predictorElasticNet: Wrapper function for elastic net regression

In jpvert/kmr4toxicogenetics: Kernel multitask regression for toxicogenetics

Description

Wrapper function to perform elastic net regression with cv.glmnet that trains a model on training set and then predicts on test set for multiple tasks.

Usage

predictorElasticNet(patientsTrain, patientsTest, response, alpha = 0.5)

Arguments

patientsTrain	Matrix of training descriptors, of dimension n x p, for n training patients with p descriptors.
patientsTest	Matrix of test descriptors, of dimension m x p, for m test patients with the same set of p descriptors.
response	Matrix of observed toxicity values, of dimension n x t, for the n training patients responding to t drugs.
alpha	The elasticnet mixing parameter. alpha=1 is the lasso penalty, and alpha=0 the ridge penalty. Default is 0.5. All other arguments are taken by default implementation of randomForest.

Value

A matrix of predicted toxicity values, of dimension m x t, for the m test patients responding to the t drugs.

Note

Prediction is made per task with no special treatment for multitask learning, nor are task features needed.

See Also

cv.glmnet

jpvert/kmr4toxicogenetics documentation built on May 24, 2019, 2:04 a.m.