Predicting Highly Enantioselective Catalysts Using Tunable Fragment Descriptors

29 July 2022, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

Catalyst optimization process is typically relying on an inductive and qualitative assumption of chemists based on screening data. While machine learning models using molecular properties or calculated 3D structures enable quantitative data evaluation, costly quantum chemical calculations are often required. In contrast, readily available binary fingerprint descriptors are time- and cost-efficient, but their predictive performance remains insufficient. Here, we describe a machine learning model based on fragment descriptors, which are fine-tuned for asymmetric catalysis and represent cyclic or polyaromatic hydrocarbons, enabling robust and efficient virtual screening. Using training data with only moderate selectivities, we designed theoretically and validated experimentally new catalysts showing higher selectivities in a previously unaddressed transformation.

Keywords

Asymmetric Catalysis
Machine Learning

Supplementary materials

Title
Description
Actions
Title
Supporting Information
Description
General information, synthetic procedures, spectral data, computational details, HPLC and GC traces
Actions
Title
Modeling data
Description
Screening data, machine learning models, benchmark, and modeling results
Actions

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.