def get_genes_from_kegg_pathway(pathway):
from bioservices.kegg import KEGG
k = KEGG()
k.organism = 'hsa'
pathway = k.get(pathway)
genes = k.parse(pathway)['GENE']
entrez, symbol = zip(*[i.split(' ') for i in genes])
return symbol
def __connect(self, organism_code):
"""
Purpose: Connect to the KEGG database specified by organism_code.
@param organism_code: Use 'hsa' to connect to h**o sapien.
@return: n/a
"""
k = KEGG()
k.organism = organism_code
return k
#from Bio import Entrez
from bioservices.kegg import KEGG
import sys
k = KEGG()
#Entrez.email = "*****@*****.**"
#file = open(sys.argv[1], "r")
file = open("../data/ids5.txt", "r")
result = ""
k.organism = "lpl"
k.get()
#for line in file.readlines():
#
file.close()
print(result)
# for line in file.readlines():
# handle = Entrez.esearch(db="pubmed", term=line)
# record = Entrez.read(handle)
# ids = record["IdList"]
# print(ids)
"""
KEGG module example
====================
Histogram of KEGG pathways relations
"""
#################################################
#
from pylab import *
# extract all relations from all pathways
from bioservices.kegg import KEGG
s = KEGG()
s.organism = "hsa"
# retrieve more than 260 pathways so it takes time
max_pathways = 10
results = [s.parse_kgml_pathway(x) for x in s.pathwayIds[0:max_pathways]]
relations = [x['relations'] for x in results]
# plot
hist([len(this) for this in relations], 20)
xlabel('number of relations')
ylabel('#')
title("number of relations per pathways")
grid(True)
Author: Daniel Esposito
Date: 28/12/2015
Purpose: Wrapper Class for accessing KEGG via the bioservices interface. So far this class implements
methods to obtain all pathways and then all reactions from those pathways in edgelist format
tagged with the type of reaction.
"""
from bioservices.kegg import KEGG
from predict.parsing import PPI
import pandas as pd
# ----------------------------------- UTILS -------------------------------- #
kegg = KEGG()
kegg.organism = 'hsa'
reactions_to_exclude = [
'missing-interaction',
'indirect-effect',
'expression',
'repression',
'compound',
'hidden-compound'
]
def uniprot_cmp(x, y):
t = {'P':0, 'Q':1, 'O':2}
try:
x_num = t[x[0]]
except KeyError:
x_num = ord(x[0])
import re
from bioservices.kegg import KEGG
# -- KEGG bioservice
bioser = KEGG(cache=True)
bioser.organism = 'hsa'
# Get pathways
keggp = {p: bioser.get(p) for p in bioser.pathwayIds}
print '[INFO] Pathways fetched'
# Get reactions
keggr = {r: bioser.get(r) for r in bioser.reactionIds}
print '[INFO] Reactions fetched'
# Get enzymes
kegge = {e: bioser.get(e) for e in bioser.enzymeIds}
print '[INFO] Enzymes fetched'
# keggc = {c: bioser.get(c) for c in bioser.compoundIds}
# print '[INFO] Compounds fetched'
#
# # Get modules
# keggm = {m: bioser.get(m) for m in bioser.moduleIds}
# print '[INFO] Modules fetched'
# -- KEGG methods
def get_pathway_names(pathways=None):
pathways_ = pathways if pathways else set(keggp)
return {p: re.findall('NAME\s+(.*)?\n', keggp[p])[0].split(' - ')[0] for p in pathways_}
"""
KEGG module example
====================
Histogram of KEGG pathways relations
"""
#################################################
#
from pylab import *
# extract all relations from all pathways
from bioservices.kegg import KEGG
s = KEGG()
s.organism = "hsa"
# retrieve more than 260 pathways so it takes time
max_pathways = 10
results = [s.parse_kgml_pathway(x) for x in s.pathwayIds[0:max_pathways]]
relations = [x['relations'] for x in results]
# plot
hist([len(this) for this in relations], 20)
xlabel('number of relations')
ylabel('#')
title("number of relations per pathways")
grid(True)
