On the use of real-world datasets for reaction yield prediction-Reference-Cited by-同舟云学术

On the use of real-world datasets for reaction yield prediction

Published:2023 Issue:19 Volume:14 Page:4997-5005
ISSN:2041-6520
Container-title:Chemical Science
language:en
Short-container-title:Chem. Sci.

Author:

Saebi Mandana¹,Nan Bozhao²,Herr John E.²,Wahlers Jessica²,Guo Zhichun¹,Zurański Andrzej M.³^ORCID,Kogej Thierry⁴,Norrby Per-Ola⁵^ORCID,Doyle Abigail G.³⁶^ORCID,Chawla Nitesh V.¹^ORCID,Wiest Olaf²^ORCID

Affiliation:

1. Department of Computer Science and Engineering and Lucy Family Institute for Data and Society, University of Notre Dame, Notre Dame, IN 46556, USA

2. Department of Chemistry and Biochemistry, University of Notre Dame, Notre Dame, IN 46556, USA

3. Department of Chemistry, Princeton University, Princeton, New Jersey 08544, USA

4. Molecular AI, Discovery Sciences, R&D, AstraZeneca, Pepparedsleden 1, SE-431 83 Mölndal, Gothenburg, Sweden

5. Data Science and Modelling, Pharmaceutical Sciences, R&D, AstraZeneca, Pepparedsleden 1, SE-431 83 Mölndal, Gothenburg, Sweden

6. Department of Chemistry and Biochemistry, University of California, Los Angeles, California 90095, USA

Abstract

An attributed graph neural network predicts the yield of Suzuki–Miyaura and Buchwald–Hartwig reactions for datasets from high-throughput experimentation (HTE) but not for a more diverse real-world dataset from electronic lab notebooks (ELNs).

Funder

National Science Foundation

Publisher

Royal Society of Chemistry (RSC)

Subject

General Chemistry

Link

http://pubs.rsc.org/en/content/articlepdf/2023/SC/D2SC06041H

Reference55 articles.

1. Application of Q2MM to predictions in stereoselective synthesis

2. A Holy Grail in Chemistry: Computational Catalyst Design: Feasible or Fiction?

3. Automation and computer-assisted planning for chemical synthesis