diff --git a/man/metadata-set.Rd b/man/metadata-set.Rd
index 4db691f..1ca164c 100644
--- a/man/metadata-set.Rd
+++ b/man/metadata-set.Rd
@@ -10,6 +10,6 @@ metadata(object) <- value
 Sets metadata to a \code{scPred} object. Metadata must be a dataframe
 \itemize{
 \item row names: ids matching the column names of the expression matrix
-\item columns: associated metadata such as cell type, conditions, sample or, batch. 
+\item columns: associated metadata such as cell type, conditions, sample or, batch.
 }
 }
diff --git a/man/plotLoadings-scPred-method.Rd b/man/plotLoadings-scPred-method.Rd
index de292c1..dd2bd54 100644
--- a/man/plotLoadings-scPred-method.Rd
+++ b/man/plotLoadings-scPred-method.Rd
@@ -12,7 +12,7 @@
 
 \item{pc}{The number of the principal component to be plotted}
 
-\item{n}{Top `n` variable genes to plot. Notice that the number of plotted genes is n*2 as both 
+\item{n}{Top `n` variable genes to plot. Notice that the number of plotted genes is n*2 as both
 negative and positive loadings are considered}
 }
 \value{
diff --git a/man/plotLoadings.Rd b/man/plotLoadings.Rd
index a229685..0630da1 100644
--- a/man/plotLoadings.Rd
+++ b/man/plotLoadings.Rd
@@ -11,7 +11,7 @@ plotLoadings(object, pc = 1, n = 10)
 
 \item{pc}{The number of the principal component to be plotted}
 
-\item{n}{Top `n` variable genes to plot. Notice that the number of genes plotted is n*2 as both 
+\item{n}{Top `n` variable genes to plot. Notice that the number of genes plotted is n*2 as both
 negative and positive loadings are considered}
 }
 \description{
diff --git a/man/trainModel.Rd b/man/trainModel.Rd
index de661f6..5aba55e 100644
--- a/man/trainModel.Rd
+++ b/man/trainModel.Rd
@@ -5,14 +5,15 @@
 \title{Train a prediction model}
 \usage{
 trainModel(object, model = "svmRadial", resampleMethod = "cv",
-  number = 10, seed = 66, metric = c("ROC", "Accuracy", "Kappa"),
-  returnData = TRUE, savePredictions = "final")
+  number = 5, seed = 66, metric = c("ROC", "PR", "Accuracy",
+  "Kappa"), imbalance = 0.1, returnData = FALSE,
+  savePredictions = "final", allowParallel = FALSE)
 }
 \arguments{
-\item{object}{An \code{scPred} object with informative PCs obtained using 
+\item{object}{An \code{scPred} object with informative PCs obtained using
 the \code{getInformativePCs} function}
 
-\item{model}{Classification model supported via \code{caret} package. A list of all models can be found here: 
+\item{model}{Classification model supported via \code{caret} package. A list of all models can be found here:
 https://topepo.github.io/caret/available-models.html
 Default: support vector machine with polynomial kernel}
 
@@ -24,7 +25,7 @@ Default: support vector machine with polynomial kernel}
 
 \item{returnData}{If \code{TRUE}, training data is returned}
 
-\item{savePredictions}{an indicator of how much of the hold-out predictions for each resample should be 
+\item{savePredictions}{an indicator of how much of the hold-out predictions for each resample should be
 saved. Values can be either "all", "final", or "none". A logical value can also be used that convert to
  "all" (for true) or "none" (for false). "final" saves the predictions for the optimal tuning parameters.}
 }
@@ -40,8 +41,8 @@ Trains a prediction model from an \code{scPred} object
 ## A numeric seed is provided for the K-fold cross validation
 ## The metric ROC is used to select the best tuned model. "Accuracy" and "Kappa" may be used too.
 
-object <- trainModel(object = object, 
-                     seed = 1234, 
+object <- trainModel(object = object,
+                     seed = 1234,
                      metric = "ROC")
 
 }