def cluster_genes_heatprop(seed_genes, cluster_x_y_z):
'''
Function to establish drugs potentially related to an input gene list, using network propagation methods
inputs:
- seed_genes: genes from which to initiate heat propagation simulation
- path_to_DB_file: path to drug bank file, including filename
- path_to_cluster_file: path to cluster file, including filename
- plot_flag: should we plot the subnetwork with heat overlaid? Default False
'''
#G_DB = nx.Graph()
#G_DB.add_edges_from(DB_el)
G_cluster = cluster_x_y_z #load_cluster_data(path_to_cluster_file)
# calculate the degree-normalized adjacency matrix
Wprime = network_prop.normalized_adj_matrix(G_cluster['cluster'],
weighted=True)
# run the network_propagation simulation starting from the seed genes
Fnew = network_prop.network_propagation(G_cluster['cluster'], Wprime,
seed_genes)
# sort heat vector Fnew
Fnew.sort(ascending=False)
H = G_cluster['cluster'].subgraph(Fnew.head(500).keys())
return H
def drug_gene_heatprop(seed_genes,path_to_DB_file,path_to_cluster_file,plot_flag=False):
'''
Function to establish drugs potentially related to an input gene list, using network propagation methods
inputs:
- seed_genes: genes from which to initiate heat propagation simulation
- path_to_DB_file: path to drug bank file, including filename
- path_to_cluster_file: path to cluster file, including filename
- plot_flag: should we plot the subnetwork with heat overlaid? Default False
'''
# load and parse the drug-bank file into a dict ()
DBdict = load_DB_data(path_to_DB_file)
# make a network out of drug-gene interactions
DB_el = []
for d in DBdict.keys():
node_list = DBdict[d]['node_list']
for n in node_list:
DB_el.append((DBdict[d]['drugbank_id'],n['name']))
G_DB = nx.Graph()
G_DB.add_edges_from(DB_el)
G_cluster = load_cluster_data(path_to_cluster_file)
# calculate the degree-normalized adjacency matrix
Wprime = network_prop.normalized_adj_matrix(G_cluster,weighted=True)
# run the network_propagation simulation starting from the seed genes
Fnew = network_prop.network_propagation(G_cluster,Wprime,seed_genes)
# sort heat vector Fnew
Fnew.sort(ascending=False)
# if plot_flag is on plot the cluster genes with heat overlaid
if plot_flag:
pos = nx.spring_layout(G_cluster)
plt.figure(figsize=(10,10))
nx.draw_networkx_edges(G_cluster,pos=pos,alpha=.03)
nx.draw_networkx_nodes(G_cluster,pos=pos,node_size=20,alpha=.8,node_color=Fnew[G_cluster.nodes()],cmap='jet',
vmin=0,vmax=np.max(Fnew)/10)
nx.draw_networkx_nodes(G_cluster,pos=pos,nodelist=seed_genes,node_size=50,alpha=.7,node_color='red',linewidths=2)
plt.grid('off')
plt.title('Sample subnetwork: post-heat propagation',fontsize=16)
# find the drugs related to hot genes
gene_drug_df = find_drugs_from_hot_genes(Fnew,G_DB,seed_genes,keep_seed_genes =True)
return gene_drug_df
def drug_gene_heatprop(seed_genes, cluster_x_y_z, plot_flag=False):
'''
Function to establish drugs potentially related to an input gene list, using network propagation methods
inputs:
- seed_genes: genes from which to initiate heat propagation simulation
- path_to_DB_file: path to drug bank file, including filename
- path_to_cluster_file: path to cluster file, including filename
- plot_flag: should we plot the subnetwork with heat overlaid? Default False
'''
# load and parse the drug-bank file into a dict ()
#DBdict = load_DB_data(path_to_DB_file)
# make a network out of drug-gene interactions
# DB_el = []
# for d in DBdict.keys():
# node_list = DBdict[d]['node_list']
# for n in node_list:
# DB_el.append((DBdict[d]['drugbank_id'],n['name']))
#load_DB_el()
start_time = time.time()
G_DB = nx.Graph()
G_DB.add_edges_from(DB_el)
G_cluster = cluster_x_y_z #load_cluster_data(path_to_cluster_file)
# calculate the degree-normalized adjacency matrix
Wprime = network_prop.normalized_adj_matrix(G_cluster, weighted=True)
# run the network_propagation simulation starting from the seed genes
Fnew = network_prop.network_propagation(G_cluster, Wprime, seed_genes)
# sort heat vector Fnew
#Fnew.sort(ascending=False)
Fnew.sort_values(inplace=True, ascending=False)
# if plot_flag is on plot the cluster genes with heat overlaid
if plot_flag:
pos = nx.spring_layout(G_cluster)
plt.figure(figsize=(10, 10))
nx.draw_networkx_edges(G_cluster, pos=pos, alpha=.03)
nx.draw_networkx_nodes(G_cluster,
pos=pos,
node_size=20,
alpha=.8,
node_color=Fnew[G_cluster.nodes()],
cmap='jet',
vmin=0,
vmax=np.max(Fnew) / 10)
nx.draw_networkx_nodes(G_cluster,
pos=pos,
nodelist=seed_genes,
node_size=50,
alpha=.7,
node_color='red',
linewidths=2)
plt.grid('off')
plt.title('Sample subnetwork: post-heat propagation', fontsize=16)
# find the drugs related to hot genes
gene_drug_df = find_drugs_from_hot_genes(Fnew,
G_DB,
seed_genes,
keep_seed_genes=True)
#print gene_drug_df
return gene_drug_df
def main(num_reps=10,
seed_gene_file='HC_genes/ASD_HC_no_shared_200114.tsv',
int_file='../interactomes/G_PCnet.gpickle',
out_name='ASD',
rand_method='degree_binning',
single_or_double='single',
save_fnew_rand=False):
'''
Calculate z-scores for heat propagation
python netprop_zscore.py 10 HC_genes/ASD_HC_no_shared_200114.tsv ../interactomes/G_PCnet.gpickle ASD degree_binning single False
'''
print('number of randomizations = ' + str(num_reps))
print('background interactome = ' + int_file)
print('randomization method = ' + rand_method)
print('single or double = ' + single_or_double)
print('save Fnew rand = ' + save_fnew_rand)
num_reps = int(num_reps)
# load interactome and select focal interactome
Gint = nx.Graph()
Gint = nx.read_gpickle(int_file)
if 'None' in Gint.nodes():
Gint.remove_node('None')
# load HC genes
HC_genes_temp = pd.read_csv(seed_gene_file,
sep='\t',
index_col='Unnamed: 0')
seed_HC = [
str(g[1:-1]).strip("'")
for g in HC_genes_temp['seed_genes'].tolist()[0][1:-1].split(', ')
]
print(seed_gene_file + ':')
print(len(seed_HC))
seed_HC = list(np.intersect1d(Gint.nodes(), seed_HC))
print(len(seed_HC))
# calculate the z-score
# calc Wprime from Gint
Wprime = network_prop.normalized_adj_matrix(Gint, conserve_heat=True)
if single_or_double == 'single': # calculate z-scores from a single set of seed genes
print('calculating z-scores: ' + seed_gene_file)
z_seed, Fnew_rand_seed = calc_zscore_heat(Gint,
Wprime,
seed_HC,
num_reps=num_reps,
rand_method=rand_method)
z_seed.to_csv('z_' + out_name + '_' + str(num_reps) + '_reps_' +
rand_method + '.tsv',
sep='\t')
if save_fnew_rand == 'True': # if true, save out the vector of randoms (this can be a large file)
pd.DataFrame(Fnew_rand_seed).to_csv('Fnew_' + out_name + '_rand' +
str(num_reps) + '_reps_' +
rand_method + '.tsv',
sep='\t')
elif single_or_double == 'double': # calculate z-scores from two sets of seed genes:
# --- not currently functional ----
print('calculating ASD-CHD z-scores')
z_ASD_CHD, Fnew_rand_ASD_CHD = calc_zscore_heat_double(
Gint,
Wprime,
ASD_HC,
CHD_HC,
num_reps=num_reps,
rand_method=rand_method)
z_ASD_CHD.to_csv('z_' + out_name + '_' + str(num_reps) + '_reps_' +
rand_method + '.tsv',
sep='\t')
def main(num_reps=10,
seed_gene_file='HC_genes/example_seed.tsv',
int_file='../interactomes/G_PCnet.gpickle',
out_name='ASD',
rand_method='degree_binning',
single_or_double='single'):
'''
Calculate z-scores for heat propagation
Inputs:
num_reps: number of randomizations
seed_gene_file: location of file containing seed genes (see example for format... clunky format due to historical reasons... need to improve)
int_file: location of interactome to use (gpickle format)
out_name: identifier for output files (currently saves in current directory... need to update to allow setting of save location)
rand_method: type of randomization (default = 'degree_binning', alternate method 'degree_ks_test' deprecated)
single_or_double: single network prop or double network prop. (default = 'single'. 'double' is deprecated)
python netprop_zscore.py 10 HC_genes/example_seed.tsv ../interactomes/G_PCnet.gpickle ASD degree_binning single
'''
print('number of randomizations = ' + str(num_reps))
print('background interactome = ' + int_file)
print('randomization method = ' + rand_method)
print('single or double = ' + single_or_double)
num_reps = int(num_reps)
# load interactome and select focal interactome
Gint = nx.Graph()
Gint = nx.read_gpickle(int_file)
if 'None' in Gint.nodes():
Gint.remove_node('None')
# load HC genes
HC_genes_temp = pd.read_csv(seed_gene_file,
sep='\t',
index_col='Unnamed: 0')
seed_HC = [
str(g[1:-1]).strip("'")
for g in HC_genes_temp['seed_genes'].tolist()[0][1:-1].split(', ')
]
print(seed_gene_file + ':')
print(len(seed_HC))
seed_HC = list(np.intersect1d(Gint.nodes(), seed_HC))
print(len(seed_HC))
# calculate the z-score
# calc Wprime from Gint
Wprime = network_prop.normalized_adj_matrix(Gint, conserve_heat=True)
if single_or_double == 'single': # calculate z-scores from a single set of seed genes
print('calculating z-scores: ' + seed_gene_file)
z_seed, Fnew_rand_seed = calc_zscore_heat(Gint,
Wprime,
seed_HC,
num_reps=num_reps,
rand_method=rand_method)
z_seed.to_csv('z_' + out_name + '_' + str(num_reps) + '_reps_' +
rand_method + '.tsv',
sep='\t')
#pd.DataFrame(Fnew_rand_seed).to_csv('Fnew_'+outname+'_rand'+str(num_reps)+'_reps_'+rand_method+'.tsv',sep='\t')
elif single_or_double == 'double': # calculate z-scores from two sets of seed genes:
# --- keeping for completeness, but currently not functional ----
print('calculating ASD-CHD z-scores')
z_ASD_CHD, Fnew_rand_ASD_CHD = calc_zscore_heat_double(
Gint,
Wprime,
ASD_HC,
CHD_HC,
num_reps=num_reps,
rand_method=rand_method)
z_ASD_CHD.to_csv('z_' + out_name + '_' + str(num_reps) + '_reps_' +
rand_method + '.tsv',
sep='\t')