loading . . . Machine learning/molecular mechanics enzymology for the next generation of computational enzymatic catalysis We highlight how machine learning interatomic potentials (MLIPs), embedded within hybrid machine learning and molecular mechanics (ML/MM) frameworks, are transforming computational enzymology. By replacing the costly quantum mechanics (QM) region with reactive MLIPs trained on diverse datasets, ML/MM achieves near-QM accuracy with speedups on the order of thousands, enabling quantitative prediction of stereoselectivity and mutant effects in enzymatic catalysis. Key frontiers, including long-range corrections, field-aware embeddings, reaction modeling, and excited-state simulations, are discussed as pathways toward next-generation computational enzyme design. http://dlvr.it/TRJpC6
