DLKcat cannot predict meaningful k _cat values for mutants and unfamiliar enzymes

The recently published DLKcat model, a deep learning approach for predicting enzyme turnover numbers (k _cat), claims to enable high-throughput k _cat predictions for metabolic enzymes from any organism and to capture k _cat changes for mutated enzymes. Here, we critically evaluate these claims. We show that for enzymes with <60% sequence identity to the training data DLKcat predictions become worse than simply assuming a constant average k _cat value for all reactions. Furthermore, DLKcat's ability to predict mutation effects is much weaker than implied, capturing none of the experimentally observed variation across mutants not included in the training data. These findings highlight significant limitations in DLKcat's generalizability and its practical utility for predicting k _cat values for novel enzyme families or mutants, which are crucial applications in fields such as metabolic modeling.