ChemRxiv
These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
1/1
0/0

A Graph-Convolutional Neural Network Model for the Prediction of Chemical Reactivity

preprint
submitted on 03.10.2018 and posted on 04.10.2018 by Connor W. Coley, Wengong Jin, Luke Rogers, Timothy F. Jamison, Tommi S Jaakkola, William H. Green, Regina Barzilay, Klavs F. Jensen
We present a supervised learning approach to predict the products of organic reactions given their reactants, reagents, and solvent(s). The prediction task is factored into two stages comparable to manual expert approaches: considering possible sites of reactivity and evaluating their relative likelihoods. By training on hundreds of thousands of reaction precedents covering a broad range of reaction types from the patent literature, the neural model makes informed predictions of chemical reactivity. The model predicts the major product correctly over 85% of the time requiring around 100 ms per example, a significantly higher accuracy than achieved by previous machine learning approaches, and performs on par with expert chemists with years of formal training. We gain additional insight into predictions via the design of the neural model, revealing an understanding of chemistry qualitatively consistent with manual approaches.

Funding

ARO W911NF-16-2-0023; NSF GRFP Grant No. 1122374

History

Email Address of Submitting Author

ccoley@mit.edu

Institution

Massachusetts Institute of Technology

Country

United States

ORCID For Submitting Author

0000-0002-8271-8723

Declaration of Conflict of Interest

There are no conflicts to declare.

Exports