def add_consensus(alignment, threshold=0.9, ambiguous='-', name='consensus'):
"""Add a consensus line"""
a = SummaryInfo(alignment)
# cons=a.dumb_consensus(threshold, ambiguous)
cons = a.gap_consensus(threshold, ambiguous)
alignment.extend([SeqRecord(cons, id=name, name=name)])
return alignment
def get_hist_ss_in_aln_as_string(alignment,type='Unknown',debug=0):
""" gets an annotation line as a string, borrowed from aln2html"""
sinfo=SummaryInfo(alignment)
cons=sinfo.gap_consensus(threshold=0.9, ambiguous='X')
features=get_hist_ss_in_aln_for_html(alignment,type=type,debug=0)
f_description=''
annot_line=[0,1,2]
if(features):
annot_line[0]=list(' '*len(cons))
annot_line[1]=list(' '*len(cons))
annot_line[2]=list(' '*len(cons))
keys=sorted(list(features.keys()),key=lambda x: x[0])
for k in keys:
if(features[k].get('description',0)):
f_description+='{0}-{1};'.format(features[k]['symbol'],features[k]['description'])
lev=features[k].get('level',0)
if(re.match('^\s+$',''.join(annot_line[lev][k[0]:k[1]+1]))):
annot_line[lev][k[0]:k[1]+1]=features[k]['symbol']*(k[1]-k[0]+1)
else:
lev+=1
if(re.match('^\s+$',''.join(annot_line[lev][k[0]:k[1]+1]))):
annot_line[lev][k[0]:k[1]+1]=features[k]['symbol']*(k[1]-k[0]+1)
else:
lev+=1
if(re.match('^\s+$',''.join(annot_line[lev][k[0]:k[1]+1]))):
annot_line[lev][k[0]:k[1]+1]=features[k]['symbol']*(k[1]-k[0]+1)
return annot_line[0] #other are ignored currently
def add_consensus(alignment,threshold=0.9, ambiguous='-',name='consensus'):
"""Add a consensus line"""
a=SummaryInfo(alignment)
# cons=a.dumb_consensus(threshold, ambiguous)
cons=a.gap_consensus(threshold, ambiguous)
alignment.extend([SeqRecord(cons,id=name,name=name)])
return alignment
def get_hist_ss_in_aln_as_string(alignment, type='Unknown', debug=0):
""" gets an annotation line as a string, borrowed from aln2html"""
sinfo = SummaryInfo(alignment)
cons = sinfo.gap_consensus(threshold=0.9, ambiguous='X')
features = get_hist_ss_in_aln_for_html(alignment, type=type, debug=0)
f_description = ''
annot_line = [0, 1, 2]
if (features):
annot_line[0] = list(' ' * len(cons))
annot_line[1] = list(' ' * len(cons))
annot_line[2] = list(' ' * len(cons))
keys = sorted(list(features.keys()), key=lambda x: x[0])
for k in keys:
if (features[k].get('description', 0)):
f_description += '{0}-{1};'.format(features[k]['symbol'],
features[k]['description'])
lev = features[k].get('level', 0)
if (re.match('^\s+$', ''.join(annot_line[lev][k[0]:k[1] + 1]))):
annot_line[lev][k[0]:k[1] +
1] = features[k]['symbol'] * (k[1] - k[0] + 1)
else:
lev += 1
if (re.match('^\s+$', ''.join(annot_line[lev][k[0]:k[1] + 1]))):
annot_line[lev][k[0]:k[1] +
1] = features[k]['symbol'] * (k[1] - k[0] + 1)
else:
lev += 1
if (re.match('^\s+$',
''.join(annot_line[lev][k[0]:k[1] + 1]))):
annot_line[lev][k[0]:k[1] +
1] = features[k]['symbol'] * (k[1] - k[0] +
1)
return annot_line[0] #other are ignored currently
def test_proteins(self):
alpha = HasStopCodon(Gapped(generic_protein, "-"), "*")
a = MultipleSeqAlignment([
SeqRecord(Seq("MHQAIFIYQIGYP*LKSGYIQSIRSPEYDNW-", alpha),
id="ID001"),
SeqRecord(Seq("MH--IFIYQIGYAYLKSGYIQSIRSPEY-NW*", alpha),
id="ID002"),
SeqRecord(Seq("MHQAIFIYQIGYPYLKSGYIQSIRSPEYDNW*", alpha),
id="ID003")
])
self.assertEqual(32, a.get_alignment_length())
s = SummaryInfo(a)
c = s.dumb_consensus(ambiguous="X")
self.assertEqual(str(c), "MHQAIFIYQIGYXXLKSGYIQSIRSPEYDNW*")
c = s.gap_consensus(ambiguous="X")
self.assertEqual(str(c), "MHXXIFIYQIGYXXLKSGYIQSIRSPEYXNWX")
m = s.pos_specific_score_matrix(chars_to_ignore=['-', '*'], axis_seq=c)
self.assertEqual(
str(m),
""" A D E F G H I K L M N P Q R S W Y
M 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
H 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
X 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2.0 0.0 0.0 0.0 0.0
X 2.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
F 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Y 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0
Q 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
G 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Y 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0
X 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2.0 0.0 0.0 0.0 0.0 0.0
X 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2.0
L 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
K 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
S 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0
G 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Y 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Q 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0
S 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
R 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0
S 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0
P 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0
E 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Y 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0
X 0.0 2.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
N 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0
W 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0
X 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
""")
ic = s.information_content(chars_to_ignore=['-', '*'])
self.assertAlmostEqual(ic, 133.061475107, places=6)
def test_nucleotides(self):
filename = "GFF/multi.fna"
format = "fasta"
alignment = AlignIO.read(filename, format, alphabet=unambiguous_dna)
summary = SummaryInfo(alignment)
c = summary.dumb_consensus(ambiguous="N")
self.assertEqual(str(c), "NNNNNNNN")
c = summary.gap_consensus(ambiguous="N")
self.assertEqual(str(c), "NNNNNNNN")
expected = {"A": 0.25, "G": 0.25, "T": 0.25, "C": 0.25}
m = summary.pos_specific_score_matrix(chars_to_ignore=["-"],
axis_seq=c)
self.assertEqual(
str(m), """ A C G T
N 2.0 0.0 1.0 0.0
N 1.0 1.0 1.0 0.0
N 1.0 0.0 2.0 0.0
N 0.0 1.0 1.0 1.0
N 1.0 2.0 0.0 0.0
N 0.0 2.0 1.0 0.0
N 1.0 2.0 0.0 0.0
N 0.0 2.0 1.0 0.0
""")
# Have a generic alphabet, without a declared gap char, so must tell
# provide the frequencies and chars to ignore explicitly.
ic = summary.information_content(e_freq_table=expected,
chars_to_ignore=["-"])
self.assertAlmostEqual(ic, 7.32029999423075, places=6)
def test_proteins(self):
a = MultipleSeqAlignment([
SeqRecord(Seq("MHQAIFIYQIGYP*LKSGYIQSIRSPEYDNW-"), id="ID001"),
SeqRecord(Seq("MH--IFIYQIGYAYLKSGYIQSIRSPEY-NW*"), id="ID002"),
SeqRecord(Seq("MHQAIFIYQIGYPYLKSGYIQSIRSPEYDNW*"), id="ID003")
])
self.assertEqual(32, a.get_alignment_length())
s = SummaryInfo(a)
c = s.dumb_consensus(ambiguous="X")
self.assertEqual(str(c), "MHQAIFIYQIGYXXLKSGYIQSIRSPEYDNW*")
c = s.gap_consensus(ambiguous="X")
self.assertEqual(str(c), "MHXXIFIYQIGYXXLKSGYIQSIRSPEYXNWX")
m = s.pos_specific_score_matrix(chars_to_ignore=["-", "*"], axis_seq=c)
self.assertEqual(
str(m),
""" A D E F G H I K L M N P Q R S W Y
M 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
H 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
X 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2.0 0.0 0.0 0.0 0.0
X 2.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
F 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Y 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0
Q 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
G 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Y 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0
X 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2.0 0.0 0.0 0.0 0.0 0.0
X 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2.0
L 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
K 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
S 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0
G 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Y 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Q 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0
S 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
R 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0
S 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0
P 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0
E 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Y 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0
X 0.0 2.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
N 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0
W 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0
X 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
""")
letters = IUPACData.protein_letters
base_freq = 1.0 / len(letters)
e_freq_table = {letter: base_freq for letter in letters}
ic = s.information_content(e_freq_table=e_freq_table,
chars_to_ignore=["-", "*"])
self.assertAlmostEqual(ic, 133.061475107, places=6)
def test_proteins(self):
alpha = HasStopCodon(Gapped(generic_protein, "-"), "*")
a = MultipleSeqAlignment([
SeqRecord(Seq("MHQAIFIYQIGYP*LKSGYIQSIRSPEYDNW-", alpha), id="ID001"),
SeqRecord(Seq("MH--IFIYQIGYAYLKSGYIQSIRSPEY-NW*", alpha), id="ID002"),
SeqRecord(Seq("MHQAIFIYQIGYPYLKSGYIQSIRSPEYDNW*", alpha), id="ID003")])
self.assertEqual(32, a.get_alignment_length())
s = SummaryInfo(a)
c = s.dumb_consensus(ambiguous="X")
self.assertEqual(str(c), "MHQAIFIYQIGYXXLKSGYIQSIRSPEYDNW*")
c = s.gap_consensus(ambiguous="X")
self.assertEqual(str(c), "MHXXIFIYQIGYXXLKSGYIQSIRSPEYXNWX")
m = s.pos_specific_score_matrix(chars_to_ignore=['-', '*'], axis_seq=c)
self.assertEqual(str(m), """ A D E F G H I K L M N P Q R S W Y
M 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
H 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
X 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2.0 0.0 0.0 0.0 0.0
X 2.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
F 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Y 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0
Q 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
G 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Y 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0
X 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2.0 0.0 0.0 0.0 0.0 0.0
X 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 2.0
L 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
K 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
S 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0
G 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Y 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Q 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0
S 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0
I 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
R 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0
S 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0
P 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0
E 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
Y 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0
X 0.0 2.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
N 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0 0.0 0.0 0.0 0.0 0.0
W 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 3.0 0.0
X 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
""")
ic = s.information_content(chars_to_ignore=['-', '*'])
self.assertAlmostEqual(ic, 133.061475107, places=6)
def trim_aln_gaps(alignment,threshold=0.8):
"""Removes positions with more than threshold gaps in alignment"""
a=SummaryInfo(alignment)
cons=a.gap_consensus(threshold=threshold, ambiguous='X')
new_aln=alignment[:,0:0]
for c,i in zip(cons,range(len(cons))):
if(c=='-'):
continue
else:
new_aln+=alignment[:,i:i+1]
return new_aln
def trim_aln_gaps(alignment, threshold=0.8):
"""Removes positions with more than threshold gaps in alignment"""
a = SummaryInfo(alignment)
cons = a.gap_consensus(threshold=threshold, ambiguous='X')
new_aln = alignment[:, 0:0]
for c, i in zip(cons, range(len(cons))):
if (c == '-'):
continue
else:
new_aln += alignment[:, i:i + 1]
return new_aln
def get_hist_ss_in_aln(alignment, type='Unknown', debug=0):
"""Returns sequence elements in histone alignment, all numbers assume first element in seq has number 0!!! Not like in PDB"""
#Let's extract consensus
if (debug):
print(alignment)
a = SummaryInfo(alignment)
cons = a.gap_consensus(threshold=0.5, ambiguous='X')
cons = Seq(str(cons).replace('-', 'X'))
if (debug):
print("Consensus")
print(cons)
hv, ss = get_hist_ss(cons, type, debug)
return hv, ss
def get_hist_ss_in_aln(alignment,type='Unknown',debug=0):
"""Returns sequence elements in histone alignment, all numbers assume first element in seq has number 0!!! Not like in PDB"""
#Let's extract consensus
if(debug):
print alignment
a=SummaryInfo(alignment)
cons=a.gap_consensus(threshold=0.5, ambiguous='X')
cons=Seq(str(cons).replace('-','X'))
if(debug):
print "Consensus"
print cons
hv,ss=get_hist_ss(cons,type,debug)
return hv,ss
def getConservedDomain(self):
cons = []
align = SummaryInfo(self.__alignment)
consenso = str(align.gap_consensus())
temp = ''
for i in range(len(consenso)):
if consenso[i] not in "X-":
temp += consenso[i]
else:
if temp != '':
cons.append(temp)
temp = ''
max_cons = ''
for i in cons:
if len(i) > len(max_cons): max_cons = i
return max_cons
def output_consensus(y, threshold_value, consensus_output_dir):
"""Takes as input an alignment file
and outputs a consensus sequence in fasta format"""
file_name = os.path.basename(y)
fasta_name = file_name.split('_align')[0]
alignment = AlignIO.read(open(y), "fasta")
summary_align = SummaryInfo(alignment)
consensus = summary_align.gap_consensus(threshold = threshold_value,
ambiguous = 'N',
consensus_alpha = alphabet,
require_multiple = 1)
consensus_seq = SeqRecord.SeqRecord(consensus,id=fasta_name+"_consensus")
output_file_name = str(consensus_output_dir+'/'+fasta_name+"_cons.fasta")
output_handle = open(output_file_name, "w")
print "Writing consensus sequence for " + fasta_name
SeqIO.write(consensus_seq, output_handle, "fasta")
output_handle.close()
def test_nucleotides(self):
filename = "GFF/multi.fna"
format = "fasta"
alignment = AlignIO.read(filename, format, alphabet=unambiguous_dna)
summary = SummaryInfo(alignment)
c = summary.dumb_consensus(ambiguous="N")
self.assertEqual(str(c), 'NNNNNNNN')
self.assertNotEqual(c.alphabet, unambiguous_dna)
self.assertTrue(isinstance(c.alphabet, DNAAlphabet))
c = summary.gap_consensus(ambiguous="N")
self.assertEqual(str(c), 'NNNNNNNN')
self.assertNotEqual(c.alphabet, unambiguous_dna)
self.assertTrue(isinstance(c.alphabet, DNAAlphabet))
expected = FreqTable({"A": 0.25, "G": 0.25, "T": 0.25, "C": 0.25},
FREQ, unambiguous_dna)
m = summary.pos_specific_score_matrix(chars_to_ignore=['-'],
axis_seq=c)
self.assertEqual(str(m), """ A C G T
N 2.0 0.0 1.0 0.0
N 1.0 1.0 1.0 0.0
N 1.0 0.0 2.0 0.0
N 0.0 1.0 1.0 1.0
N 1.0 2.0 0.0 0.0
N 0.0 2.0 1.0 0.0
N 1.0 2.0 0.0 0.0
N 0.0 2.0 1.0 0.0
""")
# Have a generic alphabet, without a declared gap char, so must tell
# provide the frequencies and chars to ignore explicitly.
ic = summary.information_content(e_freq_table=expected,
chars_to_ignore=['-'])
self.assertAlmostEqual(ic, 7.32029999423075, places=6)
def aln2html(msa,filename,features=None,title=None,description=True,field1w=20,field2w=35):
"""
This function outputs HTML from msa and annotates features.
msa - Biopython MSA,
filename - html file to output the result.
features - a dictionary of features, organized as follows:
{(begin,end):{'level':0(default),'symbol':'H','description':'desc'}}
if features overlap and not levels, they will be split to different levels.
Only three levels (0,1,2) are available.
"""
style="""
pre,td{margin: 0px;padding: 0px;border: 0px;}
.pos{color:blue;}
.neg{color:red;}
.pol{color:green;}
.hphob{color:grey;}
.def{color:black;}
.conserved{background:lightblue;}
.nonconserved{background:white;}
"""
sinfo=SummaryInfo(msa)
cons=sinfo.gap_consensus(threshold=0.9, ambiguous='X')
#Let's work on features
f_description=''
msatext=''
annot_line=[0,1,2]
if(features):
annot_line[0]=list(' '*len(cons))
annot_line[1]=list(' '*len(cons))
annot_line[2]=list(' '*len(cons))
keys=sorted(list(features.keys()),key=lambda x: x[0])
for k in keys:
if(features[k].get('description',0)):
f_description+='{0}-{1};'.format(features[k]['symbol'],features[k]['description'])
lev=features[k].get('level',0)
if(re.match('^\s+$',''.join(annot_line[lev][k[0]:k[1]+1]))):
annot_line[lev][k[0]:k[1]+1]=features[k]['symbol']*(k[1]-k[0]+1)
else:
lev+=1
if(re.match('^\s+$',''.join(annot_line[lev][k[0]:k[1]+1]))):
annot_line[lev][k[0]:k[1]+1]=features[k]['symbol']*(k[1]-k[0]+1)
else:
lev+=1
if(re.match('^\s+$',''.join(annot_line[lev][k[0]:k[1]+1]))):
annot_line[lev][k[0]:k[1]+1]=features[k]['symbol']*(k[1]-k[0]+1)
if(not re.match('^\s+$',''.join(annot_line[2]))):
msatext='<TR><TD><PRE>{0:<{field1w}}</PRE></TD>'.format('annotation',field1w=field1w+2)
if(description):
msatext+='<TD><PRE>{0:<{field2w}}</PRE></TD>'.format('level 2',field2w=field2w+2)
for c in annot_line[2]:
msatext+='<TD><PRE>{0}</PRE></TD>'.format(c)
msatext+='</TR>'
if(not re.match('^\s+$',''.join(annot_line[1]))):
msatext='<TR><TD><PRE>{0:<{field1w}}</PRE></TD>'.format('annotation',field1w=field1w+2)
if(description):
msatext+='<TD><PRE>{0:<{field2w}}</PRE></TD>'.format('level 1',field2w=field2w+2)
for c in annot_line[1]:
msatext+='<TD><PRE>{0}</PRE></TD>'.format(c)
msatext+='</TR>'
if(not re.match('^\s+$',''.join(annot_line[0]))):
msatext='<TR><TD><PRE>{0:<{field1w}}</PRE></TD>'.format('annotation',field1w=field1w+2)
if(description):
msatext+='<TD><PRE>{0:<{field2w}}</PRE></TD>'.format('level 0',field2w=field2w+20)
for c in annot_line[0]:
msatext+='<TD><PRE>{0}</PRE></TD>'.format(c)
msatext+='</TR>'
f_description+='<BR><BR>'
for s in msa:
if(re.search(r'\d\d+',s.id)):
gi=re.search(r'(\d\d+)',s.id).group(1)
line='<TR><TD><PRE><a href="http://www.ncbi.nlm.nih.gov/protein/?term={0}">{1:<{field1w}}</a></PRE></TD>'.format(gi,s.id[:field1w],field1w=field1w+2)
if(description):
line+='<TD><PRE>{0:<{field2w}}</PRE></TD>'.format(s.description[:field2w],field2w=field2w+2)
else:
line='<TR><TD><PRE>{0:<{field1w}}</PRE></TD>'.format(s.id[:field1w],field1w=field1w+2)
if(description):
line+='<TD><PRE>{0:<{field2w}}</PRE></TD>'.format(s.description[:field2w],field1w=field1w+2)
for c,i in zip(s.seq,range(len(s.seq))):
line+='<TD><PRE class="{0} {1}">{2}</PRE></TD>'.format(restypedict.get(c,'def'),'conserved' if c==cons[i] and c!='-' else 'nonconserved',c)
line+='</TR>'
msatext=msatext+line
a=open(filename,'w')
a.write("""
<!DOCTYPE html>
<HTML>
<HEAD>
<META http-equiv="Content-Type" content="text/html; charset=utf-8"/>
<TITLE>MultipleSequenceAlignment</TITLE>
<style>
{style}
</style>
</HEAD>
<BODY style="background-color:white; color:black; a:link:blue; a:active:red; a:visited:purple">
{title}<BR><BR>
{features}
<TABLE style="border:0px; border-spacing:0px; background-color:white; color:black; a:link:blue; a:active:red; a:visited:purple;">
{msatext}
</TABLE>
</BODY>
</HTML>
""".format(\
title=title,\
msatext=msatext,\
style=style,\
features=f_description
))
a.close()
def getPerc(self):
align = SummaryInfo(self.__alignment)
return float(1 - (align.gap_consensus().count("X") +
align.gap_consensus().count("-")) /
len(str(align.gap_consensus())))
def getConsenso(self):
align = SummaryInfo(self.__alignment)
return align.gap_consensus()
