Convert your 'lover letter' in DNA sequence!

gistfile1.py

#!/usr/bin/python

import sys,os,re
def translate(datafile):
#
# Regex strips all of space and non alphabetic from the sentence
#
  regex = re.compile('[\s|\W|0-9_]')
#
# Dictionary for the Amido acid - Codon relationship
#


	codon = {
	'A':'GCT', # Alanine
	'B':'GTG', # Let's use one of 'V' codon as 'B'. 
	'C':'TGT', # Cysteine
	'D':'GAT', # Aspartate
	'E':'GAA', # Glutamate
	'F':'TTT', # Phenylanaline
	'G':'GGT', # Glycine
	'H':'CAT', # Histidine
	'I':'ATT', # Isoleucine
	'J':'AGA', # In this time, let's steal one of Argninine Codon.
	'K':'AAA', # Lysine
	'L':'TTA', # Leucine
	'M':'ATG', # Methionine
	'N':'AAT', # Asparagine
	'O':'TAG', # Pyrrolysine..Do you know new 22th amino acid is out there? It is called 'Pyrrolysine'
	'P':'CCT', # Proline
	'Q':'CAA', # Glutamine
	'R':'CGT', # Arginine
	'S':'TCT', # Serine
	'T':'ACT', # Threonine
	'U':'TGA', # Selenocysteine..This is 21th amino acid
	'V':'GTT', # Valine
	'W':'TGG', # Tryptopin
	'X':'AGT', # 'X' amino acid would be so weird..Anyway, steal again from serine.
	'Y':'TAT', # Tyrosine
	'Z':'GGG', # 'Z'...Let's steal one of Glycine Codon 'GGG'
	'*':'TAA' # This is the 'Stop' Codon. 
                  # There are other two stop codon (TAG and TGA), 
                  # but they are already used for two rare amino acids.
	}

	try:
		f=open(datafile)
		filecontent=f.readlines()
		oneline=""
		for line in filecontent:
			oneline = oneline+regex.sub('',line)
		aminoacid='M'+oneline.upper()+'*' 
#
# Add 'Start Codon' and 'Stop Codon'. Yes..I would like to make a 'functional' protein..LOL
#
		nucleotide =""
		for ch in aminoacid:
			nucleotide = nucleotide+codon[ch];
		print ">"+oneline
		print nucleotide

	except IOError as e:
		print 'f**k'

if __name__ =='__main__':

	for arg in sys.argv[1:]:
		if os.path.isfile(arg):
			translate(arg)