DRACON: Disconnected Graph Neural Network for Atom Mapping in Chemical Reactions

Machine learning solved many challenging problems in computer-assisted synthesis prediction (CASP). We formulate a reaction prediction problem in terms of node-classification in a disconnected graph of source molecules and generalize a graph convolution neural network for disconnected graphs. Here we demonstrate that our approach can successfully predict reaction outcome and atom-mapping during a chemical transformation. A set of experiments using the USPTO dataset demonstrates excellent performance and interpretability of the proposed model. Our model uses an unsupervised approach to atom-mapping and bridges the gap between data-driven and traditional rule-based methods. Implicitly learned latent vector representation of chemical reactions strongly correlates with the class of the chemical reaction. Reactions with similar templates group together in the latent vector space.