Add prune_cutree_to_dendlist?

[talgalili]

Answers:
https://stackoverflow.com/questions/48167369/r-getting-subtrees-from-dendrogram-based-on-cutree-labels/48180908#48180908

# install.packages("dendextend")

library(dendextend)
dend <- iris[,-5] %>% dist %>% hclust %>% as.dendrogram %>% 
  set("labels_to_character")
dend <- dend %>% color_branches(k=5)

# plot(dend)

prune_cutree_to_dendlist <- function(dend, k) {
  clusters <- cutree(dend,k, order_clusters_as_data = FALSE)
  # unique_clusters <- unique(clusters) # could also be 1:k but it would be less robust
  # k <- length(unique_clusters)
  # for(i in unique_clusters) { 
  dends <- vector("list", k)
  for(i in 1:k) { 
    leves_to_prune <- labels(dend)[clusters != i]
    dends[[i]] <- prune(dend, leves_to_prune)
    
  }
  
  class(dends) <- "dendlist"
  
  dends
}

prunned_dends <- prune_cutree_to_dendlist(dend, 5)
sapply(prunned_dends, nleaves)

par(mfrow = c(2,3))
plot(dend, main = "original dend")
sapply(prunned_dends, plot)

[lucacerone]

Hi Tal, thanks again for this function! Just one more question.

Say I want to make an heatmap of cluster 1 using heatmap.2,
I get the subset with

sub_data = data[clusters == 1, ]
# not I get the relevant dendrogram as output by your function
sub_dent = prunned_dends[[1]]

What about the ordering? In your function you use order_clusters_as_data = FALSE, how can I re-arrange the dendrogram so that when I add it to the rows in heatmap.2 the dendrogram actually corresponds to the data (apology for the silly question, I am very new to dendextend).

[talgalili]

Hi @lucacerone
It is better to sample the data and re-run the hclust on it (or just let heatmap.2 do the trick). Prunned trees have values in their leaves that may lead to odd behaviors, so it is not advised. Also, have a look at the heatmaply R package, for an interactive version of heatmap.2. Cheers.

[lucacerone]

Hi @talgalili, actually what I wanted to do (which also originated my original question in stackoverflow) is to zoom "as is" on a heatmap. The fact is that if I re-run hclust some sub-pattern that appear in the heatmap with the overall data, can change position and it is harder in a presentation to explain that what they are looking for is exactly the same as before, just with a different re-arrangement.

I'll surely have a look at heatmaply soon :)

[talgalili]

Hi @lucacerone the best way to zoom in into the heatmap (unless using heatmaply, which allows for interactive zooming) is to pick the subset of items in the cluster and run the heatmap with that sub dendrogram and subset of the data. Here is an example code for how to do it using the new get_dendrograms function:

# needed packages:
# install.packages(gplots)
# install.packages(viridis)
# install.packages(devtools)
# devtools::install_github('talgalili/dendextend') # dendextend from github

# define dendrogram object to play with:
dend <- iris[,-5] %>% dist %>% hclust %>% as.dendrogram %>%  set("labels_to_character") %>% color_branches(k=5)
dend_list <- get_subdendrograms(dend, 5)

# Plotting the result
par(mfrow = c(2,3))
plot(dend, main = "Original dendrogram")
sapply(dend_list, plot)

# plot a heatmap of only one of the sub dendrograms
par(mfrow = c(1,1))
library(gplots)
sub_dend <- dend_list[[1]] # get the sub dendrogram
# make sure of the size of the dend
nleaves(sub_dend)
length(order.dendrogram(sub_dend))
# get the subset of the data
subset_iris <- as.matrix(iris[order.dendrogram(sub_dend),-5])
# update the dendrogram's internal order so to not cause an error in heatmap.2
order.dendrogram(sub_dend) <- rank(order.dendrogram(sub_dend))
heatmap.2(subset_iris, Rowv = sub_dend, trace = "none", col = viridis::viridis(100))

[lucacerone]

Thank you so much Tal! This is really helpful!
Cheers!

[talgalili]

I'm glad that you find it helpful :)

…

On Jan 22, 2018 11:49, "Luca Cerone" ***@***.***> wrote: Thank you so much Tal! This is really helpful! Cheers! — You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub <#61 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AA7khhIieEu9b656sfm7Zk92q6XG_LnFks5tNFmtgaJpZM4RY1LV> .