def test_alifold(self):
print "testing alifold()"
align = ["GCCAUCCGAGGGAAAGGUU", "GAUCGACAGCGUCU-AUCG", "CCGUCUUUAUGAGUCCGGC"]
(css, cen) = RNA.alifold(align)
self.assertEqual(css,"(((.(((...)))..))).")
self.assertEqual(RNA.consens_mis(align), "SMBHBHYDRBGDVWmVKBB")
RNA.free_alifold_arrays()
def Consensus(aln, ribosum):
'''Calculate the consensus MFE from an Biopython Alignment object'''
if ribosum == True:
RNA.cvar.ribo = 1
else:
RNA.cvar.ribo = 0
aln_seqs = []
for rec in aln:
aln_seqs.append(str(rec.seq))
cons_str, cons_en = RNA.alifold(aln_seqs)
return (cons_str, cons_en)
def SCI(aln, ribosum):
'''Calculate the Structure Conservation Index as done in RNAz
Args:
aln - AlignIO alignment object
Returns:
sci - structure conservation index
'''
aln_seqs = []
for rec in aln:
aln_seqs.append(str(rec.seq))
#if ARGS.v >= 1: print rec.seq
if ribosum == True:
RNA.cvar.ribo = 1
else:
RNA.cvar.ribo = 0
#Call AliFold
cons_str, cons_en = RNA.alifold(aln_seqs)
#if ARGS.v >= 1: print(cons_str, cons_en)
aln_e = 0
#Call RNAfold for single Sequences
for s in aln_seqs:
s = s.replace(
'-', '') #might be a problem for other gap chars, use regex :(
if s == '': continue #Exclude pure gaps
stru, en = RNA.fold(s)
aln_e += en
#sci = E_consensus / (1/N) * Sum(E_single seq)
try:
sci = float(cons_en) / (float(aln_e) / len(aln_seqs))
#if ARGS.v >= 1:
# print 'Mean E: ',( float(aln_e) / len(aln_seqs) ), 'Consensus E: ', cons_en #For Debug
except ZeroDivisionError:
sci = 0
#if ARGS.v >= 2: print 'Sum of all free energies = 0 (Caught ZeroDivisionError)'
return sci
import RNA
# The RNA sequence alignment
sequences = [
"CUGCCUCACAACGUUUGUGCCUCAGUUACCCGUAGAUGUAGUGAGGGU",
"CUGCCUCACAACAUUUGUGCCUCAGUUACUCAUAGAUGUAGUGAGGGU",
"---CUCGACACCACU---GCCUCGGUUACCCAUCGGUGCAGUGCGGGU"
]
# compute the consensus sequence
cons = RNA.consensus(sequences)
# predict Minmum Free Energy and corresponding secondary structure
(ss, mfe) = RNA.alifold(sequences)
# print output
print "%s\n%s [ %6.2f ]" % (cons, ss, mfe)
