A graph-convolutional neural network model for the prediction of chemical reactivity.

Coley CW, Jin W, Rogers L, Jamison TF, Jaakkola TS, Green WH, Barzilay R, Jensen KF. · 2019

Read A graph-convolutional neural network model for the prediction of chemical reactivity. by Coley CW, Jin W, Rogers L, Jamison TF, Jaakkola TS, Green WH, Barzilay R, Jensen KF. (2019) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc6335848.txt.

Description

Coley and co-authors teach a neural network to predict chemical reaction products. Their paper appeared in Chemical Science. Chemists usually predict outcomes by training and intuition. A reliable computer method could speed that work. It could also flag side products early. The team framed each molecule as a graph. Atoms form the nodes of the graph.

Their graph-convolutional model learns from past reactions. It takes reactants, reagents, and solvents as input. It then predicts the major product formed. The approach covers a broad range of organic reactions. It can validate routes that planning software suggests. That raises confidence before any lab work begins. The authors present it as a step toward automated reaction checks. It supports, rather than replaces, chemist judgment.

Catalog record

CREATORColey CW, Jin W, Rogers L, Jamison TF, Jaakkola TS, Green WH, Barzilay R, Jensen KF.
YEAR2019
COLLECTIONPAPERS
FORMATTXT
FILE SIZE31 KB
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC6335848

Browse the full library · About the Tower of Babel