def Goldstandard_from_cluster_File(gsF, foundprots=""):
clusters = GS.Clusters(need_to_be_mapped=False)
clusters.read_file(gsF)
if foundprots != "": clusters.remove_proteins(foundprots)
gs = GS.Goldstandard_from_Complexes("All")
gs.complexes = clusters
gs.make_pos_neg_ppis()
return gs
def create_goldstandard(clusters, target_taxid, valprots):
if target_taxid != "9606" and target_taxid != "":
orthmap = GS.Inparanoid(taxid=target_taxid)
else:
orthmap = ""
gs = GS.Goldstandard_from_Complexes("Goldstandard")
gs.make_reference_data(clusters, orthmap, found_prots=valprots)
return gs
def Goldstandard_from_PPI_File(gsF, foundprots=""):
out = GS.Goldstandard_from_Complexes("gs")
gsFH = open(gsF)
for line in gsFH:
line = line.rstrip()
ida, idb, class_label = line.split("\t")[0:3]
if foundprots != "" and (ida not in foundprots
or idb not in foundprots):
continue
edge = "\t".join(sorted([ida, idb]))
if class_label == "positive":
out.positive.add(edge)
else:
out.negative.add(edge)
gsFH.close()
return out
def cut(args):
fc, scoreF, outF = args
if fc == "00000000": sys.exit()
this_scores = get_fs_comb(fc)
scoreCalc = CS.CalculateCoElutionScores("", "", "", "", cutoff=0.5)
empty_gs = GS.Goldstandard_from_Complexes()
empty_gs.positive = set([])
empty_gs.negative = set([])
scoreCalc.readTable(scoreF, empty_gs)
print scoreCalc.to_predict
feature_comb = feature_selector([fs.name for fs in this_scores], scoreCalc)
feature_comb.open()
outFH = open(outF, "w")
print >> outFH, "\t".join(feature_comb.scoreCalc.header)
for i in range(feature_comb.to_predict):
edge, edge_scores = feature_comb.get_next()
if edge == "" or edge_scores == []: continue
print >> outFH, "%s\t%s" % (edge, "\t".join(map(str, edge_scores)))
outFH.close()
feature_comb.close()