Hokkaido University Collection of Scholarly and Academic Papers >
Institute for Chemical Reaction Design and Discovery : ICReDD >
Peer-reviewed Journal Articles, etc >
Predicting Highly Enantioselective Catalysts Using Tunable Fragment Descriptors
Title: | Predicting Highly Enantioselective Catalysts Using Tunable Fragment Descriptors |
Authors: | Tsuji, Nobuya Browse this author →KAKEN DB | Sidorov, Pavel Browse this author →KAKEN DB | Zhu, Chendan Browse this author | Nagata, Yuuya Browse this author →KAKEN DB | Gimadiev, Timur Browse this author →KAKEN DB | Varnek, Alexandre Browse this author | List, Benjamin Browse this author →KAKEN DB |
Keywords: | Asymmetric Catalysis | Machine Learning | Organocatalysis |
Issue Date: | 23-Jan-2023 |
Publisher: | Wiley-Blackwell |
Journal Title: | Angewandte chemie-international edition |
Volume: | 62 |
Issue: | 11 |
Start Page: | e202218659 |
Publisher DOI: | 10.1002/anie.202218659 |
Abstract: | Catalyst optimization processes typically rely on inductive and qualitative assumptions 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 challenging asymmetric tetrahydropyran synthesis. |
Type: | article |
URI: | http://hdl.handle.net/2115/88658 |
Appears in Collections: | 化学反応創成研究拠点:ICReDD (Institute for Chemical Reaction Design and Discovery : ICReDD) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)
|
|