def loader(ncbi_tax_id=9606):
all_up = uniprot_input.all_uniprots(organism=ncbi_tax_id)
return (dataio.get_pfam_regions(uniprots=all_up,
dicts='uniprot',
keepfile=True))
def get_uniprot_sec(organism=9606):
"""
Downloads and processes the mapping between secondary and
primary UniProt IDs.
Yields pairs of secondary and primary UniProt IDs.
:param int organism:
NCBI Taxonomy ID of the organism.
"""
if organism is not None:
proteome = uniprot_input.all_uniprots(organism=organism)
proteome = set(proteome)
sec_pri = []
url = urls.urls['uniprot_sec']['url']
c = curl.Curl(url, silent=False, large=True)
for line in filter(
lambda line: len(line) == 2 and
(organism is None or line[1] in proteome),
map(lambda i: i[1].decode('utf-8').split(),
filter(lambda i: i[0] >= 30, enumerate(c.result)))):
yield line
def read_mapping_uniprot_list(self,
param,
uniprots=None,
ncbi_tax_id=None):
mapping_o = {}
mapping_i = {}
ncbi_tax_id = param.ncbi_tax_id \
if ncbi_tax_id is None else ncbi_tax_id
if uniprots is None:
uniprots = uniprot_input.all_uniprots(ncbi_tax_id,
swissprot=param.swissprot)
if param.targetNameType != 'uniprot':
utarget = self._read_mapping_uniprot_list('ACC',
param.target_ac_name,
uniprots)
_ = utarget.readline()
ac_list = list(
map(lambda l: l.decode('ascii').split('\t')[1].strip(),
utarget))
else:
ac_list = uniprots
udata = self._read_mapping_uniprot_list(param.target_ac_name,
param.ac_name, ac_list)
_ = udata.readline()
for l in udata:
l = l.decode('ascii').strip().split('\t')
if l[1] not in mapping_o:
mapping_o[l[1]] = []
mapping_o[l[1]].append(l[0])
if param.bi:
if l[0] not in mapping_i:
mapping_i[l[0]] = []
mapping_i[l[0]].append(l[1])
self.mapping["to"] = mapping_o
self.cleanDict(self.mapping["to"])
if param.bi:
self.mapping["from"] = mapping_i
self.cleanDict(self.mapping["from"])
def get_uniprot_sec(organism=9606):
if organism is not None:
proteome = uniprot_input.all_uniprots(organism=organism)
proteome = set(proteome)
sec_pri = []
url = urls.urls['uniprot_sec']['url']
c = curl.Curl(url, silent=False, large=True)
data = c.result
return filter(
lambda line: len(line) == 2 and
(organism is None or line[1] in proteome),
map(lambda i: i[1].decode('utf-8').split(),
filter(lambda i: i[0] >= 30, enumerate(data))))
def load_proteome(self, taxon, swissprot_only=True):
key = (taxon, swissprot_only)
if key not in self._proteomes:
self._proteomes[key] = (set(uniprot_input.all_uniprots(*key)))
for protein in self._proteomes[key]:
self._taxonomy[protein] = key
if not swissprot_only:
self.load_proteome(taxon, True)
