4.6 Article

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

Journal

PLOS BIOLOGY
Volume 19, Issue 10, Pages -

Publisher

PUBLIC LIBRARY SCIENCE
DOI: 10.1371/journal.pbio.3001402

Keywords

-

Funding

  1. Volkswagenstiftung (in the Life? program)
  2. Deutsche Forschungsgemeinschaft [CRC 1310, EXC 2048/1, 390686111]

Ask authors/readers for more resources

The study developed a model using machine and deep learning methods to predict KM values for natural enzyme-substrate combinations, providing genome-scale KM predictions that can help relate metabolite concentrations to cellular physiology.
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.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available