def test_msa_to_stockholm_extensive(self):
fp = get_data_path('stockholm_all_data_types')
msa = TabularMSA([DNA('GAGGCCATGCCCAGGTGAAG',
metadata=OrderedDict([('DT', 'February 1, 2016'),
('NM', 'Unknown')])),
DNA('ACCTGAGCCACAGTAGAAGT'),
DNA('CCCTTCGCTGGAAATGTATG',
metadata={'DT': 'Unknown'},
positional_metadata=OrderedDict([('AS',
list('CCGAAAGT'
'CGTTCGA'
'AAATG')),
('SS',
list('GGCGAGTC'
'GTTCGAGC'
'TGG'
'C'))]))],
metadata=OrderedDict([('NM', 'Kestrel Gorlick'),
('DT', 'February 11, 2016'),
('FN', 'Writer test file')]),
positional_metadata=OrderedDict([('AS_cons',
list('CGTTCGTTCTAAC'
'AATTCCA')),
('SS_cons',
list('GGCGCTACGACCT'
'ACGACCG'))]),
index=['seq1', 'seq2', 'seq3'])
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_rn_not_list_of_refs_error(self):
msa = TabularMSA([], metadata={'RN': '1'})
with self.assertRaisesRegex(
StockholmFormatError, r"Expected 'RN'.*list of reference"
".*got '1'"):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_msa_to_stockholm_multiple_references(self):
fp = get_data_path('stockholm_multiple_references')
msa = TabularMSA(
[],
metadata={'RN': [OrderedDict([('RM', '123456789'),
('RT', 'Title 1'),
('RA', 'Author 1'),
('RL', 'Location 1'),
('RC', 'Comment 1')]),
OrderedDict([('RM', '987654321'),
('RT', 'Title 2'),
('RA', 'Author 2'),
('RL', 'Location 2'),
('RC', 'Comment 2')]),
OrderedDict([('RM', '132465879'),
('RT', 'Title 3'),
('RA', 'Author 3'),
('RL', 'Location 3'),
('RC', 'Comment 3')])]})
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_rn_not_list_of_refs_error(self):
msa = TabularMSA([], metadata={'RN': '1'})
with self.assertRaisesRegex(StockholmFormatError,
r"Expected 'RN'.*list of reference"
".*got '1'"):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_unoriginal_index_error(self):
msa = TabularMSA([DNA('ATCGCCAGCT'), DNA('TTGTGCTGGC')],
index=['seq1', 'seq1'])
with self.assertRaisesRegex(StockholmFormatError,
'index labels must be unique.'):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_unoriginal_index_error(self):
msa = TabularMSA(
[DNA('ATCGCCAGCT'), DNA('TTGTGCTGGC')], index=['seq1', 'seq1'])
with self.assertRaisesRegex(StockholmFormatError,
r'index labels must be unique.'):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_msa_to_stockholm_extensive(self):
fp = get_data_path('stockholm_all_data_types')
msa = TabularMSA([
DNA('GAGGCCATGCCCAGGTGAAG',
metadata=OrderedDict([('DT', 'February 1, 2016'),
('NM', 'Unknown')])),
DNA('ACCTGAGCCACAGTAGAAGT'),
DNA('CCCTTCGCTGGAAATGTATG',
metadata={'DT': 'Unknown'},
positional_metadata=OrderedDict(
[('AS', list('CCGAAAGT'
'CGTTCGA'
'AAATG')),
('SS', list('GGCGAGTC'
'GTTCGAGC'
'TGG'
'C'))]))
],
metadata=OrderedDict([('NM', 'Kestrel Gorlick'),
('DT', 'February 11, 2016'),
('FN', 'Writer test file')]),
positional_metadata=OrderedDict([
('AS_cons', list('CGTTCGTTCTAAC'
'AATTCCA')),
('SS_cons', list('GGCGCTACGACCT'
'ACGACCG'))
]),
index=['seq1', 'seq2', 'seq3'])
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_msa_to_stockholm_multiple_references(self):
fp = get_data_path('stockholm_multiple_references')
msa = TabularMSA(
[],
metadata={'RN': [OrderedDict([('RM', '123456789'),
('RT', 'Title 1'),
('RA', 'Author 1'),
('RL', 'Location 1'),
('RC', 'Comment 1')]),
OrderedDict([('RM', '987654321'),
('RT', 'Title 2'),
('RA', 'Author 2'),
('RL', 'Location 2'),
('RC', 'Comment 2')]),
OrderedDict([('RM', '132465879'),
('RT', 'Title 3'),
('RA', 'Author 3'),
('RL', 'Location 3'),
('RC', 'Comment 3')])]})
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_handles_missing_metadata_efficiently(self):
msa = TabularMSA([DNA('ACTG'), DNA('GTCA')], index=['seq1', 'seq2'])
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
self.assertIsNone(msa._metadata)
self.assertIsNone(msa._positional_metadata)
self.assertIsNone(msa[0]._metadata)
self.assertIsNone(msa[0]._positional_metadata)
def test_invalid_reference_tag_error(self):
msa = TabularMSA([], metadata={'RN': [OrderedDict([('RL', 'Flagstaff'),
('foo', 'bar')])]})
with self.assertRaisesRegex(StockholmFormatError,
"Invalid reference.*foo' found in.*1.*Vali"
"d reference tags are:"):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_invalid_reference_tag_error(self):
msa = TabularMSA([], metadata={'RN': [OrderedDict([('RL', 'Flagstaff'),
('foo', 'bar')])]})
with self.assertRaisesRegex(StockholmFormatError,
r"Invalid reference.*foo' found "
"in.*1.*Valid reference tags are:"):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_msa_to_stockholm_single_tree(self):
fp = get_data_path('stockholm_single_tree_without_id')
msa = TabularMSA([], metadata=OrderedDict([('NH', 'ABCD')]))
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_round_trip_empty(self):
fp = get_data_path('stockholm_no_data')
msa = _stockholm_to_tabular_msa(fp, constructor=Protein)
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_round_trip_empty(self):
fp = get_data_path('stockholm_no_data')
msa = _stockholm_to_tabular_msa(fp, constructor=Protein)
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_msa_to_stockholm_empty(self):
fp = get_data_path('stockholm_no_data')
msa = TabularMSA([])
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_round_trip_nonstring_index_values(self):
fp = get_data_path('stockholm_nonstring_labels')
msa = _stockholm_to_tabular_msa(fp, constructor=DNA)
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_round_trip_nonstring_index_values(self):
fp = get_data_path('stockholm_nonstring_labels')
msa = _stockholm_to_tabular_msa(fp, constructor=DNA)
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_msa_to_stockholm_minimal(self):
fp = get_data_path('stockholm_minimal')
msa = TabularMSA([DNA('TGTGTCGCAGTTGTCGTTTG')], index=['0235244'])
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_rn_data_not_in_dict_error(self):
msa = TabularMSA([], metadata={'RN': [OrderedDict([('RL',
'Flagstaff')]),
'Incorrect Item']})
with self.assertRaisesRegex(StockholmFormatError,
"Expected reference information.*stored"
" as a dictionary, found.*2 stored as "
"'str'"):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_msa_to_stockholm_single_tree_as_dict(self):
fp = get_data_path('stockholm_single_tree_with_id')
msa = TabularMSA([], metadata={'NH': {'tree1': 'ABCD'}})
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_msa_to_stockholm_empty(self):
fp = get_data_path('stockholm_no_data')
msa = TabularMSA([])
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_msa_to_stockholm_minimal(self):
fp = get_data_path('stockholm_minimal')
msa = TabularMSA([DNA('TGTGTCGCAGTTGTCGTTTG')], index=['0235244'])
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_rn_data_not_in_dict_error(self):
msa = TabularMSA([], metadata={'RN': [OrderedDict([('RL',
'Flagstaff')]),
'Incorrect Item']})
with self.assertRaisesRegex(StockholmFormatError,
r"Expected reference information.*stored"
" as a dictionary, found.*2 stored as "
"'str'"):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_msa_to_stockholm_single_tree(self):
fp = get_data_path('stockholm_single_tree_without_id')
msa = TabularMSA([], metadata=OrderedDict([('NH', 'ABCD')]))
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_msa_to_stockholm_single_tree_as_dict(self):
fp = get_data_path('stockholm_single_tree_with_id')
msa = TabularMSA([], metadata={'NH': {'tree1': 'ABCD'}})
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_msa_to_stockholm_data_only(self):
fp = get_data_path('stockholm_data_only')
msa = TabularMSA([RNA('ACUCCGACAUGCUCC'),
RNA('UAGUGCCGAACGCUG'),
RNA('GUGUGGGCGUGAUUC')],
index=['seq1', 'seq2', 'seq3'])
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_msa_to_stockholm_data_only(self):
fp = get_data_path('stockholm_data_only')
msa = TabularMSA([RNA('ACUCCGACAUGCUCC'),
RNA('UAGUGCCGAACGCUG'),
RNA('GUGUGGGCGUGAUUC')],
index=['seq1', 'seq2', 'seq3'])
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_gc_wrong_dataframe_item_length_error(self):
seq1 = list('GAGCAAGCCACTAGA')
seq1.append('GG')
pos_metadata_dataframe = pd.DataFrame({'AC': seq1,
'SS': list('TCCTTGAACTACCCGA'),
'AS': list('TCAGCTCTGCAGCGTT')})
msa = TabularMSA([DNA('TCCTTGAACTACCCGA')],
positional_metadata=pos_metadata_dataframe)
with self.assertRaisesRegex(StockholmFormatError,
'Multiple sequence alignment positional '
'metadata.*must contain a single character'
'.*Found value\(s\) in column AC'):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_gc_wrong_dataframe_item_length_error(self):
seq1 = list('GAGCAAGCCACTAGA')
seq1.append('GG')
pos_metadata_dataframe = pd.DataFrame({'AC': seq1,
'SS': list('TCCTTGAACTACCCGA'),
'AS': list('TCAGCTCTGCAGCGTT')})
msa = TabularMSA([DNA('TCCTTGAACTACCCGA')],
positional_metadata=pos_metadata_dataframe)
with self.assertRaisesRegex(StockholmFormatError,
'Multiple sequence alignment positional '
'metadata.*must contain a single character'
'.*Found value\(s\) in column AC'):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_msa_to_stockholm_multiple_trees(self):
fp = get_data_path('stockholm_multiple_trees')
msa = TabularMSA([],
metadata=OrderedDict([('NH',
OrderedDict([('tree1', 'ABCD'),
('tree2', 'EFGH'),
('tree3', 'IJKL')
]))]))
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_msa_to_stockholm_single_reference(self):
fp = get_data_path('stockholm_single_reference')
msa = TabularMSA(
[],
metadata={'RN': [OrderedDict([('RM', '123456789'),
('RT', 'A Title'),
('RA', 'The Author'),
('RL', 'A Location'),
('RC', 'Comment')])]})
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_msa_to_stockholm_nonstring_values(self):
fp = get_data_path('stockholm_nonstring_labels')
msa = TabularMSA([DNA('ACTG', metadata=OrderedDict([(8, 123)]),
positional_metadata=OrderedDict([(1.0,
[1, 2, 3, 4])])
)],
metadata=OrderedDict([(1.3, 2857)]),
positional_metadata=OrderedDict([(25, [4, 3, 2, 1])]),
index=[11214])
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_msa_to_stockholm_nonstring_values(self):
fp = get_data_path('stockholm_nonstring_labels')
msa = TabularMSA([DNA('ACTG', metadata=OrderedDict([(8, 123)]),
positional_metadata=OrderedDict([(1.0,
[1, 2, 3, 4])])
)],
metadata=OrderedDict([(1.3, 2857)]),
positional_metadata=OrderedDict([(25, [4, 3, 2, 1])]),
index=[11214])
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_msa_to_stockholm_multiple_trees(self):
fp = get_data_path('stockholm_multiple_trees')
msa = TabularMSA([], metadata=OrderedDict([('NH',
OrderedDict([('tree1',
'ABCD'),
('tree2',
'EFGH'),
('tree3',
'IJKL')]))]))
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_msa_to_stockholm_single_reference(self):
fp = get_data_path('stockholm_single_reference')
msa = TabularMSA(
[],
metadata={'RN': [OrderedDict([('RM', '123456789'),
('RT', 'A Title'),
('RA', 'The Author'),
('RL', 'A Location'),
('RC', 'Comment')])]})
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
obs = fh.getvalue()
fh.close()
with io.open(fp) as fh:
exp = fh.read()
self.assertEqual(obs, exp)
def test_unoriginal_gc_feature_names_error(self):
pos_metadata_dataframe = pd.DataFrame.from_items([
('AC', list('GAGCAAGCCACTA'
'GA')), ('SS', list('TCCTTGAACTACC'
'CG')),
('SS', list('TCAGCTCTGCAGC'
'GT')), ('AC', list('GTCAGGCGCTCGG'
'TG'))
])
msa = TabularMSA([DNA('CCCCTGCTTTCGTAG')],
positional_metadata=pos_metadata_dataframe)
with self.assertRaisesRegex(
StockholmFormatError, 'Multiple sequence alignment positional '
'metadata.*must be unique. Found 2 '
'duplicate'):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_gr_wrong_dataframe_item_length_error(self):
seq1 = list('GAGCAAGCCACTAGA')
seq1.append('GG')
pos_metadata_dataframe = pd.DataFrame({
'AC': seq1,
'SS': list('TCCTTGAACTACCCGA'),
'AS': list('TCAGCTCTGCAGCGTT')
})
msa = TabularMSA([
DNA('TCCTTGAACTACCCGA', positional_metadata=pos_metadata_dataframe)
])
with six.assertRaisesRegex(
self, StockholmFormatError,
'Sequence-specific positional metadata.*'
'must contain a single character.*Found '
'value\(s\) in column AC'):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_unoriginal_gr_feature_names_error(self):
pos_metadata_dataframe = pd.DataFrame.from_items([
('AC', list('GAGCAAGCCACTA'
'GA')), ('SS', list('TCCTTGAACTACC'
'CG')),
('AS', list('TCAGCTCTGCAGC'
'GT')), ('SS', list('GTCAGGCGCTCGG'
'TG'))
])
msa = TabularMSA([
DNA('CGTCAATCTCGAACT', positional_metadata=pos_metadata_dataframe)
],
index=['seq1'])
with self.assertRaisesRegex(
StockholmFormatError, 'Sequence-specific positional metadata.*'
'must be unique. Found 1 duplicate'):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_unoriginal_gc_feature_names_error(self):
pos_metadata_dataframe = pd.DataFrame(
[
list('GAGCAAGCCACTAGA'),
list('TCCTTGAACTACCCG'),
list('TCAGCTCTGCAGCGT'),
list('GTCAGGCGCTCGGTG')
],
index=['AC', 'SS', 'SS', 'AC']
).T
msa = TabularMSA([DNA('CCCCTGCTTTCGTAG')],
positional_metadata=pos_metadata_dataframe)
with self.assertRaisesRegex(StockholmFormatError,
r'Multiple sequence alignment positional '
'metadata.*must be unique. Found 2 '
'duplicate'):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
def test_unoriginal_gr_feature_names_error(self):
pos_metadata_dataframe = pd.DataFrame.from_items([('AC',
list('GAGCAAGCCACTA'
'GA')),
('SS',
list('TCCTTGAACTACC'
'CG')),
('AS',
list('TCAGCTCTGCAGC'
'GT')),
('SS',
list('GTCAGGCGCTCGG'
'TG'))])
msa = TabularMSA([DNA('CGTCAATCTCGAACT',
positional_metadata=pos_metadata_dataframe)],
index=['seq1'])
with self.assertRaisesRegex(StockholmFormatError,
'Sequence-specific positional metadata.*'
'must be unique. Found 1 duplicate'):
fh = io.StringIO()
_tabular_msa_to_stockholm(msa, fh)
