Given a DNA string with ambiguous IUPAC characters, print all the possible unambiguous DNA strings

make_unambiguous.R

make_unambiguous <- function(dna) {
  require(tidyverse)
  require(S4Vectors)
  iupac <- tibble(code = c("A", "C", "G", "T",
                           "R", "Y", "S", "W",
                           "K", "M", "B", "D",
                           "H", "V", "N"),
                  base = c("A", "C", "G", "T",
                           "AG", "CT", "GC", "AT",
                           "GT", "AC", "CGT", "AGT",
                           "ACT", "ACG", "ACGT"))

  tibble(dna) |>
    separate_rows(dna, sep = '(?<=.)(?=.)') |>
    left_join(iupac, by = c("dna" = "code")) |>
    pull(base) |>
    str_split("") |>
    expand.grid(stringsAsFactors = FALSE) |>
    unite(col = sequence, sep = "") |>
    as_vector()
}

make_unambiguous(dna = "AAYGANAGYCARAGYAAR")

https://bioinformatics.stackexchange.com/a/21315/3967