Mechanism-Informed Rules Tunably Balance Novelty and Feasibility of Predicted Enzymatic Reactions

Enzymes catalyze reactions with remarkable specificity and can unlock recalcitrant feedstocks that are dilute, complex, and variable in their constituent molecules. While characterized enzymatic reactions cover a wide range of chemistries, there are an undetermined number of cryptic activities for every known one. These cryptic activities can be elicited through rational design, adaptive laboratory evolution, and increasingly, generative models of proteins. However, prior to tuning a catalyst, one must efficiently predict viable novel reactions. In this work, we leverage the growing amount of mechanistic enzyme information, specifically the Mechanism and Catalytic Site Atlas, to construct a set of reaction rules that can meet this demand. By explicitly utilizing mechanistic information, the rule sets developed here more accurately identify molecular structures required for catalysis compared to existing curated and heuristically constructed rules. The 899 Distilled rules are constructed directly from characterized mechanisms and recapitulate 62.5% of atom-mapped reactions from Rhea. The Learned rule set is generated from a classifier trained on structural patterns putatively required for catalytic mechanisms. The Learned rules recapitulate all atom-mapped Rhea reactions and precisely predict mechanism-required atoms (ROC-AUC = 0.98). Additionally, our Learned rules exhibit a more favorable trade-off between novelty and feasibility and provide users with fine-grained control over this trade-off. The rules are compatible with all SMARTS-based reaction network expansion and retrosynthesis software.