creating a heatmap where the data has NaN values in it

Question

I am trying to create a heatmap using the heatmap.2 package. My data has lot's of NaN values in it, and what I would like to do is the following. Every time there is a NaN value, simply have the cell be colored as light grey (or some other neutral color, maybe white), and all of the other values (which are log2 expression) to have a standard green/yellow/red coloring scheme. Here is my code that I have ben using:

heatmap.2(as.matrix(foo2[rowSums (abs(foo2)) != 0,]),
          col = redgreen,
          margins = c(12, 22),
          trace = "none", 
          xlab = "Comparison",
          lhei = c(2, 8),
          scale = c("none"),
          symbreaks = min(foo2 = 0, na.rm = TRUE),
          na.color = "blue",
          cexRow = 0.5,
          cexCol = .7,
          main = "DE geness",
          Colv = F)

This works well when there is no NaN values, but when the data has NaN, I am getting an error which says:

Error in hclustfun(distfun(x)) : 
  NA/NaN/Inf in foreign function call (arg 11)

Essentially, I would like to have it ignore the NaN's in the data. I am not sure how to handle this. any help would be greatly appreciated.

Answer 1

TL;DR: The issue is likely due to delegated distfun and not the heatmap2 function itself. The default dist function tries to calculate the distance between your data points, and if the distance calculation returns an NA, the clustering function cannot handle that.

---

The longer version:

I have recently experienced the same issue as the OP, and had to dig in quite a bit to understand why the problem wasn't reproducible for others.

The essential issue is as follows: heatmap2 by default passes hclust and hclustfun and dist as distfun parameters. The error message clearly states that it's hclustfun (which in this case defaults to hclust) that does not like the NAs.

The next bit of information is this: even though the data matrix includes NAs the results of dist (which are passed in to hclust) might be free from NAs, which is the case for @kdauria's answer. See below:

> library(gplots)
> mat = matrix( rnorm(25), 5, 5)
> mat[c(1,6,8,11,15,20,22,24)] = NaN
> 
> heatmap.2( mat,
+            col = colorpanel(100,"red","yellow","green"),
+            margins = c(12, 22),
+            trace = "none", 
+            xlab = "Comparison",
+            lhei = c(2, 8),
+            scale = c("none"),
+            symbreaks = min(mat, na.rm=TRUE),
+            na.color="blue",
+            cexRow = 0.5, cexCol = 0.7,
+            main = "DE genes", 
+            dendrogram = "row", 
+            Colv = FALSE )
> ?dist
> mat
           [,1]       [,2]        [,3]        [,4]       [,5]
[1,]        NaN        NaN         NaN -1.10103187 -1.4396185
[2,] -0.8821449  1.4891180  0.41956063 -0.06442867        NaN
[3,] -2.5912928        NaN -0.56603029 -0.55177559 -2.0313602
[4,]  0.8348197  0.2199583  0.06318663  1.59697764        NaN
[5,] -0.2632078 -1.2193110         NaN         NaN  0.8618543
> dist(mat)
         1        2        3        4
2 2.317915                           
3 1.276559 2.623637                  
4 6.032933 3.050821 5.283828         
5 5.146250 4.392798 5.871684 2.862324

The random valued matrix does not reproduce the problem because it avoids the issue at hand. Which brings me to the question: what does it take to get NAs from dist?

---

My data had some outlying large values which I thought to be the reason, however I only managed to reproduce the problem by adding a row of NAs:

> mat = matrix(rnorm(49), 7, 7)
> mat[c(3,17,28, 41)] = mat[c(3,17,28, 41)] * 100000
> mat
              [,1]        [,2]          [,3]          [,4]        [,5]          [,6]       [,7]
[1,] -6.175928e-01  1.68691561 -1.233250e+00 -7.355322e-01 -0.37392178  3.559804e-01  1.7536137
[2,]  6.680429e-01  0.90590237 -1.375424e+00  5.842512e-01 -0.09376548 -3.556098e-01 -1.2926535
[3,] -3.739372e+04 -1.74534887 -2.241643e+05 -2.209226e-01 -0.86769435 -4.590908e-01  1.6306854
[4,] -1.283405e+00  0.20698245  3.635557e-01  3.673208e-01 -0.12339047  1.119922e+00  0.4301094
[5,] -5.430687e-02 -0.75219479  2.609126e+00 -1.340564e-01  0.54016622  2.885021e-01  0.9237946
[6,] -8.395116e-01  0.03675002  2.455545e+00  4.432025e-02 -0.86194910  1.302758e+05  0.6062505
[7,]  1.817036e-01 -1.46137388 -1.853179e+00 -2.177306e+03  2.36763806 -2.273134e+00  1.2440088
> dist(mat)
             1            2            3            4            5            6
2 3.726858e+00                                                                 
3 2.272605e+05 2.272606e+05                                                    
4 2.966078e+00 3.537475e+00 2.272620e+05                                       
5 4.787577e+00 5.039154e+00 2.272644e+05 3.016614e+00                          
6 1.302754e+05 1.302762e+05 2.619559e+05 1.302747e+05 1.302755e+05             
7 2.176576e+03 2.177895e+03 2.272705e+05 2.177679e+03 2.177179e+03 1.302963e+05
> mat = rbind(mat[1:4, ], rep(NA,7), mat[5:6, ])
> mat
              [,1]        [,2]          [,3]        [,4]        [,5]          [,6]       [,7]
[1,] -6.175928e-01  1.68691561 -1.233250e+00 -0.73553223 -0.37392178  3.559804e-01  1.7536137
[2,]  6.680429e-01  0.90590237 -1.375424e+00  0.58425125 -0.09376548 -3.556098e-01 -1.2926535
[3,] -3.739372e+04 -1.74534887 -2.241643e+05 -0.22092261 -0.86769435 -4.590908e-01  1.6306854
[4,] -1.283405e+00  0.20698245  3.635557e-01  0.36732078 -0.12339047  1.119922e+00  0.4301094
[5,]            NA          NA            NA          NA          NA            NA         NA
[6,] -5.430687e-02 -0.75219479  2.609126e+00 -0.13405635  0.54016622  2.885021e-01  0.9237946
[7,] -8.395116e-01  0.03675002  2.455545e+00  0.04432025 -0.86194910  1.302758e+05  0.6062505
> dist(mat)
             1            2            3            4            5            6
2 3.726858e+00                                                                 
3 2.272605e+05 2.272606e+05                                                    
4 2.966078e+00 3.537475e+00 2.272620e+05                                       
5           NA           NA           NA           NA                          
6 4.787577e+00 5.039154e+00 2.272644e+05 3.016614e+00           NA             
7 1.302754e+05 1.302762e+05 2.619559e+05 1.302747e+05           NA 1.302755e+05
> heatmap.2( mat,
+            col = colorpanel(100,"red","yellow","green"),
+            margins = c(12, 22),
+            trace = "none", 
+            xlab = "Comparison",
+            lhei = c(2, 8),
+            scale = c("none"),
+            symbreaks = min(mat, na.rm=TRUE),
+            na.color="blue",
+            cexRow = 0.5, cexCol = 0.7,
+            main = "DE genes", 
+            dendrogram = "row", 
+            Colv = FALSE )
Error in hclustfun(distfun(x)) : 
  NA/NaN/Inf in foreign function call (arg 11)

However the situation does not appear to be specific to the case where there is a row entirely composed of NAs. For example:

> mat
              [,1]        [,2]          [,3]       [,4]       [,5]          [,6]       [,7]
[1,]           NaN         NaN           NaN        NaN         NA -7.531027e-01  0.2238252
[2,]  3.210084e-01 -1.55702840  2.777516e-01  0.2176875  1.3310334 -9.621561e-01        NaN
[3,]  1.159837e+05  0.04480172 -1.649482e+04        NaN  2.4748122  8.446133e-01 -0.4240776
[4,] -8.584051e-01         NaN           NaN  1.0557713 -1.0855826 -5.638023e-02 -0.3789979
[5,]            NA          NA -2.539003e-01 -0.4552776  0.3856384            NA         NA
[6,]           NaN  1.31986556           NaN -1.0393147 -1.9197183 -1.434064e+00  0.6334569
[7,]           NaN -0.42180912           NaN -0.8023476 -0.8264077  4.471358e+04  0.5046408
> dist(mat)
             1            2            3            4            5            6
2 5.531033e-01                                                                 
3 3.225471e+00 1.386143e+05                                                    
4 1.723619e+00 3.913983e+00 1.534332e+05                                       
5           NA 1.949799e+00 3.085851e+04 3.945524e+00                          
6 1.486699e+00 6.010961e+00 6.905415e+00 3.743585e+00 4.449179e+00             
7 8.365286e+04 5.915178e+04 5.914939e+04 5.915058e+04 2.358664e+00 5.290752e+04