def _process_boolean_group_args(values, postfix):
if postfix:
values = {
'%s%s' % (val, postfix)
for val in common.to_list(values)
}
return ' or '.join(common.to_set(values))
def setup(self):
self.name = self._get_param('name')
self.id_type_enzyme = self._get_param('id_type_enzyme', 'genesymbol')
self.id_type_substrate = self._get_param(
'id_type_substrate',
'genesymbol',
)
self.id_type_substrate = common.to_list(self.id_type_substrate)
self.ncbi_tax_id = self._get_param('ncbi_tax_id', 9606)
self.organisms_supported = self._get_param(
'organisms_supported',
False,
)
self.allow_mixed_organisms = self._get_param(
'allow_mixed_organisms',
False,
)
self.input_method = self._get_param('input_method')
self.set_method()
def biomart_query(
attrs,
filters=None,
transcript=False,
gene=False,
dataset='hsapiens_gene_ensembl',
):
"""
Use https://www.ensembl.org/biomart/martview/ to check for attribute
and dataset names.
"""
_attrs = []
if gene:
_attrs.append('ensembl_gene_id')
if transcript:
_attrs.append('ensembl_transcript_id')
_attrs.extend(common.to_list(attrs))
filters = common.to_list(filters)
record = collections.namedtuple('EnsemblRecord', _attrs)
_logger._log(
'Downloading data from Ensembl Biomart: '
'dataset=`%s`, '
'%s'
'attributes=`%s`.' % (
dataset,
('filters=`%s`, ' % ', '.join(filters) if filters else ''),
', '.join(_attrs),
))
rewsp = re.compile(r'\n\s+')
xml_template_path = os.path.join(common.DATA, 'ensembl_biomart_query.xml')
with open(xml_template_path, 'r') as fp:
xml_template = fp.read()
filter_part = ''.join(_filter_xml_template % _filter
for _filter in filters)
attr_part = ''.join(_attr_xml_template % _attr for _attr in _attrs)
xml_query = xml_template % (
dataset,
filter_part,
attr_part,
)
xml_query = rewsp.sub('', xml_query)
biomart_url = urls.urls['ensembl']['biomart_url'] % xml_query
c = curl.Curl(biomart_url, large=True, silent=False)
success = False
for line in c.result:
line = line.strip('\n\r').split('\t')
success = success or line[0] == '[success]'
if len(line) == len(record._fields):
yield record(*line)
if not success:
_logger._log('Error: Interrupted transfer while downlading data '
'from Ensembl Biomart (missing `success` tag).')
def pathwaycommons_interactions(
resources=None,
types=None,
by_interaction=False,
version=12,
):
interactions = collections.defaultdict(set) if by_interaction else []
types = common.to_set(types)
resources = {
res.lower()
for res in (common.to_list(resources) or (
pc_res.name for pc_res in pathwaycommons_resources))
}
prg = progress.Progress(
len(resources),
'Processing PathwayCommons',
1,
percent=False,
)
url = urls.urls['pwcommons']['url']
for resource in pathwaycommons_resources:
if not resources & {resource.pc_label, resource.name.lower()}:
continue
prg.step()
_version = min(resource.version, version)
resource_url = url % (_version, _version, resource.pc_label)
c = curl.Curl(resource_url, silent=False, large=True)
for l in c.result:
if hasattr(l, 'decode'):
l = l.decode('ascii')
l = l.strip('\n\r').split('\t')
if not types or l[1] in types:
if by_interaction:
a_b = (l[0], l[1], l[2])
b_a = (l[2], l[1], l[0])
directed = l[1] in pathwaycommons_directed_types
key = (b_a if (a_b not in interactions and not directed
and b_a in interactions) else a_b)
interactions[key].add(
PathwayCommonsInteraction(*key,
resource=resource.name))
else:
l.append(resource.name)
interactions.append(PathwayCommonsInteraction(*l))
return interactions