Journal Article

Deep learning allows genome-scale prediction of Michaelis constants from structural features

Lercher, Martin J., Kroll, Alexander, Engqvist, Martin K. M., Heckmann, David

2021

Overview

The Michaelis constant K M describes the affinity of an enzyme for a specific substrate and is a central parameter in studies of enzyme kinetics and cellular physiology. As measurements of K M are often difficult and time-consuming, experimental estimates exist for only a minority of enzyme–substrate combinations even in model organisms. Here, we build and train an organism-independent model that successfully predicts K M values for natural enzyme–substrate combinations using machine and deep learning methods. Predictions are based on a task-specific molecular fingerprint of the substrate, generated using a graph neural network, and on a deep numerical representation of the enzyme’s amino acid sequence. We provide genome-scale K M predictions for 47 model organisms, which can be used to approximately relate metabolite concentrations to cellular physiology and to aid in the parameterization of kinetic models of cellular metabolism.

• Publisher: Public Library of Science,Public Library of Science (PLoS)
• Subject: Amino acid sequence / Amino acids / Artificial intelligence / Binding sites / Biology and Life Sciences / cell metabolism / Chemical fingerprinting / Computer and Information Sciences / Databases, Genetic / Deep Learning / DNA sequencing / E coli / enzyme substrate / Enzymes / Enzymes - metabolism / Genome / Genome-wide association studies / Genomes / Graph neural networks / Kinetics / Learning algorithms / Metabolism / Metabolites / Metabolomics / Methods / Methods and Resources / Michaelis constant / Models, Biological / molecular fingerprinting / Neural networks / Neural Networks, Computer / Nucleotide sequence / Nucleotide sequencing / Organisms / Parameterization / Physical Sciences / Physiology / Predictions / Proteins / Research and Analysis Methods / Substrate Specificity / Substrates