This is not the latest version of this item. The latest version can be found here.
Machine learned prediction of reaction template applicability for data-driven retrosynthetic predictions of energetic materials
Name
c2acbabbc34f857e10e841827a8fac672a05.pdf
Description
Accepted version
Size
404.65 KB
Format
Adobe PDF
Checksum (MD5)
57568ca3e9fe40dacb0cde404bb949dd
Author(s)
Fortunato, ME
Coley, CW
Barnes, BC
Jensen, KF
Date Issued
2020
Journal
AIP Conference Proceedings
Publisher
AIP Publishing
Citation
Fortunato, ME, Coley, CW, Barnes, BC and Jensen, KF. 2020. "Machine learned prediction of reaction template applicability for data-driven retrosynthetic predictions of energetic materials." AIP Conference Proceedings, 2272.
Version
Author's final manuscript
Abstract
State of the art computer-aided synthesis planning models are naturally biased toward commonly reported chemical reactions, thus reducing the usefulness of those models for the unusual chemistry relevant to shock physics. To address this problem, a neural network was trained to recognize reaction template applicability for small organic molecules to supplement the rare reaction examples of relevance to energetic materials. The training data for the neural network was generated by brute force determination of template subgraph matching for product molecules from a database of reactions in U.S. patent literature. This data generation strategy successfully augmented the information about template applicability for rare reaction mechanisms in the reaction database. The increased ability to recognize rare reaction templates was demonstrated for reaction templates of interest for energetic material synthesis such as heterocycle ring formation.
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
10.1063/12.0000850
