def findPathways(cvDict,gmtName, geneDict):
aliasDict, dict1, dict2={}, {}, {} # set up dicts for reading KEGG files
# read in kegg gene symbol dictionaries
nc.parseKEGGdicthsa('inputData/hsa00001.keg',aliasDict,dict1)
nc.parseKEGGdict('inputData/ko00001.keg',aliasDict,dict2)
namelist=find_overlaps(gmtName,cvDict) # find list of pathways with overlaps with the genes from omics data
print('num of overlap nodes: ' + str(len(namelist)))
for name in namelist:
retrieveGraph(name,aliasDict,dict1,dict2, cvDict, geneDict) # find and store gpickles for graphs found
def pipeline_fig_s3(filename):
#Utility for supplementaryFigure3
#python2 version, uses a GMT file as input
aliasDict, dict1, dict2 = {}, {}, {} # set up dicts for reading KEGG files
nc.parseKEGGdicthsa('inputData/hsa00001.keg', aliasDict,
dict1) #read in kegg gene symbol dictionaries
nc.parseKEGGdict('inputData/ko00001.keg', aliasDict, dict2)
keggDict = read_gmt(filename) # read in GMT file
namelist = keggDict.keys() # retain all pathways
pathwayGraphs = {} #dictionary of digraphs
for name in namelist:
pathwayGraphs[name] = retrieveGraph(
name, aliasDict, dict1,
dict2) # find and store gpickles for graphs found
pickle.dump(pathwayGraphs, open('pathwayGraphs.pickle',
"wb")) # save data in correct format
pathwayGraphs = pickle.Unpickler(open('pathwayGraphs.pickle', "rb")).load()
supplement_S3(pathwayGraphs)
Created on Thu May 14 10:28:45 2020
@author: Swapnil Keshari
Summary: This file rewires the network form the Dict 2 which is imported from dataprocessing_1 file
Networkx Version 2.2
"""
import networkx as nx
import matplotlib.pyplot as plt
import networkConstructor as nc
from dataprocessing_1 import Dict2
G = nx.DiGraph()
#Creates a network
code = '04060'
aliasDict, dict1, dict2 = {}, {}, {} # set up dicts for reading KEGG files
nc.parseKEGGdicthsa('inputData/hsa00001.keg', aliasDict, dict1)
nc.parseKEGGdict('inputData/ko00001.keg', aliasDict, dict2)
coder = str('ko' + code)
nc.uploadKEGGcodes([coder], G, dict2)
coder = str('hsa' + code)
nc.uploadKEGGcodes_hsa([coder], G, dict1, dict2)
#Check for common Genes in the graph and the data (CSV) genes
Gene = set(Dict2.keys())
Gene1 = set(G.nodes())
Gene2 = Gene1.intersection(Gene)
nx.write_gml(G, "04060_initial.gml")
#Remove Self Edges
for edge in list(G.edges()):
if edge[0] == edge[1]: