def test_unaligned_muscle(self):
if not functions.which('muscle'):
_LOG.warning('muscle not found... skipping tests.')
return
seq1 = SeqRecord(Seq('AC--GTNAC-TYATR'), id='1')
seq2 = SeqRecord(Seq('ACN-GTAAC--CATT'), id='2')
# 'ACGTNACTYATR'
# 'ACNGTAACCATT'
diffs, l = seqstats.get_differences(seq1, seq2, aligned = False,
ignore_gaps = False,
aligner_tools = ['muscle'])
e = {11: ('R', 'T'),
3: ('T', 'G'),
6: ('C', 'A'),
7: ('T', 'C')}
self.assertEqual(diffs, e)
self.assertEqual(l, 12)
seq1 = SeqRecord(Seq('ATCCGT'), id='1')
seq2 = SeqRecord(Seq('ACCGT'), id='2')
diffs, l = seqstats.get_differences(seq1, seq2, aligned = False,
ignore_gaps = True,
aligner_tools = ['muscle'])
self.assertEqual(diffs, {})
self.assertEqual(l, 5)
diffs, l = seqstats.get_differences(seq1, seq2, aligned = False,
ignore_gaps = False,
aligner_tools = ['muscle'])
self.assertEqual(diffs, {1: ('T', '-')})
self.assertEqual(l, 6)
def test_unaligned_muscle(self):
if not functions.which('muscle'):
_LOG.warning('muscle not found... skipping tests.')
return
distance_iter = seqstats.sample_distance_iter(
seq_iter = self.seqs,
sample_size = 2,
per_site = False,
aligned = False,
ignore_gaps = True,
aligner_tools = ['muscle'])
for i, (seq1, seq2, d, drc) in enumerate(distance_iter):
self.assertEqual(
self.expected[seq1.id][seq2.id],
d)
self.assertEqual(i, 5)
distance_iter = seqstats.sample_distance_iter(
seq_iter = self.seqs,
sample_size = 2,
per_site = True,
aligned = False,
ignore_gaps = True,
aligner_tools = ['muscle'])
for i, (seq1, seq2, d, drc) in enumerate(distance_iter):
self.assertAlmostEqual(
self.expected[seq1.id][seq2.id] / 4.0,
d)
self.assertEqual(i, 5)
def test_unaligned_muscle(self):
if not functions.which('muscle'):
_LOG.warning('muscle not found... skipping tests.')
return
seq1 = SeqRecord(Seq('AC--GTNAC-TYATR'), id='1')
seq2 = SeqRecord(Seq('ACN-GTAAC--CATT'), id='2')
# 'ACGTNACTYATR'
# 'ACNGTAACCATT'
d = seqstats.distance(seq1, seq2, per_site = False, aligned = False,
ignore_gaps = False,
aligner_tools = ['muscle'])
self.assertEqual(d, 4)
dps = seqstats.distance(seq1, seq2, per_site = True, aligned = False,
ignore_gaps = False,
aligner_tools = ['muscle'])
self.assertAlmostEqual(dps, 4 / float(12))
seq1 = SeqRecord(Seq('ATCCGT'), id='1')
seq2 = SeqRecord(Seq('ACCGT'), id='2')
d = seqstats.distance(seq1, seq2, per_site = False, aligned = False,
ignore_gaps = True,
aligner_tools = ['muscle'])
self.assertEqual(d, 0)
dps = seqstats.distance(seq1, seq2, per_site = True, aligned = False,
ignore_gaps = True,
aligner_tools = ['muscle'])
self.assertEqual(dps, 0.0)
d = seqstats.distance(seq1, seq2, per_site = False, aligned = False,
ignore_gaps = False,
aligner_tools = ['muscle'])
self.assertEqual(d, 1)
dps = seqstats.distance(seq1, seq2, per_site = True, aligned = False,
ignore_gaps = False,
aligner_tools = ['muscle'])
self.assertEqual(dps, 1 / float(6))
def test_rev_comp_gappy_muscle(self):
if not functions.which('muscle'):
_LOG.warning('muscle not found... skipping tests.')
return
self.rc_seqs = dataio.get_buffered_seq_iter([self.gappy_path])
d, e = seqsum.summarize_distances(self.rc_seqs,
sample_size=5,
per_site=False,
aligned=False,
ignore_gaps=True,
do_full_alignment=False,
aligner_tools=['muscle'],
full_aligner_tools=None)
self.assertTrue(len(e) < 1)
self.assertEqual(len(d), 31)
def __init__(self, exe='muscle', out_path=None, **kwargs):
self.__class__.count += 1
self.name = self.__class__.__name__ + '-' + str(self.count)
self.exe = functions.which(exe)
if not self.exe:
raise errors.ExternalToolNotFoundError(
'Cannot find muscle executable')
_LOG.debug('{0}: Using exe {1!r}'.format(self.name, self.exe))
self.kwargs = kwargs
if ('input' in self.kwargs) or ('out' in self.kwargs):
raise ValueError('MuscleAligner does not accept keyword '
'arguments `input`/`out`.')
if out_path:
out_path = expand_path(out_path)
self.out_path = out_path
self.cmd = None
def __init__(self, exe='mafft', out_path=None, **kwargs):
self.__class__.count += 1
self.name = self.__class__.__name__ + '-' + str(self.count)
self.exe = functions.which(exe)
if not self.exe:
raise errors.ExternalToolNotFoundError(
'Cannot find mafft executable')
_LOG.debug('{0}: Using exe {1!r}'.format(self.name, self.exe))
self.kwargs = kwargs
if 'input' in self.kwargs:
raise ValueError('MafftAligner does not accept the keyword '
'argument `input`.')
if not self.kwargs:
self.kwargs = {'auto': True}
self.out_path = out_path
self.cmd = None
def __init__(self, exe = 'muscle', out_path = None, **kwargs):
self.__class__.count += 1
self.name = self.__class__.__name__ + '-' + str(self.count)
self.exe = functions.which(exe)
if not self.exe:
raise errors.ExternalToolNotFoundError(
'Cannot find muscle executable')
_LOG.debug('{0}: Using exe {1!r}'.format(self.name, self.exe))
self.kwargs = kwargs
if ('input' in self.kwargs) or ('out' in self.kwargs):
raise ValueError('MuscleAligner does not accept keyword '
'arguments `input`/`out`.')
if out_path:
out_path = expand_path(out_path)
self.out_path = out_path
self.cmd = None
def __init__(self, exe = 'mafft', out_path = None, **kwargs):
self.__class__.count += 1
self.name = self.__class__.__name__ + '-' + str(self.count)
self.exe = functions.which(exe)
if not self.exe:
raise errors.ExternalToolNotFoundError(
'Cannot find mafft executable')
_LOG.debug('{0}: Using exe {1!r}'.format(self.name, self.exe))
self.kwargs = kwargs
if 'input' in self.kwargs:
raise ValueError('MafftAligner does not accept the keyword '
'argument `input`.')
if not self.kwargs:
self.kwargs = {'auto': True}
self.out_path = out_path
self.cmd = None
def test_full_alignment_muscle(self):
if not functions.which('muscle'):
_LOG.warning('muscle not found... skipping tests.')
return
d, e = seqsum.summarize_distances(self.seqs,
sample_size=0,
per_site=False,
aligned=False,
ignore_gaps=True,
do_full_alignment=True,
aligner_tools=['muscle'])
self.assertEqual(e, [])
self.assertEqual(sorted(d.keys()), sorted(self.expected_means.keys()))
for k in iterkeys(d):
self.assertEqual(d[k].maximum, self.expected_maxs[k])
self.assertAlmostEqual(d[k].mean, self.expected_means[k])
def test_rev_comp_error_mafft_full(self):
if not functions.which('mafft'):
_LOG.warning('mafft not found... skipping tests.')
return
self.rc_seqs = dataio.get_buffered_seq_iter([self.rc_path])
d, e = seqsum.summarize_distances(self.rc_seqs,
sample_size=0,
per_site=False,
aligned=False,
ignore_gaps=False,
do_full_alignment=True,
aligner_tools=['mafft'],
full_aligner_tools=['mafft'])
self.assertEqual(len(e), 11)
for rce in e:
self.assertTrue('Homo_sapiens' in rce)
self.assertEqual(len(d), 12)