def calcAbundance(alignmentFile, consensusFile, abundanceFile, abundancePercentFile, verbose):
print('Calculating the abundance matrix...')
alignment = AlignIO.read(alignmentFile, "fasta")
summary = SummaryInfo(alignment)
consensusSeq = SeqIO.read(consensusFile, 'fasta')
if (len(consensusSeq) == alignment.get_alignment_length()):
abundanceMatrix = summary.pos_specific_score_matrix(consensusSeq)
else:
with open(consensusFile, "w") as f:
SeqIO.write(SeqRecord( summary.dumb_consensus(), id='consensus'), f, "fasta")
abundanceMatrix = summary.pos_specific_score_matrix()
if verbose:
print("Abundance matrix (absolute values):")
print(str(abundanceMatrix))
with open(abundanceFile, 'w') as f:
f.write(str(abundanceMatrix))
for pos, abundance in enumerate(abundanceMatrix):
for res, value in abundance.items():
abundanceMatrix[pos][res] = 100.0 * float(value) / float(len(alignment))
if verbose:
print("Abundance matrix (percentages):")
print(str(abundanceMatrix))
with open(abundancePercentFile, 'w') as f:
f.write(str(abundanceMatrix))
print('OK')
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 _run_hmmer_single_thread(sequences, iter=3):
pbar = tqdm(range(len(sequences)), desc="sequences processed")
database = "data/Uniprot/uniprot_sprot.fasta"
outpth = os.path.join(tmp_dir, "align.sto")
for seqid, seq in sequences.items():
pbar.update(1)
cline = "jackhmmer -N %d --acc --noali -A %s - %s" % (iter, outpth, database)
child = subprocess.Popen(cline,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
universal_newlines=True,
shell=(sys.platform != "win32"))
stdout, _ = child.communicate(input=">%s\n%s" % (seqid, seq))
assert child.returncode == 0
info = SummaryInfo(AlignIO.read(outpth, "stockholm"))
pssm = info.pos_specific_score_matrix(chars_to_ignore=[GAP])
db.pssm.update_one({
"_id": seqid}, {
'$set': {"pssm": pssm.pssm, "seq": seq}
}, upsert=True)
pbar.close()
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 make_consensus(alignment_file, format_alignment):
from Bio import AlignIO
from Bio.Align.AlignInfo import SummaryInfo
format = format_alignment
alignment = AlignIO.read(alignment_file, format)
summary = SummaryInfo(alignment)
mat = summary.pos_specific_score_matrix()
consensus = ""
l = list()
for row in mat:
key, freq = max(row.items(), key=operator.itemgetter(1))
consensus = "".join([consensus, key])
l.append(freq / len(alignment._records))
consensus = consensus.strip("-")
return consensus, l
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)
