Learning organo-transition metal catalyzed reactions by graph neural networks.

ABSTRACT

Chemical reaction outcome prediction presents a fundamental challenge in synthetic chemistry. Most existing machine learning (ML) approaches focus on chemical reactions of typical elements. We developed a simple ML model focused on organo-transition metal-catalyzed reactions (OMCRs). Instead of overall reactions observed in experiments, we let the ML model learn the sequence of simplified elementary reactions. This drastically reduced the complexity of the model and helped it find common patterns from distinct reactions. We let a graph neural network learn the reactivity index of a pair of atoms. The model was able to learn a wide variety of OMCRs, and the accuracy of reaction prediction reached 97%, even though the model has extremely fewer learnable parameters than other standards. The learned reactivity indices of bonds nicely summarize the knowledge of reactions in the dataset.