def findReaction_fromRxn2Putative(lReactants_ids, lProducts_ids, lLeft,
lRight):
## vengono confrontati il primo argomento col terzo, e il secondo col quarto
lSideSx = []
for item in lReactants_ids:
lSideSx.append(len(gL.intersect(item, list(lLeft))) != 0)
lSideDx = []
for item in lProducts_ids:
lSideDx.append(len(gL.intersect(item, list(lRight))) != 0)
if all(lSideSx) == True and all(lSideDx) == True:
return True
else:
return False
def findTC_transports(lR, r):
lFindR = [len(gL.intersect(l, r)) != 0 for l in lR]
if any(lFindR) == True:
return True
else:
return False
def findReaction_rhea(lReactants_ids, lProducts_ids, lLeft, lRight):
## The first vs. the third and the second vs. the fourth arguments of the function are compared
lSideSx = []
for item in lReactants_ids:
lSideSx_internal = []
for possibleComp in lLeft:
lSideSx_internal.append(len(gL.intersect(item, possibleComp)) != 0)
lSideSx.append(any(lSideSx_internal))
lSideDx = []
for item in lProducts_ids:
lSideDx_internal = []
for possibleComp in lRight:
lSideDx_internal.append(len(gL.intersect(item, possibleComp)) != 0)
lSideDx.append(any(lSideDx_internal))
if all(lSideSx) == True and all(lSideDx) == True:
return True
else:
return False
dfMetsFromModel_products = dfMetsFromModel_products.drop_duplicates(
subset=['Id'])
lProducts_ids_original = list(
dfMetsFromModel_products['lIdentifiers'].dropna())
lReactants_ids_original_tuple = map(tuple, lReactants_ids_original)
lProducts_ids_original_tuple = map(tuple, lProducts_ids_original)
ltransportedMets = list(
set(lReactants_ids_original_tuple).intersection(
lProducts_ids_original_tuple))
if len(ltransportedMets) != 0:
lReactants_ids = []
for l in ltransportedMets:
l = [el for el in l if el.isdigit() == True]
chebiIdentifiers = gL.intersect(l,
list(dfChebiCompounds['Id']))
dfChebiExplodedFilter = dfChebiCompounds_exploded[
dfChebiCompounds_exploded['ParentalChebiIds_exploded'].
isin(chebiIdentifiers)]
dfChebiFilter = dfChebiCompounds[dfChebiCompounds['Id'].isin(
chebiIdentifiers)]
lAllChebi2Search = []
if dfChebiExplodedFilter.empty is False:
for riga in list(
dfChebiExplodedFilter['ParentalChebiIds']):
lAllChebi2Search += riga
for riga in list(dfChebiExplodedFilter['AllChebiIds']):
lAllChebi2Search += riga
dfSearch = dfSearch.reset_index(drop=True)
for lec in list(dfSearch['ec_number'].dropna()):
for ec in lec:
lEc.append(ec[4:-1])
allmetacycEnzymes = list(dfSearch['enzymes_of_reaction'].dropna())
for l in allmetacycEnzymes:
for el in l:
lAnd = []
dfProt1 = dfMetacyc_proteins[dfMetacyc_proteins['MetaCycId'] == el]
dfProt2 = dfMetacyc_proteins[dfMetacyc_proteins['Component_of'] ==
el]
dfProt = pd.concat([dfProt1, dfProt2])
if dfProt.empty is False:
for rowdfProt in dfProt.itertuples():
if len(gL.intersect(rowdfProt.lSpecies, taxId)) != 0:
if pd.isna(rowdfProt.Uniprot) is False:
dfCorrespondingGenes = dfuniprot2Org[
dfuniprot2Org['uniprot'] == 'up:' +
rowdfProt.Uniprot]
for foundGene in list(
dfCorrespondingGenes['keggGeneId']):
if [foundGene.split(':')[1]] not in lMetaEnzOR:
geneId2search = foundGene.split(':')[1]
lMetaEnzOR, dGenesFromKegg = rxnL.checkNadNadpDependencies_or(
nadp, nad, geneId2search,
orgCode + ':' + geneId2search,
lMetaEnzOR, dGenesFromKegg)
lgenes = rowdfProt.lGenes
lComponents = rowdfProt.Components
foundGenes = dfMetacyc_genes[
lCompartments.append(unipLoc['#text'].lower())
elif '#text' in unipLoc and '@evidence' not in unipLoc:
lCompartments.append(unipLoc['#text'].lower())
lCompartments_sistemati = []
for comp in lCompartments:
if comp in dCompartments:
comp = dCompartments[comp]
elif 'integral component of' in comp:
comp = comp.replace('integral component of', '').strip()
if comp in dCompartments:
comp = dCompartments[comp]
lCompartments_sistemati.append(comp)
lCompartments_sistemati = gL.unique(lCompartments_sistemati)
knownComps = gL.intersect(lCompartments_sistemati, lPossibleCompartments)
unknown = gL.difference(lCompartments_sistemati, lPossibleCompartments)
if len(unknown) != 0:
for unk in unknown:
if unk not in dname2GO:
idGo = genesL.getGOsearch(unk)
if idGo != '':
lAncestors = genesL.getGOAncestors(idGo)
lnewComps = []
for anc in lAncestors:
if anc in dAnc2Name and dAnc2Name[anc] in lPossibleCompartments:
lnewComps.append(dAnc2Name[anc])
else:
name = genesL.getGOName(anc)
if name != '' and name in lPossibleCompartments:
dRxn2Compartments[r.id] = lRxnComps
# Filter genes associated to each reaction according to the associated compartment
dfGenes2Compartment = pd.read_csv(os.path.join(OUTDIR, dfGenes2Comp + '.csv'), sep = '\t', dtype = {'Gene': str})
dfGenes2Compartment['lCompartments'] = dfGenes2Compartment['lCompartments'].apply(literal_eval)
dGenes2Compartment = dfGenes2Compartment.set_index('Gene')['lCompartments'].to_dict()
dfModelRxns2Genes = pd.read_csv(os.path.join(OUTDIR, dfrxns2Genes + '.csv'), sep = '\t', dtype = {'Rxn': str, 'KeggId': str, 'GPR': str, 'Name': str, 'IsTransport': bool, 'IsExchange': bool, 'GPRrule': str})
dfModelRxns2Genes['lGenes'] = dfModelRxns2Genes['lGenes'].apply(literal_eval)
lGenesFiltered_all = []
for row in dfModelRxns2Genes.itertuples():
lCompRxnModel = gL.unique(dRxn2Compartments[row.Rxn_conv])
if len(row.lGenes) != 0 and len(lCompRxnModel) != 0:
lAllGene_currentRxn = []
for l in row.lGenes:
lAllGene_currentRxn += l
lAllGene_currentRxn = gL.unique(lAllGene_currentRxn)
lGenes2Remove = []
for g in lAllGene_currentRxn:
if len(dGenes2Compartment[g]) != 0 and len(gL.intersect(gL.unique(dGenes2Compartment[g]), lCompRxnModel)) == 0:
lGenes2Remove.append(g)
lGenesFiltered = [[el for el in l if el not in lGenes2Remove] for l in row.lGenes]
lGenesFiltered = [subL for subL in lGenesFiltered if subL != []]
lGenesFiltered_all.append(lGenesFiltered)
else:
lGenesFiltered_all.append(row.lGenes)
dfModelRxns2Genes['lGenes_filtered'] = lGenesFiltered_all
dfModelRxns2Genes.to_csv(os.path.join(OUTDIR, outputFileName + '.csv'), sep = '\t', index = False)
def jaccard(list1, list2):
intersection = len(gL.intersect(list1, list2))
union = len(gL.union(list1, list2))
return intersection / union
if '||' not in row.description:
lDescription.append([row.description])
else:
lDescription.append(row.description.split('||'))
dfchem_xref['description_splt'] = lDescription
dfchem_merge = pd.merge(dfchem_prop, dfchem_xref, on = 'ID')
dfchem_merge['name'] = dfchem_merge['name'].str.lower()
## Load list of metabolites from model
dfmets = pd.read_csv(os.path.join(OUTDIR, inputFuzzy), sep = '\t', dtype=str)
dfmets['Name'] = dfmets['Name'].str.lower()
## get identifiers associated to common metabolites
inMetaNetX = gL.intersect(dfmets['Name'].tolist(), dfchem_merge['name'].tolist())
dfchem_merge_group = dfchem_merge[dfchem_merge['name'].isin(dfmets['Name'].tolist())]
dfFinal = dfchem_merge_group.groupby('ID')[['source', 'name']].agg(list).reset_index()
## test how many metabolites of the input model are not included in the column 'name' of dfchem_merge dataframe
notInMetaNetX = gL.difference(dfmets['Name'].tolist(), dfchem_merge['name'].tolist())
dfFinal_p2 = pd.DataFrame({'ID':[], 'source':[], 'description_splt':[]})
dfFilter = dfchem_merge[dfchem_merge.apply(lambda x: notInMetaNetX[0] in [el.lower() for el in x['description_splt']] , axis=1)].reset_index()
if dfFilter.empty == True:
print('NOT FOUND:\t', notInMetaNetX[0])
else:
dfFinal_p2 = dfFilter[['ID', 'source', 'description_splt']]
dfFinal_p2 = dfFinal_p2.groupby('ID')[['source', 'description_splt']].agg(list).reset_index()
print(dfFinal_p2)
for i0, row0 in resAllInfo.iterrows():
lisoformsFromUniprot0 += row0[
'otherIsoforms'] # the "otherIsoforms" column includes the isoforms retrieved from Uniprot
lIsoformsFromKegg0 += row0[
'isoform'] # the "isoforms" column includes the isoforms retrieved from KEGG
luniprot0_append += row0[
'id_uniprot'] # also used the Uniprot identifiers included in id_uniprot column
nomi0 = row0['proteinNames'] + row0[
'geneNames'] + row0['subunitsFromName'] + row0[
'geneName_fromKEGG'] # use all the names retrieved for the protein
lnames0 += nomi0
lIsoformsIndications0.append(row0['isoformIndication'])
lRedundancy0 += row0['redundancy']
comparison0 = [
len(gL.intersect(rule, luniprot0_append)) != 0
for rule in dfGenesRelationships['uniprotId']
]
res = dfGenesRelationships.loc[comparison0]
for i0, r0 in res.iterrows():
lnames0 += r0['gene']
lcomplex0 += r0['AND']
luniprot0 = gL.unique(luniprot0 + luniprot0_append)
lcomplex0 = gL.unique(lcomplex0)
lnames0 = gL.unique(lnames0)
lisoformsFromUniprot0 = gL.unique(lisoformsFromUniprot0)
lIsoformsIndications0 = gL.unique(lIsoformsIndications0)
lIsoformsFromKegg0 = gL.unique(lIsoformsFromKegg0)
for u1 in luniprot1:
resAllInfo = dfCompleteGenesInfo[
rfind('[')].strip()
else:
dReactants[reactant.id] = reactant.name
lReactants = list(dReactants.values())
lReactants.sort()
dProducts = {}
for product in rxn.products:
if testModel == 'y7' or testModel == 'y8':
dProducts[
product.id] = product.name[:product.name.rfind('[')].strip()
else:
dProducts[product.id] = product.name
lProducts = list(dProducts.values())
lProducts.sort()
if len(gL.intersect(lReactants, lProducts)) != 0:
lTransport.append(True)
metTrasportati = gL.intersect(lReactants, lProducts)
lMetsTrasportati.append(metTrasportati)
else:
lTransport.append(False)
lMetsTrasportati.append([])
dfRxns['Name'] = lNames
dfRxns['IsTransport'] = lTransport
dfRxns['trasportedMets'] = lMetsTrasportati
initialLetter = all(el.startswith('M_') for el in list(dfMetsFromModel['Id']))
# Check which reactions are exchange reactions
lExchange = []
def detectEqualSubsProds(lLeft, lRight):
if len(gL.intersect(lLeft, lRight)) != 0:
return gL.intersect(lLeft, lRight)
else:
return []
def checkEqualSubsProds(lLeft, lRight):
if len(gL.intersect(lLeft, lRight)) != 0:
return True
else:
return False
