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


Let's dig deeper into the details of the algorithm. The authors used a Weisfeiler-Lehman Network, a type of graph-convolutional neural network, as depicted in the figure below. First, for each atom-atom pair (including pairs of atoms that are not bound or are located in different reactants) the neural network predicts the likelihood of the bond order to change. The starting point is from a graph representation of reactants (A), where atoms are featurized by atomic number, formal charge, degree of connectivity, valence and aromaticity, and bonds are featurized by bond order and ring status. These atom-level features are iteratively updated (B) by incorporating information from neighbor atoms.