# translation.py
# Author: Sami Khuri
# Last updated: January 14, 2016
# 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 dictionary, slicing a list, and built-in python function range()

def translate(cds):
    """The input sequence is a DNA coding sequence (CDS)"""
 
    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',
    }
    prot = ""
    for i in range(0,len(cds),3):
        codon = cds[i:i+3]   # slice is i,1+1,i+2
        prot = prot + geneticode[codon]
    return prot
 
cds = "ATGTATCCCTACACCCATAATTGA" 
print "CDS is", cds
print "Translation of CDS is", translate(cds)