def parse(self):
'''
parse tmchem file (sentence.pubtator.tmchem), save in a dictionary the sentence id, the name of the compound and the chebi name
Save only the chebi ID, not the mesh
'''
with open(self.file) as f:
for line in f:
line=line.rstrip()
line=line.split('\t')
if(len(line)==6):
#print(line)
#print(line[0])
iddoc=line[0] #id of the sentence in TEES: ex TEES.d0.s1
#print(iddoc)
iddoc=os.path.splitext(iddoc)[0] #keep only the ID of the doc: ex TEES.d0
iddoc=self.tmpr+'.'+iddoc
#print(iddoc)
# Some chebi are parent and some are children (duplicate and in that case, we recover and take the parent)
chebimesh=line[5]
chebi=re.search('(?<=CHEBI:)\w+',chebimesh)
if(chebi):
chebientity=ChebiEntity("CHEBI:"+chebi.group(0))
parent=chebientity.get_parent_id() # ex: CHEBI:22982 as for parent CHEBI:27732
if parent:
#print('take the parent: '+chebimesh+' '+parent)
chebimesh=parent
if iddoc in self.dictmchem.keys():
#print line[3]
self.dictmchem[iddoc][line[3]]=chebimesh #iddoc: document ID (TEES), name as find in the text, chebimesh=chebi ID or mesh ID
else:
self.dictmchem[iddoc]={}
self.dictmchem[iddoc][line[3]]=chebimesh
return self.dictmchem
def save_model(self, request, obj, form, change):
if form.cleaned_data['chebi_id']:
chebi_id = form.cleaned_data['chebi_id']
chebi_comb = ChebiEntity('CHEBI:' + str(chebi_id))
parent_id = chebi_comb.get_parent_id()
if parent_id:
s = re.findall(r'\d+', parent_id)
chebi_id = int(s[0])
chebi_comb = ChebiEntity('CHEBI:' + str(chebi_id))
obj.chebi_id = chebi_id
obj.chebi_name = chebi_comb.get_name()
else:
obj.chebi_name = None
if form.cleaned_data['pubchem_id']:
comp = Compound.from_cid(form.cleaned_data['pubchem_id'])
obj.pubchem_name = comp.synonyms[0]
else:
obj.pubchem_name = None
obj.save()
def chebi_from_dictio(self, dicofile):
'''
Cecile Pereira: 14 August #TODO TEST
Read the dictionary file,
Save the info of name, id, chebi in dictionaries.
'''
#print "Read chebi dictionary file"
f=open(dicofile,'r')
tmpid=""
for line in f:
if line.startswith('ID '):
tmp=split(' ',line)
tmpid=tmp[1]
self.idname[tmpid]={}
elif line.startswith('NA '):
tmp=split(' ',line)
tmpname=clean(tmp[1])
self.nameid[tmpname]=tmpid
self.idname[tmpid][tmpname]=''
elif line.startswith('TM '):
tmp=split(' ',line) #synonyms
tmp=split('\@',tmp[1])
tmp[0]=clean(tmp[0])
self.nameid[tmp[0]]=tmpid
self.idname[tmpid][tmp[0]]='' #all the names of the ID
elif line.startswith('DB CHEB_'):
tmp=split(' ',line)
for t in tmp:
t=re.sub('^CHEB_','',t)
t=re.sub('^CHEBI:','',t)
t=re.sub('Not available','',t)
if not t == '':
chebi=t
if(chebi):
chebientity=ChebiEntity("CHEBI:"+chebi)
parent=chebientity.get_parent_id() # ex: CHEBI:22982 as for parent CHEBI:27732
if parent: #take the CHEBI parent...
self.idchebi[tmpid][parent]=''
class TestChebiEntity(unittest.TestCase):
'''COMMENT'''
def setUp(self):
'''COMMENT'''
self.__existing = ChebiEntity('4167')
self.__secondary = ChebiEntity('CHEBI:5585')
def test_get_non_existing(self):
'''COMMENT'''
self.assertRaises(ChebiException, ChebiEntity, '-1')
def test_get_id_existing(self):
'''COMMENT'''
self.assertTrue(self.__existing.get_id() == 'CHEBI:4167')
def test_get_id_secondary(self):
'''COMMENT'''
self.assertTrue(self.__secondary.get_id() == 'CHEBI:5585')
def test_get_formulae_existing(self):
'''COMMENT'''
this_formula = Formula('C6H12O6', 'KEGG COMPOUND')
self.assertTrue(this_formula in self.__existing.get_formulae())
def test_get_formulae_secondary(self):
'''COMMENT'''
this_formula = Formula('H2O', 'ChEBI')
self.assertTrue(this_formula in self.__secondary.get_formulae())
def test_get_formula_existing(self):
'''COMMENT'''
self.assertTrue(self.__existing.get_formula() == 'C6H12O6')
def test_get_formula_secondary(self):
'''COMMENT'''
self.assertTrue(self.__secondary.get_formula() == 'H2O')
def test_get_mass_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_mass(), 180.15588)
def test_get_mass_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_mass(), 18.01530)
def test_get_charge_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_charge(), 0)
def test_get_charge_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_charge(), 0)
def test_get_charge_secondary2(self):
'''COMMENT'''
self.assertEquals(-2, ChebiEntity('43474').get_charge())
def test_get_comments_existing(self):
'''COMMENT'''
this_chebi_entity = ChebiEntity('29044')
this_comment = Comment('General', 'General',
'The substituent name \'3-oxoprop-2-enyl\' is '
'incorrect but is used in various databases.',
datetime.datetime.strptime('2005-03-18',
'%Y-%M-%d'))
self.assertTrue(this_comment in this_chebi_entity.get_comments())
def test_get_comments_secondary(self):
'''COMMENT'''
this_chebi_entity = ChebiEntity('11505')
this_comment = Comment('General', 'General',
'The substituent name \'3-oxoprop-2-enyl\' is '
'incorrect but is used in various databases.',
datetime.datetime.strptime('2005-03-18',
'%Y-%M-%d'))
self.assertTrue(this_comment in this_chebi_entity.get_comments())
def test_get_source_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_source(), 'KEGG COMPOUND')
def test_get_source_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_source(), 'KEGG COMPOUND')
def test_get_prnt_id_existing(self):
'''COMMENT'''
self.assertIsNone(self.__existing.get_parent_id())
def test_get_prnt_id_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_parent_id(), 'CHEBI:15377')
def test_get_name_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_name(), 'D-glucopyranose')
def test_get_name_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_name(), 'water')
def test_get_definition_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_definition(),
'A glucopyranose having D-configuration.')
def test_get_definition_secondary(self):
'''COMMENT'''
this_chebi_entity = ChebiEntity('41140')
self.assertEqual(this_chebi_entity.get_definition(),
'D-Glucopyranose with beta configuration at the '
'anomeric centre.')
def test_get_mod_on_existing(self):
'''COMMENT'''
self.assertTrue(self.__existing.get_modified_on() >
datetime.datetime.strptime('2014-01-01',
'%Y-%M-%d'))
def test_get_mod_on_secondary(self):
'''COMMENT'''
self.assertIsNotNone(self.__secondary.get_modified_on())
def test_get_created_by_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_created_by(), 'CHEBI')
def test_get_created_by_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_created_by(), 'ops$mennis')
def test_get_star_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_star(), 3)
def test_get_star_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_star(), 3)
def test_get_db_acc_existing(self):
'''COMMENT'''
dat_acc = DatabaseAccession('MetaCyc accession', 'D-Glucose',
'MetaCyc')
self.assertTrue(dat_acc in self.__existing.get_database_accessions())
def test_get_db_acc_secondary(self):
'''COMMENT'''
dat_acc = DatabaseAccession('MetaCyc accession', 'WATER', 'MetaCyc')
self.assertTrue(dat_acc in self.__secondary.get_database_accessions())
def test_get_inchi_existing(self):
'''COMMENT'''
inchi = 'InChI=1S/C6H12O6/c7-1-2-3(8)4(9)5(10)6(11)12-2/' + \
'h2-11H,1H2/t2-,3-,4+,5-,6?/m1/s1'
self.assertEqual(self.__existing.get_inchi(), inchi)
def test_get_inchi_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_inchi(), 'InChI=1S/H2O/h1H2')
def test_get_inchi_key_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_inchi_key(),
'WQZGKKKJIJFFOK-GASJEMHNSA-N')
def test_get_inchi_key_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_inchi_key(),
'XLYOFNOQVPJJNP-UHFFFAOYSA-N')
def test_get_smiles_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_smiles(),
'OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O')
def test_get_smiles_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_smiles(), '[H]O[H]')
def test_get_mol_existing(self):
'''COMMENT'''
chebi_id = 73938
this_chebi_entity = ChebiEntity(str(chebi_id))
self.assertEqual(this_chebi_entity.get_mol(),
_read_mol_file(chebi_id))
def test_get_mol_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_mol(), _read_mol_file(15377))
def test_get_mol_file_existing(self):
'''COMMENT'''
chebi_id = 73938
self.__get_mol_file(chebi_id, chebi_id)
def test_get_mol_file_secondary(self):
'''COMMENT'''
read_id = 15377
retrieved_id = 42857
self.__get_mol_file(read_id, retrieved_id)
def test_get_names_existing(self):
'''COMMENT'''
this_name = Name('Grape sugar', 'SYNONYM', 'KEGG COMPOUND', False,
'en')
self.assertTrue(this_name in self.__existing.get_names())
def test_get_names_secondary(self):
'''COMMENT'''
this_name = Name('eau', 'SYNONYM', 'ChEBI', False, 'fr')
self.assertTrue(this_name in self.__secondary.get_names())
def test_get_references_existing(self):
'''COMMENT'''
this_chebi_entity = ChebiEntity('15347')
this_reference = Reference('WO2006008754', 'Patent', '',
'NOVEL INTERMEDIATES FOR LINEZOLID '
'AND RELATED COMPOUNDS')
self.assertTrue(this_reference in this_chebi_entity.get_references())
def test_get_references_secondary(self):
'''COMMENT'''
this_chebi_entity = ChebiEntity('22182')
this_reference = Reference('WO2006008754', 'Patent', '',
'NOVEL INTERMEDIATES FOR LINEZOLID '
'AND RELATED COMPOUNDS')
self.assertTrue(this_reference in this_chebi_entity.get_references())
def test_get_cmp_orig_existing(self):
'''COMMENT'''
this_compound_origin = CompoundOrigin('H**o sapiens', 'NCBI:9606',
None, None, None, None,
'DOI', '10.1038/nbt.2488', None)
self.assertTrue(this_compound_origin
in self.__existing.get_compound_origins())
def test_get_cmp_orig_secondary(self):
'''COMMENT'''
this_compound_origin = CompoundOrigin('H**o sapiens', 'NCBI:9606',
None, None, None, None,
'DOI', '10.1038/nbt.2488', None)
self.assertTrue(this_compound_origin
in self.__secondary.get_compound_origins())
def test_get_out_existing(self):
'''COMMENT'''
this_relation = Relation('is_a', '17634', 'C')
self.assertTrue(this_relation in self.__existing.get_outgoings())
def test_get_out_secondary(self):
'''COMMENT'''
this_relation = Relation('has_role', 'CHEBI:48360', 'C')
self.assertTrue(this_relation in self.__secondary.get_outgoings())
def test_get_in_existing(self):
'''COMMENT'''
this_relation = Relation('has_functional_parent', 'CHEBI:15866', 'C')
self.assertTrue(this_relation in self.__existing.get_incomings())
def test_get_in_secondary(self):
'''COMMENT'''
this_relation = Relation('is_conjugate_acid_of', '29412', 'C')
self.assertTrue(this_relation in self.__secondary.get_incomings())
def __get_mol_file(self, read_id, retrieved_id):
'''COMMENT'''
mol_read = _read_mol_file(read_id)
this_chebi_entity = ChebiEntity(str(retrieved_id))
textfile_retrieved = open(this_chebi_entity.get_mol_filename(), 'r')
mol_retrieved = textfile_retrieved.read()
textfile_retrieved.close()
self.assertEquals(mol_read, mol_retrieved)
class TestChebiEntity(unittest.TestCase):
'''COMMENT'''
def setUp(self):
'''COMMENT'''
self.__existing = ChebiEntity('4167')
self.__secondary = ChebiEntity('CHEBI:5585')
def test_get_non_existing(self):
'''COMMENT'''
self.assertRaises(ChebiException, ChebiEntity, '-1')
def test_get_id_existing(self):
'''COMMENT'''
self.assertTrue(self.__existing.get_id() == 'CHEBI:4167')
def test_get_id_secondary(self):
'''COMMENT'''
self.assertTrue(self.__secondary.get_id() == 'CHEBI:5585')
def test_get_formulae_existing(self):
'''COMMENT'''
this_formula = Formula('C6H12O6', 'KEGG COMPOUND')
self.assertTrue(this_formula in self.__existing.get_formulae())
def test_get_formulae_secondary(self):
'''COMMENT'''
this_formula = Formula('H2O', 'ChEBI')
self.assertTrue(this_formula in self.__secondary.get_formulae())
def test_get_formula_existing(self):
'''COMMENT'''
self.assertTrue(self.__existing.get_formula() == 'C6H12O6')
def test_get_formula_secondary(self):
'''COMMENT'''
self.assertTrue(self.__secondary.get_formula() == 'H2O')
def test_get_mass_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_mass(), 180.15588)
def test_get_mass_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_mass(), 18.01530)
def test_get_charge_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_charge(), 0)
def test_get_charge_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_charge(), 0)
def test_get_charge_secondary2(self):
'''COMMENT'''
self.assertEquals(-2, ChebiEntity('43474').get_charge())
def test_get_comments_existing(self):
'''COMMENT'''
this_chebi_entity = ChebiEntity('29044')
this_comment = Comment(
'General', 'General',
'The substituent name \'3-oxoprop-2-enyl\' is '
'incorrect but is used in various databases.',
datetime.datetime.strptime('2005-03-18', '%Y-%M-%d'))
self.assertTrue(this_comment in this_chebi_entity.get_comments())
def test_get_comments_secondary(self):
'''COMMENT'''
this_chebi_entity = ChebiEntity('11505')
this_comment = Comment(
'General', 'General',
'The substituent name \'3-oxoprop-2-enyl\' is '
'incorrect but is used in various databases.',
datetime.datetime.strptime('2005-03-18', '%Y-%M-%d'))
self.assertTrue(this_comment in this_chebi_entity.get_comments())
def test_get_source_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_source(), 'KEGG COMPOUND')
def test_get_source_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_source(), 'KEGG COMPOUND')
def test_get_prnt_id_existing(self):
'''COMMENT'''
self.assertIsNone(self.__existing.get_parent_id())
def test_get_prnt_id_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_parent_id(), 'CHEBI:15377')
def test_get_name_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_name(), 'D-glucopyranose')
def test_get_name_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_name(), 'water')
def test_get_definition_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_definition(),
'A glucopyranose having D-configuration.')
def test_get_definition_secondary(self):
'''COMMENT'''
this_chebi_entity = ChebiEntity('41140')
self.assertEqual(
this_chebi_entity.get_definition(),
'D-Glucopyranose with beta configuration at the '
'anomeric centre.')
def test_get_mod_on_existing(self):
'''COMMENT'''
self.assertTrue(self.__existing.get_modified_on() >
datetime.datetime.strptime('2014-01-01', '%Y-%M-%d'))
def test_get_mod_on_secondary(self):
'''COMMENT'''
self.assertIsNotNone(self.__secondary.get_modified_on())
def test_get_created_by_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_created_by(), 'CHEBI')
def test_get_created_by_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_created_by(), 'ops$mennis')
def test_get_star_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_star(), 3)
def test_get_star_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_star(), 3)
def test_get_db_acc_existing(self):
'''COMMENT'''
dat_acc = DatabaseAccession('MetaCyc accession', 'D-Glucose',
'MetaCyc')
self.assertTrue(dat_acc in self.__existing.get_database_accessions())
def test_get_db_acc_secondary(self):
'''COMMENT'''
dat_acc = DatabaseAccession('MetaCyc accession', 'WATER', 'MetaCyc')
self.assertTrue(dat_acc in self.__secondary.get_database_accessions())
def test_get_inchi_existing(self):
'''COMMENT'''
inchi = 'InChI=1S/C6H12O6/c7-1-2-3(8)4(9)5(10)6(11)12-2/' + \
'h2-11H,1H2/t2-,3-,4+,5-,6?/m1/s1'
self.assertEqual(self.__existing.get_inchi(), inchi)
def test_get_inchi_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_inchi(), 'InChI=1S/H2O/h1H2')
def test_get_inchi_key_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_inchi_key(),
'WQZGKKKJIJFFOK-GASJEMHNSA-N')
def test_get_inchi_key_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_inchi_key(),
'XLYOFNOQVPJJNP-UHFFFAOYSA-N')
def test_get_smiles_existing(self):
'''COMMENT'''
self.assertEqual(self.__existing.get_smiles(),
'OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O')
def test_get_smiles_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_smiles(), '[H]O[H]')
def test_get_mol_existing(self):
'''COMMENT'''
chebi_id = 73938
this_chebi_entity = ChebiEntity(str(chebi_id))
self.assertEqual(this_chebi_entity.get_mol(), _read_mol_file(chebi_id))
def test_get_mol_secondary(self):
'''COMMENT'''
self.assertEqual(self.__secondary.get_mol(), _read_mol_file(15377))
def test_get_mol_file_existing(self):
'''COMMENT'''
chebi_id = 73938
self.__get_mol_file(chebi_id, chebi_id)
def test_get_mol_file_secondary(self):
'''COMMENT'''
read_id = 15377
retrieved_id = 42857
self.__get_mol_file(read_id, retrieved_id)
def test_get_names_existing(self):
'''COMMENT'''
this_name = Name('Grape sugar', 'SYNONYM', 'KEGG COMPOUND', False,
'en')
self.assertTrue(this_name in self.__existing.get_names())
def test_get_names_secondary(self):
'''COMMENT'''
this_name = Name('eau', 'SYNONYM', 'ChEBI', False, 'fr')
self.assertTrue(this_name in self.__secondary.get_names())
def test_get_references_existing(self):
'''COMMENT'''
this_chebi_entity = ChebiEntity('15347')
this_reference = Reference(
'WO2006008754', 'Patent', '', 'NOVEL INTERMEDIATES FOR LINEZOLID '
'AND RELATED COMPOUNDS')
self.assertTrue(this_reference in this_chebi_entity.get_references())
def test_get_references_secondary(self):
'''COMMENT'''
this_chebi_entity = ChebiEntity('22182')
this_reference = Reference(
'WO2006008754', 'Patent', '', 'NOVEL INTERMEDIATES FOR LINEZOLID '
'AND RELATED COMPOUNDS')
self.assertTrue(this_reference in this_chebi_entity.get_references())
def test_get_cmp_orig_existing(self):
'''COMMENT'''
this_compound_origin = CompoundOrigin('H**o sapiens', 'NCBI:9606',
None, None, None, None, 'DOI',
'10.1038/nbt.2488', None)
self.assertTrue(
this_compound_origin in self.__existing.get_compound_origins())
def test_get_cmp_orig_secondary(self):
'''COMMENT'''
this_compound_origin = CompoundOrigin('H**o sapiens', 'NCBI:9606',
None, None, None, None, 'DOI',
'10.1038/nbt.2488', None)
self.assertTrue(
this_compound_origin in self.__secondary.get_compound_origins())
def test_get_out_existing(self):
'''COMMENT'''
this_relation = Relation('is_a', '17634', 'C')
self.assertTrue(this_relation in self.__existing.get_outgoings())
def test_get_out_secondary(self):
'''COMMENT'''
this_relation = Relation('has_role', 'CHEBI:48360', 'C')
self.assertTrue(this_relation in self.__secondary.get_outgoings())
def test_get_in_existing(self):
'''COMMENT'''
this_relation = Relation('has_functional_parent', 'CHEBI:15866', 'C')
self.assertTrue(this_relation in self.__existing.get_incomings())
def test_get_in_secondary(self):
'''COMMENT'''
this_relation = Relation('is_conjugate_acid_of', '29412', 'C')
self.assertTrue(this_relation in self.__secondary.get_incomings())
def __get_mol_file(self, read_id, retrieved_id):
'''COMMENT'''
mol_read = _read_mol_file(read_id)
this_chebi_entity = ChebiEntity(str(retrieved_id))
textfile_retrieved = open(this_chebi_entity.get_mol_filename(), 'r')
mol_retrieved = textfile_retrieved.read()
textfile_retrieved.close()
self.assertEquals(mol_read, mol_retrieved)