def homologene_uniprot_dict(self, source):
"""
Builds orthology translation table as dict from UniProt to Uniprot,
obtained from NCBI HomoloGene data. Uses RefSeq and Entrez IDs for
translation.
"""
source = self.get_source(source)
self.h**o[source] = {}
hge = dataio.homologene_dict(source, self.target, 'entrez')
hgr = dataio.homologene_dict(source, self.target, 'refseq')
self.load_proteome(source, self.only_swissprot)
for u in self._proteomes[(source, self.only_swissprot)]:
source_e = mapping.map_name(u, 'uniprot', 'entrez', source)
source_r = mapping.map_name(u, 'uniprot', 'refseqp', source)
target_u = set([])
target_r = set([])
target_e = set([])
for e in source_e:
if e in hge:
target_e.update(hge[e])
for r in source_r:
if r in hgr:
target_r.update(hgr[r])
for e in target_e:
target_u.update(
set(mapping.map_name(e, 'entrez', 'uniprot', self.target)))
for r in target_r:
target_u.update(
set(mapping.map_name(e, 'refseqp', 'uniprot',
self.target)))
target_u = \
itertools.chain(
*map(
lambda tu:
mapping.map_name(
tu, 'uniprot', 'uniprot', self.target),
target_u
)
)
self.h**o[source][u] = sorted(list(target_u))
def build_gene(self):
self.gene = set()
for entity in self._entities:
# we add the components of the complexes to the protein data
# frame; I don't know if it's necessary but does not harm I guess
if hasattr(entity, 'components'):
components = entity.components
else:
components = (entity, )
for comp in components:
name = mapping.map_name0(comp, 'uniprot', 'genesymbol')
ensembl_genes = mapping.map_name(comp, 'uniprot', 'ensembl')
for ensembl in ensembl_genes:
self.gene.add(
CellPhoneDBGene(
gene_name=name,
uniprot=comp,
hgnc_symbol=name,
ensembl=ensembl,
))
def _process(self, p):
# human leukocyte antigenes result a result an
# extremely high number of combinations
if (not p['kinase'] or (isinstance(p['substrate'], common.basestring)
and p['substrate'].startswith('HLA'))):
return
if not isinstance(p['kinase'], list):
p['kinase'] = [p['kinase']]
kinase_ups = mapping.map_names(
p['kinase'],
self.enzyme_id_type,
'uniprot',
ncbi_tax_id=self.ncbi_tax_id,
)
substrate_ups_all = set([])
for sub_id_type in (self.substrate_id_types[self.input_method.lower()]
if self.input_is(self.substrate_id_types,
'__contains__') else
[self.substrate_id_type]):
if type(sub_id_type) is tuple:
sub_id_type, sub_id_attr = sub_id_type
else:
sub_id_attr = 'substrate'
substrate_ups_all.update(
set(
mapping.map_name(
p[sub_id_attr],
sub_id_type,
'uniprot',
self.ncbi_tax_id,
)))
# looking up sequences in all isoforms:
substrate_ups = []
for s in substrate_ups_all:
if 'substrate_isoform' in p and p['substrate_isoform']:
substrate_ups.append((s, p['substrate_isoform']))
else:
se = self.get_seq(s)
if se is None:
continue
for isof in se.isoforms():
if p['instance'] is not None:
if se.match(p['instance'],
p['start'],
p['end'],
isoform=isof):
substrate_ups.append((s, isof))
else:
if se.match(p['resaa'], p['resnum'], isoform=isof):
substrate_ups.append((s, isof))
if self.trace:
if p['substrate'] not in self.sub_ambig:
self.sub_ambig[p['substrate']] = substrate_ups
for k in p['kinase']:
if k not in self.kin_ambig:
self.kin_ambig[k] = kinase_ups
# generating report on non matching substrates
if len(substrate_ups) == 0:
for s in substrate_ups_all:
se = self.get_seq(s[0])
if se is None:
continue
nomatch.append(
(s[0], s[1], ((p['substrate_refseq']
if 'substrate_refseq' in p else ''), s,
p['instance'],
se.get(p['start'], p['end']))))
# adding kinase-substrate interactions
for k in kinase_ups:
for s in substrate_ups:
if (not self.allow_mixed_organisms
and (self.get_taxon(k) != self.ncbi_tax_id
or self.get_taxon(s[0]) != self.ncbi_tax_id)):
continue
se = self.get_seq(s[0])
if se is None:
continue
res = intera.Residue(p['resnum'],
p['resaa'],
s[0],
isoform=s[1])
if p['instance'] is None:
reg = se.get_region(p['resnum'],
p['start'],
p['end'],
isoform=s[1])
if reg is not None:
p['instance'] = reg[2]
p['start'] = reg[0]
p['end'] = reg[1]
if 'typ' not in p:
p['typ'] = 'phosphorylation'
mot = intera.Motif(s[0],
p['start'],
p['end'],
instance=p['instance'],
isoform=s[1])
ptm = intera.Ptm(s[0],
motif=mot,
residue=res,
typ=p['typ'],
source=[self.name],
isoform=s[1])
dom = intera.Domain(protein=k)
if 'references' not in p:
p['references'] = []
dommot = intera.DomainMotif(domain=dom,
ptm=ptm,
sources=[self.name],
refs=p['references'])
if self.input_is('mimp'):
dommot.mimp_sources = ';'.split(p['databases'])
dommot.npmid = p['npmid']
elif self.input_is('phosphonetworks'):
dommot.pnetw_score = p['score']
elif self.input_is('dbptm'):
dommot.dbptm_sources = [p['source']]
yield dommot