Extrapolative prediction of enantioselectivity enabled by computer-driven workflow, new molecular representations and machine learning
US11664093B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 26, 2019 |
| Grant date | May 30, 2023 |
| Priority date | — |
| Expiry date | Aug 14, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG16C60/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Catalyst design in asymmetric reaction development has traditionally been driven by empiricism, wherein experimentalists attempt to qualitatively recognize structural patterns to improve selectivity. Machine learning algorithms and chemoinformatics can potentially accelerate this process by recognizing otherwise inscrutable patterns in large datasets. Herein we report a computationally guided workflow for chiral catalyst selection using chemoinformatics at every stage of development. Robust molecular descriptors that are agnostic to the catalyst scaffold allow for selection of a universal training set on the basis of steric and electronic properties. This set can be used to train machine learning methods to make highly accurate predictive models over a broad range of selectivity space. Using support vector machines and deep feed-forward neural networks, we demonstrate accurate predictive modeling in the chiral phosphoric acid-catalyzed thiol addition to N-acylimines.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.