Plotting two datasets across same x-axis in R using ggplot2 (or equivalent)

Question

EDIT: This has been solved and I have posted my learning and the code used at the bottom of the question

I would like to plot to datasets across the same x-axis with the second dataset being mirrored below the x-axis. I have attached the data set below.

So far I have tried:

#first two give me simple enough graphs
ggplot(data = plot_case) + geom_bar(mapping = aes(x= Exon, fill = Variant_Classification))
ggplot(data = plot_control) + geom_bar(mapping = aes(x= Exon, fill = Variant_Classification))

I tried to then create a negative set in the control group
plot_control$Exon <- as.numeric(plot_control$Exon) * -1
plot_all <- rbind(plot_case, plot_control)
#plotting it gives me this
ggplot(data = plot_all) + geom_col(mapping = aes(x= Exon, y=stat_count(Exon), fill = Variant_Classification))

When I actually want the second dataset below the first one like this picture:

Your help would be much appreciated, full data set below

head(plot_case)

   Variant_Classification Exon
1:      Nonsense_Mutation   22
2:        Frame_Shift_Del   28
3:      Nonsense_Mutation    7
4:      Missense_Mutation   27
5:      Missense_Mutation   28
6:      Missense_Mutation   18

full: 
dput(plot_case)
    structure(list(Variant_Classification = structure(c(5L, 1L, 5L, 
    4L, 4L, 4L, 5L, 2L, 5L, 2L, 5L, 4L, 1L, 2L, 1L, 4L, 5L, 5L, 5L, 
    5L, 6L, 5L, 3L, 2L, 3L, 4L, 4L), .Label = c("Frame_Shift_Del", 
    "Frame_Shift_Ins", "In_Frame_Del", "Missense_Mutation", "Nonsense_Mutation", 
    "Splice_Site"), class = "factor"), Exon = structure(c(22L, 28L, 
    7L, 27L, 28L, 18L, 12L, 18L, 20L, 26L, 21L, 11L, 12L, 7L, 14L, 
    13L, 22L, 20L, 15L, 20L, 20L, 21L, 19L, 7L, 3L, 11L, 4L), .Label = c("1", 
    "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", 
    "14", "15", "16", "17", "18", "19", "20", "21", "22", "23", "24", 
    "25", "26", "27", "28", "29", "30"), class = "factor")), row.names = c(NA, 
    -27L), class = c("data.table", "data.frame"), .internal.selfref = )


   head(plot_control)
   Variant_Classification Exon
1:      Missense_Mutation   1
2:      Missense_Mutation   1
3:      Missense_Mutation   1
4:      Missense_Mutation   1
5:      Missense_Mutation   1
6:      Missense_Mutation   1

dput(plot_control)
structure(list(Variant_Classification = structure(c(4L, 4L, 4L, 
4L, 4L, 4L, 4L, 2L, 2L, 2L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 2L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 7L, 4L, 4L, 1L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
2L, 2L, 4L, 5L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 7L, 7L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
5L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 2L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 6L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 1L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 4L, 4L, 7L, 7L, 
5L, 4L, 4L, 4L, 4L, 4L, 5L, 4L, 1L, 4L, 4L, 4L, 4L, 4L, 1L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 7L, 7L, 4L, 4L, 4L, 4L, 5L, 4L, 4L, 4L, 
4L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 5L), .Label = c("Frame_Shift_Del", "Frame_Shift_Ins", 
"In_Frame_Del", "Missense_Mutation", "Nonsense_Mutation", "Nonstop_Mutation", 
"Splice_Site"), class = "factor"), Exon = c(1, 1, 1, 1, 1, 1, 
1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 
4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 
5, 5, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 
7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 8, 8, 8, 8, 8, 
8, 8, 8, 8, 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 
9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 11, 11, 11, 
11, 11, 11, 11, 11, 11, 11, 11, 11, 12, 12, 12, 12, 12, 12, 12, 
12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 
12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 
12, 12, 12, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 14, 14, 14, 
14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 
15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 17, 17, 17, 17, 17, 17, 
17, 18, 18, 18, 18, 18, 18, 18, 18, 19, 19, 19, 19, 19, 19, 19, 
20, 20, 20, 20, 20, 20, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 
21, 21, 21, 21, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 23, 23, 
23, 23, 23, 23, 23, 24, 24, 25, 25, 25, 25, 25, 25, 25, 25, 25, 
25, 25, 25, 25, 26, 26, 26, 26, 26, 26, 26, 26, 27, 27, 27, 27, 
28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 29, 29, 29, 29, 29, 
29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29)), row.names = c(NA, 
-456L), class = c("data.table", "data.frame"), .internal.selfref = )

Thanks to further help I ran the code suggested below and got the following image:

I now need to get the axis to be more informative so as not to lose all the data

With further help from @__S I used:

plot_control %>%
  mutate(type = 'control') %>%
  bind_rows(plot_case %>% mutate(type ='case')) %>%
  group_by(Variant_Classification, Exon, type) %>%
  summarise(freq = n()) %>%
  mutate(freq = ifelse(type == 'control', -log(freq), freq)) %>%
  ggplot(aes(x= Exon, y = freq, fill = Variant_Classification)) + 
  geom_col() +
  geom_hline(yintercept = 0)

Which looks awesome! Looking at the accepted answerthe problem was my dataset needed tidying up before putting it through ggplot. I needed to turn it into a frequency based table which is what the group_by and summarise dplyr functions helped to do.

s__ · Accepted Answer

What about something like this:

library(dplyr)

   plot_control %>%
  mutate(type = 'control') %>%
  bind_rows(plot_case %>% mutate(type ='case')) %>%
  group_by(Variant_Classification, Exon, type) %>%
  summarise(freq = n()) %>%
  #Edit2: here you join with a data.frame with all the Exon
  right_join(data.frame(Exon = c(min(.$Exon):max(.$Exon)))) %>%
  # Edit1: here you can add the log()
  mutate(freq = ifelse(type == 'control', -log(freq), freq)) %>%
  ggplot(aes(x= as.factor(Exon), y = freq, fill = Variant_Classification)) + 
  geom_col() +
  geom_hline(yintercept = 0) +
  xlab("Exon")

With data:

plot_case <- read.table(text = '   Variant_Classification Exon
1:      Nonsense_Mutation   22
2:        Frame_Shift_Del   28
3:      Nonsense_Mutation    7
4:      Missense_Mutation   27
5:      Missense_Mutation   28
6:      Missense_Mutation   18
7:      Missense_Mutation   1', header = T)


plot_control <- read.table(text = '     Variant_Classification Exon
1:      Missense_Mutation   1
2:      Missense_Mutation   1
3:      Missense_Mutation   1
', header = T)

Plotting two datasets across same x-axis in R using ggplot2 (or equivalent)

Answers (1)

Related Questions