inner_train_model_expr: (INNER) Train expression model from methylation profiles

In BPRMeth: Model higher-order 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 [e-mail]

See Also

predict_expr

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)

BPRMeth documentation built on Nov. 8, 2020, 5:54 p.m.