PROT.py

inputseq="AUGAUGAUAGCUGUUAUUACUCCAGGUGUAUGUGAUGCUGCUGACAUUCCACCUAUCAGUGGGUACUUUGUAUCGCUUGCGUGGGCUCUAUGGCUUGCAACGUUAGACAACGCCGUCAGCUCGCAGAUGGCAAACCUCUCACAUCGAUGUAUUUAUUGUGGGAGUGCUGCGCUCUUGUCAGGAGCAGAUUGGUUGUUCUGUCGCCCUUACAUCCGCUUAUGUCAAUCUCAUGAUGAGCAAUAUCCUGUCGAAGGCUUACUUCACCCUUAUCCCAAUCCGUGUCCUGGAGCGUCGCGAAUACUUACAGAACGAGACUUCCUAUUGUAUCCCAACUCCGCGCCCCGAAACGACAUAGCUCUUGGUCGGUCUGCGGUAGAGCGGUCGCCCCCAAGCACGAACACAUCGUUGACAAUGACCUCCUGCGCUGAACGUACAAUUAUGAAAGCGCUCGCAAUCUCGGCAUGUUAUAACCGCCCCGUCUACACCGACCAUCGUGGGGAAAUCUCCACAUCGGUUUCCCGAAGAAGAGAAUUGACCGUCCACCAGUCAGAGCCGCCGCGCCCGAAUCUACACCUGAGCUACCAGUUUAACCAACGAAAUCCGUUAUAUCCGCGUGGGAAUACUAAUAGCAUCUAUUCUCAACUGGAACUGCAAUCCGCAAUCUAUUACUUUAAUUCUGAUAGAGGAGCUUGCACCGUCCCUCCCGUCCGAAACUCUGGAUGUAAUUCCAACCGGACAGGCCGACCCAUUCAGGGUGGAGAUGGGCGAGCCUUGAAUGGAUUCGAUUGCGAUUGCCGCCACCCCCGAUCUUCAUCCGGGCUUGUAAUACGGCUUCCUUCAGACUUGACGACAUUCAAAGGCUUAUGGGUGUGCUACUUUCUGGUAGAUGGAUUCAUAUGGUGCCGCGUUGGGGUUCGAACAAUGCUUGUUCAGUACUCAAACCGAGCUCCUCUUUGCUCAUUCCGUCUAAGACGAUUACUCCUCGCAAACCAGAAGCCCUACAAAAUAAGCACGGAUUCGCCUUGUCGCUUCGCGCACAUUUGUAUCGCCGGCUUACAAAUAUCCGUGCUCUAUACAGUUCACGGUAGUCCCUUCGUCAACCUUGGUAUACCGGAUAUGAGACCGGUCGUCGGACUGCCCCACACGGUGCUGAGACAAGUCACUGCGGAGAGCGUUAAUGCUGCUGACCUUUUAGAUCAUCGCUAUAACAAAAGACUCACGGUUCAAUUGCGCCGACCUAUGGAUAGAAGACCCGAGAGACAGGUGGUAGUCAAGCUAACGCGUGGAGCCCAGCUUAGUACAGAGCCUCGUGUAAAAGAGCUGGGCAAUGCCUACCAAAUACCCCCGAGCCAAGCGUGUCAGCAUUAUUCGCAAUUGCGGCUGGCGAAUGGCAAGACCACCCCCACUGAAAUGAAGUCGCAAAAGUUAACCCAGUUGCGGCCCAUGUAUCUUGAAGACCUACAUUACUACGAAGCGGGUUCGUGUCUCCAGGACAACCUCAAAUACACCUGUUGCUAUAAUGGGCUCUUCGGUCGGCAGCUACUAGUUGGUAAGAAAGGGUAUCCCGUGACGCUGCUUGAAAUUCCGGCUAUUCCCUUCGAUCUAAGUAAUAUACAUACUUCCAUGGCGGGCGGAGAUCAGCGUAUACGGUUCCCCAAAAGCAAGAUCCAAAGGGGCGGCGACAAUUAUUCUGGUAUCGGGAAUGGUUCUGUAUUCUUCAAUGAUGCCCCACGUUGUACGUCCAGUUACCAUCUUGCCAGGGACCACGUUCGUGGUCGCAUAUCGCCCAAGGAUGUGCCGCCUGUGUCUUAUGGGAAUUCUGACUACUACACACCGUGUGCCUUGCCCAUCUCCCACUGGGAGUUAAAGCGCGCGCCACCCAGAGGUAGUGGAACCACUAACAAGAGUAAGCUAGUCAAACUUGGAUGCCGCACUAUCUUACGUCGUGAAUUUAGCCAAGCCAGUCUAGUGUGGGCUCAGCCCCCGGGCGGACAGACCUCGGCUUCCCGCCGACUCCGAGACUCACGGCCAGUUAAGCCUUGCCGCGCCAGCUUUAUUAUCAUCAAGUGCAUUCAAUUCAGUGUGCUUGUUUUUCUAUGCACGUAUAAUAGUGAGACUAAGCUAAAAUCGUGCAUGUCUUCAAUUCUCAACAUCGGCAAGCACCCGGACAUAACUGAAAACACCCGACGUCGAUGUCCGCAAUCAUUAUCUGGGUUUAUUUUGACCAACUUUUGCAAGCUAGUCAUCGUUCUCUGUUUAGCAACGCUCAUGAAGGUCGAAGUCGGUGUGGAUCGCCCGAGCUUACUCUUCAAGUGGUUCUUGAUGGUAAUUGGCAAGCGCGACAAAAUGGCGUCAUUUUGCUCAGGUUCGGUUCAGGGUGGGAGCCAUUGGGGCCAGGGGCCGAGCAUUCCAUGGUCGAACCGACUGUGCAUAACGCAAACAGAGGGCGGGUCGGAGGGUCUAUUGGACUUAGAUGAUCGUCUGGAUCCAACUCCUUCUAGACGCGCUCAACCCUGCUGGCGCCCCUUCACCCUCCAGCUGUUUACUAUUACCGUAAGAGAUACACUCGCCGCUCGGAAGUGUAUAGAUAGAUCCACCGUCGUAAUGAAUGUCCGUCUUGACGAUGACGUCCGUCCUUAUUGUCCGAACGAAUCUACUCUAGAAUUCGCGUCUAUGCUUCCCGACACUCUUCGAAAGGGGUUAUCCGCAAUACGCACGGAAGGCGCGUCUUUGACUUCUACUCGUCAAGGCAACGCGGUCCCAUACAGUUGCCAGUCUGAAAUCCGCAAGGCGUCCUGUGGUCUCAGUUUGUGCGCGCAAGAAAGGUAUUUAGCCUCCAAUAGGCCAGAUCCAAUCUCAAUAUUAAGUCAGUGGCGUUGCAAAUACAGACCGCCCGUGUCUACCCUAUGGUCCGAUUCCCGGGUACAAGUGUCCUAUCAAGGAUUAUGUGCAAGGGUAUUUCAUAGAAUCACCGGGCUGGGAGAUUCUCCUCUAUCACUAAACCAACACAAGUACAACAACUCUACAAAUGUGCUCAAUCUAUGUGAAAACCGCAUGAAAUCGUUAAUCCGCACGUCUGCAGGUCUGAAUUGUCGAUGGUUGCAUUUUUAUACGACGCACUCCCUUAUUACCGUAGACAGAUUACAUCCACGACUUCGCGUUAGAAAUCAAGCUAAGGCAGGAGGUGUUCGGACCUGUAGGUCAUCGGGGCACAUGAAAAGGCAAGUGAAUUCUAGUCGGCCAUCUUCAAAGUCAACCCGGGUCCGAUGGGGCCGGCAUUCUGCGCAUCGUCGACCAGCCUCAAAUCUACCGCCUGGCGAAACUAAUAGGUUGCGGCGGUUCUGGUGGGUGUUGGUCCCUGCAGUCACACCAGUUAUUAUUUCAGUAGCUAGCACUAUUGACUGCGGCCACGGGCUGGGCUUAGCAGGACCUCGCCUAACUCAUCAUCCACCUUCGGCACCACCGAUGGGAGCGAUAAGGCUUAGUUAUCGUAUUGAUAUGAUAGGCCCAGUUUCGAGCAAUUUCCGAAUAUUUCCCGAAAGUGGACGAGACAGUCCGUUAGUCCACAAUGCACCACCUCCUGCAUUGUUCCGUAGGAUUUUCACGUACAGAUUCGCGGGAGCCCGACUUUCCGGUGAAUGGUUAAUUCUGAUCAGCAAUCGCGAGCGGAUGGGACUAGCAAAGUGGAACUCCCCCGCGGCCCGAGACCGAGAAAUCGGCCCAGUGUUCGGAGGCUCUGCCAAUAGCUAUGAGGCGGUUCCGUGCACUUUAGACGGUACCAGCCAAACUCAGAUAUGCUUGUUGAUGUGUGGUUCUGACUGCUUGCGCACCCUUGAUUUGAGACUCACGGUAAGUACCUCUUAUGGACCGGGAGCUCCGUCCGCAUUCGAUGAUCGGCAUAAUCUGGAGACAGUUCGGGUCCACUGCGAAAGCGGUGAGUCGGAGACAGCUGCUGGUGCCACUCCGCUGUCACCCAAAAUUGAAUUCAACAGUGUAUGUUCGCUUACACCUAACAGGGAAUUUGACAGCGGGACACGUGCGGCGAGACGUUUCACCGAUCGUGGGUUGAGACCGGGCUUCGCAUGCUUAUACUUCGAUGGUUUCGAUUUGACGGUUAAUCCGCAGCAGAACGGCGCAUCUUCAAUAGGUUAUACAGUUAAGUUCACACUUCUGCUCAUUCGUCUGUGCUUCUGCACCUCUGGAUUGCCUCAGCUGGUCUUUGAGGUCACGCUUAAUCUUGAGAGAGUACUAGUAGGUGAUGGGUGGAAGCAAAGCGACCACCGCGGCUUCCAAAAUACCGCCGGUACACAGCCUGAAGUGUCCCAGCGCACACGGCCCGUAUAUUAUCUCAGGCCCAACCGGAUGGUCCGUCAUCUUAGCUUUCAAAAGGUUAGAGCCGCUAGUCGAAUGCUAUGUUACCGAGAAGGAAUACACUCUGUCAAACAAAAGCCUGAUACAAAUUUGGGGGACAUCUCACUUGCGUCUUGCACGGUCUCCCGUACACAGUACGUUAAGGGGUCAAUUCCAUCAACAUUUCCGAACGACUUGCGGAAUUUCCACAUGAGGGUUCGAGUCCUAUGUGCCUGCAGGGUCCUAGGUACAUGGAAUCGCACCGGACGGUGUGGCCCUAACUCUAUAGACCUCGAAUUGGGUUGUGGGUCAGUGGACCUUAGGGACAUGGCUCCUAAUCACACUCGUCGAGGGAAGGUACGGUGCUACCAUCUCACAUUCGUCGUCACAAUGAUGGCACAGUUGUCGCUUACGAGCGGCGAGGGUCUUGUGCUUAUCAUAUCACGCUUUGAUAACUACUCCAAUACCCCAUCAAUCUCGAGGGGAUCGUGGUACAUUUCGGGGGCGCCCCGAGGCCACUACAGGGCCCGUCAGUCCUCGCUUGACCUUACCGAGACAAGAGUUCAAAAUGGUACCGACGCUUUGUAUUGGAGACGAAUCACUCGCACAGCCCAACAGCAGAAAAGGCUGCUAGCGGUUACUAGCAAUUCCUGUAGGAGGAGAAUCCAGUGGAAGCCUACAGUAUGUUGCACGUGUGCAGAGUUAUCCCACUUGUUUCUGCUAAGCGCUAAGGUACUAGGCCAUGCCCUGCUUACGAUUAGGACGAAACCUUUUACCGGCUAUGUGUUCAGGAGCGGUGGAUACUUGUACGCCUAUAUGUCUGGCAUCCCUGAAUAUAACAAGAGACUGAGAAGGUAUACGGCUGACACAGUCUGUUUGACCUGCAAACCUACGUUGGCAUACUUCGUAGCUCUUCGCUCGUCAAGAGUAGUGGAUCCGCAUACAGUUAACGGAUCCGGAGUUACCAAAAAAAGUCAAAAGAAGCUACGGAUCAUCACGACAACUAUGACUUCAGACCGGUGCAUGGACCACCACCUUCCAAGACGAUGUUUGCAAAGUCUUGCACUCCGGGUGCGCUGGCUAACGUUGAAAAUGGCAUUCCGUUAUCAAUAUAAAGCGCGCCUCUGCCUUGGAAGUCUAUGUGCCUCACUUUCCUUGCAUUACCUGCGCGUACGCGUUGUUCUAGCUGCUGUUCGAAUGCGAUACUCGCCAAUCAUUAAUGACUUAAAUGAUUAUUUUGUGAAAUGUAUUAUCGUAAAGGUCGUUAUACUGUUACGUUCGCCUGGAGACCAAAUUUGGCAAUGUCAGGAUCGUUGGACUUACGUAGGGUUCAUCGAUAAAGUUAAAUCUAUCUCCGGCCUCGCCAGCAUGUAUUCCGUGUUAAUUAAACCGGUGACCUCCCCAUACGUUUUGAGGUGCGUGGUAUUACGUAUUGAUCCGACGGUGCAACAACGCUUUAUUAGGCCGAUAAUUAAGGGCGACAUCAACCAGCGCACUAGUGCCCAAGCUAAACACUCAACAAUCGCGAGUACUGAUGUUGCCUCCUGCACCGAGUCUGAUGCCGCGCCCCAUAAAGCUCUAGUAGCGCUUUUAUUCGUAGCUCAAGAUAGCAGUUUUCGCGUUGCAUCAACUGAGACACGACGACAUCUCAACGACCAAGGUGCGCGCUCGGCCACUCCCACCCCGAUCUGCCGGGGUUGCUUCGACGGUCUAGGGCAAUGCCACGAUGCAUCGCCUUUCAAGACUCAACCUUGGGACAACGAGUGCCGCCCGAAAAGCGCUCGUCGGAAGUUCCUGUUAGACACAGUACAUUGCUCUCGUAUGUCCAGGCAUGCAUCCCCAGACCCCAUUUCUGCAAAGAACCCCUUGACCAGCUCCAUGCGUAAGAUACACUCACUUAGGCGAGUACCAAAACUAUGGUGUGCACUCUGCGGCGAUCUCUUUAUGAGGAAAUACUCAGCAGCCCUGUUUCAGCACCCGAUAAAUGGCGCGCUGGGGCUCGGCUUGCUUUCUCGAGUGGGGAGCGUCCAAGCGCGUCGUGUCUAUUACCUUAAAGGAUACUGGUUAUGGGGUACAGUCAUAUUGACUUUUCUUGCCGUUCCACGAGGUAUUUCGAGACUCAUUGAUAUGACGCCGGCCUACGCACGGUCUUGGGCGUGGGGGUAUACAGCUCGUAACGUUAGUCAGAGGAUUCUUGGAUGCAUCCGGUGGGCACCUAUAUUGAGAGUUGUUCCAGAAUGUCCAGGUGGCCCCUCAUCACCUCGACUGAGUACAUUGAUGAAAUACCAUACGAGUUCAGGCAAGCUCACGAUUUUCGUGAAAAUAGGUUCCCACGGUUGGCGCCCAUAUAGAAGUUUGCGGCAUCUGACCGGAACUAGGUGUCGUGAUCAUAUUAGGGCAUCUCUCUUUCAAGGACUCGAACACGUGAUGCCGGCGCUGUUACCCGGCGCCCUAUACGACUAUUCGUUAAGAAUAAAAGACACACACCCUACGUCUCCUCAAGUAGUUCCUCGGGUUGUUGAUGAUCCUUGCGGCGAACAUAGUAAGCUAUAUGCUGUCAGGUGUCGCGGAGCCGUUUUCUGGGCACAAUUCCCACCGACUCACCAUCUGUUUUCUUCAGUUUUACACAUUGGAUGGGUUGUUGGUAAGGCCAUGAGAGCUCCCGGAAACGACCAAGAACCAGAUUACCUCCCAGUCACACCGUUACACCCAGCUGGUUAUCGGAAAUGGUGGCGGAUUCGAUGGUUCAGUAUAUAUGGCGACAUGUCCAAUCUUCUAGUUGACCCUCUAGCUGAUGCGGCUAAACUCAUAGGAUACCUCGCUGCUAGGAGUAUUUUUGUUAGGUUGCCGCUUCGACAACCUUCGUAUAAUUACCGCUUUAGCACAAAAGACGGCCGUCUUGACCUCGGCGAGACAUUUGUCUCGCCUCCGGUGAUCUACGUGACUACAUCGGUGACAACGCUCGGUCACCUUCCAGGUGUUGUUGAGUACACGGAGACGCACCCAUCCGUUCACACCUUAAUCGUUACUGACCCUGGCGCGCGAGGCGGGUUGCGCGCAGUUACGCGUGGAACUACAGGGCCAGCCGGCCCUGUAUGUCAGGGUACAGGUGAUCAGGCCAUAGAGGGGCGUGGCUUCGUGGAGAUCCAAAGCACGCCAGCCGAAUUUCGCAAGGGUCGUUCAAGAGGCGGGUUAUUAAUGCGAGAUCGCAGGAAAUUUGCACCAUCGGGGUGCGAUCCCAUUCUAUGUAACGUGAAGCGGCGGCAGAACGAUGCAUCGGGAGUUCAAUUUUUACAAAAAGAAUGUUCGGAAGGGAGUUCUAUGUUCCGUGCUGCAUCGAUUUUUAAACACAAAAACAGUCGCCGGAGCCUGUGGUUACUGGUUCCACUGAGCUCUGCCAUCUGGACCGAUGGGAAUCUUCUACGUAAAUGCCUGCGUGCCUCGUGGUUUCUACUCACCCAAAUUCUUUAUUUCCCCCUCCGAUCCUCAAACUGGUCUACUGAAGGCGAAAUUAGGAAUGGCUCCAUGUUGGCAAAUCUACUUCUCGUGAGACCACCCAGACUCAAGUCACGCAGACCGUGGGUAGAUGUGCACUGGGAUCCAAGAGCGAGACUAUGCAUUGGAAGGCUGCUCGAAAAACAAGGGUCGACUUCAUGGGGGCACGUACCAAGAAAGAUGAUUCGUGAAAUUUGUGAGCCGGUGCGAGGAAACCCAUUGUGGUUCCCGCCCGAAACUGGAGGAAGAGUCGAGCCCCUCCUGCGAGCCAACGUUGGUCUAUUUGCCUUAACCGGGCACGGUGUAAAUCCUACCCCCGACCGUGCUAACAGGUGGAGGAGGUUCCCUCGAGCCGUGUAUAGUAAUCGAACUGCCUCUCGUCAUACGAUCAAUCAAGCCGGGAGCUUCCUUACUCGACUUGGUGCGACGCGAACGUACAUUUCUUUAUCCGAUGAGAAGGGUCGCAUACGUCACUGUUGCGCGGAAUUCGCGAAUCCGCCCAAUAGCUGUGACACGCUCACGAUGACCCAUCCAGCGACACUUAACGGAAUUGUCGCUUUGGCCCGACAUUUUCGCAUAUUAUACCGCGUGCUCGUGGGAGAGCCUUUGAAGACAUUGAUAACAUGUGAUUCGGGAAUUUGUUCGCUCCCCCCGCACCACCCAAGCCUUCGGGGACCUUCGGUUAUGGUACUUCGGAUGCCGCCACGUACGAAGCCCCGCCCUUCUGCCGAGUCCAUAUGCCAUCGCGCUGUGAACUCGCGCUUGCACCUGUCAUUGUCUGUGAAAUGUCAUUAUCCAAACAGGUGUGGAGCGGCUACAUCUCAGGCCGUGAAGACUAAGCAAACCUCCCCCGCAGAGGACGUGGCACGGGGAGUUACGACAGAAGGAACGAUGUGUCACAGUAAGCAACACCGUCGUACGAUCGACUAUACGUCGAACUGGGGCGGUUUGAAGCUCUUAACCUCCAUGCCACCCUACACUGGGGCCGGAUGUUACUCUGGUUGUGAAUUGUUGAGCGCUUACACCUCCACCAAGUCCGAGAUUAGCCACCGAUUGAUUAACCGAGCAGCACAAUCUGUUCUGUCCAGAGCGGUGCAGGUCGCGCACUUCCUUAGACUGAGUUUCGAGCCCCUACUAUUUAAUCUCAUGACCAUUUAUGGCAGAGGAUCGAUUAGAGCAGUUAUCAGCCGUCAGACUCGCGUUCUUCAAUCACUCUGCCACGUCCACGCCUUCCGCAACUCUCAAGAAUCGAAGCCGGAACACACGCUCCCUUCCUCUGGUAGCGAUUCUUGCCACCCUCGACGACUCGAGUUUCCUUUUCUUCGUAUAGUACAUGGUGCCGUCGGCGACGAUUAUAUGUCCCUGAAACGUCCUACCCCUAAGGUUCUCUGGUCAUACCUACCGAAUCUCUUCAUAAGAAAGCGGGGGGGCAAAAGGAGACCUAGUACCGUAAAACGGCGCACGGAAUCGAGGGUAGGGCUAUCGAGGUAUGAGCGCACCCUGCAGCGACUUCGAUGGUGGGUAUCGGUCUGCCUACAGCUCAUAAUACAGAGGUUCGGAGCGGCCCGGUCCAAGCCUUGGUAUCGAUCGGAUUUCCGAGACCUCAAACUCCCCAUGCACAGUACCUACUACAAGUUCGUAGCCCGUGUCUCUGCGCCUUAUAUUAACAAACUGCUACCAACUAGUCGAGGAUCCGUUGGUCUCGUCGGCAUUUCACGGAACUCAGAUCGUUUUGGAAUCUCGAGAUACGCGGCGCGAGCCCCUUGGGCACAGCCUUCCGCUCGGGACGUUAACCGCCGUCUUUGCCGUGUUCGACGGCUCCCUAGCGUUACAAAGAUCCUACGCAGUGAAUGGCUGGUUGCAAGGAUUAAACCAGGAGCGUGUUGGUCGUACUUUCCAUUCAUUUACGCUACCCGUGUUGGAAGUAUUGACUGCUUGGUAGGUUUAACGAAGAGCAACCCGAAUACGCCGGAGGAGGACGUUUCCAACGCAUUACAGCCGUCCCGAAGUCGACUGACCGUCGCAACUACUUGA"

f = open ("standardrna.code.txt")
data = {}
for l in f:
    sl = l.split()
    key = sl[0]
    value = sl[2]
    data[key] = value    

f.close()

b1 = data['Base1']
b2 = data['Base2']
b3 = data['Base3']
aa = data['AAs']
st = data['Starts']

codons = {}

init = {}
n = len(aa)
for i in range(n):
    codon = b1[i] + b2[i] + b3[i]
    codons[codon] = aa[i]
    init[codon] = (st[i] == 'M')

def protein_seq(seq):
    seqlen = len(seq)
    aaseq = []
    for i in range(0,seqlen,3):
        codon = seq[i:i+3]
        aa = codons[codon]
        aaseq.append(aa)
    return ''.join(aaseq)

print protein_seq(inputseq)