fusemlr: fusemlr

In fuseMLR: Fusing Machine Learning in R

fusemlr

Description

Trains the Training object passed as argument. A training object must contain the training layers and a training meta-layer. A training layer encapsulates data modalities, a variable selection method and a learner. Use the function createTraining to create a training object, createTrainLayer to add training layers to the created training object, and createTrainMetaLayer to add a meta-layer with the corresponding meta-learner to the training object. The function fusemlr is designed to train all training layers and the meta-learner. After training the layer-specific base models and the meta-model will be stored in the training object which can be used for predictions.

Usage

fusemlr(
  training,
  ind_subset = NULL,
  use_var_sel = FALSE,
  resampling_method = NULL,
  resampling_arg = list(),
  seed = NULL
)

Arguments

training	Training Training object for storing training layers.
ind_subset	vector ID subset to be used for training.
use_var_sel	boolean If TRUE and no variable selection has been performed for the provide training object, then a variable selection will proceed the training. Otherwise, if variable selection has been previously performed, the selected variables will be used for training.
resampling_method	function Function for internal validation. If not specify, the resampling function from the package caret is used for a 10-folds cross-validation.
resampling_arg	list List of arguments to be passed to the function.
seed	integer Random seed used for resampling. Default is NULL, which generates the seed from R.

Value

The current object is returned, with each learner trained on each layer.

References

Fouodo C.J.K, Bleskina M. and Szymczak S. (2024). fuseMLR: An R package for integrative prediction modeling of multi-omics data, paper submitted.

See Also

createTrainLayer, createTrainMetaLayer, extractModel and extractData.

fuseMLR documentation built on April 3, 2025, 8:49 p.m.