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 make_ccle_matrix_subset():
'''
This will save a subset of the downsampled matrix using the proteins of interest
'''
from clustergrammer import Network
import json_scripts
print('-- load CCLE downsampled data')
# load downsampled CCLE data
net = Network()
net.load_file('CCLE/CCLE_kmeans_ds_col_100.txt')
df = net.export_df()
# load proteins of interest
filename = 'proteins_of_interest/proteins_of_interest.json'
poi = json_scripts.load_to_dict(filename)
all_poi = []
for inst_type in poi:
all_poi.extend(poi[inst_type])
# only keep pois that are found in the CCLE
all_genes = df.index.tolist()
found_poi = list(set(all_genes) & set(all_poi))
num_found_poi = len(found_poi)
print(
str(num_found_poi) +
' proteins of interest were found in the CCLE data')
# filter dataframe using row list (transpose and transpose-back)
##################################################################
df = df.transpose()
df = df[found_poi]
df = df.transpose()
# save version without protein categories (e.g. kinase)
df.to_csv('CCLE/CCLE_kmeans_ds_col_100_poi_no_cats.txt', sep='\t')
row_cats = []
for inst_gene in found_poi:
# add protein type to gene names
found_type = ''
for inst_type in poi:
if inst_gene in poi[inst_type]:
found_type = inst_type
gene_name = 'gene: ' + inst_gene
cat_name = 'type: ' + found_type
inst_tuple = (gene_name, cat_name)
row_cats.append(inst_tuple)
# redefine index
df.index = row_cats
print('-- save matrix with proteins_of_interest subset')
df.to_csv('CCLE/CCLE_kmeans_ds_col_100_poi.txt', sep='\t')
def main():
from clustergrammer import Network
# load CCLE cell lines
filename = '../lung_cellline_3_1_16/lung_cl_all_ptm/precalc_processed/ccle_cl_names.txt'
f = open(filename, 'r')
lines = f.readlines()
f.close()
cl_names = []
for inst_line in lines:
inst_line = inst_line.strip()
cl_names.append(inst_line)
filename = '../lung_cellline_3_1_16/lung_cl_all_ptm/precalc_processed/CCLE_lung.txt'
net = Network()
net.load_file(filename)
ccle_lung = net.export_df()
cols = ccle_lung.columns.tolist()
# simplify cols, disguard meta-data
######################################
simple_cols = []
for inst_col in cols:
proc_col = inst_col[0].split(': ')[1].replace('NCI', '')
if 'CALU' in proc_col:
proc_col = proc_col.replace('CALU', 'Calu-')
if 'LOU' in proc_col:
proc_col = proc_col.replace('LOU', 'Lou-')
if 'CAL' in proc_col:
proc_col = proc_col.replace('CAL', 'CAL-')
simple_cols.append(proc_col)
ccle_lung.columns = simple_cols
cols = ccle_lung.columns.tolist()
found_cols = []
for inst_col in cols:
if inst_col in cl_names:
found_cols.append(inst_col)
# found all cell lines
print('found ' + str(len(found_cols)))
# save subset of cell lines that are also found in the CST PTM data
ccle_cst_lung = ccle_lung[cl_names]
save_filename = '../lung_cellline_3_1_16/lung_cl_all_ptm/precalc_processed/CCLE_CST_lung.txt'
ccle_cst_lung.to_csv(save_filename, sep='\t')
