Averaging the replicate data in omics / biostatistics

Question

I have a dataframe for gene expression data. Samples are named as Genotype_Time_Replicate (e.g. AOX_1h_4).

E.g. data set

df <- structure(list(ID = c("AT5G54740.1", "AT5G55730.2", "AT5G57655.2", "AT5G64100.1", "AT5G64260.1", "AT5G67360.1", "AT1G30630.1", "AT1G62380.1", "AT1G70830.1", "AT3G14990.1", "AT4G18800.1", "AT4G24510.1", "AT5G15650.1", "AT5G19820.1", "AT5G59840.1", "AT5G47200.1", "AT1G12840.1", "AT1G76030.1", "AT1G78900.2", "AT3G42050.1", "AT4G11150.1", "AT1G11860.2", "AT1G17290.1" ), 
                     Location = c("extracellular", "extracellular", "extracellular", "extracellular", "extracellular", "extracellular", "golgi", "golgi", "golgi", "golgi", "golgi", "golgi", "golgi", "golgi", "golgi", "ER", "ER", "ER", "mitochondrion", "mitochondrion", "mitochondrion", "mitochondrion", "mitochondrion"), 
                     AOX_1h_1 = c(0.844651873, 0.50954096, 1.12e-08, 0.012981372, 0.978148381, 0.027579578, 0.068010151, 0.410629215, 0.253838635, 0.033631788, 0.335713512, 0.982799013, 0.025910457, 0.793810264, 0.762431665, 0.152154436, 0.027114103, 0.000227, 1.07e-05, 0.721209032, 0.086281162, 0.483130711, 0.014795515), 
                     AOX_1h_2 = c(0.894623378, 0.011521413, 1.62e-06, 0.085249729, 0.02863972, 0.956962154, 0.225208718, 0.932679767, 0.002574192, 0.071700671, 0.233682544, 0.936572874, 1.12e-05, 0.241658735, 0.865205515, 0.000537, 0.103471292, 8.66e-07, 1.22e-08, 0.950878446, 0.145012176, 0.092919172, 0.599713247), 
                     AOX_1h_3 = c(0.880951025, 0.00145276, 8.59e-10, 0.087023475, 0.675527672, 0.765543306, 0.305860948, 0.899172011, 0.020973476, 0.542988545, 0.735571562, 0.157569324, 0.025488075, 0.071006507, 0.262324019, 0.080470612, 0.0436526, 6.65e-09, 5.63e-10, 0.020557091, 0.069577215, 0.005502212, 0.852099232), 
                     AOX_1h_4 = c(0.980823252, 0.158123518, 0.00210702, 0.006317657, 0.30496173, 0.489709702, 0.091469807, 0.958443361, 0.015583593, 0.566165972, 0.66746161, 0.935102341, 0.087733288, 0.744313619, 0.021169383, 0.633250945, 0.257489406, 0.024345088, 0.000355, 0.226279179, 0.004038493, 0.479275204, 0.703522761), 
                     AOX_2h_1 = c(0.006474022, 0.246530998, 5.38e-06, 0.47169153, 0.305973663, 0.466202566, 0.191733645, 0.016121487, 0.234839116, 0.043866023, 0.089819656, 0.107934599, 2.09e-06, 0.413229678, 0.464078018, 0.004118766, 0.774970986, 3.79e-07, 2.3e-10, 0.428591262, 0.002326292, 0.385580707, 0.106216066), 
                     AOX_2h_2 = c(0.166169729, 0.005721199, 7.77e-08, 0.099146712, 0.457164663, 0.481987525, 7.4e-05, 0.969805081, 0.100894997, 0.062103337, 0.095718425, 0.001686206, 0.009710516, 0.134651787, 0.887036569, 0.459218152, 0.074576369, 3.88e-09, 3.31e-15, 0.409645805, 0.064874307, 0.346371524, 0.449444779),
                     AOX_2h_3 = c(1.06e-05, 0.576589898, 4.03e-08, 0.787468189, 0.971119601, 0.432593753, 0.000274, 0.86932399, 0.08657663, 4.22e-06, 0.071190008, 0.697384316, 0.161623604, 0.422628778, 0.299545652, 0.767867006, 0.00295567, 0.078724176, 4.33e-09, 0.988576028, 0.080278831, 0.66505527, 0.014158693), 
                     AOX_2h_4 = c(0.010356719, 0.026506539, 9.48e-09, 0.91009296, 0.302464488, 0.894377768, 0.742233323, 0.75032613, 0.175841127, 0.000721, 0.356904918, 0.461234653, 1.08e-05, 0.65800831, 0.360085919, 0.004814238, 0.174670947, 0.004246734, 7.31e-11, 0.778725214, 0.051334623, 0.10212841, 0.155831664 ),
                     AOX_6h_1 = c(0.271681878, 0.004822226, 1.87e-11, 0.616969208, 0.158860224, 0.684690326, 0.011798791, 0.564591916, 0.000314, 4.79e-06, 0.299871385, 0.001909713, 0.00682428, 0.039107415, 0.574143284, 0.061532691, 0.050483892, 2.28e-08, 1.92e-12, 0.058747794, 0.027147473, 0.196608218, 0.513693112), 
                     AOX_6h_2 = c(5.72e-12, 0.719814288, 0.140016259, 0.927094438, 0.841229414, 0.224510089, 0.026567282, 0.242981965, 0.459311076, 0.038295888, 0.127935565, 0.453746728, 0.005023732, 0.554532387, 0.280899096, 0.336458018, 0.002024021, 0.793915731, 0.012838565, 0.873716549, 0.10097853, 0.237426815, 0.003711539), 
                     AOX_6h_3 = c(3.16e-12, 0.780424491, 0.031315419, 0.363891436, 0.09562579, 0.104833988, 3.52e-05, 0.104196756, 0.870952423, 0.002036134, 0.016480622, 0.671475063, 2.3e-05, 0.00256744, 0.66263641, 0.005026601, 0.57280276, 0.058724117, 6.4e-10, 0.030965264, 0.005301006, 0.622027012, 0.371659724), 
                     AOX_6h_4 = c(7.99e-10, 0.290847169, 0.001319424, 0.347344795, 0.743846306, 0.470908425, 0.00033, 0.016149973, 0.080036584, 0.020899676, 0.00723071, 0.187288769, 0.042514886, 0.00150443, 0.059344154, 0.06554177, 0.112601764, 0.000379, 2.36e-10, 0.78131093, 0.105861995, 0.174370801, 0.05570041 ), 
                     WT_1h_1 = c(0.857, 0.809, 2.31e-05, 0.286, 0.87, 0.396, 0.539, 0.787, 0.73, 0.427, 0.764, 0.87, 0.386, 0.852, 0.848, 0.661, 0.393, 0.0415, 0.00611, 0.843, 0.576, 0.804, 0.304 ), 
                     WT_1h_2 = c(0.898, 0.509, 0.0192, 0.729, 0.616, 0.902, 0.811, 0.9, 0.343, 0.712, 0.814, 0.901, 0.0446, 0.816, 0.896, 0.217, 0.747, 0.0143, 0.000964, 0.901, 0.776, 0.737, 0.876 ), 
                     WT_1h_3 = c(0.939, 0.627, 0.0104, 0.867, 0.932, 0.935, 0.91, 0.939, 0.803, 0.926, 0.934, 0.888, 0.813, 0.859, 0.905, 0.864, 0.838, 0.0223, 0.00917, 0.802, 0.858, 0.724, 0.938 ), 
                     WT_1h_4 = c(0.911, 0.782, 0.298, 0.396, 0.837, 0.871, 0.727, 0.91, 0.506, 0.88, 0.89, 0.909, 0.723, 0.896, 0.547, 0.887, 0.824, 0.566, 0.175, 0.814, 0.348, 0.869, 0.893),
                     WT_2h_1 = c(0.748, 0.911, 0.231, 0.929, 0.917, 0.928, 0.903, 0.801, 0.909, 0.849, 0.878, 0.884, 0.183, 0.925, 0.928, 0.719, 0.941, 0.108, 0.00817, 0.926, 0.678, 0.923, 0.884),
                     WT_2h_2 = c(0.935, 0.851, 0.163, 0.925, 0.951, 0.952, 0.63, 0.963, 0.926, 0.916, 0.925, 0.804, 0.868, 0.931, 0.961, 0.951, 0.92, 0.0706, 0.000265, 0.95, 0.917, 0.947, 0.951), 
                     WT_2h_3 = c(0.0197, 0.894, 0.000613, 0.911, 0.922, 0.877, 0.122, 0.916, 0.739, 0.0125, 0.718, 0.905, 0.801, 0.875, 0.852, 0.91, 0.302, 0.729, 0.00015, 0.923, 0.731, 0.902, 0.504),
                     WT_2h_4 = c(0.696, 0.765, 0.0142, 0.931, 0.893, 0.931, 0.925, 0.925, 0.87, 0.45, 0.899, 0.908, 0.144, 0.921, 0.899, 0.631, 0.87, 0.62, 0.0014, 0.926, 0.807, 0.844, 0.865), 
                     WT_6h_1 = c(0.898, 0.727, 0.00395, 0.921, 0.881, 0.924, 0.776, 0.919, 0.542, 0.234, 0.901, 0.67, 0.747, 0.83, 0.919, 0.848, 0.841, 0.056, 0.00144, 0.846, 0.815, 0.888, 0.916), 
                     WT_6h_2 = c(2.38e-09, 0.88, 0.708, 0.898, 0.891, 0.768, 0.443, 0.777, 0.843, 0.505, 0.695, 0.842, 0.208, 0.859, 0.794, 0.813, 0.14, 0.887, 0.326, 0.894, 0.661, 0.775, 0.182), 
                     WT_6h_3 = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), 
                     WT_6h_4 = c(0.0357, 0.953, 0.792, 0.956, 0.967, 0.96, 0.711, 0.892, 0.931, 0.899, 0.866, 0.946, 0.917, 0.799, 0.925, 0.927, 0.938, 0.72, 0.025, 0.967, 0.936, 0.945, 0.923)),
                class = "data.frame", row.names = c(NA, -23L))

I want to summarize data for each organelle (averaged by organelle and samples' replicates) and plot the Wildtype and mutant data side by side with standard error for each time point

df <- 
melted <- melt(df)
head(melted)
melted$variable<- str_replace_all(melted$variable, '_[0-9]$', '')
melted$variable <- factor(melted$variable,levels=c("WT_1h","AOX_1h","WT_2h","AOX_2h","WT_6h","AOX_6h"))
my_comparisons <- list( c("WT_1h","AOX_1h"), c("WT_2h","AOX_2h"),c("WT_6h","AOX_6h"))
ggbarplot(melted, x = "variable", y = "value", add = "mean_se",
          color = "variable", palette =  c("grey","black","grey","black","grey","black"),
          facet.by = "Location")+
  stat_compare_means(comparisons = my_comparisons, label = "p.signif")

How can I use tidyverse (dplyr / tidyr) for this purpose?

How can I use tidyverse (dplyr / tidyr) to follow this pathway instead of above scripts?

Answer 1

Another version going from the df object:

The df object is a list, and expression values after cbind are character type, so you can do

tb <- as_tibble(do.call(cbind, df)) %>%
      mutate_at(3:14, as.numeric)

NB that usually for gene expression data it is easier to read in count data using read_tsv or read.table and combine into matrix, data.frame or tibble.

NBB the df object specified has no "WT" samples (from my copy/paste anyway) so I renamed last 4 samples in tb as "WT_1h" replicates

colnames(tb)[11:14] <- paste0("WT_1h_",c(1:4))

Create means from replicates by function

rowMeanNrep <- function(tb, nm){
      varname <- paste0(nm, "_mean")
      selectn <- grep(nm, colnames(tb))
      tb %>%
         dplyr::mutate(!!varname := rowMeans(dplyr::select(., !!selectn)))
 }

Specify which timepoints to use, and apply

tps <- c("AOX_1h", "WT_1h")
tb_1h_mean <- cbind(tb_1h[,1:2],
                    do.call(cbind, lapply(tps, function(f){
                        rowMeanNrep(tb=tb, nm=f) %>% 
                        dplyr::select(paste0(f, "_mean"))
                    }))
              )

A final NB, think about using boxplots instead of barplots, see this paper

Answer 2

You can use different functions to normalise this data. I use gather() in this example alongside stringr functions to extract the data from the character vector that has 3 columns of data in it.

dat %>% 
  gather(key, value, -ID, -Location) %>%
  mutate(type = map_chr(str_split(key,"_"),~.x[1]),
         hour = map_chr(str_split(key,"_"),~.x[2]),
         n = map_chr(str_split(key,"_"),~.x[3])) %>%
  group_by(type, hour) %>%
  summarise(mean = mean(value))

Gives

# A tibble: 6 x 3
# Groups:   type [?]
type  hour      mean
<chr> <chr>     <dbl>
1   AOX    1h 0.3235302
2   AOX    2h 0.2709910
3   AOX    6h 0.2226648
4    WT    1h 0.6633866
5    WT    2h 0.7263108
6    WT    6h 0.7915662

This you can use in ggplot() to make a nice barplot.

To get it in a table you can use

dat %>% 
  gather(key, value, -ID, -Location) %>%
  mutate(type = map_chr(str_split(key,"_"),~.x[1]),
         hour = map_chr(str_split(key,"_"),~.x[2]),
         n = map_chr(str_split(key,"_"),~.x[3])) %>%
  group_by(type, hour) %>%
  summarise(mean = mean(value)) %>%
  spread(type, mean)

to get

# A tibble: 3 x 3
hour       AOX        WT
* <chr>     <dbl>     <dbl>
1    1h 0.3235302 0.6633866
2    2h 0.2709910 0.7263108
3    6h 0.2226648 0.7915662