DLTKcat: deep learning based prediction of temperature dependent enzyme turnover rates

Abstract

The enzyme turnover rate, kcat, quantifies enzyme kinetics by indicating the maximum efficiency of enzyme catalysis. Despite its importance, kcat values remain scarce in databases for most organisms, primarily due to the cost of experimental measurements. To predict kcat and account for its strong temperature dependence, DLTKcat was developed in this study and demonstrated superior performance (log10-scale RMSE = 0.88, R2 = 0.66) than previously published models. Through two case studies, DLTKcat showed its ability to predict the effect of protein sequence mutations and temperature changes on kcat values. Although its quantitative accuracy is not high enough yet to model the responses of cellular metabolism to temperature changes, DLTKcat has the potential to eventually become a computational tool to describe the temperature dependence of biological systems.