Adapted from a news release by University of Notre Dame
Imagine a world where the power of chemistry is used in concert with machine learning to solve problems in health care, materials science or energy research. Machine learning can accelerate the synthesis of molecules that hold the key to solving these problems by developing new and more efficient ways of making them.
The National Science Foundation Center for Computer-Assisted Synthesis (C-CAS), based at University of Notre Dame, was recently awarded $20 million and named one of only seven Phase II National Science Foundation Centers for Chemical Innovation in the nation. The center includes the expertise of Colorado State University chemistry researchers.
C-CAS helps chemists focus on which molecules should be made, rather than on how to make them. By reducing the time and resources needed to design and optimize synthetic routes, the tools and protocols developed by the center’s researchers provide data-driven approaches to make synthetic chemistry more predictable and efficient because less time is spent on trial-and-error approaches. The tools developed are then shared with the research community through open-source clearinghouses.
Rob Paton, professor in the College of Natural Sciences’ Department of Chemistry, helped establish the center in 2018. His work is in developing new computational approaches that enable data science to be applied to chemical reaction discovery and optimization.
“As part of the center’s Phase II work, our lab will continue to use computational chemistry and machine learning to predict the outcomes of chemical reactions and design new catalysts,” Paton said.
Besides Paton at CSU, other external faculty affiliates are at Massachusetts Institute of Technology; University of California, Los Angeles; Carnegie Mellon University; California Institute of Technology; UC Berkley; and University of Utah.
Among the center leadership’s key objectives is making the U.S. a leader in science and technology through attracting, educating and training a new generation of “data chemists.” This includes novel opportunities for researchers from historically marginalized groups.
At CSU, participants in the center on Paton’s team include Ph.D. students Liliana Gallegos and Guilian Luchini, and postdoctoral researcher Mihai Popescu. Gallegos is an inaugural recipient of a C-CAS Diversity Fellowship that will support her research for one year.
Students in the Paton Laboratory have helped discover effective approaches to digitizing the structures of organic molecules so that they can be processed by machine learning algorithms, Paton said.
Professor Rob Paton; Ph.D. students Guilian Luchini and Liliana Gallegos; and postdoctoral researcher Mihai Popescu are part of the NSF Center for Computer-Assisted Synthesis.
NSF Centers for Chemical Innovation
The NSF’s Centers for Chemical Innovation Program is a highly competitive, two-phase program. Phase I centers receive resources to develop the science, management and broader impact components of a major research center dedicated to a transformative idea before requesting Phase II funding.
C-CAS is led by Olaf Wiest of Notre Dame and brings together the expertise of data scientists, computational and synthetic chemists to change the field of synthetic chemistry from an intuition-driven to a data-driven science.
“Over the last 15 years, chemists have learned to generate much bigger datasets using computation and high throughput experimentation but are often not equipped to take full advantage of them,” said Wiest. “C-CAS will develop and share the concepts, datasets and tools to transform the practice of synthesis by maximizing the value of a quantitative approach to data analysis.”
