Abstract
Constraint-based mechanistic models have largely been exploited to predict the phenotype of microorganisms in different environments. However, phenotype predictions are limited in quality unless labor intensive experiments including the measurement of media uptake fluxes, are performed. We show how hybrid - mechanistic and neural – models provide ways to improve phenotype predictions. Our hybrid models named Artificial Metabolic Networks (AMNs) surrogate constraint-based modeling, make metabolic networks suitable for backpropagation and, consequently, can serve as an architecture for machine learning. We first show how learning principles brought by AMNs can replace the optimization principle of constraint-based modeling with excellent performances for various in silico training sets. We then illustrate how AMNs outperform mechanistic models with Escherichia coli growth rates measured in 110 different media compositions reaching regression coefficients > 0.76 on cross-validation data. We expect our hybrid AMN models to enhance constraint-based modeling and to prompt new biotechnological applications.
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
Added two new hybrid models
Abbreviations
- AMN
- Artificial Metabolic Network
- ANN
- Artificial Neural Network
- FBA
- Flux Balance Analysis
- GD
- Gradient Descent
- LP(QP)
- Linear (Quadratic) Programming
- ML
- Machine Learning
- MM
- Mechanistic Modeling
- PINN
- Physics Informed Neural Network
- RNN
- Recurrent Neural Network
- R2
- Regression coefficient calculated on training set
- Q2
- regression coefficient calculated on cross-validation sets or independent test sets (not seen during training).