Deep learning-based k(cat) prediction enables improved enzyme-constrained model reconstruction
Journal article, 2022

Enzyme turnover numbers (k(cat)) are key to understanding cellular metabolism, proteome allocation and physiological diversity, but experimentally measured k(cat) data are sparse and noisy. Here we provide a deep learning approach (DLKcat) for high-throughput k(cat) prediction for metabolic enzymes from any organism merely from substrate structures and protein sequences. DLKcat can capture k(cat) changes for mutated enzymes and identify amino acid residues with a strong impact on k(cat) values. We applied this approach to predict genome-scale k(cat) values for more than 300 yeast species. Additionally, we designed a Bayesian pipeline to parameterize enzyme-constrained genome-scale metabolic models from predicted k(cat) values. The resulting models outperformed the corresponding original enzyme-constrained genome-scale metabolic models from previous pipelines in predicting phenotypes and proteomes, and enabled us to explain phenotypic differences. DLKcat and the enzyme-constrained genome-scale metabolic model construction pipeline are valuable tools to uncover global trends of enzyme kinetics and physiological diversity, and to further elucidate cellular metabolism on a large scale.

Author

Feiran Li

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Le Yuan

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Hongzhong Lu

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Gang Li

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Yu Chen

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Martin Engqvist

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Eduard Kerkhoven

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Jens B Nielsen

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

BioInnovation Institute

Nature Catalysis

25201158 (eISSN)

Vol. 5 8 662-672

Synthetic microbial consortia-based platform for flavonoids production using synthetic biology (Synbio4Flav)

European Commission (EC) (EC/H2020/814650), 2019-01-01 -- 2023-02-28.

Bioinformatics Services for Data-Driven Design of Cell Factories and Communities (DD-DeCaF)

European Commission (EC) (EC/H2020/686070), 2016-03-01 -- 2020-02-28.

Subject Categories

Biochemistry and Molecular Biology

Bioinformatics (Computational Biology)

Bioinformatics and Systems Biology

DOI

10.1038/s41929-022-00798-z

Related datasets

Supplementary Dataset for Deep learning based k(cat) prediction enables improved enzyme constrained model reconstruction [dataset]

DOI: 10.5281/zenodo.5164209

More information

Latest update

3/7/2024 9