Automation and AI Team

Automation and AI team in Catalysis/Chemistry encompasses automation, artificial intelligence and machine learning with experiments and theory of catalysis/chemistry, to develop a synergistic technology of Catalysis Informatics. We are able to data-mine reaction from high throughput experimentation technology (HTE) and combine various reaction and catalyst characterization/spectroscopic techniques, including Dynamic Nuclear Polarization Surface Enhanced NMR spectroscopy (DNP-SENS), in situ IR/EXAFS and theoretical models combining DFT calculations with data science and machine learning algorithms to generate predictive models. These models help us to find patterns in large datasets and eventually predict novel catalysts and catalytic processes, improving fundamental knowledge on catalysis/chemistry thus accelerating discovery in catalysis and chemical science.
 

An Empirical Understanding of the Glycosylation Reaction

Selected Publications

Moon, Soo-Yeon, et al. "Predicting Glycosylation Stereoselectivity Using Machine Learning." external pageChem. Sci. (2021), Advance Article

Chatterjee, Sourav, et al. "Automated radial synthesis of organic molecules." external pageNature 579.7799 (2020): 379-384.

Silva, Jordan De Jesus, et al. "Molecular-level insight in supported olefin metathesis catalysts by combining surface organometallic chemistry, high throughput experimentation, and data analysis." external pageChem. Sci. 11 (2020), 6717-6723

Chatterjee, Sourav, et al. "An Empirical Understanding of the Glycosylation Reaction." external pageJACS 140.38 (2018): 11942-11953.

Chatterjee, Sourav, et al. "Design and operation of a radio-frequency heated micro-trickle bed reactor for consecutive catalytic reactions." external pageChem. Eng. J. 281 (2015): 884-891. (Highlighted in Journal Cover)

 

JavaScript has been disabled in your browser