def _impl_test_aligner(self, name, fn):
filename = data_source_path(fn)
alignment = Alignment()
alignment.read_filepath(filename, 'FASTA')
aln = self.get_aligner('%s' % name)
if aln is None:
_LOG.warn("test%s skipped" % name)
return
a = aln.run(alignment,
tmp_dir_par=self.ts.top_level_temp,
delete_temps=True)
reference_fn = data_source_path('%s.%s' % (name, fn))
reference_aln = Alignment()
reference_aln.read_filepath(reference_fn, 'FASTA')
_LOG.debug('Checking results from %s against %s' % (name, reference_fn))
if reference_aln != a:
i = 1
while True:
nrfn = reference_fn + '.' + str(i)
if os.path.exists(nrfn):
reference_aln = Alignment()
reference_aln.read_filepath(nrfn, 'FASTA')
_LOG.debug('Checking results from %s against %s' % (name, nrfn))
if reference_aln == a:
self.assertEquals(reference_aln, a)
return True
i += 1
else:
self.assertEquals(reference_aln, a)
def _impl_test_aligner(self, name, fn):
filename = data_source_path(fn)
alignment = Alignment()
alignment.read_filepath(filename, 'FASTA')
aln = self.get_aligner('%s' % name)
if aln is None:
_LOG.warn("test%s skipped" % name)
return
a = aln.run(alignment,
tmp_dir_par=self.ts.top_level_temp,
delete_temps=True)
reference_fn = data_source_path('%s.%s' % (name, fn))
reference_aln = Alignment()
reference_aln.read_filepath(reference_fn, 'FASTA')
_LOG.debug('Checking results from %s against %s' %
(name, reference_fn))
if reference_aln != a:
i = 1
while True:
nrfn = reference_fn + '.' + str(i)
if os.path.exists(nrfn):
reference_aln = Alignment()
reference_aln.read_filepath(nrfn, 'FASTA')
_LOG.debug('Checking results from %s against %s' %
(name, nrfn))
if reference_aln == a:
self.assertEquals(reference_aln, a)
return True
i += 1
else:
self.assertEquals(reference_aln, a)
def test1000T(self):
sd = SequenceDataset()
fp = data_source_path('1000T.fasta')
sd.read(open(fp, 'rU'), file_format='FASTA', datatype='DNA')
fp = data_source_path('1000T.tree')
tree_list = read_and_encode_splits(sd.dataset, open(fp, "rU"))
self.assertEqual(len(tree_list), 1)
def setUp(self):
self.ts = TempFS()
self.ts.create_top_level_temp(prefix='treeEstimatorTest', parent=os.curdir)
self.filename = data_source_path('mafft.anolis.fasta')
self.alignment = Alignment()
self.alignment.read_filepath(data_source_path('mafft.anolis.fasta'),
'FASTA')
def test1000T(self):
sd = SequenceDataset()
fp = data_source_path('1000T.fasta')
sd.read(open(fp, 'rU'), file_format='FASTA', datatype='DNA')
fp = data_source_path('1000T.tree')
tree_list = read_and_encode_splits(sd.dataset, open(fp, "rU"))
self.assertEqual(len(tree_list), 1)
def testCentroidEdge(self):
sd = SequenceDataset()
fp = data_source_path('100T.fasta')
sd.read(open(fp, 'rU'), file_format='FASTA', datatype='DNA')
fp = data_source_path('100T.tree')
tree_list = read_and_encode_splits(sd.dataset, open(fp, "rU"))
self.assertEqual(len(tree_list), 1)
t = PhylogeneticTree(tree_list[0])
self._do_test_centroid(t)
def testConcatenateAlignments(self):
filename1 = data_source_path('small.fasta')
filename2 = data_source_path('small.fasta')
a = Alignment()
b = Alignment()
a.datatype = "DNA"
b.datatype = "DNA"
a.read_filepath(filename1, 'FASTA')
b.read_filepath(filename2, 'FASTA')
def testConcatenateAlignments(self):
filename1 = data_source_path('small.fasta')
filename2 = data_source_path('small.fasta')
a = Alignment()
b = Alignment()
a.datatype = "DNA"
b.datatype = "DNA"
a.read_filepath(filename1, 'FASTA')
b.read_filepath(filename2, 'FASTA')
def testCentroidEdge(self):
sd = SequenceDataset()
fp = data_source_path('100T.fasta')
sd.read(open(fp, 'rU'), file_format='FASTA', datatype='DNA')
fp = data_source_path('100T.tree')
tree_list = read_and_encode_splits(sd.dataset, open(fp, "rU"))
self.assertEqual(len(tree_list), 1)
t = PhylogeneticTree(tree_list[0])
self._do_test_centroid(t)
def setUp(self):
self.set_up()
self.tiny_rna = data_source_path("tinyrna.fasta")
self.small_rna = data_source_path("smallrna.fasta")
self.small_tree = data_source_path("small.tree")
self.tiny_aln_path = self.get_path(".marker001.tinyrna.aln")
self.small_aln_path = self.get_path(".marker001.smallrna.aln")
self.init_aln_path = self.get_path("_temp_iteration_initialsearch_seq_alignment.txt")
self.iter_aln_path = self.get_path("_temp_iteration_0_seq_alignment.txt")
self.cfg_path = self.get_path("_temp_sate_config.txt")
def setUp(self):
self.set_up()
self.tiny_rna = data_source_path('tinyrna.fasta')
self.small_rna = data_source_path('smallrna.fasta')
self.small_tree = data_source_path('small.tree')
self.tiny_aln_path = self.get_path('.marker001.tinyrna.aln')
self.small_aln_path = self.get_path('.marker001.smallrna.aln')
self.init_aln_path = self.get_path(
'_temp_iteration_initialsearch_seq_alignment.txt')
self.iter_aln_path = self.get_path(
'_temp_iteration_0_seq_alignment.txt')
self.cfg_path = self.get_path('_temp_sate_config.txt')
def setUp(self):
self.set_up()
self.dna = data_source_path("small.fasta")
self.rna = data_source_path("smallrna.fasta")
self.tree = data_source_path("small.tree")
self.dna_tmp = self.get_subdir("dna")
self.rna_tmp = self.get_subdir("rna")
self.dna_aln = self.get_path(name=".marker001.small.aln", parent_dir=self.dna_tmp)
self.dna_tree = self.get_path(name=".tre", parent_dir=self.dna_tmp)
self.rna_aln = self.get_path(name=".marker001.smallrna.aln", parent_dir=self.rna_tmp)
self.rna_tree = self.get_path(name=".tre", parent_dir=self.rna_tmp)
self.dna_score = self.get_path(name=".score.txt", parent_dir=self.dna_tmp)
self.rna_score = self.get_path(name=".score.txt", parent_dir=self.rna_tmp)
self.dna_tmp_aln = self.get_path(name="_temp_iteration_0_seq_alignment.txt", parent_dir=self.dna_tmp)
self.rna_tmp_aln = self.get_path(name="_temp_iteration_0_seq_alignment.txt", parent_dir=self.rna_tmp)
def _impl_test_tree_estimator(self, name, datatype, partitions, **kwargs):
num_cpus = kwargs.get('num_cpus', None)
filename = data_source_path('anolis.fasta')
md = MultiLocusDataset()
md.read_files(seq_filename_list=[filename],
datatype=datatype)
md.relabel_for_pasta()
# alignment = Alignment()
# alignment.read_filepath(filename, 'FASTA')
te = self.get_tree_estimator(name)
if te is None:
_LOG.warn("test%s skipped" % name)
return
# alignment.datatype = datatype
if num_cpus:
a = te.run(alignment=md,
partitions=partitions,
tmp_dir_par=self.ts.top_level_temp,
delete_temps=True,
num_cpus=num_cpus)
else:
a = te.run(alignment=md,
partitions=partitions,
tmp_dir_par=self.ts.top_level_temp,
delete_temps=True)
def testDiagnoseBogus(self):
fp = data_source_path('caenophidia_mos_bogus.fasta')
self.assertRaises(Exception,
summary_stats_from_parse, [fp],
["DNA", "RNA", "PROTEIN"],
careful_parse=False)
_LOG.warn(
"WARNING: summary_stats_from_parse does not distinguish between all bogus sequences in 'careful' mode"
)
def testAlignment(self):
filename = data_source_path('small.fasta')
alignment = Alignment()
alignment.read_filepath(filename, 'FASTA')
num_taxa = alignment.get_num_taxa()
self.assertEqual(num_taxa, 32)
alignment.write_filepath(filename+'.phy', 'PHYLIP')
alignment.write_unaligned_fasta(filename+'.raw')
alignment.sub_alignment( alignment.keys()[0:2] ).write_unaligned_fasta(filename+'.partial.raw')
def setUp(self):
self.set_up()
self.multi_dir = data_source_path("testmulti/")
self.multi_mixed_dir = os.path.join(self.multi_dir, "mixed")
self.in_path1 = os.path.join(self.multi_mixed_dir, "tinydna.fasta")
self.in_path2 = os.path.join(self.multi_mixed_dir, "tinyrna.fasta")
self.aln_path1 = self.get_path(".marker001.tinydna.aln")
self.aln_path2 = self.get_path(".marker002.tinyrna.aln")
self.cfg_path = self.get_path("_temp_sate_config.txt")
self.concat_path = self.get_path("_temp_iteration_0_seq_alignment.txt")
def setUp(self):
self.set_up()
self.multi_dir = data_source_path('testmulti/')
self.multi_mixed_dir = os.path.join(self.multi_dir, 'mixed')
self.in_path1 = os.path.join(self.multi_mixed_dir, 'tinydna.fasta')
self.in_path2 = os.path.join(self.multi_mixed_dir, 'tinyrna.fasta')
self.aln_path1 = self.get_path('.marker001.tinydna.aln')
self.aln_path2 = self.get_path('.marker002.tinyrna.aln')
self.cfg_path = self.get_path('_temp_sate_config.txt')
self.concat_path = self.get_path('_temp_iteration_0_seq_alignment.txt')
def testLongestBipartition(self):
treef = data_source_path('small.tree')
pt = self.phylogeneticTreeFromFile(treef, file_format='NEWICK')
self.assertEqual(pt.n_leaves, 32)
e = pt.get_longest_edge()
subtree1, subtree2 = pt.bipartition_by_edge(e)
leaf_num = [subtree1.n_leaves, subtree2.n_leaves]
leaf_num.sort()
self.assertEqual(leaf_num, [1, 31])
def testLongestBipartition(self):
treef = data_source_path('small.tree')
pt = self.phylogeneticTreeFromFile(treef, file_format='NEWICK')
self.assertEqual(pt.n_leaves, 32)
e = pt.get_longest_edge()
subtree1, subtree2 = pt.bipartition_by_edge(e)
leaf_num = [subtree1.n_leaves, subtree2.n_leaves]
leaf_num.sort()
self.assertEqual(leaf_num, [1, 31])
def _impl_test_merger(self, name):
filename = data_source_path('merger1.fasta')
alignment1 = Alignment()
alignment1.read_filepath(filename, 'FASTA')
filename = data_source_path('merger2.fasta')
alignment2 = Alignment()
alignment2.read_filepath(filename, 'FASTA')
aln = self.get_merger('%s merger' % name)
if aln is None:
_LOG.warn("test%s skipped" % name)
return
a = aln.run(alignment1,
alignment2,
tmp_dir_par=self.ts.top_level_temp,
delete_temps=True)
reference_fn = data_source_path('merger_result.fasta')
reference_aln = Alignment()
reference_aln.read_filepath(reference_fn, 'FASTA')
self.assertEquals(reference_aln, a)
def _impl_test_merger(self, name):
filename = data_source_path('merger1.fasta')
alignment1 = Alignment()
alignment1.read_filepath(filename, 'FASTA')
filename = data_source_path('merger2.fasta')
alignment2 = Alignment()
alignment2.read_filepath(filename, 'FASTA')
aln = self.get_merger('%s merger' % name)
if aln is None:
_LOG.warn("test%s skipped" % name)
return
a = aln.run(alignment1,
alignment2,
tmp_dir_par=self.ts.top_level_temp,
delete_temps=True)
reference_fn = data_source_path('merger_result.fasta')
reference_aln = Alignment()
reference_aln.read_filepath(reference_fn, 'FASTA')
self.assertEquals(reference_aln, a)
def setUp(self):
self.set_up()
data_file = data_source_path("tiny.fasta")
unicode_name = u"m\xe9ss\xfdp\xe4th"
self.tmp_sub_dir = self.get_subdir(unicode_name)
self.data_path = self.get_path(name=unicode_name + ".fasta", parent_dir=self.tmp_sub_dir)
src = open(data_file, "rU")
out = open(self.data_path, "w")
for line in src:
out.write(line)
src.close()
out.close()
def setUp(self):
self.set_up()
data_file = data_source_path("tiny.fasta")
space_name = "a path with a lot of spaces"
self.tmp_sub_dir = self.get_subdir(space_name)
self.data_path = self.get_path(name=space_name + ".fasta", parent_dir=self.tmp_sub_dir)
src = open(data_file, "rU")
out = open(self.data_path, "w")
for line in src:
out.write(line)
src.close()
out.close()
def testCentroidBipartition(self):
treef = data_source_path('diffDecomp.nex')
pt = self.phylogeneticTreeFromFile(treef, file_format='NEXUS')
# pt.add_n_leaf_des_attr()
self.assertEqual(pt.n_leaves, 484)
e = pt.get_centroid_edge()
subtree1, subtree2 = pt.bipartition_by_edge(e)
leaf_num = [subtree1.n_leaves, subtree2.n_leaves]
leaf_num.sort()
self.assertEqual(leaf_num, [231, 253])
def testCentroidBipartition(self):
treef = data_source_path('diffDecomp.nex')
pt = self.phylogeneticTreeFromFile(treef, file_format='NEXUS')
# pt.add_n_leaf_des_attr()
self.assertEqual(pt.n_leaves, 484)
e = pt.get_centroid_edge()
subtree1, subtree2 = pt.bipartition_by_edge(e)
leaf_num = [subtree1.n_leaves, subtree2.n_leaves]
leaf_num.sort()
self.assertEqual(leaf_num, [231, 253])
def testMulti(self):
if is_test_enabled(TestLevel.EXHAUSTIVE,
_LOG,
module_name=".".join([
self.__class__.__name__,
sys._getframe().f_code.co_name
])):
self._main_execution([
'-m', '-i',
data_source_path('testmulti'), '-o', self.ts.top_level_temp,
'--temporaries=%s' % self.ts.top_level_temp, '-j',
self.job_name, '--iter-limit=1'
])
def testDiagnoseMulti(self):
multi_dir = data_source_path('testmulti/caenophidia')
fp = os.path.join(multi_dir, 'caenophidia_mos.fasta')
fp2 = os.path.join(multi_dir, 'caenophidia_mos2.fasta')
s = summary_stats_from_parse([fp, fp2], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "PROTEIN")
self.assertEqual(s[1], [(114, 189), (109, 202)])
self.assertEqual(
s[2], 116
) # two taxa names were changed and 5 were deleted, so the union is 116
self.assertEqual(s[3], False)
fp3 = data_source_path('smallrna.fasta')
s = summary_stats_from_parse([fp3, fp3], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "RNA")
self.assertEqual(s[1], [(32, 1650), (32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception,
summary_stats_from_parse, [fp, fp3],
["DNA", "RNA", "PROTEIN"],
careful_parse=False)
_LOG.warn(
"WARNING: summary_stats_from_parse will read multi with dna and protein as entirely protein. MIXED data type support is needed!"
)
fp4 = data_source_path('small.fasta')
fp5 = data_source_path('smallunaligned.fasta')
s = summary_stats_from_parse([fp4, fp4], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650), (32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception,
summary_stats_from_parse, [fp, fp3],
["DNA", "RNA", "PROTEIN"],
careful_parse=False)
_LOG.warn(
"WARNING: summary_stats_from_parse will read multi with dna and protein as entirely protein. MIXED data type support is needed!"
)
fp4 = data_source_path('small.fasta')
fp5 = data_source_path('smallunaligned.fasta')
s = summary_stats_from_parse([fp4, fp5], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650), (32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], False)
self.assertRaises(Exception,
summary_stats_from_parse, [fp, fp3],
["DNA", "RNA", "PROTEIN"],
careful_parse=False)
_LOG.warn(
"WARNING: summary_stats_from_parse will read multi with dna and protein as entirely protein. MIXED data type support is needed!"
)
def setUp(self):
self.set_up()
data_file = data_source_path('tiny.fasta')
space_name = 'a path with a lot of spaces'
self.tmp_sub_dir = self.get_subdir(space_name)
self.data_path = self.get_path(name=space_name + '.fasta',
parent_dir=self.tmp_sub_dir)
src = open(data_file, 'rU')
out = open(self.data_path, 'w')
for line in src:
out.write(line)
src.close()
out.close()
def setUp(self):
self.set_up()
data_file = data_source_path('tiny.fasta')
unicode_name = 'm\xe9ss\xfdp\xe4th'
self.tmp_sub_dir = self.get_subdir(unicode_name)
self.data_path = self.get_path(name=unicode_name + '.fasta',
parent_dir=self.tmp_sub_dir)
src = open(data_file, 'rU')
out = open(self.data_path, 'w')
for line in src:
out.write(line)
src.close()
out.close()
def setUp(self):
self.set_up()
self.anolis_file = data_source_path('anolis.fasta')
self.caenophidia_file = data_source_path('caenophidia_mos.fasta')
self.multi_dir = data_source_path('testmulti/')
self.multi_aa_dir = os.path.join(self.multi_dir, 'caenophidia')
self.figwasp_dir = os.path.join(self.multi_dir, 'figwasps')
self.hummingbird_dir = os.path.join(self.multi_dir, 'hummingbirds')
self.ambig_dna = data_source_path('small.ambiguities.fasta')
self.ambig_dna_tree = data_source_path('small.tree')
self.ambig_aa = data_source_path('caenophidia_mos.ambiguities.fasta')
self.ambig_aa_tree = data_source_path('caenophidia_mos.tre')
def setUp(self):
self.set_up()
self.anolis_file = data_source_path('anolis.fasta')
self.caenophidia_file = data_source_path('caenophidia_mos.fasta')
self.multi_dir = data_source_path('testmulti/')
self.multi_aa_dir = os.path.join(self.multi_dir, 'caenophidia')
self.figwasp_dir = os.path.join(self.multi_dir, 'figwasps')
self.hummingbird_dir = os.path.join(self.multi_dir, 'hummingbirds')
self.ambig_dna = data_source_path('small.ambiguities.fasta')
self.ambig_dna_tree = data_source_path('small.tree')
self.ambig_aa = data_source_path('caenophidia_mos.ambiguities.fasta')
self.ambig_aa_tree = data_source_path('caenophidia_mos.tre')
def setUp(self):
self.set_up()
self.dna = data_source_path('small.fasta')
self.rna = data_source_path('smallrna.fasta')
self.tree = data_source_path('small.tree')
self.dna_tmp = self.get_subdir('dna')
self.rna_tmp = self.get_subdir('rna')
self.dna_aln = self.get_path(name='.marker001.small.aln',
parent_dir=self.dna_tmp)
self.dna_tree = self.get_path(name='.tre', parent_dir=self.dna_tmp)
self.rna_aln = self.get_path(name='.marker001.smallrna.aln',
parent_dir=self.rna_tmp)
self.rna_tree = self.get_path(name='.tre', parent_dir=self.rna_tmp)
self.dna_score = self.get_path(name='.score.txt',
parent_dir=self.dna_tmp)
self.rna_score = self.get_path(name='.score.txt',
parent_dir=self.rna_tmp)
self.dna_tmp_aln = self.get_path(
name='_temp_iteration_0_seq_alignment.txt',
parent_dir=self.dna_tmp)
self.rna_tmp_aln = self.get_path(
name='_temp_iteration_0_seq_alignment.txt',
parent_dir=self.rna_tmp)
def testDiagnoseProt(self):
fp = data_source_path("caenophidia_mos.fasta")
print fp
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "PROTEIN")
self.assertEqual(s[1], [(114, 189)])
self.assertEqual(s[2], 114)
self.assertEqual(s[3], False)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"], careful_parse=True)
self.assertEqual(s[0], "PROTEIN")
self.assertEqual(s[1], [(114, 189)])
self.assertEqual(s[2], 114)
self.assertEqual(s[3], False)
self.assertRaises(Exception, summary_stats_from_parse, [fp], ["DNA", "RNA"], careful_parse=False)
self.assertRaises(Exception, summary_stats_from_parse, [fp], ["DNA", "RNA"], careful_parse=True)
def testDiagnoseRNA(self):
fp = data_source_path("smallrna.fasta")
print fp
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "RNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"], careful_parse=True)
self.assertEqual(s[0], "RNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception, summary_stats_from_parse, [fp], ["DNA", "PROTEIN"], careful_parse=False)
_LOG.warn("WARNING: summary_stats_from_parse does not distinguish between RNA and DNA in 'careful' mode")
def testDiagnoseDNA(self):
fp = data_source_path("small.fasta")
print fp
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"], careful_parse=True)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception, summary_stats_from_parse, [fp], ["RNA"], careful_parse=False)
self.assertRaises(Exception, summary_stats_from_parse, [fp], ["RNA"], careful_parse=True)
def testMulti(self):
if is_test_enabled(
TestLevel.EXHAUSTIVE, _LOG, module_name=".".join([self.__class__.__name__, sys._getframe().f_code.co_name])
):
self._main_execution(
[
"-m",
"-i",
data_source_path("testmulti"),
"-o",
self.ts.top_level_temp,
"--temporaries=%s" % self.ts.top_level_temp,
"-j",
self.job_name,
"--iter-limit=1",
]
)
def testDiagnoseMulti(self):
multi_dir = data_source_path("testmulti/caenophidia")
fp = os.path.join(multi_dir, "caenophidia_mos.fasta")
fp2 = os.path.join(multi_dir, "caenophidia_mos2.fasta")
s = summary_stats_from_parse([fp, fp2], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "PROTEIN")
self.assertEqual(s[1], [(114, 189), (109, 202)])
self.assertEqual(s[2], 116) # two taxa names were changed and 5 were deleted, so the union is 116
self.assertEqual(s[3], False)
fp3 = data_source_path("smallrna.fasta")
s = summary_stats_from_parse([fp3, fp3], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "RNA")
self.assertEqual(s[1], [(32, 1650), (32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(
Exception, summary_stats_from_parse, [fp, fp3], ["DNA", "RNA", "PROTEIN"], careful_parse=False
)
_LOG.warn(
"WARNING: summary_stats_from_parse will read multi with dna and protein as entirely protein. MIXED data type support is needed!"
)
fp4 = data_source_path("small.fasta")
fp5 = data_source_path("smallunaligned.fasta")
s = summary_stats_from_parse([fp4, fp4], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650), (32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(
Exception, summary_stats_from_parse, [fp, fp3], ["DNA", "RNA", "PROTEIN"], careful_parse=False
)
_LOG.warn(
"WARNING: summary_stats_from_parse will read multi with dna and protein as entirely protein. MIXED data type support is needed!"
)
fp4 = data_source_path("small.fasta")
fp5 = data_source_path("smallunaligned.fasta")
s = summary_stats_from_parse([fp4, fp5], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650), (32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], False)
self.assertRaises(
Exception, summary_stats_from_parse, [fp, fp3], ["DNA", "RNA", "PROTEIN"], careful_parse=False
)
_LOG.warn(
"WARNING: summary_stats_from_parse will read multi with dna and protein as entirely protein. MIXED data type support is needed!"
)
def testDiagnoseDNA(self):
fp = data_source_path('small.fasta')
print(fp)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"],
careful_parse=True)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception,
summary_stats_from_parse, [fp], ["RNA"],
careful_parse=False)
self.assertRaises(Exception,
summary_stats_from_parse, [fp], ["RNA"],
careful_parse=True)
def testDiagnoseProt(self):
fp = data_source_path('caenophidia_mos.fasta')
print(fp)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "PROTEIN")
self.assertEqual(s[1], [(114, 189)])
self.assertEqual(s[2], 114)
self.assertEqual(s[3], False)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"],
careful_parse=True)
self.assertEqual(s[0], "PROTEIN")
self.assertEqual(s[1], [(114, 189)])
self.assertEqual(s[2], 114)
self.assertEqual(s[3], False)
self.assertRaises(Exception,
summary_stats_from_parse, [fp], ["DNA", "RNA"],
careful_parse=False)
self.assertRaises(Exception,
summary_stats_from_parse, [fp], ["DNA", "RNA"],
careful_parse=True)
def testDiagnoseRNA(self):
fp = data_source_path('smallrna.fasta')
print(fp)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "RNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"],
careful_parse=True)
self.assertEqual(s[0], "RNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception,
summary_stats_from_parse, [fp], ["DNA", "PROTEIN"],
careful_parse=False)
_LOG.warn(
"WARNING: summary_stats_from_parse does not distinguish between RNA and DNA in 'careful' mode"
)
def testDNAFasta(self):
sd = SequenceDataset()
fp = data_source_path('anolis.fasta')
sd.read(open(fp, 'rU'), file_format='FASTA', datatype='DNA')
def testDiagnoseBogus(self):
fp = data_source_path("caenophidia_mos_bogus.fasta")
self.assertRaises(Exception, summary_stats_from_parse, [fp], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
_LOG.warn(
"WARNING: summary_stats_from_parse does not distinguish between all bogus sequences in 'careful' mode"
)
def testDNAFasta(self):
sd = SequenceDataset()
fp = data_source_path('anolis.fasta')
sd.read(open(fp, 'rU'), file_format='FASTA', datatype='DNA')
def setUp(self):
self.set_up()
self.data = data_source_path("tiny.lowercase.fasta")
def setUp(self):
self.set_up()
self.data = data_source_path("tiny.fasta")
self.tree = data_source_path("tiny_name_mismatch.tre")
def setUp(self):
self.set_up()
self.data = data_source_path('tiny.fasta')
self.tree = data_source_path('tiny_name_mismatch.tre')
def setUp(self):
self.set_up()
self.data = data_source_path('tiny.lowercase.fasta')
