R/codons.R

In ryanmcnamara4/myPackage: Useful functions for dealing with biological data/sequences

# List of synonymous codons
SYNONYMOUS_CODONS_DNA <- list(
  Phe = c("TTT", "TTC"),
  Leu = c("TTA", "TTG", "CTT", "CTC", "CTA", "CTG"),
  Ile = c("ATT", "ATC", "ATA"),
  Val = c("GTT", "GTC", "GTA", "GTG"),
  Ser = c("TCT", "TCC", "TCA", "TCG", "AGT", "AGC"),
  Pro = c("CCT", "CCC", "CCA", "CCG"),
  Thr = c("ACT", "ACC", "ACA", "ACG"),
  Ala = c("GCT", "GCC", "GCA", "GCG"),
  Tyr = c("TAT", "TAC"),
  His = c("CAT", "CAC"),
  Gln = c("CAA", "CAG"),
  Asn = c("AAT", "AAC"),
  Lys = c("AAA", "AAG"),
  Asp = c("GAT", "GAC"),
  Glu = c("GAA", "GAG"),
  Cys = c("TGT", "TGC"),
  Arg = c("CGT", "CGC", "CGA", "CGG", "AGA", "AGG"),
  Gly = c("GGT", "GGC", "GGA", "GGG"),
  Met = "ATG",
  Trp = "TGG",
  Stp = c("TAG", "TGA", "TAA")
)

# Character vector of all codons
ALL_CODONS_DNA = c("AAA", "AAC", "AAG", "AAT", "ACA", "ACC", "ACG", "ACT", "AGA",
               "AGC", "AGG", "AGT", "ATA", "ATC", "ATG", "ATT", "CAA", "CAC",
               "CAG", "CAT", "CCA", "CCC", "CCG", "CCT", "CGA", "CGC", "CGG",
               "CGT", "CTA", "CTC", "CTG", "CTT", "GAA", "GAC", "GAG", "GAT",
               "GCA", "GCC", "GCG", "GCT", "GGA", "GGC", "GGG", "GGT", "GTA",
               "GTC", "GTG", "GTT", "TAA", "TAC", "TAG", "TAT", "TCA", "TCC",
               "TCG", "TCT", "TGA", "TGC", "TGG", "TGT", "TTA", "TTC", "TTG",
               "TTT")

SYNONYMOUS_CODONS_RNA = sapply(SYNONYMOUS_CODONS_DNA, function(x) stringr::str_replace_all(x, 'T', 'U'))
ALL_CODONS_RNA = stringr::str_replace_all(ALL_CODONS_DNA, 'T', 'U')