Non-target taxa

# specify the path to your files
path <- "../results/MEGAN"

# get all files in the directory
files <- list.files(path, pattern = "*.tab", full.names = TRUE) 

1 Fraction of reads Arthropoda

df <- files %>%
  map_df(~{
    read_tsv(.x, col_names = FALSE) %>%
    set_names(c("phylum", "count")) %>%
    mutate(sample = str_remove(basename(.x), ".MEGAN.taxonName_to_count_summarized-phylum.tab"))  # remove the extension from the filename
  })

datatable(df)

datatable(
  df %>%
 pivot_wider(names_from = phylum, values_from = count, values_fill = 0) %>%
 mutate(total = rowSums(select(., 2:35), na.rm = TRUE)) %>%
 mutate(fraction = Arthropoda/total) %>%
 select("sample", "fraction", "Arthropoda", "Chordata", "Microsporidia", "Proteobacteria", "Bacteroidetes")
)

df %>%
 pivot_wider(names_from = phylum, values_from = count, values_fill = 0) %>%
 mutate(total = rowSums(select(., 2:35), na.rm = TRUE)) %>%
 mutate(fraction = Arthropoda/total) %>%
 select("sample", "fraction", "Arthropoda", "Chordata", "Microsporidia", "Proteobacteria", "Bacteroidetes") %>%
  ggplot(aes(x=fraction)) +
  geom_histogram(bins = 50, fill="blue", color="black") +
  labs(x="Percent", y="Frequency", title="Histogram of Arthr0poda Fraction of reads") +
  theme_minimal()

df %>%
  filter(phylum == c("Arthropoda", "Chordata", "Microsporidia", "Proteobacteria", "Bacteroidetes")) %>%
  group_by(phylum, sample) %>%
  summarise(total = mean(count, na.rm = TRUE)) %>%
  ggplot(aes(x = phylum, y = total)) +
  geom_col(position = "dodge") +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  labs(x = "Category", y = "Total Count")

df_wider <- df %>%
 pivot_wider(names_from = phylum, values_from = count, values_fill = 0) %>%
 select("sample", "Arthropoda", "Chordata", "Microsporidia", "Proteobacteria", "Bacteroidetes")

datatable(df_wider)