Automated model refinement using genetic interaction data

General concept

This approach reconciles discrepancies between measured and model-predicted epsistatic interactions using a machine-learning algorithm to predict model changes that will correct predictions of negative epsistatic interactions between genes. By utilizing all of the data to minimize model mispredictions, this is done by using a two-stage genetic algorithm, allowing changes such as reaction reversibility, reaction removal, and changes to the biomass function.

Items to consider when implementing

Software packages with this method

Applications of interest

Description of study and link to study:

What was learned with this method:

Relevant references

Szappanos, et al.

Related methods

Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License