Deep learning basedkcatprediction enables improved enzyme constrained model reconstruction

Abstract Enzyme turnover numbers ( k cat values) are key parameters to understand cell metabolism, proteome allocation and physiological diversity, but experimentally measured k cat data are sparse and noisy. Here we provide a deep learning approach to predict k cat values for metabolic enzymes in a high-throughput manner with the input of substrate structures and protein sequences. Our approach can capture k cat changes for mutated enzymes and identify amino acid residues with great impact on k cat values. Furthermore, we applied the approach to predict genome scale k cat values for over 300 yeast species, demonstrating that the predicted k cat values are consistent with current evolutional understanding. Additionally, we designed an automatic pipeline using the predicted k cat values to parameterize enzyme-constrained genome scale metabolic models (ecGEMs) facilitated by a Bayesian approach, which outperformed the default ecGEMs in predicting phenotypes and proteomes and enabled to explain phenotype differences among yeast species. The deep learning k cat prediction approach and automatic ecGEM construction pipeline would thus be a valuable tool to uncover the global trend of enzyme kinetics and physiological diversity, and to further elucidate cell metabolism on a large scale.