# to convert network in gml to json format for web visulization
import json
import networkx as nx
from networkx.readwrite import json_graph
import sys
sys.path.append('/Users/zichen/Documents/bitbucket/maayanlab_utils')
from fileIO import mysqlTable2dict
d_sename_umls = mysqlTable2dict('sep', 'side_effects', 2, 1)
def gml2json(gml_fn, json_fn):
G = nx.read_gml(gml_fn)
print G.number_of_nodes(), G.number_of_edges()
for node_id in G.nodes():
node_dict = G.node[node_id]
if '|' in node_dict['label']:
sl = node_dict['label'].split('|')
label = '%s (%s)' % (sl[1], sl[0])
G.node[node_id]['label'] = label
# clean labels and add xref
if node_dict['type'] == "SE":
G.node[node_id]['type'] = 'triangle-up'
G.node[node_id]['xref'] = d_sename_umls[node_dict['label']] # umls
else:
sl = G.node[node_id]['label'].split('(')
xref = sl[-1]
label = '('.join(sl[0:-1])
label = label.strip()
PREDICTION_DF = HOME + '/Documents/Zichen_Projects/drug_se_prediction/PTs_RF1000_proba_df_n20338x1053.txt'
## for side effects
# GMT_FN = HOME+'/Documents/Zichen_Projects/drug_se_prediction/RF1000_GOtCS_AUC_0.7_proba_0.6_prediction_only.gmt'
GMT_FN = HOME+'/Documents/Zichen_Projects/drug_se_prediction/ET100_GOtCS_AUC_0.76_proba_0.75.gmt'
GML_FN = HOME+'/Documents/Zichen_Projects/drug_se_prediction/side_effect_network.gml'
## for drugs
# GMT_FN = HOME+'/Documents/Zichen_Projects/drug_se_prediction/RF1000_GOtCS_AUC_0.7_proba_0.6_prediction_only_flipped.gmt'
# GML_FN = HOME+'/Documents/Zichen_Projects/drug_se_prediction/drug_network.gml'
CSV_FN = GML_FN.replace('.gml', '.csv')
JSON_FN = CSV_FN.replace('.csv', '.json')
## retrieve meta data about SE
d_umls_pt = mysqlTable2dict('sep', 'side_effects', 1, 2)
d_pt_umls = mysqlTable2dict('sep', 'side_effects', 2, 1)
d_soc_pt = read_gmt(HOME+'/Documents/bitbucket/pertid2trainingset/Y_matrix_no_mfc/SOC_to_pt.gmt')
print len(d_soc_pt)
d_umls_soc = {}
for soc, pts in d_soc_pt.items():
for pt in pts:
umls = d_pt_umls[pt]
if umls is not None:
if umls not in d_umls_soc:
d_umls_soc[umls] = soc
# else:
# d_umls_soc[umls].append(soc) # one PT may have multiple SOCs
# for pt in d_umls_soc:
# if len(d_umls_soc[pt]) != 1:
if kwargs['umls_id'] in d_umls_soc:
kwargs['soc'] = d_umls_soc[kwargs['umls_id']]
else:
kwargs['soc'] = None
instance = get_or_create(session, SideEffect, **kwargs)
for pvals, pert_id in zip(mat, pert_ids):
mask = pvals > 0.5
se_names_pos = se_names[mask].tolist()
aucs_pos = aucs[mask].tolist()
pvals_pos = pvals[mask].tolist()
add_predictions(se_names_pos, aucs_pos, pert_id, pvals_pos, session)
## transfer association tables
# sider_connections
d_pert_ids = mysqlTable2dict('maaya0_SEP', 'drugs_lincs', 0, 1)
d_umls_id = mysqlTable2dict('maaya0_SEP', 'side_effects', 0, 1)
conn = MySQLdb.connect(host='localhost',
user='******',
passwd='',
db='maaya0_SEP')
cur = conn.cursor()
query = """SELECT * FROM `%s`""" % 'sider_connections'
cur.execute(query)
d_pert_umls_ids = {}
for row in cur:
pert_id, umls_id = row
if pert_id in d_pert_ids and umls_id in d_umls_id:
if pert_id not in d_pert_umls_ids:
d_pert_umls_ids[pert_id] = [umls_id]
kwargs['soc'] = None
instance = get_or_create(session, SideEffect, **kwargs)
for pvals, pert_id in zip(mat, pert_ids):
mask = pvals > 0.5
se_names_pos = se_names[mask].tolist()
aucs_pos = aucs[mask].tolist()
pvals_pos = pvals[mask].tolist()
add_predictions(se_names_pos, aucs_pos, pert_id, pvals_pos, session)
## transfer association tables
# sider_connections
d_pert_ids = mysqlTable2dict('maaya0_SEP', 'drugs_lincs', 0, 1)
d_umls_id = mysqlTable2dict('maaya0_SEP', 'side_effects', 0, 1)
conn = MySQLdb.connect(host='localhost',user='******', passwd='',db='maaya0_SEP')
cur = conn.cursor()
query = """SELECT * FROM `%s`""" %'sider_connections'
cur.execute(query)
d_pert_umls_ids = {}
for row in cur:
pert_id, umls_id = row
if pert_id in d_pert_ids and umls_id in d_umls_id:
if pert_id not in d_pert_umls_ids:
d_pert_umls_ids[pert_id] = [umls_id]
else:
if umls_id not in d_pert_umls_ids[pert_id]:
d_pert_umls_ids[pert_id].append(umls_id)
# to convert network in gml to json format for web visulization
import json
import networkx as nx
from networkx.readwrite import json_graph
import sys
sys.path.append('/Users/zichen/Documents/bitbucket/maayanlab_utils')
from fileIO import mysqlTable2dict
d_sename_umls = mysqlTable2dict('sep', 'side_effects', 2,1)
def gml2json(gml_fn, json_fn):
G = nx.read_gml(gml_fn)
print G.number_of_nodes(), G.number_of_edges()
for node_id in G.nodes():
node_dict = G.node[node_id]
if '|' in node_dict['label']:
sl = node_dict['label'].split('|')
label = '%s (%s)'%( sl[1], sl[0] )
G.node[node_id]['label'] = label
# clean labels and add xref
if node_dict['type'] == "SE":
G.node[node_id]['type'] = 'triangle-up'
G.node[node_id]['xref'] = d_sename_umls[node_dict['label']] # umls
else:
sl = G.node[node_id]['label'].split('(')
xref = sl[-1]
label = '('.join(sl[0:-1])
label = label.strip()
xref = xref.strip(')')
PREDICTION_DF = HOME + '/Documents/Zichen_Projects/drug_se_prediction/PTs_RF1000_proba_df_n20338x1053.txt'
## for side effects
# GMT_FN = HOME+'/Documents/Zichen_Projects/drug_se_prediction/RF1000_GOtCS_AUC_0.7_proba_0.6_prediction_only.gmt'
GMT_FN = HOME + '/Documents/Zichen_Projects/drug_se_prediction/ET100_GOtCS_AUC_0.76_proba_0.75.gmt'
GML_FN = HOME + '/Documents/Zichen_Projects/drug_se_prediction/side_effect_network.gml'
## for drugs
# GMT_FN = HOME+'/Documents/Zichen_Projects/drug_se_prediction/RF1000_GOtCS_AUC_0.7_proba_0.6_prediction_only_flipped.gmt'
# GML_FN = HOME+'/Documents/Zichen_Projects/drug_se_prediction/drug_network.gml'
CSV_FN = GML_FN.replace('.gml', '.csv')
JSON_FN = CSV_FN.replace('.csv', '.json')
## retrieve meta data about SE
d_umls_pt = mysqlTable2dict('sep', 'side_effects', 1, 2)
d_pt_umls = mysqlTable2dict('sep', 'side_effects', 2, 1)
d_soc_pt = read_gmt(
HOME +
'/Documents/bitbucket/pertid2trainingset/Y_matrix_no_mfc/SOC_to_pt.gmt')
print len(d_soc_pt)
d_umls_soc = {}
for soc, pts in d_soc_pt.items():
for pt in pts:
umls = d_pt_umls[pt]
if umls is not None:
if umls not in d_umls_soc:
d_umls_soc[umls] = soc
# else:
# d_umls_soc[umls].append(soc) # one PT may have multiple SOCs
