scale robotics, but rather can be used within labs by chemists doing reaction screenings. The team says this means the innovation could be translated to other chemical reactions.

"We provide the first report of a framework to combine fast synthetic chemistry experiments and quantum chemical calculations for understanding reaction mechanism and human-interpretable statistically robust machine learning models to identify chemical patterns for predicting and experimentally testing heterogeneous reactivity of N-sulfonylimines," Chopra said.

The work comes out of a collaboration with the Purdue Research Foundation Office of Technology Commercialization and highlights the wide range of applications for machine learning.

Photo: Pexels

"The unprecedented use of a machine learning model in generating chemical reactivity flowcharts helped us to understand the reactivity of traditionally used different N-sulfonylimines in MCRs," said co-author Krupal Jethava. "We believe that working hand-to-hand with organic and computational chemists will open up a new avenue for solving complex chemical reactivity problems for other reactions in the future."

"In this work, we strived to ensure that our machine learning model can be easily understood by chemists not well versed in this field," said fellow co-author Jonathan Fine. "We believe that these models have the ability not only be used to predict reactions but also be used to better understand when a given reaction will occur. To demonstrate this, we used our model to guide additional substrates to test whether a reaction will occur."

Sources: Organic Letters, Science Daily

About the Author
  • Kathryn is a curious world-traveller interested in the intersection between nature, culture, history, and people. She has worked for environmental education non-profits and is a Spanish/English interpreter.
You May Also Like
OCT 01, 2020
Chemistry & Physics
Canadian Scientists Hope to Take Lead in Neutron Research, Again
OCT 01, 2020
Canadian Scientists Hope to Take Lead in Neutron Research, Again
(Pixabay/geralt) Neutron sources are the key to advancing research in many areas such as energy storage, mechanical engi ...
SEP 29, 2020
Chemistry & Physics
The benefits of electronic blood vessels
SEP 29, 2020
The benefits of electronic blood vessels
New research published in the journal Matter reports on the development of electronic blood vessels that are capable of ...
OCT 05, 2020
Chemistry & Physics
Improving microbial elecrosynthesis
OCT 05, 2020
Improving microbial elecrosynthesis
New research from a KAUST team highlights the development of a semiconductive photocatalyst that recycles CO2 and c ...
OCT 26, 2020
Chemistry & Physics
Fighting mesothelioma with gold nanotubes
OCT 26, 2020
Fighting mesothelioma with gold nanotubes
New research published in the journal Small details how gold nanotubes could be used to treat mesothelioma cancer. ...
JAN 17, 2021
Space & Astronomy
New Way to Extract Energy from Black Holes
JAN 17, 2021
New Way to Extract Energy from Black Holes
In his theory of general relativity, Einstein predicted that black holes harbor an enormous amount of energy. And now, r ...
JAN 18, 2021
Chemistry & Physics
Watching the eletronic signals of a wandering mind
JAN 18, 2021
Watching the eletronic signals of a wandering mind
A study published recently in the Proceedings of the National Academy of Sciences contemplates the places our minds ...
Loading Comments...