supraHex 1.13.3

How to add a legend key to visDmatCluster?

Notes:
  • All results are based on supraHex (version 1.13.3).
  • R scripts (i.e. R expressions) plus necessary comments are highlighted in light-cyan background, and the rest are outputs in the screen.
  • Images displayed below may be distorted, but should be normal in your screen.
  • Functions contained in supraHex 1.13.3 are hyperlinked in-place and also listed on the right side.
  • Key texts are underlined, in bold and in pumpkin-orange color. 
    •       
    # We do not offer this functionality partly because the meta-cluster id has been displayed within the map (at seeds). 

# Another key reason is based on the fact that: the users are always willing to check gene expression pattern within each meta-cluster. Because of this, we have provided the function visDmatHeatmap, from which the legend key is shown.

data <- matrix( rnorm(100*10,mean=0,sd=1), nrow=100, ncol=10)
colnames(data) <- paste('S', seq(1:10), sep="")
sMap <- sPipeline(data=data)

    
Start at 2017-03-27 18:59:42

First, define topology of a map grid (2017-03-27 18:59:42)...
Second, initialise the codebook matrix (61 X 10) using 'linear' initialisation, given a topology and input data (2017-03-27 18:59:42)...
Third, get training at the rough stage (2017-03-27 18:59:42)...
	1 out of 7 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	2 out of 7 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	3 out of 7 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	4 out of 7 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	5 out of 7 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	6 out of 7 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	7 out of 7 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
Fourth, get training at the finetune stage (2017-03-27 18:59:42)...
	1 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	2 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	3 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	4 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	5 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	6 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	7 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	8 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	9 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	10 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	11 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	12 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	13 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	14 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	15 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	16 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	17 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	18 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	19 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	20 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	21 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	22 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	23 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	24 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
	25 out of 25 (2017-03-27 18:59:42)
	updated (2017-03-27 18:59:42)
Next, identify the best-matching hexagon/rectangle for the input data (2017-03-27 18:59:42)...
Finally, append the response data (hits and mqe) into the sMap object (2017-03-27 18:59:42)...

Below are the summaries of the training results:
   dimension of input data: 100x10
   xy-dimension of map grid: xdim=9, ydim=9, r=5
   grid lattice: hexa
   grid shape: suprahex
   dimension of grid coord: 61x2
   initialisation method: linear
   dimension of codebook matrix: 61x10
   mean quantization error: 4.61431442408722

Below are the details of trainology:
   training algorithm: batch
   alpha type: invert
   training neighborhood kernel: gaussian
   trainlength (x input data length): 7 at rough stage; 25 at finetune stage
   radius (at rough stage): from 3 to 1
   radius (at finetune stage): from 1 to 1

End at 2017-03-27 18:59:42
Runtime in total is: 0 secs


    sBase <- sDmatCluster(sMap=sMap)
visDmatCluster(sMap,sBase)
output <- visDmatHeatmap(sMap, data, sBase, base.legend.location="bottomleft", labRow=NA)

    



    
## As you have seen, heatmap is used to visualise patterns seen in genes within each meta-cluster/base. Row side bar indicates the meta-clusters/bases. 

## The returned variable "output" (NOT a text file) has 1st column for your input data ID (an integer; otherwise the row names of input data matrix), and 2nd column for the corresponding index of best-matching hexagons (i.e. gene clusters), and 3rd column for the cluster bases (i.e. gene meta-clusters). Note: it has rows in the same order as visualised in the heatmap. You can save this output into the file 'output.txt':
write.table(output, file="output.txt", quote=F, row.names=F, sep="\t")

    Source faq

    FAQ5.r

    Functions used in this FAQ