Order heatmap rows in ggplot2 facet plot - r

Question

I'm having a problem with faceted heatmap rendering in ggplot2. The idea is that I have several elements (these are genes in the real life) and several experiments (F1 and F2 in the example below). Using the F1 experiment, I'm able to create class of elements/genes based on their mean expression (high, ..., moderate, ..., low). In the heatmap produced through the example below, I would like to order each elements in each class (01, 02, 03, 04) based on its mean expression value in F1. Unfortunately, the elements appear in alphabetic order. I would be very happy to get some hints...
Best
library(ggplot2)
library(reshape2)
set.seed(123)
# let's create a fake dataset
nb.experiment <- 4
n.row <- 200
n.col <- 5
d <- matrix(round(runif(n.row * n.col),2), nc=n.col)
colnames(d) <- sprintf("%02d", 1:5)
# These strings will be the row names of each heatmap
# in the subsequent facet plot
elements <- sample(replicate(n.row/2, rawToChar(as.raw(sample(65:90, 6, replace=T)))))
# let's create a data.frame d
d <- data.frame(d,
experiment = sort(rep(c("F1","F2"), n.row/2)),
elements= elements)
# For elements related to experiment F1
# we artificially produce a gradient of values that will
# create elements with increasing row means
d[d$experiment =="F1",1:5] <- round(sweep(d[d$experiment =="F1",1:5],
1,
seq(from=1, 10, length.out = 100),
"+"), 2)
# For elements related to experiment F2
# we artificially produce a gradient of values that will
# create elements with decreasing row means
d[d$experiment =="F2",1:5] <- round(sweep(d[d$experiment =="F2",1:5],
1,
seq(from=10, 1, length.out = 100),
"+"), 2)
#print(d[d$experiment =="F1",1:5])
# Now we split the dataset by experiments
d.split <- split(d, d$experiment)
# For all experiments, we order elements based on the mean expression signal in
# F1.
row.means.F1 <- rowMeans(d.split$F1[,1:5])
pos <- order(row.means.F1)
for(s in names(d.split)){
d.split[[s]] <- d.split[[s]][pos,]
}
# We create several classes of elements based on their
# mean expression signal in F1.
cuts <- cut(1:nrow(d.split$F1), nb.experiment)
levels(cuts) <- sprintf("%02d", 1:nb.experiment)
for(s in names(d.split)){
d.split[[s]] <- split(d.split[[s]], cuts)
}
# Data are melt (their is perhaps a better solution...)
# in order to use the ggplot function
dm <- melt(do.call('rbind',lapply(d.split, melt)), id.var=c( "experiment", "elements", "variable", "L1"))
dm <- dm[, -5]
colnames(dm) <- c("experiment","elements", "pos", "rowMeanClass", "exprs")
# Now we plot the data
p <- ggplot(dm, aes(x = pos, y = elements, fill = exprs))
p <- p + geom_raster()
p <- p + facet_wrap(~rowMeanClass +experiment , scales = "free", ncol = 2)
p <- p + theme_bw()
p <- p + theme(text = element_text(size=4))
p <- p + theme(text = element_text(family = "mono", face = "bold"))
ggsave("RPlot_test.jpeg", p)

Answer 1

Using your advises I was able to find a solution (which implies to clearly specify the order of levels for the 'elements' factor). Thank you #hrbrmstr (and all others).
NB: I only added few lines compare to the original code that are denoted below with 'Added: begin' and 'Added: end' flags.
library(ggplot2)
library(reshape2)
set.seed(123)
# let's create a fake dataset
nb.experiment <- 4
n.row <- 200
n.col <- 5
d <- matrix(round(runif(n.row * n.col),2), nc=n.col)
colnames(d) <- sprintf("%02d", 1:5)
# These strings will be the row names of each heatmap
# in the subsequent facet plot
elements <- sample(replicate(n.row/2, rawToChar(as.raw(sample(65:90, 6, replace=T)))))
# let's create a data.frame d
d <- data.frame(d,
experiment = sort(rep(c("F1","F2"), n.row/2)),
elements= elements)
# For elements related to experiment F1
# we artificially produce a gradient of values that will
# create elements with increasing row means
d[d$experiment =="F1",1:5] <- round(sweep(d[d$experiment =="F1",1:5],
1,
seq(from=1, 10, length.out = 100),
"+"), 2)
# For elements related to experiment F2
# we artificially produce a gradient of values that will
# create elements with decreasing row means
d[d$experiment =="F2",1:5] <- round(sweep(d[d$experiment =="F2",1:5],
1,
seq(from=10, 1, length.out = 100),
"+"), 2)
#print(d[d$experiment =="F1",1:5])
# Now we split the dataset by experiments
d.split <- split(d, d$experiment)
# For all experiments, we order elements based on the mean expression signal in
# F1.
row.means.F1 <- rowMeans(d.split$F1[,1:5])
pos <- order(row.means.F1)
for(s in names(d.split)){
d.split[[s]] <- d.split[[s]][pos,]
}
## Added: begin ###
#Get the list of elements in proper order (based on row mean)
mean.order <- as.character(d.split$F1$elements)
## Added: end###
# We create several classes of elements based on their
# mean expression signal in F1.
cuts <- cut(1:nrow(d.split$F1), nb.experiment)
levels(cuts) <- sprintf("%02d", 1:nb.experiment)
for(s in names(d.split)){
d.split[[s]] <- split(d.split[[s]], cuts)
}
# Data are melt (their is perhaps a better solution...)
# in order to use the ggplot function
dm <- melt(do.call('rbind',lapply(d.split, melt)), id.var=c( "experiment", "elements", "variable", "L1"))
dm <- dm[, -5]
colnames(dm) <- c("experiment","elements", "pos", "rowMeanClass", "exprs")
## Added: begin###
#Ensure that dm$elements is an ordered factor with levels
# ordered as expected
dm$elements <- factor(dm$elements, levels = mean.order, ordered = TRUE)
## Added: end###
# Now we plot the data
p <- ggplot(dm, aes(x = pos, y = elements, fill = exprs))
p <- p + geom_raster()
p <- p + facet_wrap(~rowMeanClass +experiment , scales = "free", ncol = 2)
p <- p + theme_bw()
p <- p + theme(text = element_text(size=4))
p <- p + theme(text = element_text(family = "mono", face = "bold"))
ggsave("RPlot_test.jpeg", p)