Multitask prediction of site selectivity in aromatic C-H functionalization reactions
Name
d0re00071j.pdf
Size
1.83 MB
Format
Adobe PDF
Checksum (MD5)
03d01402d1bc06416710cb3d55fa994d
Author(s)
Struble, Thomas J
Coley, Connor Wilson
Jensen, Klavs F
Date Issued
April 2020
Journal
Reaction Chemistry & Engineering
Citation
Struble, Thomas J., Connor Wilson Coley, and Klavs F. Jensen, "Multitask prediction of site selectivity in aromatic C-H functionalization reactions." Reaction Chemistry & Engineering 5 (Apr. 2020): no. 896 doi 10.1039/D0RE00071J ©2020 Author(s)
Version
Final published version
Abstract
Aromatic C–H functionalization reactions are an important part of the synthetic chemistry toolbox. Accurate prediction of site selectivity can be crucial for prioritizing target compounds and synthetic routes in both drug discovery and process chemistry. However, selectivity may be highly dependent on subtle electronic and steric features of the substrate. We report a generalizable approach to prediction of site selectivity that is accomplished using a graph-convolutional neural network for the multitask prediction of 123 C–H functionalization tasks. In an 80/10/10 training/validation/testing pseudo-time split of about 58 000 aromatic C–H functionalization reactions from the Reaxys database, the model achieves a mean reciprocal rank of 92%. Once trained, inference requires approximately 200 ms per compound to provide quantitative likelihood scores for each task. This approach and model allow a chemist to quickly determine which C–H functionalization reactions – if any – might proceed with high selectivity.
MIT Department
Massachusetts Institute of Technology. Department of Chemical Engineering
Terms of Use
Creative Commons Attribution Noncommercial 3.0 unported license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1039/D0RE00071J
