Dataset Information

UniKP: a unified framework for the prediction of enzyme kinetic parameters.

ABSTRACT: Prediction of enzyme kinetic parameters is essential for designing and optimizing enzymes for various biotechnological and industrial applications, but the limited performance of current prediction tools on diverse tasks hinders their practical applications. Here, we introduce UniKP, a unified framework based on pretrained language models for the prediction of enzyme kinetic parameters, including enzyme turnover number (k_cat), Michaelis constant (K_m), and catalytic efficiency (k_cat / K_m), from protein sequences and substrate structures. A two-layer framework derived from UniKP (EF-UniKP) has also been proposed to allow robust k_cat prediction in considering environmental factors, including pH and temperature. In addition, four representative re-weighting methods are systematically explored to successfully reduce the prediction error in high-value prediction tasks. We have demonstrated the application of UniKP and EF-UniKP in several enzyme discovery and directed evolution tasks, leading to the identification of new enzymes and enzyme mutants with higher activity. UniKP is a valuable tool for deciphering the mechanisms of enzyme kinetics and enables novel insights into enzyme engineering and their industrial applications.

SUBMITTER: Yu H

PROVIDER: S-EPMC10713628 | biostudies-literature | 2023 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

UniKP: a unified framework for the prediction of enzyme kinetic parameters.

Yu Han H Deng Huaxiang H He Jiahui J Keasling Jay D JD Luo Xiaozhou X

Nature communications 20231211 1

Prediction of enzyme kinetic parameters is essential for designing and optimizing enzymes for various biotechnological and industrial applications, but the limited performance of current prediction tools on diverse tasks hinders their practical applications. Here, we introduce UniKP, a unified framework based on pretrained language models for the prediction of enzyme kinetic parameters, including enzyme turnover number (k<sub>cat</sub>), Michaelis constant (K<sub>m</sub>), and catalytic efficien ...[more]

PMID: 38081905

Similar Datasets

Project description:Stability and biological activity of proteins is highly dependent on their physicochemical environment. The development of realistic models of biological systems necessitates quantitative information on the response to changes of external conditions like pH, salinity and concentrations of substrates and allosteric modulators. Changes in just a few variable parameters rapidly lead to large numbers of experimental conditions, which go beyond the experimental capacity of most research groups. We implemented a computer-aided experimenting framework ("robot lab assistant") that allows us to parameterize abstract, human-readable descriptions of micro-plate based experiments with variable parameters and execute them on a conventional 8 channel liquid handling robot fitted with a sensitive plate reader. A set of newly developed R-packages translates the instructions into machine commands, executes them, collects the data and processes it without user-interaction. By combining script-driven experimental planning, execution and data-analysis, our system can react to experimental outcomes autonomously, allowing outcome-based iterative experimental strategies. The framework was applied in a response-surface model based iterative optimization of buffer conditions and investigation of substrate, allosteric effector, pH and salt dependent activity profiles of pyruvate kinase (PYK). A diprotic model of enzyme kinetics was used to model the combined effects of changing pH and substrate concentrations. The 8 parameters of the model could be estimated from a single two-hour experiment using nonlinear least-squares regression. The model with the estimated parameters successfully predicted pH and PEP dependence of initial reaction rates, while the PEP concentration dependent shift of optimal pH could only be reproduced with a set of manually tweaked parameters. Differences between model-predictions and experimental observations at low pH suggest additional protonation-sites at the enzyme or substrates critical for enzymatic activity. The developed framework is a powerful tool to investigate enzyme reaction specifics and explore biological system behaviour in a wide range of experimental conditions.

Dataset Information

UniKP: a unified framework for the prediction of enzyme kinetic parameters.

Publications

UniKP: a unified framework for the prediction of enzyme kinetic parameters.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets