def test_oligoseq_set_cropmaps_1(self):
expected_seqs = []
expected_seqs.append(_SEQUENCE_5)
expected_seqs.append(_SEQUENCE_6)
expected_seqs.append(_SEQUENCE_6.replace("+", ""))
expected_seqs.append(_SEQUENCE_5_2)
expected_seqs.append(_SEQUENCE_6_2)
expected_seqs.append(_SEQUENCE_6_2.replace("+", ""))
seq = ces.sequence(seq=_SEQUENCE_5, header=_HEADER_1)
seq_2 = ces.sequence(seq=_SEQUENCE_5_2, header=_HEADER_2)
oseq = ces.oligoseq(oligomer_id=seq.oligomer_id, imer={seq.name: seq})
oseq.add_sequence(seq_2)
cropmaps = {}
for key in oseq.imer:
cropmaps[key] = {'cropmap': _CROPMAP_1, 'cropbackmap': _CROPMAP_2}
oseq.set_cropmaps(cropmaps, cropmain=True)
obtained_seqs = []
obtained_seqs.append(oseq.imer['1'].seqs['fullseq'])
obtained_seqs.append(oseq.imer['1'].seqs['cropseq'])
obtained_seqs.append(oseq.imer['1'].seqs['mainseq'])
obtained_seqs.append(oseq.imer['2'].seqs['fullseq'])
obtained_seqs.append(oseq.imer['2'].seqs['cropseq'])
obtained_seqs.append(oseq.imer['2'].seqs['mainseq'])
self.assertDictEqual(oseq.imer['1'].cropmap, _CROPMAP_1)
self.assertDictEqual(oseq.imer['1'].cropbackmap, _CROPMAP_2)
self.assertDictEqual(oseq.imer['2'].cropmap, _CROPMAP_1)
self.assertDictEqual(oseq.imer['2'].cropbackmap, _CROPMAP_2)
for n in range(len(expected_seqs)):
self.assertEqual(expected_seqs[n], obtained_seqs[n])
def test_oligoseq_chainlist_1(self):
expected_chains = {'C', 'D', 'E', 'F'}
seq = ces.sequence(seq=_SEQUENCE_5, header=_HEADER_1)
seq_2 = ces.sequence(seq=_SEQUENCE_6_2.replace("+", ""),
header=_HEADER_2)
oseq = ces.oligoseq(oligomer_id=seq.oligomer_id, imer={seq.name: seq})
oseq.add_sequence(seq_2)
obtained_chains = oseq.chainlist()
self.assertEqual(expected_chains, obtained_chains)
def test_oligoseq_nseqs_1(self):
expected_value = 2
seq = ces.sequence(seq=_SEQUENCE_5, header=_HEADER_1)
seq_2 = ces.sequence(seq=_SEQUENCE_6_2.replace("+", ""),
header=_HEADER_2)
oseq = ces.oligoseq(oligomer_id=seq.oligomer_id, imer={seq.name: seq})
oseq.add_sequence(seq_2)
obtained_value = oseq.nseqs()
self.assertEqual(expected_value, obtained_value)
def test_oligoseq_add_sequence_1(self):
seq = ces.sequence(seq=_SEQUENCE_5, header=_HEADER_1)
seq_2 = ces.sequence(seq=_SEQUENCE_5_2, header=_HEADER_2)
expected_keys = {'1', '2'}
expected_seqs = {seq, seq_2}
oseq = ces.oligoseq(oligomer_id=seq.oligomer_id, imer={seq.name: seq})
oseq.add_sequence(seq_2)
obtained_keys = set(oseq.imer.keys())
obtained_seqs = set(oseq.imer.values())
self.assertEqual(expected_keys, obtained_keys)
self.assertEqual(expected_seqs, obtained_seqs)
def test_oligoseq_write_1(self):
expected_output = (
">crops|1IXY_1|Chains C,D|Source: RCSB PDB|5'-D(*GP*AP*TP*AP*CP*TP*3DRP*AP*GP*AP*TP*AP*G)-3'|"
+ os.linesep + "GATACTNAGATAG" + os.linesep +
">crops|1IXY_2|Chains E,F|Source: RCSB PDB|5'-D(*CP*TP*AP*TP*CP*TP*GP*AP*GP*TP*AP*TP*C)-3'|"
+ os.linesep + "CTATCTGAGTATC" + os.linesep)
seq = ces.sequence(seq=_SEQUENCE_5, header=_HEADER_1)
seq_2 = ces.sequence(seq=_SEQUENCE_5_2, header=_HEADER_2)
oseq = ces.oligoseq(oligomer_id=seq.oligomer_id, imer={seq.name: seq})
oseq.add_sequence(seq_2)
returned_output = oseq.write(outdir='string')
self.assertEqual(expected_output, returned_output)
def test_oligoseq_length_1(self):
expected_length_1 = 13
expected_length_2 = 10
seq = ces.sequence(seq=_SEQUENCE_5, header=_HEADER_1)
seq_2 = ces.sequence(seq=_SEQUENCE_6_2.replace("+", ""),
header=_HEADER_2)
oseq = ces.oligoseq(oligomer_id=seq.oligomer_id, imer={seq.name: seq})
oseq.add_sequence(seq_2)
obtained_length_1 = oseq.length(1)
obtained_length_2 = oseq.length(2)
self.assertEqual(expected_length_1, obtained_length_1)
self.assertEqual(expected_length_2, obtained_length_2)
def test_oligoseq_whatseq_1(self):
chains = [{'C', 'D'}, {'E', 'F'}]
expected_seqnum = ['1', '1', '2', '2']
seq = ces.sequence(seq=_SEQUENCE_5, header=_HEADER_1)
seq_2 = ces.sequence(seq=_SEQUENCE_6_2.replace("+", ""),
header=_HEADER_2)
oseq = ces.oligoseq(oligomer_id=seq.oligomer_id, imer={seq.name: seq})
oseq.add_sequence(seq_2)
obtained_seqnum = []
for aset in chains:
for ch in aset:
obtained_seqnum.append(oseq.whatseq(ch))
self.assertListEqual(expected_seqnum, obtained_seqnum)
def parseseq(instream, inset=None):
"""Parse sequence(s).
:param instream: Imported-to-string sequence file content (fasta format).
:type instream: str
:param inset: Sequence IDs to return, if None it returns them all, defaults to None.
:type inset: set or dict or str, optional
:raises TypeError: When inset a set [str]; or instream is not a string.
:return: Parsed sequences.
:rtype: dict [str, :class:`crops.elements.sequences.oligoseq`]
"""
if isinstance(instream, str) is False:
logging.critical('Input argument instream should be a string.')
raise TypeError
if inset is not None:
if (not isinstance(inset, str) and not isinstance(inset, dict)
and not isinstance(inset, set)):
logging.critical('Input argument inset should be a set or, '
'alternatively a string or a dictionary.')
raise TypeError
elif isinstance(inset, str):
temp = inset
inset = set()
inset.add(temp)
upperset = set()
for element in inset:
if not isinstance(element, str):
logging.critical('Elements in inseq should be strings.')
raise TypeError
upperset.add(element.upper())
newseqs = {}
newid = []
head = ''
chain = ''
ignore = False
ignore = False
indx = -1
inseqlines = instream.splitlines()
inseqlines.append('')
for raw in range(len(inseqlines)):
line = inseqlines[raw].rstrip()
if (not line or line.startswith(">")) and not ignore:
if indx >= 0:
if newid['mainid'] not in newseqs:
newseqs[newid['mainid']] = oligoseq(
oligomer_id=newid['mainid'])
aseq = sequence(seqid=newid['seqid'],
oligomer=newid['mainid'],
seq=chain,
chains=newid['chains'],
source=newid['source'],
header=head,
extrainfo=newid['comments'])
newseqs[newid['mainid']].add_sequence(aseq)
else:
pass
if line.startswith(">"):
newid = retrieve_id(line)
head = line
indx += 1
chain = ''
if inset is not None:
ignore = False if newid['mainid'] in upperset else True
elif line.startswith("#") or line.startswith(' #'):
continue
else:
if not ignore:
chain += str(line)
return newseqs