def test_retrieve_id_17(self):
expected_tags = {
'mainid':
'N1NU19',
'chains': {
'A0A023VGG0', 'A0A064D5Y7', 'A0A096Y6F3', 'A0A097J0G2',
'A0A0A0CK90', 'A0A0A8NVJ2', 'A0A0B6VLZ4', 'A0A0C4XWE1',
'A0A0D5XR52', 'A0A0D7LBA5', 'A0A0E0SXV4', 'A0A0F0SXM7',
'A0A0F0T558', 'A0A0F1AU30', 'A0A0H3AEJ2', 'A0A0H3YD74',
'A0A0J0IP13', 'A0A0K2S451', 'A0A0K3RSM2', 'A0A0M1V7U1',
'A0A0N9NKB1', 'A0A0R4CY03', 'A0A0R9Q1C9', 'A0A0V9GPN4',
'A0A0V9J4A8', 'A0A0W1W990', 'A0A126JTC8', 'A0A142BNX4',
'A0A144XRS0', 'A0A167SUV6', 'A0A1B3B6M7', 'A0A1C0D4B4',
'A0A1J0E5N', 'A0A1Q8YU31', 'A0A1U7FUF6', 'A0A1W6AR35',
'A0A1W6ARV1', 'A0A1Y0F4W8', 'A0A220UU09', 'A0A221KL77',
'A0A2I7QEW9', 'A0A2I8R9F4', 'A0A2I8XNZ0', 'A0A2K9V063',
'A0A2L0TKR8', 'A0A2N1EL23', 'A0A2R4DIJ7', 'A0A2R4KLJ4',
'A0A2S1XWH3', 'A0A2S4RFM4', 'A0PB04', 'A4IUB3', 'B6VP02',
'C4NUX0', 'C4NVF2', 'C6GA28', 'D2Y9Z2', 'D3VGJ5', 'D3VLT8',
'E1ITU2', 'E7DBG1', 'E7DBH5', 'F2Z7X9', 'F5BPS4', 'H9TK43',
'K0H5V6', 'K4N9S7', 'K4W3W9', 'K4Y465', 'N1NU19', 'T0P0P2',
'T0QDZ9', 'U3PHU8', 'U9YS98', 'V9SJY4', 'W1JB02'
},
'seqid':
'14',
'source':
'UniClust90_2018_08',
'comments':
'Representative=N1NU19 n=76 Descriptions=[Conjugal transfer protein TraV|Type IV conjugative transfer system protein TraV|Sex pilus assembly protein|Conjugative transfer protein TraV|Sex pilus assembly|Type IV conjugative transfer system lipoprotein (TraV)] Members=A0A126JTC8,A0A0E0SXV4,A0A0F1AU30,A0A167SUV6,A0PB04,U9YS98,A0A144XRS0,D2Y9Z2,A0A142BNX4,C4NVF2,A0A0J0IP13,A0A0K3RSM2,A0A097J0G2,A4IUB3,W1JB02,A0A0H3YD74,A0A1W6ARV1,T0QDZ9,A0A0V9GPN4,A0A0V9J4A8,E7DBH5,A0A2S4RFM4,C4NUX0,A0A2R4DIJ7,A0A023VGG0,A0A0A0CK90,U3PHU8,A0A096Y6F3,A0A0K2S451,B6VP02,A0A2I8R9F4,A0A2R4KLJ4,K0H5V6,K4Y465,D3VLT8,F5BPS4,A0A0B6VLZ4,T0P0P2,A0A0D7LBA5,E1ITU2,A0A0N9NKB1,A0A1C0D4B4,H9TK43,A0A0F0SXM7,A0A0A8NVJ2,A0A220UU09,K4W3W9,F2Z7X9,A0A0M1V7U1,A0A0W1W990,C6GA28,A0A2I8XNZ0,A0A2K9V063,A0A0R4CY03,A0A2S1XWH3,A0A1Q8YU31,V9SJY4,A0A0C4XWE1,A0A2L0TKR8,A0A2N1EL23,A0A0R9Q1C9,K4N9S7,N1NU19,A0A1B3B6M7,A0A0D5XR52,A0A0F0T558,A0A2I7QEW9,A0A1Y0F4W8,A0A221KL77,E7DBG1,A0A064D5Y7,A0A1U7FUF6,A0A0H3AEJ2,D3VGJ5,A0A1W6AR35,A0A1J0E5N4'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[16])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_4(self):
expected_tags = {
'mainid': 'UPI0000000005',
'chains': {'UPI0000000005'},
'seqid': '1',
'source': 'UniParc',
'comments': 'status=active'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[3])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_11(self):
expected_tags = {
'mainid': 'ABCDE',
'chains': {'j', 'k', 'l'},
'seqid': None,
'source': 'RCSB PDB',
'comments': None
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[10])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_7(self):
expected_tags = {
'mainid': '3J4F',
'chains': {'A'},
'seqid': None,
'source': 'RCSB PDB',
'comments': 'PDBID|CHAIN|SEQUENCE'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[6])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_14(self):
expected_tags = {
'mainid': 'HJ41',
'chains': {'A', 'B', 'C'},
'seqid': '1',
'source': 'CROPS',
'comments': 'these are some comments'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[13])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_12(self):
expected_tags = {
'mainid': '6AVG',
'chains': {'B', 'C'},
'seqid': '2',
'source': 'PDBe',
'comments': None
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[11])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_5(self):
expected_tags = {
'mainid': 'P05067',
'chains': {'P05067'},
'seqid': '1',
'source': 'UniProtKB/SwissProt (archived)',
'comments': 'archived from Release 18.0 01-MAY-1991 SV=3'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[4])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_6(self):
expected_tags = {
'mainid': 'Q55167',
'chains': {'Q55167'},
'seqid': '1',
'source': 'UniProtKB/TrEMBL (archived)',
'comments': 'archived from Release 17.0 01-JUN-2001 SV=1'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[5])
self.assertDictEqual(retrieved_tags, expected_tags)
def parsemap(instream):
"""Parse cropmap from string.
:param instream: Imported-to-string cropmap file content.
:type instream: str
:return: Mapping and backmapping coordinates.
:rtype: dict [str, dict [str, dict [str, dict [int, int]]]]
"""
mapdict = {}
newid = []
indx = -1
inmaplines = instream.splitlines()
inmaplines.append('')
for raw in range(len(inmaplines)):
line = inmaplines[raw].rstrip()
if (not line or line.startswith(">")):
if indx >= 0:
if newid['mainid'] not in mapdict:
mapdict[newid['mainid']] = {}
if newid['seqid'] not in mapdict[newid['mainid']]:
mapdict[newid['mainid']][newid['seqid']] = {}
mapdict[newid['mainid']][
newid['seqid']]['cropmap'] = copy.deepcopy(forthmap)
mapdict[newid['mainid']][
newid['seqid']]['cropbackmap'] = copy.deepcopy(backmap)
if not line:
try:
line = f.readline().rstrip()
if not line:
break
except Exception:
break
if line.startswith(">"):
newid = retrieve_id(line)
indx += 1
forthmap = {}
backmap = {}
elif line.startswith("#") or line.startswith(' #'):
pass
else:
m = line.split(' ')
if m[1] != '0':
forthmap[int(m[0])] = int(m[1])
backmap[int(m[1])] = int(m[0])
else:
forthmap[int(m[0])] = None
return mapdict
def test_retrieve_id_3(self):
expected_tags = {
'mainid':
'Q9K794',
'chains': {'Q9K794'},
'seqid':
'1',
'source':
'UniRef50',
'comments':
'Putative AgrB-like protein n=2 Tax=Bacillus TaxID=1386 RepID=AGRB_BACHD'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[2])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_2(self):
expected_tags = {
'mainid':
'Q3SA23',
'chains': {'Q3SA23'},
'seqid':
'1',
'source':
'UniProtKB/TrEMBL',
'comments':
'Q3SA23_9HIV1 Protein Nef (Fragment) OS=Human immunodeficiency virus 1 OX=11676 GN=nef PE=3 SV=1'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[1])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_1(self):
expected_tags = {
'mainid':
'Q6GZX4',
'chains': {'Q6GZX4'},
'seqid':
'1',
'source':
'UniProtKB/SwissProt',
'comments':
'001R_FRG3G Putative transcription factor 001R OS=Frog virus 3 (isolate Goorha) OX=654924 GN=FV3-001R PE=4 SV=1'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[0])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_15(self):
expected_tags = {
'mainid':
'A0A094PJX3',
'chains': {'A0A094PJX'},
'seqid':
'30',
'source':
'UniClust30_2018_08',
'comments':
'Representative=A0A094PJX3 n=1 Descriptions=[Uncharacterized protein] Members=A0A094PJX3'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[14])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_10(self):
expected_tags = {
'mainid':
'6AVG',
'chains': {'B', 'C'},
'seqid':
'2',
'source':
'RCSB PDB',
'comments':
'T-cell receptor alpha variable 4,TCR alpha chain|H**o sapiens'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[9])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_9(self):
expected_tags = {
'mainid':
'6LN2',
'chains': {'A'},
'seqid':
None,
'source':
'MrBUMP',
'comments':
"resolution: 3.20 experiment: XRAY release_date: 2020-03-18 [ 476678 : ALL ] ['29-1054'] <SEQSE>29,1054<SEQSE> <100>1<100> <95>1<95> <90>1<90> <70>0<70> <50>0<50>"
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[8])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_8(self):
expected_tags = {
'mainid':
'3J4F',
'chains': {'D'},
'seqid':
None,
'source':
'MrBUMP',
'comments':
'resolution: 8.60 experiment: EMIC release_date: 2013-07-24 [ 3 : ALL ]'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[7])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_16(self):
expected_tags = {
'mainid':
'U1GGI9',
'chains': {'A0A239WXC9', 'A0A2W5CTJ', 'U1GGI9', 'U7JT03'},
'seqid':
'39',
'source':
'UniClust90_2018_08',
'comments':
'Representative=U1GGI9 n=4 Descriptions=[ATP-dependent Clp protease adapter protein ClpS|ATP-dependent Clp protease adapter ClpS] Members=U7JT03,A0A239WXC9,U1GGI9,A0A2W5CTJ1'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[15])
self.assertDictEqual(retrieved_tags, expected_tags)
def test_retrieve_id_13(self):
expected_tags = {
'mainid': '6DWU',
'chains': {
'AA', 'AC', 'AE', 'AG', 'AI', 'AK', 'AM', 'AO', 'AQ', 'AS',
'AU', 'BA', 'BC', 'BE', 'BG', 'BI', 'BK', 'BM', 'BO', 'BQ',
'BS', 'BU', 'CA', 'CC', 'CE', 'CG', 'CI', 'CK', 'CM', 'CO',
'CQ', 'CS', 'CU', 'DA', 'DC', 'DE', 'DG', 'DI', 'DK', 'DM',
'DO', 'DQ', 'DS', 'DU'
},
'seqid': '1',
'source': 'RCSB PDB',
'comments': 'Cationic trypsin|Bos taurus (9913)'
}
retrieved_tags = cit.retrieve_id(_HEADERS_LIST.splitlines()[12])
self.assertDictEqual(retrieved_tags, expected_tags)
def __init__(self,
seqid=None,
oligomer=None,
seq=None,
chains=None,
source=None,
header=None,
biotype=None,
extrainfo=None):
self.oligomer_id = None
self.name = None
self.chains = set()
self.source = None
self.source_headers = []
self.crops_header = None
self.seqs = {}
self.biotype = None
self.infostring = None
self.cropmap = None
self.cropbackmap = None
self.msa = None
self.cropmsa = None
self.intervals = None
if header is not None:
if isinstance(header, str):
self.source_headers.append(header)
try:
header_info = retrieve_id(header)
except Exception:
logging.warning(
'Header format not recognised. Information not extracted.'
)
header_info = None
else:
logging.critical("Argument 'header' should be a string.")
raise TypeError
else:
header_info = None
if seqid is not None:
if isinstance(seqid, str):
self.name = seqid
elif isinstance(seqid, int):
self.name = str(seqid)
else:
logging.critical("Sequence ID 'seqid' should be a string.")
raise TypeError
else:
if header_info is not None:
if 'seqid' in header_info:
self.name = header_info['seqid']
else:
self.name = '1'
if seq is not None:
if isinstance(seq, str):
self.seqs['mainseq'] = seq
else:
logging.critical("Chain sequence 'seq' should be a string.")
raise TypeError
else:
self.seqs['mainseq'] = ''
if oligomer is not None:
if isinstance(oligomer, str):
self.oligomer_id = oligomer
else:
logging.critical("Oligomer ID 'oligomer' should be a string.")
raise TypeError
else:
if header_info is not None:
if 'mainid' in header_info:
self.oligomer_id = header_info['mainid']
if chains is not None:
if isinstance(chains, set):
for ch in chains:
if isinstance(ch, str):
self.chains.add(ch)
else:
logging.critical(
"Chain IDs in 'chains' set should be strings.")
raise TypeError
else:
logging.critical(
"Argument 'chains' should be a set of strings.")
raise TypeError
else:
if header_info is not None:
if 'chains' in header_info:
self.chains = header_info['chains']
if source is not None:
if isinstance(source, str):
self.source = source
else:
logging.critical("Argument 'source' should be a string.")
raise TypeError
else:
if header_info is not None:
if 'source' in header_info:
self.source = header_info['source']
if biotype is not None:
if biotype.lower() == 'guess':
self.biotype = guess_type(seq)
else:
self.biotype = biotype
else:
self.biotype = None
if extrainfo is not None:
if isinstance(extrainfo, str):
self.infostring = extrainfo
else:
logging.critical("Argument 'extrainfo' should be a string.")
raise TypeError
else:
if header_info is not None:
if 'comments' in header_info:
self.infostring = header_info['comments']
else:
self.infostring = ""
if oligomer is None:
self.crops_header = makeheader(mainid='NOID',
seqid=self.name,
chains=self.chains,
source=self.source,
extrainfo=self.infostring)
else:
self.crops_header = makeheader(mainid=self.oligomer_id,
seqid=self.name,
chains=self.chains,
source=self.source,
extrainfo=self.infostring)
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
