-- Converts DNA sequences into amino acid sequences
-- by Scot Drysdale on 9/26/07


-- Converts a sequence of bases in DNA to a sequence of amino acids          
dna2proteins :: [Char] -> [Char]
dna2proteins (b1:b2:b3:rest) = lookupSure [b1, b2, b3] codes : 
                               dna2proteins rest
  where
    codes :: [([Char], Char)]
    codes =  [("ATA", 'I'), ("ATC", 'I'), ("ATT", 'I'), ("ATG", 'M'), 
              ("ACA", 'T'), ("ACC", 'T'), ("ACG", 'T'), ("ACT", 'T'), 
              ("AAC", 'N'), ("AAT", 'N'), ("AAA", 'K'), ("AAG", 'K'), 
              ("AGC", 'S'), ("AGT", 'S'), ("AGA", 'R'), ("AGG", 'R'), 
              ("CTA", 'L'), ("CTC", 'L'), ("CTG", 'L'), ("CTT", 'L'),
              ("CCA", 'P'), ("CCC", 'P'), ("CCG", 'P'), ("CCT", 'P'), 
              ("CAC", 'H'), ("CAT", 'H'), ("CAA", 'Q'), ("CAG", 'Q'), 
              ("CGA", 'R'), ("CGC", 'R'), ("CGG", 'R'), ("CGT", 'R'), 
              ("GTA", 'V'), ("GTC", 'V'), ("GTG", 'V'), ("GTT", 'V'), 
              ("GCA", 'A'), ("GCC", 'A'), ("GCG", 'A'), ("GCT", 'A'), 
              ("GAC", 'D'), ("GAT", 'D'), ("GAA", 'E'), ("GAG", 'E'), 
              ("GGA", 'G'), ("GGC", 'G'), ("GGG", 'G'), ("GGT", 'G'), 
              ("TCA", 'S'), ("TCC", 'S'), ("TCG", 'S'), ("TCT", 'S'), 
              ("TTC", 'F'), ("TTT", 'F'), ("TTA", 'L'), ("TTG", 'L'), 
              ("TAC", 'Y'), ("TAT", 'Y'), ("TAA", '_'), ("TAG", '_'), 
              ("TGC", 'C'), ("TGT", 'C'), ("TGA", '_'), ("TGG", 'W')] 
dna2proteins _ = []       -- Note 1 or 2 bases at end not converted.


-- Looks up a key in a list of (key, datum) pairs.
-- Throws an exception if the key is not found.
lookupSure :: [Char] -> [([Char], Char)] -> Char
lookupSure str ((key, datum) : rest) = if str == key then datum
                                       else lookupSure str rest
lookupSure str _ = error (str ++ " not found")