This section is under development.
One of the use cases of GenoML is target identification. GenoML is designed to support the identification and prioritization of potential interventional targets for follow-up. This capability utilizes one of the strengths of machine learning models. As part of the model development, GenoML outputs the feature importances of a model by specifying the
--feature_selection option during
munge. This capability allows prioritizing the factors that impact the predictive model the most. Furthermore, we are adding more features to help with model interpretability, particularly when it relates to the "targetable" features.