Annotating GCMS chromatograms

Using ggplot for GCMS chromagrams visualization

Learning points

• how to read GCMS data into R
• how to extract the scan time and TIC embedded within the lists
• how to use ggplot for data visualization and annotation

Things to improve

• reading files using iteratively?
• using more updated xcms tutorial found at https://bioconductor.org/packages/release/bioc/vignettes/xcms/inst/doc/xcms.html

Load packages

library(pacman)

p_load(tidyverse, metaMSdata, xcms)

Import data

The cdf files were taken from metaMSdata package, available on Bioconductor.

# define path for data stored in metaMSdata package
cdfpath <- system.file("extdata", package = "metaMSdata")
files <- list.files(cdfpath, "_RP_pos", full.names = T)
files

[1] "/Library/Frameworks/R.framework/Versions/4.1/Resources/library/metaMSdata/extdata/STDmix_RP_pos01.CDF"
[2] "/Library/Frameworks/R.framework/Versions/4.1/Resources/library/metaMSdata/extdata/STDmix_RP_pos02.CDF"
[3] "/Library/Frameworks/R.framework/Versions/4.1/Resources/library/metaMSdata/extdata/STDmix_RP_pos03.CDF"
[4] "/Library/Frameworks/R.framework/Versions/4.1/Resources/library/metaMSdata/extdata/STDmix_RP_pos04.CDF"

file_a <- xcmsRaw("/Library/Frameworks/R.framework/Versions/4.1/Resources/library/metaMSdata/extdata/STDmix_RP_pos01.CDF")

file_b <- xcmsRaw("/Library/Frameworks/R.framework/Versions/4.1/Resources/library/metaMSdata/extdata/STDmix_RP_pos02.CDF")

file_c <- xcmsRaw("/Library/Frameworks/R.framework/Versions/4.1/Resources/library/metaMSdata/extdata/STDmix_RP_pos03.CDF")

file_d <- xcmsRaw("/Library/Frameworks/R.framework/Versions/4.1/Resources/library/metaMSdata/extdata/STDmix_RP_pos04.CDF")

Extracting lists for retention time and TIC

file_a_tic <- file_a@tic

file_a_scan_time <- file_a@scantime


df_file_a <- bind_cols(file_a_scan_time, file_a_tic) %>% mutate(sample = "a")

names(df_file_a) <- c("scan_time", "tic", "sample")

#

file_b_tic <- file_b@tic

file_b_scan_time <- file_b@scantime

df_file_b <- bind_cols(file_b_scan_time, file_b_tic) %>%
  mutate(sample = "b")

names(df_file_b) <- c("scan_time", "tic", "sample")

#

file_c_tic <- file_c@tic

file_c_scan_time <- file_c@scantime

df_file_c <- bind_cols(file_c_scan_time, file_c_tic) %>%
  mutate(sample = "c")

names(df_file_c) <- c("scan_time", "tic", "sample")

#

file_d_tic <- file_d@tic

file_d_scan_time <- file_d@scantime

df_file_d <- bind_cols(file_d_scan_time, file_d_tic) %>%
  mutate(sample = "d")


names(df_file_d) <- c("scan_time", "tic", "sample")

# df_ all

df_all <- rbind(df_file_a,

                df_file_b,

                df_file_c,

                df_file_d) %>%

  mutate(sample = factor(sample))

 

df_all$sample %>% unique()

[1] a b c d
Levels: a b c d

glimpse(df_all)

Rows: 10,455
Columns: 3
$ scan_time <dbl> 3.460, 4.751, 6.036, 7.321, 8.611, 9.898, 11.188, …
$ tic       <dbl> 988.8397, 877.0441, 907.7909, 890.6389, 881.1803, …
$ sample    <fct> a, a, a, a, a, a, a, a, a, a, a, a, a, a, a, a, a,…

GGplot

df_all %>% 
  ggplot(aes(x = scan_time/60,
             y = tic, col = sample)) +
  
  geom_line(aes(col = sample), size = 1) +

  # facet_grid(sample ~.) +

  labs(x = "scan_time(min)",
       caption = "Source: metaMSdata package",
       col = "Sample") +

  theme_classic()

Adding Annotations

library(datapasta)

annotate_df <- tibble::tribble(

            ~Compound,   ~rt,

           "Linalool", 17.86,
  "Methyl salicylate", 22.44,
  "Ethyl hexanoate", 10.77

  )

join_annotate <- df_all %>%
  mutate(scan_time_round = round(scan_time/60, 2)) %>%
  left_join(annotate_df, by = c("scan_time_round" = "rt")) %>%
  filter(!duplicated(Compound)) %>%
  filter(!is.na(Compound))

# Adding to plot
df_all %>%
  ggplot(aes(x = scan_time/60,
             y = tic, col = sample)) +

  geom_line(aes(col = sample), size = 1) +

  # facet_grid(sample ~.) +

  labs(x = "scan_time(min)",
       title = "GCMS chromagram overlay for Standard Mixes",
       caption = "Source: metaMSdata package") +

  scale_x_continuous(expand = c(0,0),
                     breaks = seq(0, 70, 5)) +

  scale_y_continuous(expand = c(0,0),
                     breaks = seq(0, 30000, 5000)) +

  ggrepel::geom_text_repel(data = join_annotate,
                           aes(x = scan_time_round,
                               label = Compound),
                           col = "darkblue",
                           nudge_y = 5000,
                           size = 5) +

  theme_classic() +

  theme(axis.title = element_text(size = 12, face = "bold"))

References

Wehrens R, Franceschi P (2021). metaMSdata: Example CDF data for the metaMS package. R package version 1.28.0.

https://www.intechopen.com/chapters/52527