Mechanism-Informed Rules Tunably Balance Novelty and Feasibility of Predicted Enzymatic Reactions
- 23 June 2026
- journal article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (13) , 7688-7700
Abstract
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.Keywords
Funding Information
- National Laboratory of the Rockies (DE-AC36-08GO28308)
- National Institute of General Medical Sciences (T32GM008449)
- National Institute of General Medical Sciences (T32GM153505)
This publication has 50 references indexed in Scilit:
- EVODEX: A Cheminformatics Framework for Mechanistic Abstraction and Prediction of Enzymatic ReactionsJournal of Chemical Information and Modeling, 2026
- Chemprop: A Machine Learning Package for Chemical Property PredictionJournal of Chemical Information and Modeling, 2023
- Permutation Invariant Graph-to-Sequence Model for Template-Free Retrosynthesis and Reaction PredictionJournal of Chemical Information and Modeling, 2022
- Machine Learning of Reaction Properties via Learned Representations of the Condensed Graph of ReactionJournal of Chemical Information and Modeling, 2021
- EHreact: Extended Hasse Diagrams for the Extraction and Scoring of Enzymatic Reaction TemplatesJournal of Chemical Information and Modeling, 2021
- Curating a comprehensive set of enzymatic reaction rules for efficient novel biosynthetic pathway designMetabolic Engineering, 2021
- Underground metabolism: network-level perspective and biotechnological potentialCurrent Opinion in Biotechnology, 2018
- RetroPath2.0: A retrosynthesis workflow for metabolic engineersMetabolic Engineering, 2018
- Directed Evolution: Bringing New Chemistry to LifeAngewandte Chemie International Edition, 2017
- Discovery and analysis of novel metabolic pathways for the biosynthesis of industrial chemicals: 3‐hydroxypropanoateBiotechnology and Bioengineering, 2010