def depod_enzyme_substrate(organism=9606):
result = []
reunip = re.compile(r'uniprotkb:([A-Z0-9]+)')
reptm = re.compile(r'([A-Z][a-z]{2})-([0-9]+)')
repmidsep = re.compile(r'[,|]\s?')
url = urls.urls['depod']['urls'][0]
c = curl.Curl(url, silent=False, encoding='ascii')
data = c.result
data = [x.split('\t') for x in data.split('\n')]
del data[0]
url_mitab = urls.urls['depod']['urls'][1]
c_mitab = curl.Curl(url_mitab, silent=False, encoding='iso-8859-1')
data_mitab = c_mitab.result
data_mitab = [x.split('\t') for x in data_mitab.split('\n')]
del data_mitab[0]
for i, l in enumerate(data):
if (len(l) > 6 and l[2] == 'protein substrate'
and taxonomy.ensure_ncbi_tax_id(l[3].split('(')[0].strip())
== organism and l[4].strip() != 'N/A'):
enzyme_uniprot = reunip.search(data_mitab[i][0]).groups()[0]
substrate_uniprot = reunip.search(data_mitab[i][1]).groups()[0]
for enzyme_up, substrate_up in itertools.product(
mapping.map_name(enzyme_uniprot, 'uniprot', 'uniprot'),
mapping.map_name(substrate_uniprot, 'uniprot', 'uniprot'),
):
for resaa, resnum in reptm.findall(l[4]):
resnum = int(resnum)
resaa = (common.aminoa_3_to_1_letter[resaa] if resaa
in common.aminoa_3_to_1_letter else resaa)
result.append({
'instance': None,
'kinase': enzyme_up,
'resaa': resaa,
'resnum': resnum,
'references': repmidsep.split(l[6].strip()),
'substrate': substrate_up,
'start': None,
'end': None,
'typ': 'dephosphorylation',
})
return result
def celltalkdb_annotations(organism=9606):
"""
Retrieves annotation of protein ligand and receptor roles from CellTalkDB
http://tcm.zju.edu.cn/celltalkdb/index.php
:param int,str organism:
Human and mouse supported, in case of incomprehensible value will
fall back to human.
:return:
Dictionary of annotations with UniProt IDs as keys.
"""
CellTalkDBAnnotation = collections.namedtuple('CellTalkDBAnnotation', [
'role',
'pmid',
])
ncbi_tax_id = taxonomy.ensure_ncbi_tax_id(organism)
ncbi_tax_id = ncbi_tax_id if ncbi_tax_id in {9606, 10090} else 9606
annot = collections.defaultdict(set)
for rec in celltalkdb_download(organism=ncbi_tax_id):
for role in ('ligand', 'receptor'):
uniprots = mapping.map_name(
getattr(rec, '%s_gene_symbol' % role),
'genesymbol',
'uniprot',
ncbi_tax_id=ncbi_tax_id,
)
for uniprot in uniprots:
annot[uniprot].add(
CellTalkDBAnnotation(
role=role,
pmid=rec.evidence,
))
return annot
def hippie_interactions(
score_threshold=.75,
only_human=False,
only_sources=None,
only_methods=None,
methods=False,
sources=False,
references=True,
organisms=False,
):
only_sources = common.to_set(only_sources)
only_methods = common.to_set(only_methods)
HippieInteraction = collections.namedtuple(
'HippieInteraction',
[
'id_a',
'id_b',
'score',
'methods',
'references',
'sources',
'organisms',
],
)
tps = lambda i: tuple(sorted(i))
url = urls.urls['hippie']['url']
c = curl.Curl(url, large=True, silent=False)
result = set()
for i, l in enumerate(c.result):
l = l.strip('\r\n').split('\t')
score = float(l[4])
if score < score_threshold:
continue
ids_a_1 = mapping.map_name(l[0], 'uniprot-entry', 'uniprot')
ids_a_2 = mapping.map_name(l[1], 'entrez', 'uniprot')
ids_b_1 = mapping.map_name(l[2], 'uniprot-entry', 'uniprot')
ids_b_2 = mapping.map_name(l[3], 'entrez', 'uniprot')
for id_a, id_b in itertools.product(ids_a_1 | ids_a_2,
ids_b_1 | ids_b_2):
details = dict((
dd[0],
set(dd[1].split(',')),
) for dd in (d.split(':') for d in l[5].split(';')))
_sources = details['sources'] if 'sources' in details else set()
experiments = (details['experiments']
if 'experiments' in details else set())
if not all((
not only_methods or experiments & only_methods,
not only_methods or _sources & only_sources,
)):
continue
_organisms = {9606}
if 'species' in details:
names = {
spec.split('(')[0].strip()
for spec in details['species']
}
_organisms = {
taxonomy.ensure_ncbi_tax_id(name)
for name in names
}
_organisms.discard(None)
if only_human and 9606 not in _organisms:
continue
result.add(
HippieInteraction(
id_a=id_a,
id_b=id_b,
score=score,
methods=tps(experiments) if methods else None,
references=(tps(details['pmids']) if references else None),
sources=tps(_sources) if sources else None,
organisms=tps(_organisms) if organisms else None,
))
return list(result)
def iptmnet_interactions(organism=9606):
ptm_url = urls.urls['iptmnet']['ptms']
score_url = urls.urls['iptmnet']['scores']
c = curl.Curl(score_url, large=True, silent=False)
scores = {}
for line in c.result:
line = line.strip('\n\r').split('\t')
if not line[2]:
continue
site = resite.match(line[1])
if not site:
continue
resaa, resnum = site.groups()
resnum = int(resnum)
score = int(line[4])
substrate, isoform = inputs_common._try_isoform(line[0])
enzyme = line[2]
key = (
enzyme,
substrate,
isoform,
line[3].lower(), # PTM type
resaa,
resnum,
)
scores[key] = score
c = curl.Curl(ptm_url, large=True, silent=False)
for line in c.result:
line = line.strip('\n\r').split('\t')
if not line or not line[6]:
continue
ncbi_tax_id = taxonomy.ensure_ncbi_tax_id(line[4].strip())
if organism and ncbi_tax_id != organism:
continue
substrate, s_isoform = inputs_common._try_isoform(line[2])
ptm_type = line[0].lower()
enzyme, e_isoform = inputs_common._try_isoform(line[6])
enzyme_ids = (mapping.map_name(
line[6],
'pro',
'uniprot',
ncbi_tax_id=organism,
) if line[6].startswith('PR:') else (enzyme, ))
refs = line[9].split(',')
resnum, resaa = resite.match(line[5]).groups()
key = (
line[6],
substrate,
isoform,
ptm_type,
resaa,
resnum,
)
score = scores[key] if key in scores else None
for _enzyme in enzyme_ids:
yield IptmnetInteraction(
enzyme=_enzyme,
substrate=substrate,
enzyme_isoform=e_isoform,
substrate_isoform=s_isoform,
ptm_type=ptm_type,
resaa=resaa,
resnum=resnum,
score=score,
references=refs,
)
def get_pfam(uniprots=None, organism=9606):
if uniprots is None:
uniprots = uniprot_input.all_uniprots(
organism=organism,
swissprot=True,
)
u_pfam = {}
pfam_u = {}
if uniprots is not None:
prg = progress.Progress(
len(uniprots) / 30,
'Downloading data from UniProt',
1,
)
data_all = []
for i in xrange(0, len(uniprots), 30):
to = i + 30
thisPart = uniprots[i:to]
thisPart = ' OR '.join(['accession:%s' % u for u in thisPart])
get = {
'query': thisPart,
'format': 'tab',
'columns': 'id,database(Pfam)'
}
for j in xrange(3):
c = curl.Curl(urls.urls['uniprot_basic']['url'], get=get)
data = c.result
if data is not None:
break
if data is None:
return None, None
data = data.split('\n')
del data[0]
del data[-1]
data_all += data
prg.step()
prg.terminate()
else:
organism = taxonomy.ensure_ncbi_tax_id(organism)
if not organism:
return None, None
organismQuery = 'organism:%u AND reviewed:yes' % organism
get = {
'query': organismQuery,
'format': 'tab',
'columns': 'id,database(Pfam)'
}
for j in xrange(3):
c = curl.Curl(
urls.urls['uniprot_basic']['url'],
get=get,
silent=False,
outf='uniprot-pfam-%u.tab' % organism,
)
data_all = c.result
if data_all is not None:
break
if data_all is None:
return None
data_all = data_all.split('\n')
del data_all[0]
for l in data_all:
l = l.split('\t')
pfams = re.sub(';$', '', l[1]).strip()
pfams = pfams.split(';') if pfams else []
if l[0] not in u_pfam:
u_pfam[l[0]] = []
u_pfam[l[0]] += pfams
for pfam in pfams:
if pfam not in pfam_u:
pfam_u[pfam] = []
pfam_u[pfam].append(l[0])
return u_pfam, pfam_u
def gpcrdb_annotations(organism=9606):
"""
:param int,str organism:
Only human and mouse (9606 and 10090) are supported.
"""
GpcrdbAnnotation = collections.namedtuple('GpcrdbAnnotation', [
'gpcr_class',
'family',
'subfamily',
])
organism = taxonomy.ensure_ncbi_tax_id(organism)
if organism not in (9606, 10090):
return {}
i_uniprot = 31 if organism == 10090 else 15
url = urls.urls['gpcrdb']['families']
c = curl.Curl(url, silent=False, large=True)
result = collections.defaultdict(set)
for line in c.result:
if line[0] != ' ':
cls = line.split('|')[0].strip()
family = None
subfamily = None
elif line[4] != ' ':
family = line.strip()
subfamily = None
elif line[8] != ' ':
subfamily = line.strip()
else:
line = line.strip().strip('"')
if line.startswith('gpcr'):
line = line.split('","')
uniprot = line[i_uniprot]
if uniprot:
result[uniprot].add(
GpcrdbAnnotation(
gpcr_class=cls,
family=family,
subfamily=subfamily,
))
return dict(result)
def _cellchatdb_organism(organism = 9606):
ncbi_tax_id = taxonomy.ensure_ncbi_tax_id(organism)
ncbi_tax_id = 10090 if ncbi_tax_id == 10090 else 9606
return ncbi_tax_id
def __init__(
self,
components,
ncbi_tax_id=9606,
name=None,
ids=None,
sources=None,
interactions=None,
references=None,
proteins=None,
attrs=None,
):
"""
Represents a molecular complex.
components : list,dict
Either a list of identifiers or a dict with identifiers as keys
and stoichiometric coefficients as values. List of identifiers
also assumed to represent stoichiometry by repetition
of identifiers.
ncbi_tax_id : int
NCBI taxonomy identifier of the complex. It implies all members
of the complex belong to the same organism. Support for multi-
organism complexes will be implemented in the future.
name : str
A custom name or identifier of the complex.
ids : dict
Identifiers. If ``sources`` is a set, list or tuple it should be
a dict with database names as keys and set of identifiers as
values. If ``sources`` is a string, it can be a set of
identifiers or a single identifier.
sources : set,str
Database(s) the complex has been defined in.
interactions : list,dict
Interactions between the components of the complex. Either
a list of tuples of component IDs or a dict with tuples as
keys and custom interaction properties as values.
proteins : list,dict
Synonym for `components`, kept for compatibility.
"""
components = components or proteins
if not isinstance(components, dict):
self.components = dict(collections.Counter(components))
else:
self.components = components
self.proteins = self.components
self.name = name
self.ids = collections.defaultdict(set)
self.add_ids(ids, source=sources)
self.sources = common.to_set(sources)
self.references = common.to_set(references)
self.ncbi_tax_id = taxonomy.ensure_ncbi_tax_id(ncbi_tax_id)
self.attrs = {}
if isinstance(attrs, dict):
self.attrs.update(attrs)
self.interactions = interactions