# translation.py 
# Author: Sami Khuri
# Last updated: December 28, 2017
# Purpose: To perform translation of a coding sequence (CDS).
#          A CDS starts with the start codon: ATG, and ends with a 
#          stop codon: TAA, TAG, or TGA, and its length is a multiple of three. 
# Program uses a user-defined function: translate; a dictionary where the key
#         is a codon and value its amino acid translation, slicing a list,
#         the while loop, the python function range() and method join()
#

def translate(seq):
    """Translate a DNA sequence to an amino acid sequence."""
    geneticode = {
    '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',
    }
    seq = seq.upper()
    length = len(seq)
    pos = 0
    # Let us save the amino acid sequence in a list called protein
    protein = []
    while (pos < (length-2)):       # while we still have codons to translate
        codon = seq[pos:pos+3]
        # Get the appropriate amino acid from the dictionary
        aa = geneticode[codon]
        protein.append(aa)
        pos = pos + 3
    return "".join(protein)

# The main program starts here
handle_CDS_mutant = open("CDS_mutant.txt","r")
seq_CDS_mutant = handle_CDS_mutant.read()

outfile = open("Protein_mutant.txt", "w")
outfile.write (translate(seq_CDS_mutant))

handle_CDS_mutant.close()
outfile.close()