def download_all_kegg_pathways(species_code='mmu'):
"""
"""
pathways_str = REST.kegg_list("pathway", species_code).read()
pathways = {p.split('\t')[0]:{'name':p.split('\t')[1]} for p in pathways_str.rstrip().split('\n')}
def get_genes_for(pathways):
for pathway in pathways:
pathways[pathway]['geneid'] = set(); pathways[pathway]['gene_symbol'] = set()
pathway_file = REST.kegg_get(pathway).read() # query and read each pathway
# iterate through each KEGG pathway file, keeping track of which section
# of the file we're in, only read the gene in each pathway
current_section = None
for line in pathway_file.rstrip().split("\n"):
section = line[:12].strip() # section names are within 12 columns
if not section == "":
current_section = section
if current_section == "GENE":
try:
gene_identifiers, _ = line[12:].split("; ")[:2]
geneid, gene_symbol = gene_identifiers.split()
pathways[pathway]['geneid'].add(int(geneid))
pathways[pathway]['gene_symbol'].add(gene_symbol)
except: pass#print('Discarded:', line);
get_genes_for(pathways)
return pathways
def load_taxon_id(self, in_code=None):
''' lets try getting it directly from KEGG based on inputted organism 3-letter code
a bit hairy but it works! TODO: cache the org_table and gen_table in cache/'''
if self.taxon_id is not None:
return self.taxon_id
import Bio.KEGG.REST as kegg ## requires BioPython 1.65 or later!
if in_code is None:
in_code = self.tables['run_infos'].organism[0]
org_table = kegg.kegg_list('organism').readlines()
org_table = ''.join(org_table)
buf = cStringIO.StringIO(org_table)
org_table = pd.read_table(buf, sep='\t', header=None)
#full_org_name = org_table.ix[org_table[1]==in_code][2].values[0]
buf.close()
kegg_code = org_table.ix[org_table[1] == in_code][0].values[0]
gen_table = kegg.kegg_list('genome').readlines()
gen_table = ''.join(gen_table)
buf = cStringIO.StringIO(gen_table)
gen_table = pd.read_table(buf, sep='\t', header=None)
buf.close()
taxon_id = int(
gen_table.ix[gen_table[0] == 'genome:' +
kegg_code][1].values[0].split(', ')[2].split('; ')[0])
self.taxon_id = taxon_id
return taxon_id
def get_kegg_gene_to_external_map(species):
"""Maps kegg genes to external gene names.
Legacy function for goverlap. Deprecated. """
kegg_list = REST.kegg_list(species)
clean_kegg_info = re.compile(r"{}:|\n".format(species))
parse_kegg_info = re.compile(r"[^\t;\n]+")
rowdicts = []
for kegg_info in kegg_list:
try:
kegg_info = kegg_info.decode("utf-8")
except AttributeError:
pass
kegg_info = re.sub(clean_kegg_info, "", kegg_info)
kegg_data = re.findall(parse_kegg_info, kegg_info)
for gene in kegg_data[1].split(", "):
rowdict = {"entrezgene": kegg_data[0], "gene": gene}
rowdicts.append(rowdict)
return DataFrame.from_dict(rowdicts)
def fetch_entry_list(database):
"connects to appropriate KEGG database and fetches list of all entries"
all_entries_df = pd.read_csv(REST.kegg_list(database),
sep='\t',
header=None,
names=['id', 'description'])
return all_entries_df
def get_kegg(self, K_number):
print(K_number)
self.cur.execute(
"""SELECT K_number from kegg_reference where K_number = ?""",
(K_number, ))
if self.cur.fetchone():
return
name = definition = identifier = ec_number = None
try:
kegg_list = REST.kegg_list(K_number).read()
identifier, definition = kegg_list.strip().split("\t",
1)[1:][0].split(
";", 1)
definition = definition.rstrip("]").split("[EC:")
name = definition[0]
ec_number = None
if len(definition) == 2:
ec_number = definition[1]
except Exception as e:
sys.stderr.write("\t".join([K_number, str(e)]))
finally:
self.cur.execute(
"""INSERT OR IGNORE INTO kegg_reference(K_number, name, identifier, ec_number)
VALUES(?,?,?,?)""",
(K_number, name, identifier, ec_number))
sys.stderr.write(str(self.cur.lastrowid) + "\n")
self.conx.commit()
def create_id_name_dict(db):
## Grab list of ids in db
id_name_dict = dict()
raw_list = REST.kegg_list(db)
id_name_list = [s.split('\t') for s in raw_list.read().splitlines()]
for i in id_name_list:
id_name_dict[i[0]] = i[1]
return id_name_dict
def queryAllPathway(fpathway=None, fpathwayInfo=None, hsa='hsa'):
human_pathways = REST.kegg_list("pathway", hsa).read()
repair_pathways = []
repair_pathways_info = []
for line in human_pathways.rstrip().split("\n"):
entry, description = line.split("\t")
entry = entry.split(':')[1]
repair_pathways.append(entry)
repair_pathways_info.append((entry, description))
if fpathway: saveList(repair_pathways, fpathway)
if fpathwayInfo: saveList(repair_pathways_info, fpathwayInfo)
return repair_pathways
def _retrieve_lists(dbs):
lists = dict()
for db in dbs:
## Retreive all entry ids and names
id_name_dict = dict()
raw_list = REST.kegg_list(db)
id_name_list = [s.split('\t') for s in raw_list.read().splitlines()]
for i in id_name_list:
id_name_dict[i[0]] = i[1]
lists[db] = list(id_name_dict.keys())
return lists
def get_pathway_to_definition_map(species):
"""Map kegg paths to their definition."""
kegg_list = REST.kegg_list("pathway", species)
clean_kegg_path = re.compile(r"path:{}|\n".format(species))
rowdicts = []
for kegg_path_line in kegg_list:
kegg_info = re.sub(clean_kegg_path, "", kegg_path_line)
pathway, definition = kegg_info.split("\t")
definition = definition.split(" - ")[0] # Remove species info
rowdict = {"kegg_pathway": pathway, "kegg_pathway_definition":
definition}
rowdicts.append(rowdict)
return DataFrame.from_dict(rowdicts)
def get_individual(target):
try:
individual = REST.kegg_list(target).readlines()
target_db = []
name = []
for line in individual:
entity = line.strip().split('\t')
target_db.append(entity[0])
name.append(entity[1])
df_individual = pd.DataFrame({target : target_db, "name" : name})
df_individual.replace('.+(?<=\:)','', regex=True, inplace=True)
df_individual.to_csv("./database/"+'kegg_'+target+'.tsv', sep = '\t', index = None)
except HTTPError:
sys.exit("ERROR: Please select the available database according to the following URL. (http://www.kegg.jp/kegg/rest/keggapi.html) ")
return df_individual
def kegg_rest(type: str,
argument: str,
optional_argument: str = "",
sleep_time: float = .5) -> List[str]:
"""This function calls Biopython's KEGG REST function and returns the lines as a string list.
All empty lines are deleted from the list as they do not contain any information.
Arguments
----------
* type: str ~ The KEGG REST action. Can be either 'info', 'get', 'link' or 'list.
* argument: str ~ The argument for the KEGG order.
* optional_argument: str="" ~ The second argument which is necessary for 'link' and 'list' actions
to work correctly.
* sleep_time: float=10.0 ~ The time that shall be waited after a REST action is performed.
Its default value of 10.0 seconds is in accordance with the NCBI
rule that its servers shall not be contacted more often than every
10 seconds. KEGG might have lower or higher required sleep times,
but I did not find any specified time step.
"""
# Execute correct Biotpython KEGG REST function.
if type == "info":
kegg_data = REST.kegg_info(argument)
elif type == "get":
kegg_data = REST.kegg_get(argument)
elif type == "link":
kegg_data = REST.kegg_link(argument, optional_argument)
elif type == "list":
kegg_data = REST.kegg_list(argument, optional_argument)
elif type == "find":
kegg_data = REST.kegg_find(argument, optional_argument)
# Wait the sleep time doing nothing.
time.sleep(sleep_time)
# Get one string per line of the KEGG REST result.
lines: List[str] = kegg_data.read().split("\n")
# Delete empty lines.
not_empty_lines: List[str] = [i for i in lines if len(i) > 0]
return not_empty_lines
def get_kegg_gene_to_external_map(species):
"""Maps kegg genes to external gene names."""
kegg_list = REST.kegg_list(species)
clean_kegg_info = re.compile(r"{}:|\n".format(species))
parse_kegg_info = re.compile(r"[^\t;\n]+")
rowdicts = []
for kegg_info in kegg_list:
kegg_info = re.sub(clean_kegg_info, "", kegg_info)
kegg_data = re.findall(parse_kegg_info, kegg_info)
for gene in kegg_data[1].split(", "):
rowdict = {"kegg_gene": kegg_data[0], "gene": gene}
rowdicts.append(rowdict)
return DataFrame.from_dict(rowdicts)
def save_all_kegg_pathway_files(paths):
"""Uses the KEGG REST API to find and save all pathway data files for each species in the input dictionary.
Args:
paths (dict of str:str): A mapping between strings referencing species and paths to the output directory for each.
"""
for species, path in paths.items():
pathways = REST.kegg_list("pathway", species)
for pathway in pathways:
# Get the pathway file contents through the REST API.
pathway_id = pathway.split()[0]
pathway_file = REST.kegg_get(dbentries=pathway_id).read()
# Where should the contents of the obtained file be written?
pathway_id_str = pathway_id.replace(":", "_")
filename = os.path.join(path, "{}.txt".format(pathway_id_str))
if not os.path.exists(path):
os.makedirs(path)
with open(filename, "w") as outfile:
outfile.write(pathway_file)
def main():
# 'hsa', 'dme'
for pwid in ['dre', 'cel', 'sce', 'mmu']:
human_pathways = REST.kegg_list('pathway', pwid).read()
pathways = [line for line in human_pathways.strip().split('\n')]
# Get the genes for pathways and add them to a list
pathways_dict = defaultdict(list)
for pathway in pathways:
entry, description = pathway.split('\t')
pathway_file = REST.kegg_get(
entry).read() # query and read each pathway
# iterate through each KEGG pathway file, keeping track of which section
# of the file we're in, only read the gene in each pathway
current_section = None
for line in pathway_file.rstrip().split('\n'):
section = line[:12].strip(
) # section names are within 12 columns
if not section == '':
current_section = section
if current_section == 'GENE':
if len(line[12:].split('; ')) > 1:
gene_identifiers, *gene_description = line[12:].split(
'; ')
gene_id, gene_symbol = gene_identifiers.split()
pathways_dict[description.split(' - ')[0]].append(
gene_symbol)
with open('in/{0}.gmt'.format(pwid), 'w') as pw_file:
out_pw = [
'{0}\t\t{1}\n'.format(desc,
'\t'.join(sorted(pathways_dict[desc])))
for desc in sorted(pathways_dict)
if len(pathways_dict[desc]) > 4
]
pw_file.writelines(out_pw)
return None
def find_kegg(genes):
count=0
lpl_pathways = REST.kegg_list("pathway", "lpl").read()
entries = []
for line in lpl_pathways.rstrip().split("\n"):
entry, description = line.split("\t")
#print(line)
entries.append(entry)
print(entries)
pathway = {}
for i in genes:
for entry in entries:
count+=1
get = REST.kegg_get(entry, option=None)
get_read = get.readlines()
if any(i in s for s in get_read):
print(entry)
print(i)
#checkt of j als een k in de dictionary staat, maakt een lijst van alle values van de key wanneer dit zo is en updat de key met de ljst+ nieuwe gen id)
if i in pathway:
k = pathway.get(i)
#print(k)
m = []
if isinstance(k, list):
for l in k:
m.append(l)
else:
m.append(k)
if entry not in m:
m.append(entry)
pathway.update({i:m})
#voegt j als een nieuwe key toe aan de dictionary
else:
pathway[i] = []
pathway.update({i:entry})
print(pathway, count)
print(pathway)
return pathway
def get_pathway_to_definition_map(species):
"""Map kegg paths to their definition."""
kegg_list = REST.kegg_list("pathway", species)
clean_kegg_path = re.compile(r"path:{}|\n".format(species))
rowdicts = []
for kegg_path_line in kegg_list:
try:
kegg_path_line = kegg_path_line.decode("utf-8")
except AttributeError:
pass
kegg_info = re.sub(clean_kegg_path, "", kegg_path_line)
pathway, definition = kegg_info.split("\t")
definition = definition.split(" - ")[0] # Remove species info
rowdict = {"kegg_pathway": pathway,
"kegg_pathway_definition": definition}
rowdicts.append(rowdict)
return DataFrame.from_dict(rowdicts)
def update_files(base_dir="/data/databases/kegg/"):
for db in ["pathway", "ko", "cpd", "brite"]:
with open(base_dir + db + ".txt", "w") as h:
data = REST.kegg_list(db).read()
h.write(data)
# wget http://www.kegg.jp/kegg-bin/download_htext?htext=br08901.keg&format=json&filedir=
# wget http://www.kegg.jp/kegg-bin/download_htext?htext=br08001.keg&format=json&filedir=
L = list(open(base_dir + "pathway.txt"))
for pathway in tqdm(L):
pw = "ko" + pathway.split()[0].split(":map")[1]
kgmlpath = base_dir + "ko/" + pw + ".kgml"
if not os.path.exists(kgmlpath):
with open(kgmlpath, "w") as h:
try:
data = REST.kegg_get(pw, option="kgml").read()
h.write(data)
sleep(1)
except:
pass
def get_network(org, opt='ec'):
# Creating a Parser Object
graph = k.KeggParser()
# Store pathways that doesn't have EC numbers
error = []
# Getting organism
list1 = r.kegg_list('pathway', org).read()
list1 = list1.split('\n')
list1.remove('')
print('Retrieving data from KEGG PATHWAY database. ' + str(time.ctime()))
# For each path getting enzymes and reactions
for path in list1:
try:
path = path.split('\t')
# print (path[0])
graph.genes = parse.read(r.kegg_get(path[0], 'kgml'))
graph.genes_default = parse.read(
r.kegg_get("path:" + opt + path[0][-5:], 'kgml'))
graph.path = path
except Exception:
error.append(path[0])
continue
# print ("getting relations")
graph.get_relations()
# print ("getting reaction")
graph.get_reactions()
# print ('Unretrieved data',error)
graph.ref = opt
genes = 0
for i in graph.ec_org_target.items():
genes += len(i[1].split())
# print (graph.ec_org_target.keys())
# Building Graph
graph.building_graph(2)
return (graph)
def amount_pathway_genes():
"""
Function to measure the amount repair genes in a human pathway.
:return:
"""
human_pathways = REST.kegg_list("pathway", "hsa").read()
# Filter all human pathways for repair pathways
repair_pathways = []
for line in human_pathways.rstrip().split("\n"):
entry, description = line.split("\t")
if "repair" in description:
repair_pathways.append(entry)
# Get the genes for pathways and add them to a list
repair_genes = []
for pathway in repair_pathways:
pathway_file = REST.kegg_get(pathway).read() # query and read each pathway
# iterate through each KEGG pathway file, keeping track of which section
# of the file we're in, only read the gene in each pathway
current_section = None
for line in pathway_file.rstrip().split("\n"):
section = line[:12].strip() # section names are within 12 columns
if not section == "":
current_section = section
if current_section == "GENE":
gene_identifiers, gene_description = line[12:].split("; ")
gene_id, gene_symbol = gene_identifiers.split()
if not gene_symbol in repair_genes:
repair_genes.append(gene_symbol)
print("There are %d repair pathways and %d repair genes. The genes are:" % \
(len(repair_pathways), len(repair_genes)))
print(", ".join(repair_genes))
def t_KEGG_Query():
"""Tests Bio.KEGG API Wrapper"""
print("Testing Bio.KEGG.query\n\n")
# info tests
resp = REST.kegg_info("kegg")
resp.read()
print(resp.url)
resp = REST.kegg_info("pathway")
resp.read()
print(resp.url)
# list tests
resp = REST.kegg_list("pathway")
resp.read()
print(resp.url)
resp = REST.kegg_list("pathway", "hsa")
resp.read()
print(resp.url)
resp = REST.kegg_list("organism")
resp.read()
print(resp.url)
resp = REST.kegg_list("hsa")
resp.read()
print(resp.url)
resp = REST.kegg_list("T01001")
resp.read()
print(resp.url)
resp = REST.kegg_list("hsa:10458+ece:Z5100")
resp.read()
print(resp.url)
resp = REST.kegg_list(["hsa:10458", "ece:Z5100"])
resp.read()
print(resp.url)
resp = REST.kegg_list("cpd:C01290+gl:G00092")
resp.read()
print(resp.url)
resp = REST.kegg_list(["cpd:C01290", "gl:G00092"])
resp.read()
print(resp.url)
resp = REST.kegg_list("C01290+G00092")
resp.read()
print(resp.url)
resp = REST.kegg_list(["C01290", "G00092"])
resp.read()
print(resp.url)
# find tests
resp = REST.kegg_find("genes", "shiga+toxin")
resp.read()
print(resp.url)
resp = REST.kegg_find("genes", ["shiga", "toxin"])
resp.read()
print(resp.url)
resp = REST.kegg_find("compound", "C7H10O5", "formula")
resp.read()
print(resp.url)
resp = REST.kegg_find("compound", "O5C7", "formula")
resp.read()
print(resp.url)
resp = REST.kegg_find("compound", "174.05", "exact_mass")
resp.read()
print(resp.url)
resp = REST.kegg_find("compound", "300-310", "mol_weight")
resp.read()
print(resp.url)
# get tests
resp = REST.kegg_get("cpd:C01290+gl:G00092")
resp.read()
print(resp.url)
resp = REST.kegg_get(["cpd:C01290", "gl:G00092"])
resp.read()
print(resp.url)
resp = REST.kegg_get("C01290+G00092")
resp.read()
print(resp.url)
resp = REST.kegg_get(["C01290", "G00092"])
resp.read()
print(resp.url)
resp = REST.kegg_get("hsa:10458+ece:Z5100")
resp.read()
print(resp.url)
resp = REST.kegg_get(["hsa:10458", "ece:Z5100"])
resp.read()
print(resp.url)
resp = REST.kegg_get("hsa:10458+ece:Z5100", "aaseq")
resp.read()
print(resp.url)
resp = REST.kegg_get(["hsa:10458", "ece:Z5100"], "aaseq")
resp.read()
print(resp.url)
resp = REST.kegg_get("hsa05130", "image")
resp.read()
print(resp.url)
# conv tests
resp = REST.kegg_conv("eco", "ncbi-geneid")
resp.read()
print(resp.url)
resp = REST.kegg_conv("ncbi-geneid", "eco")
resp.read()
print(resp.url)
resp = REST.kegg_conv("ncbi-gi", "hsa:10458+ece:Z5100")
resp.read()
print(resp.url)
resp = REST.kegg_conv("ncbi-gi", ["hsa:10458", "ece:Z5100"])
resp.read()
print(resp.url)
# link tests
resp = REST.kegg_link("pathway", "hsa")
resp.read()
print(resp.url)
resp = REST.kegg_link("hsa", "pathway")
resp.read()
print(resp.url)
resp = REST.kegg_link("pathway", "hsa:10458+ece:Z5100")
resp.read()
print(resp.url)
resp = REST.kegg_link("pathway", ["hsa:10458", "ece:Z5100"])
resp.read()
print(resp.url)
#!/usr/bin/env python
# encoding: utf-8
"""
@author: zhuhz
@file: keggAPI_v1.py
@time: 2020/6/17 9:13
"""
from Bio.KEGG import REST
orthologies = REST.kegg_list('orthology').read()
res = 'ko' + '\t' + 'ko name' + '\t' + 'ko des' + '\t' + 'map' + '\t' + 'map name' + '\t' + 'map class' + '\n'
for orth in orthologies.rstrip().split('\n'):
ko_entry, ko_des = orth.strip().split('\t')
ko_id = ko_entry.strip().split(':')[1]
try:
ko_name, ko_func = ko_des.strip().split('; ', 1)
except ValueError:
ko_name = ko_des
ko_func = ko_des
ko_info = REST.kegg_get(ko_entry).read()
current_section = None
for line in ko_info.rstrip().split('\n'):
section = line[:12].strip()
if not section == '':
current_section = section
if current_section == 'PATHWAY':
maps = line[12:]
for map in maps.rstrip().split('\n'):
map_entry, map_name = (
def get_organisms():
organisms = REST.kegg_list('organism').read()
organisms = [i.split('\t') for i in organisms.split('\n')]
return organisms
#!/usr/bin/env python
# encoding: utf-8
"""
@author: zhuhz
@file: keggAPI.py
@time: 2020/6/16 13:58
"""
from Bio.KEGG import REST
pathways = REST.kegg_list('pathway').read()
# print(type(pathways))
res = 'ko' + '\t' + 'ko name' + '\t' + 'ko des' + '\t' + 'module' + '\t' + 'module name' + '\t' + 'map' + '\t' + 'map name' + '\t' + 'map class' + '\n'
for pathway in pathways.rstrip().split('\n'):
map_entry, map_description = pathway.split('\t')
# print(map_entry)
map = REST.kegg_get(map_entry).read()
# print(type(map))
current_section = None
for line in map.rstrip().split('\n'):
section = line[:12].strip()
if not section == '':
current_section = section
if current_section == 'NAME':
map_name = line[12:]
elif current_section == 'CLASS':
map_class = line[12:]
# elif current_section == 'PATHWAY_MAP':
# map_des = line[22:]
elif current_section == 'MODULE':
def get_pathways(organism):
pathways = REST.kegg_list('pathway', organism).read()
pathways = [i.split('\t')[0] for i in pathways.split('\n')]
return pathways
from Bio.KEGG import REST
drug = REST.kegg_list('drug').read()
# 가져올 수 있는 것: brite, pathway, genome(gene은 안됨), module, enzyme, glycan, compound, reaction, network, drug, disease
drug_list = []
drug_name=input("찾고 싶은 약과 관련된 것을 입력해주세요: ")
# 찾고 싶은 약과 관련된 것을 입력받아 검색한다(예: vaccine)
for line in drug.rstrip().split("\n"):
entry, description = line.split("\t")
if drug_name in description:
drug_list.append(description)
print(drug_list)
from Bio.KEGG import REST
from bioservices import Reactome
import csv
from input import inp
#gene_list = ['POLD1', 'POLE3', 'ABO', 'TP53']
gene_list = inp
specie = "hsa"
human_pathways = REST.kegg_list("pathway", specie).read()
human_pathways_dict = {}
repair_pathways = []
repair_pathways_dict = {}
for line in human_pathways.rstrip().split("\n"):
entry, description = line.split("\t")
human_pathways_dict[entry] = description
if "DNA" in description:
repair_pathways.append(entry)
repair_pathways_dict[entry] = description
rejected = []
gene_dict = dict((gene,[]) for gene in gene_list)
i = 0
len_ = len(human_pathways_dict.keys())
for pathway in human_pathways_dict.keys():
i += 1
print str(i) + ' // ' + str(len_)
#print pathway
def t_KEGG_Query():
"""Tests Bio.KEGG API Wrapper"""
print("Testing Bio.KEGG.query\n\n")
# info tests
resp = REST.kegg_info("kegg")
resp.read()
print(resp.url)
resp = REST.kegg_info("pathway")
resp.read()
print(resp.url)
# list tests
resp = REST.kegg_list("pathway")
resp.read()
print(resp.url)
resp = REST.kegg_list("pathway", "hsa")
resp.read()
print(resp.url)
resp = REST.kegg_list("organism")
resp.read()
print(resp.url)
resp = REST.kegg_list("hsa")
resp.read()
print(resp.url)
resp = REST.kegg_list("T01001")
resp.read()
print(resp.url)
resp = REST.kegg_list("hsa:10458+ece:Z5100")
resp.read()
print(resp.url)
resp = REST.kegg_list(["hsa:10458", "ece:Z5100"])
resp.read()
print(resp.url)
resp = REST.kegg_list("cpd:C01290+gl:G00092")
resp.read()
print(resp.url)
resp = REST.kegg_list(["cpd:C01290", "gl:G00092"])
resp.read()
print(resp.url)
resp = REST.kegg_list("C01290+G00092")
resp.read()
print(resp.url)
resp = REST.kegg_list(["C01290", "G00092"])
resp.read()
print(resp.url)
# find tests
resp = REST.kegg_find("genes", "shiga+toxin")
resp.read()
print(resp.url)
resp = REST.kegg_find("genes", ["shiga", "toxin"])
resp.read()
print(resp.url)
resp = REST.kegg_find("compound", "C7H10O5", "formula")
resp.read()
print(resp.url)
resp = REST.kegg_find("compound", "O5C7", "formula")
resp.read()
print(resp.url)
resp = REST.kegg_find("compound", "174.05", "exact_mass")
resp.read()
print(resp.url)
resp = REST.kegg_find("compound", "300-310", "mol_weight")
resp.read()
print(resp.url)
# get tests
resp = REST.kegg_get("cpd:C01290+gl:G00092")
resp.read()
print(resp.url)
resp = REST.kegg_get(["cpd:C01290", "gl:G00092"])
resp.read()
print(resp.url)
resp = REST.kegg_get("C01290+G00092")
resp.read()
print(resp.url)
resp = REST.kegg_get(["C01290", "G00092"])
resp.read()
print(resp.url)
resp = REST.kegg_get("hsa:10458+ece:Z5100")
resp.read()
print(resp.url)
resp = REST.kegg_get(["hsa:10458", "ece:Z5100"])
resp.read()
print(resp.url)
resp = REST.kegg_get("hsa:10458+ece:Z5100", "aaseq")
resp.read()
print(resp.url)
resp = REST.kegg_get(["hsa:10458", "ece:Z5100"], "aaseq")
resp.read()
print(resp.url)
resp = REST.kegg_get("hsa05130", "image")
resp.read()
print(resp.url)
# conv tests
resp = REST.kegg_conv("eco", "ncbi-geneid")
resp.read()
print(resp.url)
resp = REST.kegg_conv("ncbi-geneid", "eco")
resp.read()
print(resp.url)
resp = REST.kegg_conv("ncbi-gi", "hsa:10458+ece:Z5100")
resp.read()
print(resp.url)
resp = REST.kegg_conv("ncbi-gi", ["hsa:10458", "ece:Z5100"])
resp.read()
print(resp.url)
# link tests
resp = REST.kegg_link("pathway", "hsa")
resp.read()
print(resp.url)
resp = REST.kegg_link("hsa", "pathway")
resp.read()
print(resp.url)
resp = REST.kegg_link("pathway", "hsa:10458+ece:Z5100")
resp.read()
print(resp.url)
resp = REST.kegg_link("pathway", ["hsa:10458", "ece:Z5100"])
resp.read()
print(resp.url)
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")
#13.10.KEGG.py
from Bio.KEGG import REST
human_pathways = REST.kegg_list("pathway", "hsa").read()
hepatitis_pathways = []
for line in human_pathways.rstrip().split("\n"):
entry, description = line.split("\t")
if "hepatitis" in description.lower():
hepatitis_pathways.append(entry)
print(entry, description)
print(hepatitis_pathways)
hepatitis_genes = []
for pathway in hepatitis_pathways:
pathway_file = REST.kegg_get(pathway).read()
current_section = None
for line in pathway_file.rstrip().split("\n"):
section = line[:12].strip()
if not section == "":
current_section = section
if current_section == "GENE":
gene_identifiers, gene_description = line[12:].split("; ")
gene_id, gene_symbol = gene_identifiers.split()
if not gene_symbol in hepatitis_genes:
hepatitis_genes.append(gene_symbol)
print(
analysis_folder=os.path.dirname(__file__)
KEGG_data_folder=os.path.join(analysis_folder, 'KEGG_data/')
import urllib.request
#Download KEGG onthology
if not os.path.isfile(os.path.join(KEGG_data_folder,'ko00001.json')):
url='https://www.genome.jp/kegg-bin/download_htext?htext=ko00001&format=json&filedir='
urllib.request.urlretrieve(url, os.path.join(KEGG_data_folder,'ko00001.json'))
#get all human pathways
hsa_path_list=KEGG_REST.kegg_list('pathway','hsa')
identifiers=[]
for line in hsa_path_list:
identifiers.append(line.partition('\t')[0][5:])
for identifier in identifiers:
KGML_handle=KEGG_REST.kegg_get(identifier,option='kgml')
file=open(os.path.join(KEGG_data_folder,identifier+'.kgml'),'w')
file.write(KGML_handle.read())
file.close()
#%%
parse_pathways=1
if parse_pathways:
from Bio.KEGG import REST
from bioservices import Reactome
import csv
from input import inp
#gene_list = ['POLD1', 'POLE3', 'ABO', 'TP53']
gene_list = inp
specie = "hsa"
human_pathways = REST.kegg_list("pathway", specie).read()
human_pathways_dict = {}
repair_pathways = []
repair_pathways_dict = {}
for line in human_pathways.rstrip().split("\n"):
entry, description = line.split("\t")
human_pathways_dict[entry] = description
if "DNA" in description:
repair_pathways.append(entry)
repair_pathways_dict[entry] = description
rejected = []
gene_dict = dict((gene, []) for gene in gene_list)
i = 0
len_ = len(human_pathways_dict.keys())
for pathway in human_pathways_dict.keys():
i += 1
print str(i) + ' // ' + str(len_)
#print pathway
pathway_file = REST.kegg_get(pathway).read()
current_section = None
from Bio.Seq import Seq
from Bio.KEGG import Enzyme
from Bio.KEGG import REST
from Bio.KEGG.KGML import KGML_parser
from Bio.KEGG import Map
#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)
#print(record.entry)
organisms = REST.kegg_list("organism").read()
organismlist = []
for line in organisms.rstrip().split("\n"):
#print(line)
code = line.split("\t")[1]
organismlist.append(code)
#print(organismlist)
#parser = KGML_parser.KGMLparser()
#open("human_map.xml",'w').write(REST.kegg_get("hsa05130",option="kgml").read())
human_map = KGML_parser.read(REST.kegg_get("hsa01100",option="kgml"))
cpds = human_map.compounds
for cpd in cpds:
print(cpd.name)
graphics = cpd.graphics
for graphic in graphics:
print(graphic.x)
rxns = human_map.reaction_entries
from Bio.KEGG import REST
import urllib.request
import re
import sys
##### TO DO #############
#### Get Organism ID from organims name #####
result = REST.kegg_list("pathway", "aga").read()
#print(result.split("\t")[0])
pathw_ids = []
pathw = []
for item in result.split("\t"):
#print(item)
#print("*")
tmp2 = item.split("\n")
if len(tmp2) > 1:
if tmp2[1] != "":
pathw.append(tmp2[0])
pathw_ids.append(tmp2[1])
#print(pathw)
for pathway in pathw_ids:
#pathway = 'hsa00010' # glycolysis
url = "http://rest.kegg.jp/get/" + pathway
with urllib.request.urlopen(url) as f:
lines = f.read().decode('utf-8').splitlines()
want = 0
for line in lines:
fields = line.split()
def list(db, org="hsa"):
# Create a static method which invokes the REST.kegg_list function from the Biopython module.
# Return the result as a bytes string
return str.encode(REST.kegg_list(db, org).read())