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 = self.mapper.map_name(u, 'uniprot', 'entrez', source)
source_r = self.mapper.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(
self.mapper.map_name(e, 'entrez', 'uniprot',
self.target)))
for r in target_r:
target_u.update(
set(
self.mapper.map_name(e, 'refseqp', 'uniprot',
self.target)))
target_u = \
itertools.chain(
*map(
lambda tu:
self.mapper.map_name(
tu, 'uniprot', 'uniprot', self.target),
target_u
)
)
self.h**o[source][u] = sorted(list(target_u))
def test_homologene_dict(self):
h = dataio.homologene_dict(9606, 10090, 'GeneSymbol')
assert 'Stard10' in h['STARD10']