We introduce the immunological Elastic Net (iEN) which integrates mechanistic immunological knowledge into a machine learning framework. Here we provide code for the application of iEN models and its optimization given a set of hyperparameter values. For a more comprehensive description of this method please see Integration of Mechanistic Immunological Knowledge into a Machine Learning Pipeline Improves Predictions
.
Installation of the 'immunological-EN' can be accomplished easiest through the terminal. All libraries dependent for the optimization and fitting of iEN models must be installed prior to building and installing the package from the source files. To install all dependencies please run this command prior to installation install.packages(c('pROC', 'Metrics', 'Matrix', 'glmnet', 'knitr'))
See DESCRIPTION
file for a full list of imported and suggested packages.
install.packages(path_to_file, repos = NULL, type="source")
where the file is iEN_0.99.0.tar.gz
iEN
package should now be available in R via the library('iEN')
commandiEN_0.99.0.tar.gz
fileR CMD Build immunological-EN-master
If different, adapt this command to accommodate whichever folder name was used.tar.gz
file which was built
R CMD INSTALL iEN_0.99.0.tar.gz
For full documentation see iEN-Manual.pdf
, here we will summarize the main function of the package wich optimizes an iEN model via cross-validated grid search while also producing out-of-sample predictions on held out folds.
cv_iEN
optimizes an iEN model via K-fold cross validation gridsearch and returns out-of-sample predictions and the associated model meta data. it does so with the following parameters
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.