1

I am using this link to plot a nice dendrogram with colored labels as per the categories. The second answer is what I am looking at in this link (Tree cut and Rectangles around clusters for a horizontal dendrogram in R )which uses the code below:

d <- dist(t(mat[,3:ncol(mat)]), method = "euclidean")
H.fit <- hclust(d, method="ward")
groups <- cutree(H.fit, k=16) # cut tree into  clusters
 hcdata<- dendro_data(H.fit, type="rectangle")
  hcdata$labels <- merge(x = hcdata$labels, y = pm_gtex_comb,  by.x = "label", by.y = "sample",all=TRUE)
 ggplot() + 
 geom_segment(data=segment(hcdata), aes(x=x, y=y, xend=xend, yend=yend)) + 
 geom_text(data=label(hcdata), aes(x, y, label=label, hjust=0, color=cluster), 
        size=3) +
 geom_rect(data=rect, aes(xmin=X1-.3, xmax=X2+.3, ymin=0, ymax=ymax), 
        color="red", fill=NA)+
 geom_hline(yintercept=0.33, color="blue")+
 coord_flip() + scale_y_reverse(expand=c(0.2, 0)) + 
 theme_dendro()

I want to cut out some of the clusters as I have 16 clusters,with 145 labels so that I can view only few clusters as I want to focus/cut-out/zoom in only on couple of them.Is there any way to do this on hclust object .This is only for having a nice visualization as the figure gets messy with 145 labels.Since I want to color as per the labels,I think ggdendro suits pretty well.

For example in this link ,if you look at 3)Zooming-in on dendrograms http://gastonsanchez.com/blog/how-to/2012/10/03/Dendrograms.html

Community
  • 1
  • 1
user45292
  • 45
  • 1
  • 9

1 Answers1

2

You could try prune from the package dendextend (which can do lots of other nifty things): 

library(dendextend)
hc <- hclust(dist(USArrests), "ave")
clusters <- cutree(hc, k=3)
par(mfrow=c(1,2), mar=c(6, 4, 2, 3))
plot(as.dendrogram(hc), main="regular")
plot(dend <- prune(as.dendrogram(hc), names(clusters[clusters==1])), 
     ylim=range(hc$height), main="without cluster #1")

or if you insist on ggdendro:

ggdendro::ggdendrogram(dend)

A ggplot2 plot can be created also by using dendextend:

library(dendextend)
ggd1 <- as.ggdend(dend)
library(ggplot2)
ggplot(ggd1)
Tal Galili
  • 24,605
  • 44
  • 129
  • 187
lukeA
  • 53,097
  • 5
  • 97
  • 100
  • Thanks @lukeA, I would like to add that dendextend comes with an integration to ggplot2 (based actually on ggdendro, but which allows for the dendrogram plots to include graphical parameters such as colors and line width and type), You can see examples of this here: https://cran.r-project.org/web/packages/dendextend/vignettes/introduction.html#ggplot2-integration – Tal Galili Oct 30 '15 at 16:40
  • 1
    Thanks @TalGalili - in fact I tried that exact thing, but `as.ggdend` threw an error ("Error in FUN(X[[i]], ...) : subscript out of bounds"), so I got back to ggdendrogram. :) I have not the latest version though... – lukeA Oct 30 '15 at 16:48
  • the pruning somehow does not work for me.the result remains same as the regular plot. – user45292 Oct 30 '15 at 19:39
  • 1
    Dear @LukeA - this is a known problem that was fixed in the dendextend version on github available using: devtools::install_github('talgalili/dendextend') (I wanted to wait with updating it to CRAN until my paper gets a final published version - but you know encouraged me to update it today.) Cheers, Tal – Tal Galili Oct 30 '15 at 21:00
  • 1
    @user45292 Please edit your question and make it a [reproducible example](http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example), including the non-working `prune`. – lukeA Oct 31 '15 at 09:52
  • Update: dendextend version 1.1.2 is now on CRAN (the windows binary would probably take another day to compile there). This should fix the ggdend error you mentioned. With regards, Tal ( @lukeA ) – Tal Galili Oct 31 '15 at 15:27