def load_data(data, scores, orthmap="", fc=2, mfc=1):
if type(data) is list:
paths = data
else:
paths = [os.path.join(data, fn) for fn in next(os.walk(data))[2]]
elutionDatas = []
elutionProts = set([])
for elutionFile in paths:
if elutionFile.rsplit(os.sep, 1)[-1].startswith("."): continue
elutionFile = elutionFile.rstrip()
elutionData = CS.ElutionData(elutionFile,
frac_count=fc,
max_frac_count=mfc)
if orthmap != "":
if orthmap != False:
mapper = GS.Inparanoid("", inparanoid_cutoff=1)
mapper.readTable(orthmap, direction=0)
elutionData.orthmap(mapper)
elutionDatas.append(elutionData)
elutionProts = elutionProts | set(elutionData.prot2Index.keys())
for score in scores:
score.init(elutionData)
return elutionProts, elutionDatas
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 orth_map(args):
clusterF, taxid, outF = args
clust = GS.Clusters(False)
clust.read_file(clusterF)
orthmap = GS.Inparanoid(taxid=taxid)
orthmap.mapComplexes(clust)
clust.merge_complexes()
clust.filter_complexes()
outFH = open(outF, "w")
outFH.write(clust.to_string())
outFH.close()