variancePartition (version 1.2.5)

plotVarPart: Violin plot of variance fractions

Description

Violin plot of variance fraction for each gene and each variable

Usage

plotVarPart(obj, col = c(ggColorHue(ncol(obj) - 1), "#bebebe99"), label.angle = 20, main = "", convertToPercent = TRUE, ...)
"plotVarPart"(obj, col = c(ggColorHue(ncol(obj) - 1), "#bebebe99"), label.angle = 20, main = "", convertToPercent = TRUE, ...)
"plotVarPart"(obj, col = c(ggColorHue(ncol(obj) - 1), "#bebebe99"), label.angle = 20, main = "", convertToPercent = TRUE, ...)
"plotVarPart"(obj, col = c(ggColorHue(ncol(obj) - 1), "#bebebe99"), label.angle = 20, main = "", convertToPercent = TRUE, ...)

Arguments

obj

varParFrac object returned by fitExtractVarPart or extractVarPart

col

vector of colors

label.angle

angle of labels on x-axis

main

title of plot

convertToPercent

multiply fractions by 100 to convert to percent values

...

additional arguments

Value

Makes violin plots of variance components model. This function uses the graphics interface from ggplot2. Warnings produced by this function usually ggplot2 warning that the window is too small.

Examples

# load library
# library(variancePartition)

# optional step to run analysis in parallel on multicore machines
# Here, we used 4 threads
library(doParallel)
cl <- makeCluster(4)
registerDoParallel(cl)
# or by using the doSNOW package

# load simulated data:
# geneExpr: matrix of gene expression values
# info: information/metadata about each sample
data(varPartData)

# Specify variables to consider
# Age is continuous so we model it as a fixed effect
# Individual and Tissue are both categorical, so we model them as random effects
form <- ~ Age + (1|Individual) + (1|Tissue) 

varPart <- fitExtractVarPartModel( geneExpr, form, info )
 
# violin plot of contribution of each variable to total variance
plotVarPart( sortCols( varPart ) )

# stop cluster
stopCluster(cl)