RC-GNN: A predictive model of enzyme-reaction pairs

Abstract

Uncharacterized functions of enzymes represent untapped opportunity to develop therapeutics, unlock the sustainable synthesis of materials, and understand the evolution of life-sustaining metabolic networks. Uncharacterized enzymes and reactions, generated by protein language models and computer-aided synthesis tools, respectively, make up a large part of this opportunity. Given the technical complexity of high-throughput enzymatic activity screens, predictive models are needed that can pre-screen enzyme-reaction pairs in silico. We present Reaction-Center Graph Neural Network, (RC-GNN) a model capable of predicting whether an enzyme, represented by an amino acid sequence, can significantly catalyze a given reaction, represented by its full set of reactants and products. We explicitly evaluated RC-GNNs generalization to queries highly dissimilar from those present in the training dataset. In the most difficult conditions tested, our models achieve 0.88 and 0.84 ROC-AUC on classification tasks featuring globally selected and synthetic negatives, respectively. On a time-based split an RC-GNN achieved 0.91 ROC-AUC. The ability to successfully make predictions on enzymes and reactions distinct from those used during training makes RC-GNN especially useful for both metabolic engineers and evolutionary biologists who need to reason about uncharacterized enzymatic reactions.