Plot similarity matrix with pheatmap

Source: R/plot-similarity-matrix-2.R

Plot similarity matrix with pheatmap

plotSimilarityMatrix2(
  X,
  y = NULL,
  clusLabels = NULL,
  colX = NULL,
  colY = NULL,
  myLegend = NULL,
  fileName = "posteriorSimilarityMatrix.pdf",
  save = FALSE,
  semiSupervised = FALSE,
  scale = "none",
  showObsNames = FALSE,
  clr = FALSE,
  clc = FALSE,
  plotWidth = 500,
  plotHeight = 450
)

Arguments

X

Similarity matrix.
y

Vector
clusLabels

Cluster labels
colX

Colours for the matrix
colY

Colours for the response
myLegend

Vector of strings with the names of the variables
fileName

Name of pdf file
save

Boolean flag: if TRUE, the plot is saved as a png file.
semiSupervised

Boolean flag: if TRUE, the response is plotted next to the matrix.
scale

Used as input for the parameter "scale" of the gplot::heatmap.2() function. Can be either "none" or "columns".
showObsNames

Boolean. If TRUE, observation names are shown in the plot. Default is FALSE.
clr

Boolean. If TRUE, rows are ordered by hierarchical clustering. Default is FALSE.
clc

Boolean. If TRUE, columns are ordered by hierarchical clustering. Default is FALSE.
plotWidth

Plot width. Default is 500.
plotHeight

Plot height. Default is 450.

Examples

# Load one dataset with 300 observations, 2 variables, 6 clusters
data <- as.matrix(read.csv(system.file("extdata", "dataset1.csv",
package = "klic"), row.names = 1))
cluster_labels <- as.matrix(read.csv(system.file("extdata",
"cluster_labels.csv", package = "klic"), row.names = 1))
# Compute consensus clustering with K=6 clusters
cm <- coca::consensusCluster(data, 6)
# Plot consensus (similarity) matrix
plotSimilarityMatrix2(cm)
# Plot consensus (similarity) matrix with response
names(cluster_labels) <- as.character(1:300)
rownames(cm) <- names(cluster_labels)
plotSimilarityMatrix2(cm, y = cluster_labels)