Multidimensional scaling plot of distances between gene expression profiles
Plot samples on a two-dimensional scatterplot so that distances on the plot approximate the typical log2 fold changes between the samples.
## Default S3 method:
plotMDS(x, top = 500, labels = NULL, pch = NULL, cex = 1,
dim.plot = c(1,2), ndim = max(dim.plot), gene.selection = "pairwise",
xlab = NULL, ylab = NULL, plot = TRUE, ...)
## S3 method for class 'MDS'
plotMDS(x, labels = NULL, pch = NULL, cex = 1, dim.plot = NULL,
xlab = NULL, ylab = NULL, ...)x |
any data object which can be coerced to a matrix, for example an |
top |
number of top genes used to calculate pairwise distances. |
labels |
character vector of sample names or labels. Defaults to |
pch |
plotting symbol or symbols. See |
cex |
numeric vector of plot symbol expansions. |
dim.plot |
integer vector of length two specifying which principal components should be plotted. |
ndim |
number of dimensions in which data is to be represented. |
gene.selection |
character, |
xlab |
title for the x-axis. |
ylab |
title for the y-axis. |
plot |
logical. If |
... |
any other arguments are passed to |
This function uses multidimensional scaling (MDS) to produce a principal coordinate (PCoA) or principal component (PCA) plot showing the relationships between the expression profiles represented by the columns of x.
If gene.selection = "common", or if the top is equal to or greater than the number of rows of x, then a PCA plot is constructed from the top genes with largest standard deviations across the samples.
If gene.section = "pairwise" and top is less than nrow(x) then a PCoA plot is produced and distances on the plot represent the leading log2-fold-changes.
The leading log-fold-change between a pair of samples is defined as the root-mean-square average of the top largest log2-fold-changes between those two samples.
The PCA and PCoA plots produced by gene.selection="common" and gene.selection="pairwise", respectively, use similar distance measures but the PCA plot uses the same genes throughout whereas the PCoA plot potentially selects different genes to distinguish each pair of samples.
The pairwise choice is the default.
It potentially gives better resolution than a PCA plot if different molecular pathways are relevant for distinguishing different pairs of samples.
If pch=NULL, then each sample is represented by a text label, defaulting to the column names of x.
If pch is not NULL, then plotting symbols are used.
See text for possible values for col and cex.
If plot=TRUE, a plot is created on the current graphics device.
An object of class "MDS" is also invisibly returned.
This is a list containing the following components:
distance.matrix |
numeric matrix of pairwise distances between columns of |
cmdscale.out |
output from the function |
dim.plot |
dimensions plotted |
x |
x-xordinates of plotted points |
y |
y-cordinates of plotted points |
gene.selection |
gene selection method |
Di Wu and Gordon Smyth
Ritchie, ME, Phipson, B, Wu, D, Hu, Y, Law, CW, Shi, W, and Smyth, GK (2015). limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic Acids Research 43, e47. http://nar.oxfordjournals.org/content/43/7/e47
An overview of diagnostic functions available in LIMMA is given in 09.Diagnostics.
# Simulate gene expression data for 1000 probes and 6 microarrays.
# Samples are in two groups
# First 50 probes are differentially expressed in second group
sd <- 0.3*sqrt(4/rchisq(1000,df=4))
x <- matrix(rnorm(1000*6,sd=sd),1000,6)
rownames(x) <- paste("Gene",1:1000)
x[1:50,4:6] <- x[1:50,4:6] + 2
# without labels, indexes of samples are plotted.
mds <- plotMDS(x, col=c(rep("black",3), rep("red",3)) )
# or labels can be provided, here group indicators:
plotMDS(mds, col=c(rep("black",3), rep("red",3)), labels= c(rep("Grp1",3), rep("Grp2",3)))Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.