def test_duplicate_sequence_names_error(self):
fp = get_data_path('stockholm_duplicate_sequence_names')
with self.assertRaisesRegex(
StockholmFormatError,
'duplicate sequence name.*ASR132.*supported by the reader.'):
_stockholm_to_tabular_msa(fp, constructor=RNA)
def test_stockholm_duplicate_tree_id_error(self):
fp = get_data_path('stockholm_duplicate_tree_ids')
with self.assertRaisesRegex(StockholmFormatError,
'Tree.*tree1.*in file.'):
_stockholm_to_tabular_msa(fp, constructor=DNA)
def test_nonexistent_gs_error(self):
fp = get_data_path('stockholm_invalid_nonexistent_gs')
with self.assertRaisesRegex(StockholmFormatError,
'GS or GR.*nonexistent sequence.*AC14.'):
_stockholm_to_tabular_msa(fp, constructor=RNA)
def test_stockholm_multi_line_tree_no_id(self):
fp = get_data_path('stockholm_multi_line_tree_no_id')
msa = _stockholm_to_tabular_msa(fp, constructor=DNA)
exp = TabularMSA([], metadata={'NH': 'ABCDEFGH'})
self.assertEqual(msa, exp)
def test_stockholm_single_tree_with_id(self):
fp = get_data_path('stockholm_single_tree_with_id')
msa = _stockholm_to_tabular_msa(fp, constructor=DNA)
exp = TabularMSA([], metadata={'NH': {'tree1': 'ABCD'}})
self.assertEqual(msa, exp)
def test_missing_header_error(self):
fp = get_data_path('stockholm_missing_header')
with self.assertRaisesRegex(StockholmFormatError,
'File missing.*header'):
_stockholm_to_tabular_msa(fp, constructor=DNA)
def test_data_type_error(self):
fp = get_data_path('stockholm_invalid_data_type')
with self.assertRaisesRegex(StockholmFormatError,
"Unrecognized.*'#=GZ"):
_stockholm_to_tabular_msa(fp, constructor=DNA)
def test_unsupported_constructor_error(self):
fp = get_data_path('empty')
with self.assertRaisesRegex(TypeError,
r'`constructor`.*`GrammaredSequence`.'):
_stockholm_to_tabular_msa(fp, constructor=TabularMSA)
def test_stockholm_extensive_mixed(self):
fp = get_data_path('stockholm_extensive_mixed')
msa = _stockholm_to_tabular_msa(fp, constructor=Protein)
exp = TabularMSA(
[
Protein(
'MTCRAQLIAVPRASSLAE..AIACAQKM....'
'RVSRVPVYERS',
positional_metadata={
'SA':
list('9998877564'
'53524252..'
'55152525..'
'..36463774'
'777')
}),
Protein(
'EVMLTDIPRLHINDPIMK..GFGMVINN....'
'..GFVCVENDE',
metadata={'OS': 'Bacillus subtilis'},
positional_metadata={
'SS':
list('CCCCCCCHHHH'
'HHHHHHH..HE'
'EEEEEE....E'
'EEEEEE'
'EEEH')
}),
Protein(
'EVMLTDIPRLHINDPIMK..GFGMVINN...'
'...GFVCVENDE',
positional_metadata={
'AS':
list('___________'
'_____*_____'
'___________'
'________'
'__'),
'IN':
list('___________'
'_1_________'
'_____2_____'
'_____0_'
'___')
})
],
metadata={
'ID': 'CBS',
'AC': 'PF00571',
'AU': 'Bateman A',
'SQ': '67'
},
positional_metadata={
'SS_cons':
list('CCCCCHHHHHHHH'
'HHHHH..EEEEEE'
'EE....EEEEEEE'
'EEEH')
},
index=['O83071/192-246', 'O31698/88-139', 'O31699/88-139'])
self.assertEqual(msa, exp)
def test_differing_data_lengths_gc_error(self):
fp = get_data_path('stockholm_differing_gc_data_length')
with self.assertRaisesRegex(ValueError, r'Number.*12.*(10).'):
_stockholm_to_tabular_msa(fp, constructor=RNA)
def test_no_constructor_error(self):
fp = get_data_path('empty')
with self.assertRaisesRegex(ValueError, r'Must provide.*parameter.'):
_stockholm_to_tabular_msa(fp)
def test_differing_sequence_lengths_error(self):
fp = get_data_path('stockholm_differing_seq_lengths')
with self.assertRaisesRegex(ValueError, r'Each sequence.*11 != 10'):
_stockholm_to_tabular_msa(fp, constructor=RNA)
def test_stockholm_missing_reference_number_error(self):
fp = get_data_path('stockholm_missing_rn_tag')
with self.assertRaisesRegex(StockholmFormatError,
r"Expected 'RN'.*'RL' tag."):
_stockholm_to_tabular_msa(fp, constructor=DNA)
def test_stockholm_multiple_multi_line_trees(self):
fp = get_data_path('stockholm_multiple_multi_line_trees')
msa = _stockholm_to_tabular_msa(fp, constructor=DNA)
exp = TabularMSA([], metadata={'NH': {'tree1': 'ABCDEFGH',
'tree2': 'IJKLMNOP'}})
self.assertEqual(msa, exp)
def test_duplicate_gc_error(self):
fp = get_data_path('stockholm_duplicate_gc')
with self.assertRaisesRegex(
StockholmFormatError, 'Found duplicate GC.*SS_cons.*supported '
'by the reader.'):
_stockholm_to_tabular_msa(fp, constructor=DNA)
def test_stockholm_minimal(self):
fp = get_data_path('stockholm_minimal')
msa = _stockholm_to_tabular_msa(fp, constructor=DNA)
exp = TabularMSA([DNA('TGTGTCGCAGTTGTCGTTTG')], index=['0235244'])
self.assertEqual(msa, exp)
def test_empty_file_error(self):
fp = get_data_path('empty')
with self.assertRaisesRegex(StockholmFormatError, 'File is empty.'):
_stockholm_to_tabular_msa(fp, constructor=RNA)
def test_stockholm_no_data(self):
fp = get_data_path('stockholm_no_data')
msa = _stockholm_to_tabular_msa(fp, constructor=DNA)
exp = TabularMSA([])
self.assertEqual(msa, exp)
def test_missing_footer_error(self):
fp = get_data_path('stockholm_missing_footer')
with self.assertRaisesRegex(StockholmFormatError,
'Final line.*only "//".'):
_stockholm_to_tabular_msa(fp, constructor=DNA)
def test_stockholm_with_whitespace_only_lines(self):
fp = get_data_path('stockholm_whitespace_only_lines')
msa = _stockholm_to_tabular_msa(fp, constructor=DNA)
exp = TabularMSA([], metadata={'AL': 'ABCD', 'NM': '1234'})
self.assertEqual(msa, exp)
def test_malformed_gc_line_error(self):
fp = get_data_path('stockholm_malformed_gc_line')
with self.assertRaisesRegex(StockholmFormatError,
'Line contains 2.*must contain.*3.'):
_stockholm_to_tabular_msa(fp, constructor=DNA)
def test_stockholm_metadata_only(self):
fp = get_data_path('stockholm_metadata_only')
msa = _stockholm_to_tabular_msa(fp, constructor=DNA)
exp = TabularMSA([], metadata={'NM': 'Kestrel Gorlick',
'DT': 'February 5th, 2016'})
self.assertEqual(msa, exp)
