def test_exceptions(self):
with open("KEGG/enzyme.sample") as handle:
with self.assertRaises(ValueError) as context:
list(Enzyme.read(handle))
self.assertTrue("More than one record found in handle" in str(context.exception))
records = Enzyme.parse(handle)
for i in range(0, 6):
next(records)
self.assertRaises(StopIteration, next, records)
def test_exceptions(self):
with open("KEGG/enzyme.sample") as handle:
with self.assertRaises(ValueError) as context:
list(Enzyme.read(handle))
self.assertIn("More than one record found in handle",
str(context.exception))
records = Enzyme.parse(handle)
for i in range(0, 6):
next(records)
self.assertRaises(StopIteration, next, records)
def test_irregular(self):
"""enzyme.irregular tests."""
with open("KEGG/enzyme.irregular") as handle:
records = list(Enzyme.parse(handle))
self.assertEqual(len(records), 2)
self.assertEqual(records[0].entry, "1.14.18.1")
self.assertEqual(records[-1].entry, "3.4.21.50")
def test_sample(self):
with open("KEGG/enzyme.sample") as handle:
records = list(Enzyme.parse(handle))
self.assertEqual(len(records), 8)
self.assertEqual(records[0].entry, "1.1.1.1")
self.assertEqual(records[0].name,
['Alcohol dehydrogenase', 'Aldehyde reductase'])
self.assertEqual(records[0].pathway,
[('PATH', 'MAP00010', 'Glycolysis / Gluconeogenesis'),
('PATH', 'MAP00071', 'Fatty acid metabolism'),
('PATH', 'MAP00120', 'Bile acid biosynthesis'),
('PATH', 'MAP00350', 'Tyrosine metabolism'),
('PATH', 'MAP00561', 'Glycerolipid metabolism')])
self.assertEqual(records[0].structures,
[('PDB', ['1A4U', '1A71', '1A72', '1ADB', '1ADC',
'1ADF', '1ADG', '1AGN', '1AXE', '1AXG',
'1B14', '1B15', '1B16', '1B2L', '1BTO',
'1CDO', '1D1S', '1D1T', '1DDA', '1DEH',
'1E3E', '1E3I', '1E3L', '1EE2', '1HDX',
'1HDY', '1HDZ', '1HET', '1HEU', '1HF3',
'1HLD', '1HSO', '1HSZ', '1HT0', '1HTB',
'1LDE', '1LDY', '1QLH', '1QLJ', '1TEH',
'2OHX', '2OXI', '3BTO', '3HUD', '5ADH',
'6ADH', '7ADH'])])
self.assertEqual(records[0].dblinks,
[('IUBMB Enzyme Nomenclature', ['1.1.1.1']),
('ExPASy - ENZYME nomenclature database', ['1.1.1.1']),
('WIT (What Is There) Metabolic Reconstruction', ['1.1.1.1']),
('BRENDA, the Enzyme Database', ['1.1.1.1']),
('SCOP (Structural Classification of Proteins)', ['1.1.1.1'])])
self.assertEqual(records[-1].entry, "2.7.2.1")
def test_4letter(self):
with open("KEGG/enzyme.4letter") as handle:
records = list(Enzyme.parse(handle))
self.assertEqual(len(records), 1)
self.assertEqual(records[0].entry, "5.4.2.2")
self.assertEqual(records[0].genes[0], ("HSA", ["5236", "55276"]))
self.assertEqual(records[0].genes[8],
("CSAB", ["103224690", "103246223"]))
def test_4letter(self):
with open("KEGG/enzyme.4letter") as handle:
records = list(Enzyme.parse(handle))
self.assertEqual(len(records), 1)
self.assertEqual(records[0].entry, "5.4.2.2")
self.assertEqual(records[0].genes[0], ('HSA', ['5236', '55276']))
self.assertEqual(records[0].genes[8],
('CSAB', ['103224690', '103246223']))
def t_KEGG_Enzyme(testfiles):
"""Tests Bio.KEGG.Enzyme functionality."""
for file in testfiles:
fh = open(os.path.join("KEGG", file))
print "Testing Bio.KEGG.Enzyme on " + file + "\n\n"
records = Enzyme.parse(fh)
for record in records:
print record
print "\n"
def test_4letter(self):
with open("KEGG/enzyme.4letter") as handle:
records = list(Enzyme.parse(handle))
self.assertEqual(len(records), 1)
self.assertEqual(records[0].entry, "5.4.2.2")
self.assertEqual(records[0].genes[0],
('HSA', ['5236', '55276']))
self.assertEqual(records[0].genes[8],
('CSAB', ['103224690', '103246223']))
def t_KEGG_Enzyme(testfiles):
"""Tests Bio.KEGG.Enzyme functionality."""
for file in testfiles:
fh = open(os.path.join("KEGG", file))
print("Testing Bio.KEGG.Enzyme on " + file + "\n\n")
records = Enzyme.parse(fh)
for record in records:
print(record)
print("\n")
fh.close()
def get_kegg_annotation():
"""
Get annotation ec:5.4.2.2 from kegg database and write to txt file.
Print annotation
:return:
"""
request = REST.kegg_get("ec:5.4.2.2")
open("ec_5.4.2.2.txt", "w").write(request.read())
records = Enzyme.parse(open("ec_5.4.2.2.txt"))
record = list(records)[0]
print(record.classname)
def t_KEGG_Enzyme(testfiles):
"""Tests Bio.KEGG.Enzyme functionality."""
for file in testfiles:
fh = open(os.path.join("KEGG", file))
print("Testing Bio.KEGG.Enzyme on " + file + "\n\n")
records = Enzyme.parse(fh)
for i, record in enumerate(records):
print(record)
fh.seek(0)
if i == 0:
print(Enzyme.read(fh))
else:
try:
print(Enzyme.read(fh))
assert False
except ValueError as e:
assert str(e) == 'More than one record found in handle'
print("\n")
fh.close()
def test_sample(self):
with open("KEGG/enzyme.sample") as handle:
records = list(Enzyme.parse(handle))
self.assertEqual(len(records), 8)
self.assertEqual(records[0].entry, "1.1.1.1")
self.assertEqual(records[0].name, [
'alcohol dehydrogenase', 'aldehyde reductase', 'ADH',
'alcohol dehydrogenase (NAD)', 'aliphatic alcohol dehydrogenase',
'ethanol dehydrogenase', 'NAD-dependent alcohol dehydrogenase',
'NAD-specific aromatic alcohol dehydrogenase',
'NADH-alcohol dehydrogenase', 'NADH-aldehyde dehydrogenase',
'primary alcohol dehydrogenase', 'yeast alcohol dehydrogenase'
])
self.assertEqual(
records[0].pathway,
[('PATH', 'ec00010', 'Glycolysis / Gluconeogenesis'),
('PATH', 'ec00071', 'Fatty acid degradation'),
('PATH', 'ec00260', 'Glycine, serine and threonine metabolism'),
('PATH', 'ec00350', 'Tyrosine metabolism'),
('PATH', 'ec00592', 'alpha-Linolenic acid metabolism'),
('PATH', 'ec00625', 'Chloroalkane and chloroalkene degradation'),
('PATH', 'ec00626', 'Naphthalene degradation'),
('PATH', 'ec00830', 'Retinol metabolism'),
('PATH', 'ec00980',
'Metabolism of xenobiotics by cytochrome P450'),
('PATH', 'ec00982', 'Drug metabolism - cytochrome P450'),
('PATH', 'ec01100', 'Metabolic pathways'),
('PATH', 'ec01110', 'Biosynthesis of secondary metabolites'),
('PATH', 'ec01120',
'Microbial metabolism in diverse environments'),
('PATH', 'ec01130', 'Biosynthesis of antibiotics')])
self.assertEqual(
records[0].dblinks,
[('ExplorEnz - The Enzyme Database', ['1.1.1.1']),
('IUBMB Enzyme Nomenclature', ['1.1.1.1']),
('ExPASy - ENZYME nomenclature database', ['1.1.1.1']),
('UM-BBD (Biocatalysis/Biodegradation Database)', ['1.1.1.1']),
('BRENDA, the Enzyme Database', ['1.1.1.1']),
('CAS', ['9031-72-5'])])
self.assertEqual(records[-1].entry, "2.7.2.1")
self.assertEqual(
str(records[-1]).replace(" ", "").split("\n")[:10], [
'ENTRYEC2.7.2.1', 'NAMEacetatekinase', 'acetokinase', 'AckA',
'AK', 'acetickinase', 'acetatekinase(phosphorylating)',
'CLASSTransferases;',
'Transferringphosphorus-containinggroups;',
'Phosphotransferaseswithacarboxygroupasacceptor'
])
def test_sample(self):
with open("KEGG/enzyme.sample") as handle:
records = list(Enzyme.parse(handle))
self.assertEqual(len(records), 8)
self.assertEqual(records[0].entry, "1.1.1.1")
self.assertEqual(records[0].name, [
"alcohol dehydrogenase", "aldehyde reductase", "ADH",
"alcohol dehydrogenase (NAD)", "aliphatic alcohol dehydrogenase",
"ethanol dehydrogenase", "NAD-dependent alcohol dehydrogenase",
"NAD-specific aromatic alcohol dehydrogenase",
"NADH-alcohol dehydrogenase", "NADH-aldehyde dehydrogenase",
"primary alcohol dehydrogenase", "yeast alcohol dehydrogenase"
])
self.assertEqual(
records[0].pathway,
[("PATH", "ec00010", "Glycolysis / Gluconeogenesis"),
("PATH", "ec00071", "Fatty acid degradation"),
("PATH", "ec00260", "Glycine, serine and threonine metabolism"),
("PATH", "ec00350", "Tyrosine metabolism"),
("PATH", "ec00592", "alpha-Linolenic acid metabolism"),
("PATH", "ec00625", "Chloroalkane and chloroalkene degradation"),
("PATH", "ec00626", "Naphthalene degradation"),
("PATH", "ec00830", "Retinol metabolism"),
("PATH", "ec00980",
"Metabolism of xenobiotics by cytochrome P450"),
("PATH", "ec00982", "Drug metabolism - cytochrome P450"),
("PATH", "ec01100", "Metabolic pathways"),
("PATH", "ec01110", "Biosynthesis of secondary metabolites"),
("PATH", "ec01120",
"Microbial metabolism in diverse environments"),
("PATH", "ec01130", "Biosynthesis of antibiotics")])
self.assertEqual(
records[0].dblinks,
[("ExplorEnz - The Enzyme Database", ["1.1.1.1"]),
("IUBMB Enzyme Nomenclature", ["1.1.1.1"]),
("ExPASy - ENZYME nomenclature database", ["1.1.1.1"]),
("UM-BBD (Biocatalysis/Biodegradation Database)", ["1.1.1.1"]),
("BRENDA, the Enzyme Database", ["1.1.1.1"]),
("CAS", ["9031-72-5"])])
self.assertEqual(records[-1].entry, "2.7.2.1")
self.assertEqual(
str(records[-1]).replace(" ", "").split("\n")[:10], [
"ENTRYEC2.7.2.1", "NAMEacetatekinase", "acetokinase", "AckA",
"AK", "acetickinase", "acetatekinase(phosphorylating)",
"CLASSTransferases;",
"Transferringphosphorus-containinggroups;",
"Phosphotransferaseswithacarboxygroupasacceptor"
])
def test_sample(self):
with open("KEGG/enzyme.sample") as handle:
records = list(Enzyme.parse(handle))
self.assertEqual(len(records), 8)
self.assertEqual(records[0].entry, "1.1.1.1")
self.assertEqual(records[0].name,
['alcohol dehydrogenase',
'aldehyde reductase',
'ADH',
'alcohol dehydrogenase (NAD)',
'aliphatic alcohol dehydrogenase',
'ethanol dehydrogenase',
'NAD-dependent alcohol dehydrogenase',
'NAD-specific aromatic alcohol dehydrogenase',
'NADH-alcohol dehydrogenase',
'NADH-aldehyde dehydrogenase',
'primary alcohol dehydrogenase',
'yeast alcohol dehydrogenase'])
self.assertEqual(records[0].pathway,
[('PATH', 'ec00010', 'Glycolysis / Gluconeogenesis'),
('PATH', 'ec00071', 'Fatty acid degradation'),
('PATH', 'ec00260', 'Glycine, serine and threonine metabolism'),
('PATH', 'ec00350', 'Tyrosine metabolism'),
('PATH', 'ec00592', 'alpha-Linolenic acid metabolism'),
('PATH', 'ec00625', 'Chloroalkane and chloroalkene degradation'),
('PATH', 'ec00626', 'Naphthalene degradation'),
('PATH', 'ec00830', 'Retinol metabolism'),
('PATH', 'ec00980', 'Metabolism of xenobiotics by cytochrome P450'),
('PATH', 'ec00982', 'Drug metabolism - cytochrome P450'),
('PATH', 'ec01100', 'Metabolic pathways'),
('PATH', 'ec01110', 'Biosynthesis of secondary metabolites'),
('PATH', 'ec01120', 'Microbial metabolism in diverse environments'),
('PATH', 'ec01130', 'Biosynthesis of antibiotics')])
self.assertEqual(records[0].dblinks,
[('ExplorEnz - The Enzyme Database', ['1.1.1.1']),
('IUBMB Enzyme Nomenclature', ['1.1.1.1']),
('ExPASy - ENZYME nomenclature database', ['1.1.1.1']),
('UM-BBD (Biocatalysis/Biodegradation Database)', ['1.1.1.1']),
('BRENDA, the Enzyme Database', ['1.1.1.1']),
('CAS', ['9031-72-5'])])
self.assertEqual(records[-1].entry, "2.7.2.1")
self.assertEqual(str(records[-1]).replace(" ", "").split("\n")[:10],
['ENTRYEC2.7.2.1', 'NAMEacetatekinase', 'acetokinase',
'AckA', 'AK', 'acetickinase', 'acetatekinase(phosphorylating)',
'CLASSTransferases;', 'Transferringphosphorus-containinggroups;',
'Phosphotransferaseswithacarboxygroupasacceptor'])
def create_enzyme_df(path_to_file):
"""
input:path_to_file. file.gz format
output:enzyme dataframe
"""
enzyme_fields = [
method for method in dir(Enzyme.Record()) if not method.startswith('_')
]
data_matrix = []
with gzip.open(path_to_file, 'rt') as file:
for record in enzyme.parse(file):
data_matrix.append(
[getattr(record, field) for field in enzyme_fields])
enzyme_df = pd.DataFrame(data_matrix, columns=enzyme_fields)
return enzyme_df
def convert(id):
"""Fetches an EC ID from the KEGG REST API, parses it, and writes a GO record."""
# this is a dumb way of doing it, too much of a python noob to figure a better way
txt = fetch(id)
fn = "target/"+id+".kml"
fh = open(fn, "w")
fh.write(str(txt))
fh.close()
fh = open(fn)
records = Enzyme.parse(fh)
n = 0
for record in records:
write_obo(record)
n=n+1
if n==0:
print("FAIL")
fh.close()
def convert(id):
"""Fetches an EC ID from the KEGG REST API, parses it, and writes a GO record."""
# this is a dumb way of doing it, too much of a python noob to figure a better way
txt = fetch(id)
fn = "target/" + id + ".kml"
fh = open(fn, "w")
fh.write(str(txt))
fh.close()
fh = open(fn)
records = Enzyme.parse(fh)
n = 0
for record in records:
write_obo(record)
n = n + 1
if n == 0:
print("FAIL")
fh.close()
from Bio.KEGG import REST
from Bio.KEGG import Enzyme
request = REST.kegg_get("ec:7.1.2.2")
# 참고: ATP synthase의 EC번호이다
open("ec_7.1.2.2.txt", "w").write(request.read())
records = Enzyme.parse(open("ec_7.1.2.2.txt"))
record = list(records)[0]
print(record.classname)
from Bio.KEGG import Enzyme
records = Enzyme.parse(open("/home/koreanraichu/ec_5.4.2.2.txt"))
record = list(records)[0]
print(record.classname)
#!/usr/bin/env python3
from Bio.KEGG import REST
from Bio.KEGG import Enzyme
file = open("entries", "r")
lines = file.readlines()
lines = list(map(str.strip, lines))
from pprint import pprint
for line in lines:
request = REST.kegg_get(line)
a = request.read()
open("temp.txt", "w").write(a)
records = Enzyme.parse(open("temp.txt"))
try:
record = list(records)[0]
except:
print(f"nie udalo sie znalezc {line}")
continue
res = ""
for x in record.name:
res += x
# to make it work you need to add parsing description in biopython
record.description = "DUMMY"
print(line, res, record.description) # record.classname, record.sysname)
# pprint(vars(record))
from Bio.KEGG import REST
from Bio.KEGG import Enzyme
request = REST.kegg_get("ec:2.7.7.9")
open("ec_2.7.7.9.txt", "w").write(request.read())
records = Enzyme.parse(open("ec_2.7.7.9.txt"))
record = list(records)[0]
record.classname
record.entry
def test_new(self):
with open("KEGG/enzyme.new") as handle:
records = list(Enzyme.parse(handle))
self.assertEqual(len(records), 1)
self.assertEqual(records[0].entry, "6.2.1.25")
def test_irregular(self):
with open("KEGG/enzyme.irregular") as handle:
records = list(Enzyme.parse(handle))
self.assertEqual(len(records), 2)
self.assertEqual(records[0].entry, "1.14.18.1")
self.assertEqual(records[-1].entry, "3.4.21.50")
def test_sample(self):
with open("KEGG/enzyme.sample") as handle:
records = list(Enzyme.parse(handle))
self.assertEqual(len(records), 8)
self.assertEqual(records[0].entry, "1.1.1.1")
self.assertEqual(records[-1].entry, "2.7.2.1")
#12.3.KEGG_Enzyme_example.py
from Bio.KEGG import Enzyme
records = Enzyme.parse(open("ec_2.7.1.40.txt"))
record = list(records)[0]
print("classname:", record.classname)
print("sysname:", record.sysname)
print("subtrate:", record.substrate)
print("product:", record.product)
def test_new(self):
with open("KEGG/enzyme.new") as handle:
records = list(Enzyme.parse(handle))
self.assertEqual(len(records), 1)
self.assertEqual(records[0].entry, "6.2.1.25")
def KEGG(input1, input2):
# Perform the query
result = REST.kegg_info("kegg").read()
# Print overview
if input1 == "info" and input2 == "alt":
return print(result)
# Get all entries in the PATHWAY database as a dataframe
elif input1 == "pathway_overview" and input2 == "alle":
result = REST.kegg_list("pathway").read()
return to_df(result)
#Print alle biosynteseveje
elif input1 == "print_pathway":
if input2 == "alle":
result = REST.kegg_get("map01100", "image").read()
img = Image(result, width=1500, height=1000)
else:
result = REST.kegg_get(input2, "image").read()
img = Image(result)
return img
#Find the compund vanillin
elif input1 == "find_molekyle" and input2 != None:
result = REST.kegg_find("compound", input2).read() #cpd:C00755
return print(result)
elif input1 == "info_molekyle" and input2 != None: #cpd:C00755
# Get the entry information for vanillin
result = REST.kegg_get(input2).read()
return print(result)
# Display molekylær struktur for cpd:C00051 (vanillin)
elif input1 == "molekyle billede" and input2 != None:
result = REST.kegg_get(input2, "image").read() #"cpd:C00755"
return Image(result)
elif input1 == "Enzyme molekyle" and input2 != None:
result = REST.kegg_find("enzyme", input2).read()
return to_df(result)
#Enzym delen
from Bio.KEGG import Enzyme
request = REST.kegg_get(input1)
records = Enzyme.parse(request)
record = list(records)[0]
if input2 == "reaction":
return record.reaction
elif input2 == "classname":
return record.classname
elif input2 == "genes":
genes = list()
for g in record.genes:
gene_id, gene_symbol = g
genes.append(gene_id)
return genes
else:
print("Du har indskrevet nogget der ikke er gældende. Prøv igen")