Adding error bars from different columns in grouped barplot with ggplot2

Question

I´d like to add error bars to my barplot. The data for standard deviations is in two different columns.

This is my barplot:

# load packages
> library(data.table)
> library(ggplot2)
> library(tidyr)
> 
> results <- fread("Results.csv", header=TRUE, sep=";")
> 
> str(results)
Classes ‘data.table’ and 'data.frame':  7 obs. of  5 variables:
 $ Organism   : chr  "AC1432" "D3425" "BF3523" "XR2405" ...
 $ Molecule1  : num  39.5 418.4 189.2 49.3 4610.9 ...
 $ Molecule1sd: num  19.6 70.9 102.8 21.2 275.9 ...
 $ Molecule2  : num  276 6511 235 500 11205 ...
 $ Molecule2sd: num  21 291.1 109.7 67.1 94.5 ...
 - attr(*, ".internal.selfref")=<externalptr> 
> 
> df <- data.frame(results)
> 
> str(df)
'data.frame':   7 obs. of  5 variables:
 $ Organism   : chr  "AC1432" "D3425" "BF3523" "XR2405" ...
 $ Molecule1  : num  39.5 418.4 189.2 49.3 4610.9 ...
 $ Molecule1sd: num  19.6 70.9 102.8 21.2 275.9 ...
 $ Molecule2  : num  276 6511 235 500 11205 ...
 $ Molecule2sd: num  21 291.1 109.7 67.1 94.5 ...
> 
> 
> 
> # Manually set factor levels of 'Organism' column to plot in a logical order.
> df$Organism = factor(df$Organism, 
+                      levels=c("without organism", "AC1432", "BF3523", "XR2405", "D3425", "XR2463", "ATF259"))
> 
> df.g <- gather(df, Molecule1, Molecule2, -Organism, -Molecule1sd, -Molecule2sd)
> df.sd <- gather(df, Molecule1sd, Molecule2sd, -Molecule1, -Molecule2, -Organism)
> ggplot(df.g, aes(Molecule1, Molecule2)) + 
+     geom_bar(aes(fill = Organism), stat = "identity", position = "dodge")

barplot without error bar

used data:

> dput(df)
structure(list(Organism = structure(c(2L, 5L, 3L, 4L, 6L, 7L, 
1L), .Label = c("without organism", "AC1432", "BF3523", "XR2405", 
"D3425", "XR2463", "ATF259"), class = "factor"), Molecule1 = c(39.45920899, 
418.4234805, 189.162295, 49.314698, 4610.921188, 751.7070352, 
35), Molecule1sd = c(19.55450482, 70.91013667, 102.7566193, 21.20841393, 
275.8934527, 71.62450643, NA), Molecule2 = c(275.9147606, 6510.974605, 
235.247381, 499.8928585, 11205.33907, 9507.869294, 250), Molecule2sd = c(21.04668977, 
291.1223384, 109.652064, 67.1000078, 94.54544271, 707.1950335, 
NA)), row.names = c(NA, -7L), class = "data.frame")

and this is my trial for the error bars

ggplot(df.g, aes(Molecule1, Molecule2)) + 
  geom_bar(aes(fill = Organism), stat = "identity", position = "dodge") +geom_errorbar(df.sd, aes_Molecule1(ymin=Molecule1-Molecule1sd, ymax=Molecule1+Molecule1sd),aes_Molecule2(ymin=Molecule2-Molecule2sd, ymax=Molecule2+Molecule2sd), width=.2 )

but my idea doesn´t work. How can I add error bars from two different columns?

Answer 1

It might be easier if you reshape your dataset with columns for Organism, Molecule, mean and sd. Here is a tidyverse way to do it:

Package and Dataset

library(tidyverse)  

df <- data.frame(Organism = c("AC1432", "D3425", "BF3523", "XR2405",  
                              "XR2463", "ATF259", "without organism"),
                 Molecule1 = c(39.5, 418.4, 189.2, 49.3, 
                               4610.9, 800, 10),
                 Molecule1sd = c(19.6, 70.9, 102.8, 21.2, 
                                 275.9, 100, 1),
                 Molecule2 = c(276, 6511, 235, 500, 
                               11205, 9500, 250),
                 Molecule2sd = c( 21, 291.1, 109.7, 67.1,
                                  94.5, 50, 2))

# I estimated the not shown values in your str(result)

Reshaping

df2 <- df %>%
  # add meaningful ending to columnnames containing mean (m)
  select(Molecule1m = Molecule1, 
         Molecule2m = Molecule2,
         everything()) %>%
  # gather whole dataset into Molecule, mean, sd
  pivot_longer(cols = -Organism,
               names_to = c("Molecule", ".value"),
               names_pattern = "(Molecule[12])(.)") %>%
  # factor reorder levels
  mutate(Organism = factor(Organism,
                           levels=c("without organism", "AC1432", 
                                    "BF3523", "XR2405", 
                                    "D3425", "XR2463", "ATF259")))

Plot

ggplot(df2, aes(x = Molecule,
                y = m,
                fill = Organism)) +
  geom_col(position = "dodge") +
  geom_errorbar(aes(ymin = m - s, ymax = m + s),
                position = "dodge")