How to arrange x-axis in the ggplot2 (Boxplot)

General
,
1

Hi,

I have a question to arrange the x-axis in the Boxplot through ggplot2 (geom_boxplot), but not successful. Actually trying to arrange as (Batch I, Batch II, ........Batch V). Please provide inputs how to fix this issue.

dput(Data_v1)
structure(list(ID = c("CH30_0h-1", "CH30_6h-8", "CH30_6h-16", 
                      "CN1_0h-1", "CN1_6h-8", "CN1_6h-16", "400B_0h-1", "400B_6h-8", 
                      "400B_6h-16", "1111A_0h-1", "1111A_6h-8", "1111A_6h-16", "1164A_0h-1", 
                      "1164A_6h-8", "1164A_6h-16"), Gene_1 = c(-7.06771, -8.73071, 
                                                               -6.73071, -4.73797, NA, NA, -6.89689, -9.11833, -7.24038, -9.91257, 
                                                               -7.31379, -6.17557, -7.58907, -7.43676, NA), Gene_2 = c(-5.91461, 
                                                                                                                       -6.36411, -5.02691, -9.64877, NA, -4.1052, -4.9579, -4.44811, 
                                                                                                                       -4.94366, -5.61523, -5.6951, -5.6236, -5.61506, -5.724, -6.38191
                                                               ), Gene_3 = c(-2.1792, -2.3658, -2.02961, -1.26177, -2.03669, 
                                                                             -2.4839, -2.24417, -1.76436, -1.29733, -2.30767, -2.57192, -1.87333, 
                                                                             -2.72559, -2.36064, -1.59041), Gene_4 = c(-4.24441, -3.40551, 
                                                                                                                       -1.96791, -4.46717, -2.54759, -0.8027, -4.17766, -3.21896, -2.26203, 
                                                                                                                       -4.00953, -3.06621, -2.15282, -4.45781, -3.77418, -4.48653), 
               Gene_5 = c(-5.38011, -5.66761, -3.26111, -5.70527, 4.26221, 
                          -5.1683, NA, NA, NA, -4.78791, -8.95204, -6.35331, -6.34912, 
                          -5.70766, -7.71973), Gene_6 = c(-2.36521, -2.59891, -2.15781, 
                                                          -0.75477, -2.03779, -1.196, -3.06798, -3.85273, -2.89402, 
                                                          -2.13551, -2.60488, -1.93915, -2.68515, -3.7548, -2.69344
                          ), Gene_7 = c(-2.05641, -3.8735, -2.91651, -2.66677, -3.40529, 
                                        -2.8928, -3.4558, -3.89929, -3.38236, -3.92386, -4.15504, 
                                        -3.77592, -3.96861, -2.36629, -3.30789), Gene_8 = c(-1.4283, 
                                                                                            -1.79241, -1.75011, -3.25977, -2.36509, -1.9922, -2.53121, 
                                                                                            -2.58246, -2.649, -2.36292, -2.0177, -1.99138, -1.74274, 
                                                                                            -3.02425, -2.16307), Gene_9 = c(-3.32931, -3.20471, -4.11671, 
                                                                                                                            -4.95547, -2.76539, -3.227, -3.90394, -4.20117, -4.92701, 
                                                                                                                            -4.67031, -5.08027, -5.37573, -3.43241, -2.51116, -3.55333
                                                                                            ), Gene_10 = c(-2.55501, -1.24421, -1.41321, -1.56437, -2.90679, 
                                                                                                           -3.2299, -3.31768, -3.16836, -4.02685, -4.35349, -2.77335, 
                                                                                                           -4.40128, -2.77479, -2.61881, -3.58733)), class = "data.frame", row.names = c("CH30_0h-1", 
                                                                                                                                                                                         "CH30_6h-8", "CH30_6h-16", "CN1_0h-1", "CN1_6h-8", "CN1_6h-16", 
                                                                                                                                                                                         "400B_0h-1", "400B_6h-8", "400B_6h-16", "1111A_0h-1", "1111A_6h-8", 
                                                                                                                                                                                         "1111A_6h-16", "1164A_0h-1", "1164A_6h-8", "1164A_6h-16"))
#>                      ID   Gene_1   Gene_2   Gene_3   Gene_4   Gene_5   Gene_6
#> CH30_0h-1     CH30_0h-1 -7.06771 -5.91461 -2.17920 -4.24441 -5.38011 -2.36521
#> CH30_6h-8     CH30_6h-8 -8.73071 -6.36411 -2.36580 -3.40551 -5.66761 -2.59891
#> CH30_6h-16   CH30_6h-16 -6.73071 -5.02691 -2.02961 -1.96791 -3.26111 -2.15781
#> CN1_0h-1       CN1_0h-1 -4.73797 -9.64877 -1.26177 -4.46717 -5.70527 -0.75477
#> CN1_6h-8       CN1_6h-8       NA       NA -2.03669 -2.54759  4.26221 -2.03779
#> CN1_6h-16     CN1_6h-16       NA -4.10520 -2.48390 -0.80270 -5.16830 -1.19600
#> 400B_0h-1     400B_0h-1 -6.89689 -4.95790 -2.24417 -4.17766       NA -3.06798
#> 400B_6h-8     400B_6h-8 -9.11833 -4.44811 -1.76436 -3.21896       NA -3.85273
#> 400B_6h-16   400B_6h-16 -7.24038 -4.94366 -1.29733 -2.26203       NA -2.89402
#> 1111A_0h-1   1111A_0h-1 -9.91257 -5.61523 -2.30767 -4.00953 -4.78791 -2.13551
#> 1111A_6h-8   1111A_6h-8 -7.31379 -5.69510 -2.57192 -3.06621 -8.95204 -2.60488
#> 1111A_6h-16 1111A_6h-16 -6.17557 -5.62360 -1.87333 -2.15282 -6.35331 -1.93915
#> 1164A_0h-1   1164A_0h-1 -7.58907 -5.61506 -2.72559 -4.45781 -6.34912 -2.68515
#> 1164A_6h-8   1164A_6h-8 -7.43676 -5.72400 -2.36064 -3.77418 -5.70766 -3.75480
#> 1164A_6h-16 1164A_6h-16       NA -6.38191 -1.59041 -4.48653 -7.71973 -2.69344
#>               Gene_7   Gene_8   Gene_9  Gene_10
#> CH30_0h-1   -2.05641 -1.42830 -3.32931 -2.55501
#> CH30_6h-8   -3.87350 -1.79241 -3.20471 -1.24421
#> CH30_6h-16  -2.91651 -1.75011 -4.11671 -1.41321
#> CN1_0h-1    -2.66677 -3.25977 -4.95547 -1.56437
#> CN1_6h-8    -3.40529 -2.36509 -2.76539 -2.90679
#> CN1_6h-16   -2.89280 -1.99220 -3.22700 -3.22990
#> 400B_0h-1   -3.45580 -2.53121 -3.90394 -3.31768
#> 400B_6h-8   -3.89929 -2.58246 -4.20117 -3.16836
#> 400B_6h-16  -3.38236 -2.64900 -4.92701 -4.02685
#> 1111A_0h-1  -3.92386 -2.36292 -4.67031 -4.35349
#> 1111A_6h-8  -4.15504 -2.01770 -5.08027 -2.77335
#> 1111A_6h-16 -3.77592 -1.99138 -5.37573 -4.40128
#> 1164A_0h-1  -3.96861 -1.74274 -3.43241 -2.77479
#> 1164A_6h-8  -2.36629 -3.02425 -2.51116 -2.61881
#> 1164A_6h-16 -3.30789 -2.16307 -3.55333 -3.58733

dput(Sample_Pheno)
structure(list(ID = c("CH30_0h-1", "CH30_6h-8", "CH30_6h-16", 
                      "CN1_0h-1", "CN1_6h-8", "CN1_6h-16", "400B_0h-1", "400B_6h-8", 
                      "400B_6h-16", "1111A_0h-1", "1111A_6h-8", "1111A_6h-16", "1164A_0h-1", 
                      "1164A_6h-8", "1164A_6h-16"), Batch = c("Batch-I", "Batch-I", 
                                                              "Batch-I", "Batch-II", "Batch-II", "Batch-II", "Batch-III", "Batch-III", 
                                                              "Batch-III", "Batch-IV", "Batch-IV", "Batch-IV", "Batch-V", "Batch-V", 
                                                              "Batch-V")), class = "data.frame", row.names = c(NA, -15L))
#>             ID     Batch
#> 1    CH30_0h-1   Batch-I
#> 2    CH30_6h-8   Batch-I
#> 3   CH30_6h-16   Batch-I
#> 4     CN1_0h-1  Batch-II
#> 5     CN1_6h-8  Batch-II
#> 6    CN1_6h-16  Batch-II
#> 7    400B_0h-1 Batch-III
#> 8    400B_6h-8 Batch-III
#> 9   400B_6h-16 Batch-III
#> 10  1111A_0h-1  Batch-IV
#> 11  1111A_6h-8  Batch-IV
#> 12 1111A_6h-16  Batch-IV
#> 13  1164A_0h-1   Batch-V
#> 14  1164A_6h-8   Batch-V
#> 15 1164A_6h-16   Batch-V

library(reshape2)
Data_v1_melt <- melt(Data_v1,
                     id.vars = "ID",
                     variable.name = "Genes",
                     value.name = "Value")




Data_v1_merged <- merge(Data_v1_melt, Sample_Pheno, by = "ID", all = TRUE)
head(Data_v1_merged)

Data_v1_merged = Data_v1_merged[order(Data_v1_merged$Batch),]
str(Data_v1_merged)

Plot_type <- "test"
library(ggplot2)
pdf(paste0(Plot_type,"_Testing_onlyxxx.pdf"),height = 25,width = 30)
p <- ggplot(Data_v1_merged) +
  geom_boxplot(aes(x=ID, y=Value, fill=Batch))
plot(p)
dev.off()

932×535 24.4 KB

Created on 2022-01-06 by the reprex package (v2.0.1)

2

Here I've used your data alongside the tidyverse packages dplyr, tidyr and forcats to do as you asked (and tidy the data up a bit!). The important thing that I did was convert the "batch" (and "gene") columns to be numeric, and use fct_reorder to reorder the "ID" column using the now-numeric "batch".

data_v1 = structure(list(ID = c("CH30_0h-1", "CH30_6h-8", "CH30_6h-16", 
                      "CN1_0h-1", "CN1_6h-8", "CN1_6h-16", "400B_0h-1", "400B_6h-8", 
                      "400B_6h-16", "1111A_0h-1", "1111A_6h-8", "1111A_6h-16", "1164A_0h-1", 
                      "1164A_6h-8", "1164A_6h-16"), Gene_1 = c(-7.06771, -8.73071, 
                                                               -6.73071, -4.73797, NA, NA, -6.89689, -9.11833, -7.24038, -9.91257, 
                                                               -7.31379, -6.17557, -7.58907, -7.43676, NA), Gene_2 = c(-5.91461, 
                                                                                                                       -6.36411, -5.02691, -9.64877, NA, -4.1052, -4.9579, -4.44811, 
                                                                                                                       -4.94366, -5.61523, -5.6951, -5.6236, -5.61506, -5.724, -6.38191
                                                               ), Gene_3 = c(-2.1792, -2.3658, -2.02961, -1.26177, -2.03669, 
                                                                             -2.4839, -2.24417, -1.76436, -1.29733, -2.30767, -2.57192, -1.87333, 
                                                                             -2.72559, -2.36064, -1.59041), Gene_4 = c(-4.24441, -3.40551, 
                                                                                                                       -1.96791, -4.46717, -2.54759, -0.8027, -4.17766, -3.21896, -2.26203, 
                                                                                                                       -4.00953, -3.06621, -2.15282, -4.45781, -3.77418, -4.48653), 
               Gene_5 = c(-5.38011, -5.66761, -3.26111, -5.70527, 4.26221, 
                          -5.1683, NA, NA, NA, -4.78791, -8.95204, -6.35331, -6.34912, 
                          -5.70766, -7.71973), Gene_6 = c(-2.36521, -2.59891, -2.15781, 
                                                          -0.75477, -2.03779, -1.196, -3.06798, -3.85273, -2.89402, 
                                                          -2.13551, -2.60488, -1.93915, -2.68515, -3.7548, -2.69344
                          ), Gene_7 = c(-2.05641, -3.8735, -2.91651, -2.66677, -3.40529, 
                                        -2.8928, -3.4558, -3.89929, -3.38236, -3.92386, -4.15504, 
                                        -3.77592, -3.96861, -2.36629, -3.30789), Gene_8 = c(-1.4283, 
                                                                                            -1.79241, -1.75011, -3.25977, -2.36509, -1.9922, -2.53121, 
                                                                                            -2.58246, -2.649, -2.36292, -2.0177, -1.99138, -1.74274, 
                                                                                            -3.02425, -2.16307), Gene_9 = c(-3.32931, -3.20471, -4.11671, 
                                                                                                                            -4.95547, -2.76539, -3.227, -3.90394, -4.20117, -4.92701, 
                                                                                                                            -4.67031, -5.08027, -5.37573, -3.43241, -2.51116, -3.55333
                                                                                            ), Gene_10 = c(-2.55501, -1.24421, -1.41321, -1.56437, -2.90679, 
                                                                                                           -3.2299, -3.31768, -3.16836, -4.02685, -4.35349, -2.77335, 
                                                                                                           -4.40128, -2.77479, -2.61881, -3.58733)), class = "data.frame", row.names = c("CH30_0h-1", 
                                                                                                                                                                                         "CH30_6h-8", "CH30_6h-16", "CN1_0h-1", "CN1_6h-8", "CN1_6h-16", 
                                                                                                                                                                                         "400B_0h-1", "400B_6h-8", "400B_6h-16", "1111A_0h-1", "1111A_6h-8", 
                                                                                                                                                                                         "1111A_6h-16", "1164A_0h-1", "1164A_6h-8", "1164A_6h-16"))

sample_pheno <- structure(list(ID = c("CH30_0h-1", "CH30_6h-8", "CH30_6h-16", 
                      "CN1_0h-1", "CN1_6h-8", "CN1_6h-16", "400B_0h-1", "400B_6h-8", 
                      "400B_6h-16", "1111A_0h-1", "1111A_6h-8", "1111A_6h-16", "1164A_0h-1", 
                      "1164A_6h-8", "1164A_6h-16"), Batch = c("Batch-I", "Batch-I", 
                                                              "Batch-I", "Batch-II", "Batch-II", "Batch-II", "Batch-III", "Batch-III", 
                                                              "Batch-III", "Batch-IV", "Batch-IV", "Batch-IV", "Batch-V", "Batch-V", 
                                                              "Batch-V")), class = "data.frame", row.names = c(NA, -15L))

# lets use the tidyverse
library(tidyverse)

data_long = data_v1 %>%
  # pivot_longer from tidyr - does the same job as reshape, but more modern 
  pivot_longer(contains("Gene"),
               names_to = "gene",
               names_prefix = "Gene_", 
               names_transform = list(gene = as.integer)) %>%
  # join on pheno
  left_join(sample_pheno, by = "ID") %>%
  # optional rename - make names consistant
  rename(id = ID, batch = Batch) %>%
  # convert the roman numerals to be numeric
  mutate(batch = str_remove(batch, "Batch-"),
         batch = as.roman(batch) %>% as.numeric())

head(data_long)
#> # A tibble: 6 x 4
#>   id         gene value batch
#>   <chr>     <int> <dbl> <dbl>
#> 1 CH30_0h-1     1 -7.07     1
#> 2 CH30_0h-1     2 -5.91     1
#> 3 CH30_0h-1     3 -2.18     1
#> 4 CH30_0h-1     4 -4.24     1
#> 5 CH30_0h-1     5 -5.38     1
#> 6 CH30_0h-1     6 -2.37     1

data_long %>%
  # reorder the "id" column by our now numeric "batch" column
  mutate(id = fct_reorder(id, batch)) %>%
  # plot!
  ggplot(aes(x = id, y = value, fill = factor(batch))) +
  geom_boxplot() +
  labs(x = "ID", y = NULL, fill = "Batch #") +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = .5))
#> Warning: Removed 7 rows containing non-finite values (stat_boxplot).

Created on 2022-01-06 by the reprex package (v2.0.1)

3 Likes
3

As a second solution you can try this :
After reordering your dataframe and before ggplot function you can encode ID column as a factor and specify the order of the levels which are ordered alphabetically by default. The order of levels is the order in which they render to the plot. Since you have ordered your dataframe using column Batch, function unique will return the desired order or levels. So before ggplot try :

Data_v1_merged$ID <- factor(Data_v1_merged$ID, levels = unique(Data_v1_merged$ID))
1 Like
4

Hi @JackDavison
Thank you very much for the nice example. This is indeed helpful. Just one question, in case if the name of the features are different instead of Gene_1, Gene_2, ........, Gene_10. What do I have to specifically revise in pivot_longer 

structure(list(ID = c("CH30_0h-1", "CH30_6h-8", "CH30_6h-16", 
                      "CN1_0h-1", "CN1_6h-8", "CN1_6h-16", "400B_0h-1", "400B_6h-8", 
                      "400B_6h-16", "1111A_0h-1", "1111A_6h-8", "1111A_6h-16", "1164A_0h-1", 
                      "1164A_6h-8", "1164A_6h-16"), FAM120A = c(-7.06771, -8.73071, 
                                                               -6.73071, -4.73797, NA, NA, -6.89689, -9.11833, -7.24038, -9.91257, 
                                                               -7.31379, -6.17557, -7.58907, -7.43676, NA), FAM129A = c(-5.91461, 
                                                                                                                       -6.36411, -5.02691, -9.64877, NA, -4.1052, -4.9579, -4.44811, 
                                                                                                                       -4.94366, -5.61523, -5.6951, -5.6236, -5.61506, -5.724, -6.38191
                                                               ), ABCH5 = c(-2.1792, -2.3658, -2.02961, -1.26177, -2.03669, 
                                                                             -2.4839, -2.24417, -1.76436, -1.29733, -2.30767, -2.57192, -1.87333, 
                                                                             -2.72559, -2.36064, -1.59041), ELANE = c(-4.24441, -3.40551, 
                                                                                                                       -1.96791, -4.46717, -2.54759, -0.8027, -4.17766, -3.21896, -2.26203, 
                                                                                                                       -4.00953, -3.06621, -2.15282, -4.45781, -3.77418, -4.48653), 
               OTULIN = c(-5.38011, -5.66761, -3.26111, -5.70527, 4.26221, 
                          -5.1683, NA, NA, NA, -4.78791, -8.95204, -6.35331, -6.34912, 
                          -5.70766, -7.71973), PECAM1 = c(-2.36521, -2.59891, -2.15781, 
                                                          -0.75477, -2.03779, -1.196, -3.06798, -3.85273, -2.89402, 
                                                          -2.13551, -2.60488, -1.93915, -2.68515, -3.7548, -2.69344
                          ), CCL5A = c(-2.05641, -3.8735, -2.91651, -2.66677, -3.40529, 
                                        -2.8928, -3.4558, -3.89929, -3.38236, -3.92386, -4.15504, 
                                        -3.77592, -3.96861, -2.36629, -3.30789), RPS125S = c(-1.4283, 
                                                                                            -1.79241, -1.75011, -3.25977, -2.36509, -1.9922, -2.53121, 
                                                                                            -2.58246, -2.649, -2.36292, -2.0177, -1.99138, -1.74274, 
                                                                                            -3.02425, -2.16307), CXCL5A = c(-3.32931, -3.20471, -4.11671, 
                                                                                                                            -4.95547, -2.76539, -3.227, -3.90394, -4.20117, -4.92701, 
                                                                                                                            -4.67031, -5.08027, -5.37573, -3.43241, -2.51116, -3.55333
                                                                                            ), IGEA = c(-2.55501, -1.24421, -1.41321, -1.56437, -2.90679, 
                                                                                                           -3.2299, -3.31768, -3.16836, -4.02685, -4.35349, -2.77335, 
                                                                                                           -4.40128, -2.77479, -2.61881, -3.58733)), class = "data.frame", row.names = c("CH30_0h-1", 
                                                                                                                                                                                         "CH30_6h-8", "CH30_6h-16", "CN1_0h-1", "CN1_6h-8", "CN1_6h-16", 
                                                                                                                                                                                         "400B_0h-1", "400B_6h-8", "400B_6h-16", "1111A_0h-1", "1111A_6h-8", 
                                                                                                                                                                                         "1111A_6h-16", "1164A_0h-1", "1164A_6h-8", "1164A_6h-16"))
#>                      ID  FAM120A  FAM129A    ABCH5    ELANE   OTULIN   PECAM1
#> CH30_0h-1     CH30_0h-1 -7.06771 -5.91461 -2.17920 -4.24441 -5.38011 -2.36521
#> CH30_6h-8     CH30_6h-8 -8.73071 -6.36411 -2.36580 -3.40551 -5.66761 -2.59891
#> CH30_6h-16   CH30_6h-16 -6.73071 -5.02691 -2.02961 -1.96791 -3.26111 -2.15781
#> CN1_0h-1       CN1_0h-1 -4.73797 -9.64877 -1.26177 -4.46717 -5.70527 -0.75477
#> CN1_6h-8       CN1_6h-8       NA       NA -2.03669 -2.54759  4.26221 -2.03779
#> CN1_6h-16     CN1_6h-16       NA -4.10520 -2.48390 -0.80270 -5.16830 -1.19600
#> 400B_0h-1     400B_0h-1 -6.89689 -4.95790 -2.24417 -4.17766       NA -3.06798
#> 400B_6h-8     400B_6h-8 -9.11833 -4.44811 -1.76436 -3.21896       NA -3.85273
#> 400B_6h-16   400B_6h-16 -7.24038 -4.94366 -1.29733 -2.26203       NA -2.89402
#> 1111A_0h-1   1111A_0h-1 -9.91257 -5.61523 -2.30767 -4.00953 -4.78791 -2.13551
#> 1111A_6h-8   1111A_6h-8 -7.31379 -5.69510 -2.57192 -3.06621 -8.95204 -2.60488
#> 1111A_6h-16 1111A_6h-16 -6.17557 -5.62360 -1.87333 -2.15282 -6.35331 -1.93915
#> 1164A_0h-1   1164A_0h-1 -7.58907 -5.61506 -2.72559 -4.45781 -6.34912 -2.68515
#> 1164A_6h-8   1164A_6h-8 -7.43676 -5.72400 -2.36064 -3.77418 -5.70766 -3.75480
#> 1164A_6h-16 1164A_6h-16       NA -6.38191 -1.59041 -4.48653 -7.71973 -2.69344
#>                CCL5A  RPS125S   CXCL5A     IGEA
#> CH30_0h-1   -2.05641 -1.42830 -3.32931 -2.55501
#> CH30_6h-8   -3.87350 -1.79241 -3.20471 -1.24421
#> CH30_6h-16  -2.91651 -1.75011 -4.11671 -1.41321
#> CN1_0h-1    -2.66677 -3.25977 -4.95547 -1.56437
#> CN1_6h-8    -3.40529 -2.36509 -2.76539 -2.90679
#> CN1_6h-16   -2.89280 -1.99220 -3.22700 -3.22990
#> 400B_0h-1   -3.45580 -2.53121 -3.90394 -3.31768
#> 400B_6h-8   -3.89929 -2.58246 -4.20117 -3.16836
#> 400B_6h-16  -3.38236 -2.64900 -4.92701 -4.02685
#> 1111A_0h-1  -3.92386 -2.36292 -4.67031 -4.35349
#> 1111A_6h-8  -4.15504 -2.01770 -5.08027 -2.77335
#> 1111A_6h-16 -3.77592 -1.99138 -5.37573 -4.40128
#> 1164A_0h-1  -3.96861 -1.74274 -3.43241 -2.77479
#> 1164A_6h-8  -2.36629 -3.02425 -2.51116 -2.61881
#> 1164A_6h-16 -3.30789 -2.16307 -3.55333 -3.58733

Created on 2022-01-06 by the reprex package (v2.0.1)

5

You're welcome - I think in this revised case you could do something like:

data %>%
    pivot_longer(-ID, names_to = "gene")

The -ID just means "everything but the ID column" :slightly_smiling_face:

Do check out the tidyr website for more info:

6

Hi @JackDavison

Thank you. This resolves my query.

7

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.