def makeOrgSynonymes():
dOrgSyns = {}
addedMirnaIDs = list()
for mimat in MIMAT2MIRNA:
mirna = MIMAT2MIRNA[mimat]
orgmir = orgmirs.mimat2orgmir.get(mimat, None)
if orgmir == None:
continue
synid = orgmir
if synid in dOrgSyns:
orgSyn = dOrgSyns[synid]
else:
orgSyn = Synonym(synid)
allsyns = set(
mirna.make_strings(miRNA.compositions()[miRNASynonymeTYPE.MIORG]))
for syn in allsyns:
orgSyn.addSyn(syn)
dOrgSyns[synid] = orgSyn
vOrgSyns = [dOrgSyns[x] for x in dOrgSyns]
return vOrgSyns
def makeFamilySynonymes():
vFamSyns = []
for family in familyDB:
for (miID, miName) in family.childMIMATs:
mirnas = set()
for mimat in MI2MIMAT[miID]:
mirnas.add(MIMAT2MIRNA[mimat])
familySyn = Synonym(family.familyID)
for mirna in mirnas:
allIDs = set(
mirna.make_strings(
miRNA.compositions()[miRNASynonymeTYPE.FAMILY]))
for syn in allIDs:
familySyn.addSyn(syn)
vFamSyns.append(familySyn)
return vFamSyns
def makeMIMATSynonymes():
mimatSyns = []
for mimat in MIMAT2MIRNA:
mirna = MIMAT2MIRNA[mimat]
mirnaSyn = Synonym(mimat)
for syn in mirna.make_strings(
miRNA.compositions()[miRNASynonymeTYPE.MIMAT]):
mirnaSyn.addSyn(syn)
mimatSyns.append(mirnaSyn)
return mimatSyns
def makeMISynonymes():
vMISyns = []
for mi in MI2MIMAT:
mimats = MI2MIMAT[mi]
mirnas = [MIMAT2MIRNA[x] for x in mimats]
orgSyn = Synonym('ORG' + mi)
for mirna in mirnas:
allIDs = set(
mirna.make_strings(miRNA.compositions()[miRNASynonymeTYPE.MI]))
for syn in allIDs:
orgSyn.addSyn(syn)
vMISyns.append(orgSyn)
return vMISyns
ncitObo = GeneOntology(dataDir + "miRExplore/obodir/ncit.obo")
ncitTerm2Sym = NcitTermSymbolDB.loadFromFolder()
vAllSyns = []
for termID in ncitObo.dTerms:
oboNode = ncitObo.dTerms[termID]
oboID = oboNode.id
oboName = oboNode.name
oboSyns = oboNode.synonym
oboRels = oboNode.is_a
newSyn = Synonym(oboID)
newSyn.addSyn(oboName)
if oboSyns != None:
for x in oboSyns:
newSyn.addSyn(x.syn)
allOrgs = [x for x in ncitTerm2Sym.org_term2symbol]
for org in allOrgs:
ncitID = oboID[oboID.index(":") + 1:]
if ncitID in ncitTerm2Sym.org_term2symbol[org]:
orgSyms = ncitTerm2Sym.org_term2symbol[org][ncitID]
aline = [x.strip() for x in line.split('\t')]
name = aline[1]
altNames = StringIO()
altNames.write(aline[2] + "\n")
names = []
for line in csv.reader([aline[2]], dialect='phenotypes'):
for elem in line:
names.append(elem)
names = names + [name]
newSyn = Synonym( 'DISEASE' + str(len(vAllSyns)+1))
newSyn.addSyn(name)
for x in names:
if x.startswith('[D]') or x.startswith('[X]') or x.startswith('[M]'):
x = x[3:]
xsyns = []
if ' - ' in x:
xsyns += x.split(' - ')
else:
xsyns.append(x)
for xsyn in xsyns:
allNodes.append(oboNode)
globalKeywordExcludes = loadExludeWords(common=False,
cell_co=False,
disease=False,
generic=False)
for x in globalKeywordExcludes:
if 'membrane' in globalKeywordExcludes[x]:
print("Membrane: " + x)
synSet = set()
for node in allNodes:
newSyn = Synonym(node.id)
newSyn.addSyn(node.name)
if node.synonym != None:
for x in node.synonym:
if x == None:
continue
newSyn.addSyn(x.syn)
synSet.add(newSyn)
vPrintSyns = handleCommonExcludeWords(synSet,
globalKeywordExcludes,
mostCommonCount=66,
maxCommonCount=5,
minSynCount=0)