Paul Deutsch
Papers
1
Total Citations
139
H-Index
1
About
Paul Deutsch is a leading figure at the intersection of computational chemistry and asymmetric catalysis, pioneering the use of machine learning to solve long-standing challenges in reaction optimization. His most influential work, with 139 citations, demonstrates how molecular descriptors and multi-objective algorithms can rationally select solvents for complex catalytic transformations. In a landmark study on the (acac)/Josiphos-catalyzed asymmetric hydrogenation of chiral α-β unsaturated γ-lactams, Deutsch confronted two simultaneous objectives—high conversion and high diastereomeric excess. By training a machine learning model on just 25 initial solvents, his algorithm successfully identified superior solvent systems that outperformed traditional trial-and-error approaches. This work represents a paradigm shift in how chemists approach solvent selection, moving from intuition-driven experimentation to data-driven prediction. Deutsch’s contributions have established him as a key innovator in applying artificial intelligence to synthetic chemistry, offering a blueprint for accelerating the discovery of optimal reaction conditions. His research continues to inspire students and researchers seeking to merge computational tools with practical catalysis.
Research Focus
Key Achievements
Top Papers
- 1