def get_basic_set(self):
swissprots = set(
dataio.all_uniprots(
organism=self.organism, swissprot='yes'))
return dict(
filter(lambda x: x[0] in swissprots,
getattr(self.annotation, self.aspect.lower()).iteritems()))
def load_uniprots(self):
"""
Retrieves a set of all UniProt IDs to have a base set of the entire
proteome.
"""
self.uniprots = set(dataio.all_uniprots(organism=self.ncbi_tax_id))
net.lists['dgb'] = uniqList(flatList([net.mapper.map_name(dgb, 'genesymbol', 'uniprot') \
for dgb in dataio.get_dgidb()]))
net.lists['kin'] = uniqList(flatList([net.mapper.map_name(kin, 'genesymbol', 'uniprot') \
for kin in dataio.get_kinases()]))
net.lists['tfs'] = uniqList(flatList([net.mapper.map_name(tf, 'ensg', 'uniprot') \
for tf in dataio.get_tfcensus()['ensg']]))
net.lists['dis'] = uniqList(flatList([\
net.mapper.map_name(dis['genesymbol'], 'genesymbol', 'uniprot') \
for dis in dataio.get_disgenet()]))
# defining the proteome as the set of all human swissprot ids
console(':: Loading the human proteome')
proteome = dataio.all_uniprots(swissprot='yes')
fi = open(fisherFile, 'w')
# Fisher's exact test for enrichment of disease related proteins
# in OmniPath compared to their ratio in the whole proteome
console(':: Fisher\'s exact test for enrichment of disease related proteins in the network'\
'compared to their abundance in the proteome')
contDisg = np.array([[len(proteome), net.graph.vcount()],
[
len(net.lists['dis']),
len([1 for v in net.graph.vs if len(v['dis']) > 0])
]])
fi.write('Disease related proteins:\t%s\t%s\n' % stats.fisher_exact(contDisg))
# Fisher's exact test for enrichment of cancer driver proteins
# in OmniPath compared to their ratio in the whole proteome