a quick python script to take consensuspathdb data and throw it into a running neo4j instance

consensuspathdb_to_neo4j.py

# This program takes the PPI data from ConsensusDB and populates the NEO4J database with it
# By Nikhil Gopal
#
# To run: python populate_running_db.py ConsensusDB_Human_PPI nodes_list.txt
# The code to generate the nodes_list.txt file exists here: https://gist.github.com/ngopal/9164294

import os, sys
from neo4jrestclient.client import GraphDatabase
from itertools import chain, combinations

# Connect to graph database
gdb = GraphDatabase("http://localhost:7474/db/data/")

# Create a dictionary where gene names correspond to node objects
node_objects = {}
for i in open(sys.argv[2], 'r').readlines():
	if 'Label' not in i:
		node_objects[i.strip('\n')] = "null"
	else:
		continue

# Go through the PPI file
for i in open(sys.argv[1], 'r').readlines():
	if '#' in i:
		continue
	else:
		line = i.strip('\r\n').split('\t')
		genes = line[2].replace('_HUMAN','').split(',')
		score = line[3]
		# create various combinations of genes and confidence scores
		# i.e. [gene1, gene2, gene3] becomes [(gene1,gene2), (gene2,gene3), (gene1,gene3)]
		# and each combination is associated with score1
		combos = [l for l in list(combinations(genes, 2))]
		for gene1, gene2 in combos:
			if "null" in node_objects[gene1]:
				node_objects[gene1] = gdb.nodes.create(name=gene1) #node object has a property 'name' set to the value of gene1
			if "null" in node_objects[gene2]:
				node_objects[gene2] = gdb.nodes.create(name=gene2) #node object has a property 'name' set to the value of gene2
			# node object has a relationship 'interacts' with another node object, and the relationship has a property set to
			# the value of score
			node_objects[gene1].relationships.create("interacts", node_objects[gene2], confidence=score)