def cooccur(united, options, Motifs_List, Motifs_DB, list_size, db_size):
PairedMotifs_Cnts_List = countPairs(united, options, Motifs_List, getBasename(options.list_file))
PairedMotifs_Cnts_DB = countPairs(united, options, Motifs_DB, "DB")
(inputs, Ps, Edges) = ([], [], [])
num_MotifPairs = len(PairedMotifs_Cnts_List)
print "%d Pairs to Cacl Co-occuring" % num_MotifPairs
num_MotifPairs = num_MotifPairs / 100 + 1
for pair in PairedMotifs_Cnts_List.iterkeys():
(uidA, uidB) = map(int, pair.split(','))
try:
inputs.append((PairedMotifs_Cnts_List[pair], list_size, PairedMotifs_Cnts_DB[pair], db_size))
except KeyError:
pair2 = "%s,%s" % (uidB, uidA)
inputs.append((PairedMotifs_Cnts_List[pair], list_size, PairedMotifs_Cnts_DB[pair2], db_size))
#sys.stderr.write("Progress:%d%%\t%s\t%s\r" % (i / num_MotifPairs, uidA, uidB))
if options.parallel:
print "Cacling Enrichment Ratio"
ERs = ppCacl(options.parallel, inputs, enrichmen_ratio)
print "Cacling pValues"
Ps = ppCacl(options.parallel, inputs, hypergeo_cdf)
else:
print "Cacling Enrichment Ratio"
ERs = ssCacl(inputs, enrichmen_ratio)
print "Cacling pValues"
Ps = ssCacl(inputs, hypergeo_cdf)
print "Adjusting pValues"
adjPs = holm_adjustment(Ps)
Edges = formatEdges(united, PairedMotifs_Cnts_List, inputs, ERs, Ps, adjPs)
return Edges
def enrichment(united, options, Motifs_List, Motifs_DB, list_size, db_size):
print "Counting Motifs"
SeqNames_Cnts_List = countSeqNames(Motifs_List)
SeqNames_Cnts_DB = countSeqNames(Motifs_DB)
print "%s Motifs to Cacl Enrichment" % len(SeqNames_Cnts_List.keys())
inputs = [(SeqNames_Cnts_List[uid], list_size, SeqNames_Cnts_DB[uid], db_size) \
for uid in SeqNames_Cnts_List.iterkeys()]
if options.parallel:
ERs = ppCacl(options.parallel, inputs, enrichmen_ratio)
Ps = ppCacl(options.parallel, inputs, hypergeo_cdf_enrich)
else:
ERs = ssCacl(inputs, enrichmen_ratio)
Ps = ssCacl(inputs, hypergeo_cdf_enrich)
adjPs = holm_adjustment(Ps)
Nodes = formatNodes(united, SeqNames_Cnts_List, list_size,
SeqNames_Cnts_DB, db_size, ERs, Ps, adjPs)
return Nodes