if (FALSE) {
# For demonstration purposes, the following example dataset has all the
# types of data that can be used, but any one of them alone would work.
raw_data <- c(
">id:AB548412-tid:9689-Panthera leo-tax:K_Mammalia;P_Carnivora;C_Felidae;G_Panthera;S_leo",
">id:FJ358423-tid:9694-Panthera tigris-tax:K_Mammalia;P_Carnivora;C_Felidae;G_Panthera;S_tigris",
">id:DQ334818-tid:9643-Ursus americanus-tax:K_Mammalia;P_Carnivora;C_Felidae;G_Ursus;S_americanus"
)
# Build a taxmap object from classifications
extract_tax_data(raw_data,
key = c(my_seq = "info", my_tid = "info", org = "info", tax = "class"),
regex = "^>id:(.+)-tid:(.+)-(.+)-tax:(.+)$",
class_sep = ";", class_regex = "^(.+)_(.+)$",
class_key = c(my_rank = "info", tax_name = "taxon_name"))
# Build a taxmap object from taxon ids
# Note: this requires an internet connection
extract_tax_data(raw_data,
key = c(my_seq = "info", my_tid = "taxon_id", org = "info", tax = "info"),
regex = "^>id:(.+)-tid:(.+)-(.+)-tax:(.+)$")
# Build a taxmap object from ncbi sequence accession numbers
# Note: this requires an internet connection
extract_tax_data(raw_data,
key = c(my_seq = "seq_id", my_tid = "info", org = "info", tax = "info"),
regex = "^>id:(.+)-tid:(.+)-(.+)-tax:(.+)$")
# Build a taxmap object from taxon names
# Note: this requires an internet connection
extract_tax_data(raw_data,
key = c(my_seq = "info", my_tid = "info", org = "taxon_name", tax = "info"),
regex = "^>id:(.+)-tid:(.+)-(.+)-tax:(.+)$")
}
Run the code above in your browser using DataLab