R draw kmeans clustering with heatmap

cluster-analysisheatmapk-meansrvisualization

I would like to cluster a matrix with kmeans, and be able to plot it as heatmap. It sounds quite trivial, and I have seen many plots like this. I have tried to google atround, but can't find a way round it.

I'd like to be able to plot something like panel A or B on this figure.
Let say I have a matrix with 250 rows and 5 columns. I don't want to cluster the columns, just the rows.

m = matrix(rnorm(25), 250, 5)

km = kmeans(m, 10)

Then how do I plot those 10 clusters as a heatmap ? You comments and helps is more than welcome.

Thanks.

enter image description here

Best Answer

Something like the following should work:

set.seed(100)
m = matrix(rnorm(10), 100, 5)
km = kmeans(m, 10)
m2 <- cbind(m,km$cluster)
o <- order(m2[, 6])
m2 <- m2[o, ]
library(pheatmap) # I like esoteric packages!
library(RColorBrewer)
pheatmap(m2[,1:5], cluster_rows=F,cluster_cols=F, col=brewer.pal(10,"Set3"),border_color=NA)

heatmap created using the pheatmap pacakge

Related Solutions

Python – How to change the size of figures drawn with Matplotlib

figure tells you the call signature:

from matplotlib.pyplot import figure

figure(figsize=(8, 6), dpi=80)

figure(figsize=(1,1)) would create an inch-by-inch image, which would be 80-by-80 pixels unless you also give a different dpi argument.

R – Clustering and heatmap in R

If you are okay with using heatmap.2 from the gplots package that will allow you to add breaks to assign colors to ranges represented in your heatmap.
For example if you had 3 colors blue, white, and red with the values going from low to high you could do something like this:

my.breaks <- c(seq(-5, -.6, length.out=6),seq(-.5999999, .1, length.out=4),seq(.100009,5, length.out=7))
result <- heatmap.2(mtscaled, Rowv=T, scale='none', dendrogram="row", symm = T, col=bluered(16), breaks=my.breaks)

In this case you have 3 sets of values that correspond to the 3 colors, the values will differ of course depending on what values you have with your data.

One thing you are doing in your program is to call hclust on your data then to call heatmap on it, however if you look in the heatmap manual page it states: Defaults to hclust. So I don't think you need to do that. You might want to take a look at some similar questions that I had asked that might help to point you in the right direction:

Heatmap Question 1

Heatmap Question 2

If you post an image of the heatmap you get and an image of the heatmap that the other program is making it will be easier for us to help you out more.

Best Answer

Related Solutions

Python – How to change the size of figures drawn with Matplotlib

R – Clustering and heatmap in R

Related Topic