def add_mutations(cl_info):
print('add mutations\n')
from clustergrammer import Network
net = Network()
old_cl_info = net.load_json_to_dict('cell_line_muts.json')
cl_muts = old_cl_info['muts']
for inst_cl in cl_info:
# remove plex name if necessary
if '_plex_' in inst_cl:
simple_cl = inst_cl.split('_')[0]
else:
simple_cl = inst_cl
for inst_mut in cl_muts:
mutated_cls = cl_muts[inst_mut]
if simple_cl in mutated_cls:
has_mut = 'true'
else:
has_mut = 'false'
mutation_title = 'mut-'+inst_mut
# use the original long cell line name (with possible plex)
cl_info[inst_cl][mutation_title] = has_mut
return cl_info
def add_mutations(cl_info):
print('add mutations\n')
from clustergrammer import Network
net = Network()
old_cl_info = net.load_json_to_dict('cell_line_muts.json')
cl_muts = old_cl_info['muts']
for inst_cl in cl_info:
# remove plex name if necessary
if '_plex_' in inst_cl:
simple_cl = inst_cl.split('_')[0]
else:
simple_cl = inst_cl
for inst_mut in cl_muts:
mutated_cls = cl_muts[inst_mut]
if simple_cl in mutated_cls:
has_mut = 'true'
else:
has_mut = 'false'
mutation_title = 'mut-' + inst_mut
# use the original long cell line name (with possible plex)
cl_info[inst_cl][mutation_title] = has_mut
return cl_info
def make_enr_vect_clust():
import enrichr_functions as enr_fun
from clustergrammer import Network
net = Network()
g2e_post = net.load_json_to_dict('json/g2e_enr_vect.json')
net = enr_fun.make_enr_vect_clust(g2e_post, 0.001, 1)
net.write_json_to_file('viz','json/enr_vect_example.json')
def cluster():
from clustergrammer import Network
net = Network()
vect_post = net.load_json_to_dict('fake_vect_post.json')
net.load_vect_post_to_net(vect_post)
net.swap_nan_for_zero()
# net.N_top_views()
net.make_clust(dist_type='cos',views=['N_row_sum','N_row_var'], dendro=True)
net.write_json_to_file('viz','json/large_vect_post_example.json','indent')
def make_plex_matrix():
'''
Make a cell line matrix with plex rows and cell line columns.
This will be used as a negative control that should show worsening correlation
as data is normalized/filtered.
'''
import numpy as np
import pandas as pd
from clustergrammer import Network
# load cl_info
net = Network()
cl_info = net.load_json_to_dict(
'../cell_line_info/cell_line_info_dict.json')
# load cell line expression
net.load_file('../CCLE_gene_expression/CCLE_NSCLC_all_genes.txt')
tmp_df = net.dat_to_df()
df = tmp_df['mat']
cols = df.columns.tolist()
rows = range(9)
rows = [i + 1 for i in rows]
print(rows)
mat = np.zeros((len(rows), len(cols)))
for inst_col in cols:
for inst_cl in cl_info:
if inst_col in inst_cl:
inst_plex = int(cl_info[inst_cl]['Plex'])
if inst_plex != -1:
# print(inst_col + ' in ' + inst_cl + ': ' + str(inst_plex))
row_index = rows.index(inst_plex)
col_index = cols.index(inst_col)
mat[row_index, col_index] = 1
df_plex = pd.DataFrame(data=mat, columns=cols, index=rows)
filename = '../lung_cellline_3_1_16/lung_cl_all_ptm/precalc_processed/' + \
'exp-plex.txt'
df_plex.to_csv(filename, sep='\t')
def make_plex_matrix():
'''
Make a cell line matrix with plex rows and cell line columns.
This will be used as a negative control that should show worsening correlation
as data is normalized/filtered.
'''
import numpy as np
import pandas as pd
from clustergrammer import Network
# load cl_info
net = Network()
cl_info = net.load_json_to_dict('../cell_line_info/cell_line_info_dict.json')
# load cell line expression
net.load_file('../CCLE_gene_expression/CCLE_NSCLC_all_genes.txt')
tmp_df = net.dat_to_df()
df = tmp_df['mat']
cols = df.columns.tolist()
rows = range(9)
rows = [i+1 for i in rows]
print(rows)
mat = np.zeros((len(rows), len(cols)))
for inst_col in cols:
for inst_cl in cl_info:
if inst_col in inst_cl:
inst_plex = int(cl_info[inst_cl]['Plex'])
if inst_plex != -1:
# print(inst_col + ' in ' + inst_cl + ': ' + str(inst_plex))
row_index = rows.index(inst_plex)
col_index = cols.index(inst_col)
mat[row_index, col_index] = 1
df_plex = pd.DataFrame(data=mat, columns=cols, index=rows)
filename = '../lung_cellline_3_1_16/lung_cl_all_ptm/precalc_processed/' + \
'exp-plex.txt'
df_plex.to_csv(filename, sep='\t')
def post_to_clustergrammer():
from clustergrammer import Network
import requests
import json
upload_url = 'http://localhost:9000/clustergrammer/vector_upload/'
# upload_url = 'http://amp.pharm.mssm.edu/clustergrammer/vector_upload/'
net = Network()
vect_post = net.load_json_to_dict('test_vector_upload.json')
# vect_post = net.load_json_to_dict('fake_vect_post.json')
r = requests.post(upload_url, data=json.dumps(vect_post))
link = r.text
print(link)
def cluster():
from clustergrammer import Network
net = Network()
vect_post = net.load_json_to_dict('fake_vect_post.json')
net.load_vect_post_to_net(vect_post)
net.swap_nan_for_zero()
# net.N_top_views()
net.make_clust(dist_type='cos',
views=['N_row_sum', 'N_row_var'],
dendro=True)
net.write_json_to_file('viz', 'json/large_vect_post_example.json',
'indent')
def post_to_clustergrammer():
from clustergrammer import Network
import requests
import json
upload_url = 'http://localhost:9000/clustergrammer/vector_upload/'
# upload_url = 'http://amp.pharm.mssm.edu/clustergrammer/vector_upload/'
net = Network()
vect_post = net.load_json_to_dict('test_vector_upload.json')
# vect_post = net.load_json_to_dict('fake_vect_post.json')
r = requests.post(upload_url, data=json.dumps(vect_post) )
link = r.text
print(link)
def proc_locally():
from clustergrammer import Network
# import run_g2e_background
net = Network()
vect_post = net.load_json_to_dict('large_vect_post.json')
print(vect_post.keys())
# mongo_address = '10.125.161.139'
net.load_vect_post_to_net(vect_post)
net.swap_nan_for_zero()
net.N_top_views()
print(net.viz.keys())
def proc_locally():
from clustergrammer import Network
# import run_g2e_background
net = Network()
vect_post = net.load_json_to_dict('large_vect_post.json')
print(vect_post.keys())
# mongo_address = '10.125.161.139'
net.load_vect_post_to_net(vect_post)
net.swap_nan_for_zero()
net.N_top_views()
print(net.viz.keys())
def main():
net = Network()
# load genes of interest
gene_info = net.load_json_to_dict('../grant_pois/gene_info_with_dark.json')
# ENCODE, GTEx, etc
# hzome_names = ['my_CCLE_exp.txt', 'ENCODE_TF_targets.txt', 'ChEA_TF_targets.txt']
hzome_names = ['ENCODE_TF_targets.txt']
# define separate sim_cutoffs for different files
cutoffs = {}
cutoffs['my_CCLE_exp.txt'] = 0.15
cutoffs['ENCODE_TF_targets.txt'] = 0.35 ## 0.6
cutoffs['ChEA_TF_targets.txt'] = 0.2
cutoffs['my_gtex_Moshe_2017_exp.txt'] = 0.2
genes_of_class = gene_info['KIN']['all']
for hzome_name in hzome_names:
hzome_filename = '../hzome_data/' + hzome_name
print('loading data ')
# load hzome data
####################
if 'my_' in hzome_name:
# if I am providing the data, then load in normal way
net.load_file(hzome_filename)
hzome_data = net.export_df()
else:
# load data in hzome format
hzome_data = deepcopy(hzome_to_df.load_matrix(hzome_filename))
print('data loaded\n')
for gene_class in gene_info:
calc_gene_sim_mat(hzome_data, net, gene_info, gene_class, hzome_name, cutoffs)
def main():
'''
This will add cell line category information (including plexes and
gene-expression groups to the gene expression data from CCLE)
'''
from clustergrammer import Network
net = Network()
# load original CCLE gene expression data for CST lung cancer cell lines
filename = 'CCLE_gene_expression/CCLE_NSCLC_all_genes.txt'
f = open(filename, 'r')
lines = f.readlines()
f.close()
# load cell line info
cl_info = net.load_json_to_dict('cell_line_info/cell_line_muts.json')
# write to new file
new_file = 'CCLE_gene_expression/CCLE_NSCLC_cats_all_genes.txt'
fw = open(new_file, 'w')
fw.close()
def main():
'''
This will add cell line category information (including plexes and
gene-expression groups to the gene expression data from CCLE)
'''
from clustergrammer import Network
net = Network()
# load original CCLE gene expression data for CST lung cancer cell lines
filename = 'CCLE_gene_expression/CCLE_NSCLC_all_genes.txt'
f = open(filename, 'r')
lines = f.readlines()
f.close()
# load cell line info
cl_info = net.load_json_to_dict('cell_line_info/cell_line_muts.json')
# write to new file
new_file = 'CCLE_gene_expression/CCLE_NSCLC_cats_all_genes.txt'
fw = open(new_file, 'w')
fw.close()
