Skip to main content
Cross Validated

Return to Question

removed tag; cleaned code for improved readability; light editing & formatting
Source Link
gung - Reinstate Monica
gung - Reinstate Monica
  • 147.5k
  • 89
  • 406
  • 717

I'm using heatmap.2heatmap.2 to cluster my data, using the centroid method for clustering and the maximum method for calculating the distance matrix:

library("gplots")
library("RColorBrewer")

test           <- matrix(c(0.96, 0.07, 0.97, 0.98, 
                           0.50, 0.28, 0.29, 0.77, 
                           0.08, 0.96, 0.51, 0.51, 
                           0.14,  0.19, 0.41, 0.51), ncol=4, byrow=TRUE)
colnames(test) <- c("Exp1","Exp2","Exp3","Exp4")
rownames(test) <- c("Gene1","Gene2","Gene3", "Gene4")
test           <- as.table(test)
mat =           <- data.matrix(test)

heatmap.2(mat, dendrogram="row", Rowv=TRUE,
  Colv=FALSE, distfun 
 = function        distfun=function(x) dist(x,method = 'maximum'method='maximum'),
hclustfun = function        hclustfun=function(x) hclust(x,method = 'centroid'method='centroid'),
xlab = NULL, ylab = NULL     xlab=NULL, ylab=NULL, key=TRUE,
  keysize=1, trace="none", 
          density.info=c("none"),
  margins=c(6, 12), col=bluered
 )

This gives a heatmap with inversions in the cluster tree, which is inherent to the centroid method. A solution to avoid inversions is to use the Euclidean or the city-block distance, and indeed if you change maximum to euclideanEuclidean in the above example the inversions are gone.  (for reference see chapter 4.1.1 in this link).

Now as for my problem, when I use my actual data instead of this example table the inversions are still there when I change to euclideanEuclidean. The R code is exactly the same as in this example, only the data is different. When I use cluster 3.0cluster 3.0 and java treeviewjava treeview with the euclideanEuclidean and centroid method there are no inversions in my data as expected. So why does R give inversions? The theory and other software says it shouldn't.

Update: This is an example were changing maximum to euclideanEuclidean does not fix inversions (as opposed to the above example were it did fix it)

library("gplots")
library("RColorBrewer")

test           <- matrix(c(0.96, 0.07, 0.97, 0.98, 0.99, 0.50, 
                           0.28, 0.29, 0.77, 0.78, 0.08, 0.96, 
                           0.51, 0.51, 0.55, 0.14, 0.19, 0.41, 
                           0.51, 0.40, 0.97, 0.98, 0.99, 0.50, 
                           0.28                               ), ncol=6, byrow=TRUE)
colnames(test) <- c("Exp1", "Exp2", "Exp3", "Exp4", "Exp5", "Exp6")
rownames(test) <- c("Gene1", "Gene2", "Gene3", "Gene4")
test           <- as.table(test)
mat=datamat            <- data.matrix(test)

heatmap.2(mat, dendrogram="row", Rowv=TRUE,
  Colv=FALSE, distfun 
 = function        distfun=function(x) dist(x,method = 'maximum'method='maximum'),
hclustfun = function        hclustfun=function(x) hclust(x,method = 'centroid'method='centroid'),
xlab = NULL, ylab = NULL     xlab=NULL, ylab=NULL, key=TRUE, 
 keysize=1, trace="none", 
          density.info=c("none"),
  margins=c(6, 12), col=bluered
 )

I'm using heatmap.2 to cluster my data, using the centroid method for clustering and the maximum method for calculating the distance matrix:

library("gplots")
library("RColorBrewer")

test <- matrix(c(0.96, 0.07, 0.97, 0.98, 0.50, 0.28, 0.29, 0.77, 0.08, 0.96, 0.51, 0.51, 0.14,  0.19, 0.41, 0.51), ncol=4, byrow=TRUE)
colnames(test) <- c("Exp1","Exp2","Exp3","Exp4")
rownames(test) <- c("Gene1","Gene2","Gene3", "Gene4")
test <- as.table(test)
mat = data.matrix(test)

heatmap.2(mat, dendrogram="row", Rowv=TRUE,
 Colv=FALSE, distfun = function(x) dist(x,method = 'maximum'),
hclustfun = function(x) hclust(x,method = 'centroid'),
xlab = NULL, ylab = NULL, key=TRUE,
 keysize=1, trace="none", density.info=c("none"),
 margins=c(6, 12), col=bluered
 )

This gives a heatmap with inversions in the cluster tree, which is inherent to the centroid method. A solution to avoid inversions is to use the Euclidean or the city-block distance, and indeed if you change maximum to euclidean in the above example the inversions are gone.(for reference see chapter 4.1.1 in this link)

Now as for my problem, when I use my actual data instead of this example table the inversions are still there when I change to euclidean. The R code is exactly the same as in this example, only the data is different. When I use cluster 3.0 and java treeview with the euclidean and centroid method there are no inversions in my data as expected. So why does R give inversions? The theory and other software says it shouldn't.

Update: example were changing maximum to euclidean does not fix inversions (as opposed to the above example were it did fix it)

library("gplots")
library("RColorBrewer")

test <- matrix(c(0.96, 0.07, 0.97, 0.98, 0.99, 0.50, 0.28, 0.29, 0.77, 0.78, 0.08, 0.96, 0.51, 0.51, 0.55, 0.14, 0.19, 0.41, 0.51, 0.40, 0.97, 0.98, 0.99, 0.50, 0.28),ncol=6,byrow=TRUE)
colnames(test) <- c("Exp1","Exp2","Exp3","Exp4","Exp5","Exp6")
rownames(test) <- c("Gene1","Gene2","Gene3", "Gene4")
test <- as.table(test)
mat=data.matrix(test)

heatmap.2(mat, dendrogram="row", Rowv=TRUE,
 Colv=FALSE, distfun = function(x) dist(x,method = 'maximum'),
hclustfun = function(x) hclust(x,method = 'centroid'),
xlab = NULL, ylab = NULL, key=TRUE, 
 keysize=1, trace="none", density.info=c("none"),
 margins=c(6, 12), col=bluered
 )

I'm using heatmap.2 to cluster my data, using the centroid method for clustering and the maximum method for calculating the distance matrix:

library("gplots")
library("RColorBrewer")

test           <- matrix(c(0.96, 0.07, 0.97, 0.98, 
                           0.50, 0.28, 0.29, 0.77, 
                           0.08, 0.96, 0.51, 0.51, 
                           0.14, 0.19, 0.41, 0.51), ncol=4, byrow=TRUE)
colnames(test) <- c("Exp1","Exp2","Exp3","Exp4")
rownames(test) <- c("Gene1","Gene2","Gene3", "Gene4")
test           <- as.table(test)
mat            <- data.matrix(test)

heatmap.2(mat, dendrogram="row", Rowv=TRUE, Colv=FALSE,  
          distfun=function(x) dist(x, method='maximum'),
          hclustfun=function(x) hclust(x, method='centroid'),
          xlab=NULL, ylab=NULL, key=TRUE, keysize=1, trace="none", 
          density.info=c("none"), margins=c(6, 12), col=bluered)

This gives a heatmap with inversions in the cluster tree, which is inherent to the centroid method. A solution to avoid inversions is to use the Euclidean or the city-block distance, and indeed if you change maximum to Euclidean in the above example the inversions are gone  (for reference see chapter 4.1.1 in this link).

Now as for my problem, when I use my actual data instead of this example table the inversions are still there when I change to Euclidean. The R code is exactly the same as in this example, only the data is different. When I use cluster 3.0 and java treeview with the Euclidean and centroid method there are no inversions in my data as expected. So why does R give inversions? The theory and other software says it shouldn't.

Update: This is an example were changing maximum to Euclidean does not fix inversions (as opposed to the above example were it did fix it)

library("gplots")
library("RColorBrewer")

test           <- matrix(c(0.96, 0.07, 0.97, 0.98, 0.99, 0.50, 
                           0.28, 0.29, 0.77, 0.78, 0.08, 0.96, 
                           0.51, 0.51, 0.55, 0.14, 0.19, 0.41, 
                           0.51, 0.40, 0.97, 0.98, 0.99, 0.50, 
                           0.28                               ), ncol=6, byrow=TRUE)
colnames(test) <- c("Exp1", "Exp2", "Exp3", "Exp4", "Exp5", "Exp6")
rownames(test) <- c("Gene1", "Gene2", "Gene3", "Gene4")
test           <- as.table(test)
mat            <- data.matrix(test)

heatmap.2(mat, dendrogram="row", Rowv=TRUE, Colv=FALSE,  
          distfun=function(x) dist(x, method='maximum'),
          hclustfun=function(x) hclust(x, method='centroid'),
          xlab=NULL, ylab=NULL, key=TRUE, keysize=1, trace="none", 
          density.info=c("none"), margins=c(6, 12), col=bluered)
deleted 35 characters in body
Source Link
jonas87
jonas87
  • 151
  • 5
library("gplots")
library("RColorBrewer")

test <- matrix(c(0.96, 0.07, 0.97, 0.98, 0.50, 0.28, 0.29, 0.77, 
             0.08, 0.96, 0.51, 0.51, 0.14,  0.19, 0.41, 0.51),
           ncol=4, byrow=TRUE)
colnames(test) <- c("Exp1","Exp2","Exp3","Exp4")
rownames(test) <- c("Gene1","Gene2","Gene3", "Gene4")
test <- as.table(test)
mat = data.matrix(test)

heatmap.2(mat, dendrogram="row", Rowv=TRUE,
Colv=FALSE, distfun = function(x) dist(x,method = 'maximum'),
hclustfun = function(x) hclust(x,method = 'centroid'),
xlab = NULL, ylab = NULL, key=TRUE,
keysize=1, trace="none", density.info=c("none"),
margins=c(6, 12), col=bluered
)

library("gplots")
library("RColorBrewer")

test <- matrix(c(0.96, 0.07, 0.97, 0.98, 0.50, 0.28, 0.29, 0.77, 
             0.08, 0.96, 0.51, 0.51, 0.14,  0.19, 0.41, 0.51),
           ncol=4, byrow=TRUE)
colnames(test) <- c("Exp1","Exp2","Exp3","Exp4")
rownames(test) <- c("Gene1","Gene2","Gene3", "Gene4")
test <- as.table(test)
mat = data.matrix(test)

heatmap.2(mat, dendrogram="row", Rowv=TRUE,
Colv=FALSE, distfun = function(x) dist(x,method = 'maximum'),
hclustfun = function(x) hclust(x,method = 'centroid'),
xlab = NULL, ylab = NULL, key=TRUE,
keysize=1, trace="none", density.info=c("none"),
margins=c(6, 12), col=bluered
)

library("gplots")
library("RColorBrewer")

test <- matrix(c(0.96, 0.07, 0.97, 0.98, 0.50, 0.28, 0.29, 0.77, 0.08, 0.96, 0.51, 0.51, 0.14,  0.19, 0.41, 0.51), ncol=4, byrow=TRUE)
colnames(test) <- c("Exp1","Exp2","Exp3","Exp4")
rownames(test) <- c("Gene1","Gene2","Gene3", "Gene4")
test <- as.table(test)
mat = data.matrix(test)

heatmap.2(mat, dendrogram="row", Rowv=TRUE,
Colv=FALSE, distfun = function(x) dist(x,method = 'maximum'),
hclustfun = function(x) hclust(x,method = 'centroid'),
xlab = NULL, ylab = NULL, key=TRUE,
keysize=1, trace="none", density.info=c("none"),
margins=c(6, 12), col=bluered
)
Tweeted twitter.com/#!/StackStats/status/96559076984623104
added 75 characters in body
Source Link
jonas87
jonas87
  • 151
  • 5

This gives a heatmap with inversions in the cluster tree, which is inherent to the centroid method. A solution to avoid inversions is to use the Euclidean or the city-block distance, and indeed if you change maximum to euclidean in the above example the inversions are gone.(for reference see chapter 4.1.1 in this linkthis link)

This gives a heatmap with inversions in the cluster tree, which is inherent to the centroid method. A solution to avoid inversions is to use the Euclidean or the city-block distance, and indeed if you change maximum to euclidean in the above example the inversions are gone.(for reference see chapter 4.1.1 in this link)

This gives a heatmap with inversions in the cluster tree, which is inherent to the centroid method. A solution to avoid inversions is to use the Euclidean or the city-block distance, and indeed if you change maximum to euclidean in the above example the inversions are gone.(for reference see chapter 4.1.1 in this link)

Source Link
jonas87
jonas87
  • 151
  • 5