def test_sample(self):
with open("KEGG/compound.sample") as handle:
records = list(Compound.parse(handle))
self.assertEqual(len(records), 8)
self.assertEqual(records[1].entry, "C00017")
self.assertEqual(records[1].mass, "") # Why?
self.assertEqual(records[1].formula, "C2H4NO2R(C2H2NOR)n")
self.assertEqual(records[1].name, ["Protein"])
self.assertEqual(records[1].pathway,
[("PATH", "map00450", "Selenocompound metabolism")])
self.assertEqual(len(records[1].enzyme), 21)
self.assertEqual(records[1].enzyme[0], ("2.3.2.6"))
self.assertEqual(records[1].structures, [])
self.assertEqual(records[1].dblinks[0], ("PubChem", ["3319"]))
self.assertEqual(
str(records[-1]).replace(" ", "").split("\n")[:10],
[
"ENTRYC01386",
"NAMENH2Mec",
"7-Amino-4-methylcoumarin",
"FORMULAC10H9NO2",
"DBLINKSCAS:26093-31-2",
"PubChem:4580",
"ChEBI:51771",
"ChEMBL:CHEMBL270672",
"KNApSAcK:C00048593",
"PDB-CCD:MCM",
],
)
def t_KEGG_Compound(testfiles):
"""Tests Bio.KEGG.Compound functionality."""
for file in testfiles:
fh = open(os.path.join("KEGG", file))
print "Testing Bio.KEGG.Compound on " + file + "\n\n"
records = Compound.parse(fh)
for record in records:
print record
print "\n"
def t_KEGG_Compound(testfiles):
"""Tests Bio.KEGG.Compound functionality."""
for file in testfiles:
fh = open(os.path.join("KEGG", file))
print("Testing Bio.KEGG.Compound on " + file + "\n\n")
records = Compound.parse(fh)
for record in records:
print(record)
print("\n")
fh.close()
def compound_records_to_df(file_path):
"""
Function parses all records using Biopython.Bio.KEGG.Compound parser, and returns a pandas dataframe.
<Input>
filepath = file path to a gzipped text file of KEGG enzyme records (str)
<output>
compound dataframe
"""
compound_fields = [
method for method in dir(Compound.Record())
if not method.startswith('_')
]
data_matrix = []
with gzip.open(file_path, 'rt') as file:
for record in Compound.parse(file):
data_matrix.append(
[getattr(record, field) for field in compound_fields])
compound_df = pd.DataFrame(data_matrix, columns=compound_fields)
return compound_df
def test_sample(self):
with open("KEGG/compound.sample") as handle:
records = list(Compound.parse(handle))
self.assertEqual(len(records), 8)
self.assertEqual(records[0].entry, "C00023")
self.assertEqual(records[0].mass, "") # Why?
self.assertEqual(records[0].formula, "Fe")
self.assertEqual(records[0].name,
['Iron', 'Fe2+', 'Fe(II)', 'Fe3+', 'Fe(III)'])
self.assertEqual(records[0].pathway,
[('PATH', 'MAP00860', 'Porphyrin and chlorophyll metabolism')])
self.assertEqual(records[0].enzyme[0], ('1.1.3.22', 'C'))
self.assertEqual(records[0].structures, [])
self.assertEqual(records[0].dblinks[0], ('CAS', ['7439-89-6']))
def test_sample(self):
with open("KEGG/compound.sample") as handle:
records = list(Compound.parse(handle))
self.assertEqual(len(records), 8)
self.assertEqual(records[1].entry, "C00017")
self.assertEqual(records[1].mass, "") # Why?
self.assertEqual(records[1].formula, "C2H4NO2R(C2H2NOR)n")
self.assertEqual(records[1].name, ['Protein'])
self.assertEqual(records[1].pathway,
[('PATH', 'map00450', 'Selenocompound metabolism')])
self.assertEqual(len(records[1].enzyme), 21)
self.assertEqual(records[1].enzyme[0], ('2.3.2.6'))
self.assertEqual(records[1].structures, [])
self.assertEqual(records[1].dblinks[0], ('PubChem', ['3319']))
def parse_kegg_compound(source, sdf=False):
with open(source, "r") as inp:
for record in Compound.parse(inp):
record_out = OrderedDict()
if "C" in record.entry or "D" in record.entry:
for attribute in dir(record):
if "_" not in attribute:
record_out[attribute.upper()] = ""
record_out[attribute.upper()] = getattr(
record, attribute.lower())
if sdf:
record_out["SDF"] = REST.GetMol(record_out["ENTRY"])
yield record_out
def dictionary(self, name):
"""
função que cria um dicionário com os id's do KEGG das reações/metabolitos como chaves e respetivos nomes como valores
:param name: id do KEGG para a reação/substrato
"""
if name not in self.metabolites.keys(
) and name not in self.reactions.keys():
comp = Compound.parse(REST.kegg_get(name))
for c in comp:
names = []
for n in c.name:
names.append(n.lower())
if name.startswith('cpd:'):
self.metabolites[name] = names
else:
self.reactions[name] = names
def test_sample(self):
with open("KEGG/compound.sample") as handle:
records = list(Compound.parse(handle))
self.assertEqual(len(records), 8)
self.assertEqual(records[1].entry, "C00017")
self.assertEqual(records[1].mass, "") # Why?
self.assertEqual(records[1].formula, "C2H4NO2R(C2H2NOR)n")
self.assertEqual(records[1].name,
['Protein'])
self.assertEqual(records[1].pathway,
[('PATH', 'map00450', 'Selenocompound metabolism')])
self.assertEqual(len(records[1].enzyme), 21)
self.assertEqual(records[1].enzyme[0], ('2.3.2.6'))
self.assertEqual(records[1].structures, [])
self.assertEqual(records[1].dblinks[0], ('PubChem', ['3319']))
self.assertEqual(str(records[-1]).replace(" ", "").split("\n")[:10],
['ENTRYC01386', 'NAMENH2Mec', '7-Amino-4-methylcoumarin',
'FORMULAC10H9NO2', 'DBLINKSCAS:26093-31-2',
'PubChem:4580', 'ChEBI:51771', 'ChEMBL:CHEMBL270672',
'KNApSAcK:C00048593', 'PDB-CCD:MCM'])
def test_sample(self):
with open("KEGG/compound.sample") as handle:
records = list(Compound.parse(handle))
self.assertEqual(len(records), 8)
self.assertEqual(records[1].entry, "C00017")
self.assertEqual(records[1].mass, "") # Why?
self.assertEqual(records[1].formula, "C2H4NO2R(C2H2NOR)n")
self.assertEqual(records[1].name, ['Protein'])
self.assertEqual(records[1].pathway,
[('PATH', 'map00450', 'Selenocompound metabolism')])
self.assertEqual(len(records[1].enzyme), 21)
self.assertEqual(records[1].enzyme[0], ('2.3.2.6'))
self.assertEqual(records[1].structures, [])
self.assertEqual(records[1].dblinks[0], ('PubChem', ['3319']))
self.assertEqual(
str(records[-1]).replace(" ", "").split("\n")[:10], [
'ENTRYC01386', 'NAMENH2Mec', '7-Amino-4-methylcoumarin',
'FORMULAC10H9NO2', 'DBLINKSCAS:26093-31-2', 'PubChem:4580',
'ChEBI:51771', 'ChEMBL:CHEMBL270672', 'KNApSAcK:C00048593',
'PDB-CCD:MCM'
])
def test_irregular(self):
with open("KEGG/compound.irregular") as handle:
records = list(Compound.parse(handle))
self.assertEqual(len(records), 2)
self.assertEqual(records[0].entry, "C01454")
def test_sample(self):
with open("KEGG/compound.sample") as handle:
records = list(Compound.parse(handle))
self.assertEqual(len(records), 8)
self.assertEqual(records[0].entry, "C00023")
def test_irregular(self):
with open("KEGG/compound.irregular") as handle:
records = list(Compound.parse(handle))
self.assertEqual(len(records), 2)
self.assertEqual(records[0].entry, "C01454")