def test_RfamParser_strict_invalid_structure(self):
"""RfamParser: functions when toggling strict w/ record w/ bad struct
"""
# strict
self.assertRaises(RecordError,list,\
RfamParser(self._fake_record_bad_structure_2))
#not strict
self.assertEqual(list(RfamParser(self._fake_record_bad_structure_2,\
strict=False)),[])
def test_RfamParser(self):
"""RfamParser: integrity of output """
expected_sequences =\
[''.join(['AACACAUCAGAUUUCCUGGUGUAACGAAUUUUUUAAGUGCUUCUUGCUUA',\
'AGCAAGUUUCAUCCCGACCCCCUCAGGGUCGGGAUUU']),\
''.join(['AACGCAUCGGAUUUCCCGGUGUAACGAA-UUUUCAAGUGCUUCUUGCAUU',\
'AGCAAGUUUGAUCCCGACUCCUG-CGAGUCGGGAUUU']),\
''.join(['CUCACAUCAGAUUUCCUGGUGUAACGAA-UUUUCAAGUGCUUCUUGCAUA',\
'AGCAAGUUUGAUCCCGACCCGU--AGGGCCGGGAUUU'])]
expected_structure = ''.join(\
['...<<<<<<<.....>>>>>>>....................<<<<<...',\
'.>>>>>....<<<<<<<<<<.....>>>>>>>>>>..'])
for r in RfamParser(self._fake_record):
headers,sequences,structure = r
self.assertEqual(headers['Refs']['Rfam'], ['RF00014'])
self.assertEqual(headers['Author'], 'Mifsud W')
self.assertEqualItems(sequences.values(), expected_sequences)
assert isinstance(sequences, Alignment)
self.assertEqualItems([s.Info.GenBank for s in sequences.Seqs],
[['U17136.1'],['M15749.1'],['AF090431.1']])
self.assertEqualItems([s.Info.Start for s in sequences.Seqs],
[897,154,221])
self.assertEqual(structure, expected_structure)
assert isinstance(structure,WussStructure)
def test_RFamParser_strict_invalid_headers(self):
"""RfamParser: functions when toggling strict w/ record w/ bad header
"""
self.assertRaises(RecordError,list,\
RfamParser(self._fake_record_bad_header_1))
self.assertRaises(RecordError,list,\
RfamParser(self._fake_record_bad_header_2))
# strict = False
x = list(RfamParser(self._fake_record_bad_header_1, strict=False))
obs = list(RfamParser(self._fake_record_bad_header_1,\
strict=False))[0][0].keys()
self.assertEqual(len(obs),1)
obs = list(RfamParser(self._fake_record_bad_header_2,\
strict=False))[0][0].keys()
self.assertEqual(len(obs),1)
def CMfinderParser(lines):
"""Parser for CMfinder output format
Parser tested through RfamParser test
"""
for info, alignment, struct in RfamParser(lines,strict=False):
struct = wuss_to_vienna(struct)
pairs = struct.toPairs()
return [alignment, pairs]
def test_RfamParser_strict_invalid_sequences(self):
"""RfamParser: functions when toggling strict w/ record w/ bad seq
"""
self.assertRaises(RecordError,list,
MinimalRfamParser(self._fake_record_bad_sequence_1))
# strict = False
# in 'False' mode you expect to get back as much as possible, also
# parts of sequences
self.assertEqual(len(list(RfamParser(self._fake_record_bad_sequence_1,\
strict=False))[0][1].NamedSeqs), 3)
def test_RfamParser_single_family(self):
"""RfamParser: should work on a single family in stockholm format"""
exp_header = Info()
exp_aln = {'K02120.1/628-682':\
'AUGGGAAAUUCCCCCUCCUAUAACCCCCCCGCUGGUAUCUCCCCCUCAGACUGGC',\
'D00647.1/629-683':\
'AUGGGAAACUCCCCCUCCUAUAACCCCCCCGCUGGCAUCUCCCCCUCAGACUGGC'}
exp_struct = '<<<<<<.........>>>>>>.........<<<<<<.............>>>>>>'
h, a, s = list(RfamParser(self.single_family))[0]
self.assertEqual(h,exp_header)
self.assertEqual(a,exp_aln)
self.assertEqual(s,exp_struct)
def test_RfamParser_strict_missing_fields(self):
"""RfamParser: toggle strict functions correctly """
# strict = True
self.assertRaises(RecordError,list,\
RfamParser(self._fake_record_no_headers))
self.assertRaises(RecordError,list,\
RfamParser(self._fake_record_no_sequences))
self.assertRaises(RecordError,list,\
RfamParser(self._fake_record_no_structure))
# strict = False
self.assertEqual(list(RfamParser(self._fake_record_no_headers,\
strict=False)), [])
self.assertEqual(list(RfamParser(self._fake_record_no_sequences,\
strict=False)), [])
self.assertEqual(list(RfamParser(self._fake_record_no_structure,\
strict=False)), [])
