gistfile1.py

import re
 
# Your protein input sequence. This should be replaced with something like raw_input(""),
# but for this demo I just typed the string in.
sequence = "AUGCAAGGUACUUUCAGUUGACAAUAG"   # Valid protein
#sequence = "AUGCAAGGUACUUUCAGUUGACAACAA"  # Invalid protein
 
# Performs the search. The first argument is the regular expression (regex)
# and the second argument is the sequence (as seen above).
m = re.search(r'^(AUG([ACGU]{3,})(UAA|UAG|UGA))$', sequence)
 
# "re.search" returns None if no matching pattern colud be found.
if m == None:
        print("This is not a protein")
 
else: # Else if not None, this means a pattern has been found.

	# Checks the sequence is a multiple of 3
        if(len(sequence) % 3 == 0):
                print("This is a possible protein")
        else:
                print("This is not a protein")