def describe_entity(entity: ChebiEntity) -> None:
"""
Test function to describe a ChEBI entity.
Args:
entity:
a :class:`ChebiEntity`
"""
name = entity.get_name()
out_lines = [] # type: List[str]
for other in entity.get_outgoings():
target = ChebiEntity(other.get_target_chebi_id())
out_lines.append(
f" • {name} {other.get_type()} {brief_description(target)}")
in_lines = [] # type: List[str]
for other in entity.get_incomings():
target = ChebiEntity(other.get_target_chebi_id())
in_lines.append(
f" • {brief_description(target)} {other.get_type()} {name}")
lines = ([entity.get_name(), f" ► OUTGOING ({len(out_lines)})"] +
out_lines + [f" ► INCOMING ({len(in_lines)})"] + in_lines)
report = "\n".join(lines)
log.info(f"{entity.get_id()}:\n{report}")
def has_roles(self):
if self.chebi_id:
entity = ChebiEntity('CHEBI:' + str(self.chebi_id))
outdict = dict()
for relation in entity.get_outgoings():
if relation.get_type() == 'has_role':
tid = relation.get_target_chebi_id()
t = ChebiEntity(tid)
s = re.findall(r'\d+', tid)
outdict[t.get_name()] = int(s[0])
return outdict
else:
return ''
def gen_ancestor_info(entity: ChebiEntity,
relationships: List[str] = None,
max_generations: int = None,
starting_generation_: int = 0,
seen_: Set[HashableChebiEntity] = None) \
-> Generator[Tuple[HashableChebiEntity, str, int], None, None]:
"""
Retrieves all ancestors ("outgoing" links).
Args:
entity:
starting entity
relationships:
list of valid relationship types, e.g. "has_role"
max_generations:
maximum number of generations to pursue, or ``None`` for unlimited
starting_generation_:
for internal use only, for recursion
seen_:
for internal use only, for recursion
Returns:
list: of tuples ``entity, relationship, n_generations_above_start``
"""
if max_generations is not None and starting_generation_ >= max_generations:
return
assert starting_generation_ == 0 or seen_ is not None
seen_ = seen_ or set() # type: Set[HashableChebiEntity]
relationships = relationships or DEFAULT_ANCESTOR_RELATIONSHIPS
log.debug(f"Finding ancestors of {brief_description(entity)} "
f"(generation {starting_generation_}) "
f"via relationships {relationships!r}")
for rel in entity.get_outgoings(): # type: Relation
if rel.get_type() in relationships:
target = HashableChebiEntity(rel.get_target_chebi_id())
log.debug(f"... found {brief_description(target)}")
if target in seen_:
# log.debug(f"Skipping {target!r}")
continue
seen_.add(target)
yield target, rel.get_type(), starting_generation_ + 1
yield from gen_ancestor_info(
entity=target,
relationships=relationships,
starting_generation_=starting_generation_ + 1,
seen_=seen_,
)
def check_line_for_carboxylate(line):
"""Check a line from the CHEBI compounds file for carboxylic acid.
Returns name of the protonated form.
"""
# USING OFFLINE FILE -- NOT COMPLETE
# ID, _, _, _, parent_id, name, notes, _, _, star = line
# print(name)
# print(notes)
# if 'Conjugate base of ' in notes:
# if name[-3:] == 'ate':
# acid_name = notes.replace("Conjugate base of ", '')
# acid_name = acid_name.split('acid')[0] + 'acid'
# print('Conjugate base of:', acid_name, '<<<<<<<<<<')
# return acid_name
# Using libchebipy -- Online:
ID, _, _, _, parent_id, name, notes, _, _, star = line
entity = ChebiEntity(ID)
outgoings = entity.get_outgoings()
for out in outgoings:
type = out.get_type()
id = out.get_target_chebi_id()
if type == 'is_conjugate_base_of':
print(out)
# use regular expression to remove any non alphabetic
# characters
# that may follow the name
only_alph = sub('[^A-Za-z]', '', name)
print(only_alph)
if only_alph[-3:] == 'ate' and only_alph[-5:] != 'phate':
acid_ID = id.replace("CHEBI:", "")
print('acid ID:', acid_ID)
acid_entity = ChebiEntity(acid_ID)
acid_name = acid_entity.get_name()
print('Conjugate base of:', acid_name, '<<<<<<<<<<')
return acid_name
return None
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)