R: (INNER) Train expression model from methylation profiles

inner_train_model_expr {BPRMeth}

R Documentation

(INNER) Train expression model from methylation profiles

Description

This function trains a regression model for predicting gene expression levels by taking as input the higher order methylation features extracted from specific genomic regions.

Usage

inner_train_model_expr(formula = NULL, model_name = "lm", train,
  is_summary = TRUE)

Arguments

`formula`	An object of class `formula`, e.g. see `lm` function. If NULL, the simple linear model is used.
`model_name`	A string denoting the regression model. Currently, available models are: `"svm"`, `"randomForest"`, `"rlm"`, `"mars"`, `"gp"`, and `"lm"`.
`train`	The training data.
`is_summary`	Logical, print the summary statistics.

Value

A list containing the following elements:

formula: The formula that was used.
gex_model: The fitted model.
train_pred The predicted values for the training data.
train_errors: The training error metrics.

Author(s)

C.A.Kapourani C.A.Kapourani@ed.ac.uk

Examples

# Create synthetic data
train_data <- data.frame(x = rnorm(20), y=rnorm(20, 1, 4))
res <- inner_train_model_expr(formula = y~., train = train_data)

# Using a different model
res <- inner_train_model_expr(model_name = "randomForest",
                              train = train_data)

[Package BPRMeth version 1.8.1 Index]