def main():
# Set the seed and network files
data_dir = "../../DATA/guild_tutorial/"
seed_file = data_dir + "seeds.txt"
network_file = data_dir + "interactions.sif"
scoring_folder = data_dir + "test/"
executable_path = "../guild/scoreN"
# Create input files for scoring
guild_utilities.prepare_scoring(network_file,
seed_file,
scoring_folder,
non_seed_score=0.01,
seed_score=1.0,
edge_score=1.0,
n_sample=100,
delim=" ")
# Generate cross validation files
node_scores_file = scoring_folder + "node_scores.sif"
edge_scores_file = scoring_folder + "edge_scores_netshort.sif"
# fill the code to get nodes, seed_to_score, edges and edge_to_score variables below
g = network_utilities.create_network_from_sif_file(network_file,
use_edge_data=True)
seeds = guild_utilities.get_nodes(seed_file)
nodes = g.nodes()
edges = g.edges()
seed_to_score = dict([(node, 1) for node in seeds])
edge_to_score = dict([((u, v), 1) for u, v in edges])
guild_utilities.generate_cross_validation_node_score_files(
nodes,
seed_to_score,
node_scores_file,
xval=3,
default_score=0.01,
replicable=123)
guild_utilities.generate_cross_validation_edge_score_as_node_score_files(
edges,
seed_to_score,
edge_to_score,
edge_scores_file,
xval=3,
default_score=0.01,
replicable=123)
# Run NetScore on these cross validation files
guild_utilities.run_scoring(scoring_folder,
executable_path,
scoring_type="netscore",
parameters={
"n_iteration": 2,
"n_repetition": 3
},
qname=None,
calculate_pvalue=True,
xval=3)
return
def score_mcl(node_scores_file, network_file, output_scores_file, module_file, default_non_seed_score):
g = network_utilities.create_network_from_sif_file(network_file, use_edge_data=True)
#modules = get_modules_of_graph(g, "mcl", inflation=2) # if edge weight based clustering is desired
seeds, nodes = get_seeds_from_node_scores_file(node_scores_file, default_non_seed_score)
modules = get_modules_from_file(module_file)
f = open(output_scores_file, 'w')
node_to_score = {}
#selected = set()
for module in modules:
module = set(module)
#common = module&seeds
#if 100*float(len(common))/len(module) > threshold:
#selected |= module
#score = float(len(common))/len(module)
#n = len(module)-len(common)
#if n == 0:
# continue
#score = 1.0/n
for node in module:
#node_to_score[node] = score
neighbors = set(g.neighbors(node))
common = neighbors & module
if node in common:
common.remove(node)
#if len(common) == 0:
# continue
score = float(len(common&seeds)) / len(module)
node_to_score[node] = score
for node in nodes:
if node in node_to_score:
f.write("%s\t%f\n" % (node, node_to_score[node]))
else:
f.write("%s\t0.0\n" % node)
f.close()
return
def calculate_proximity_multiple(parameter_file_prefix, i_start, i_end):
network_file, nodes_from, nodes_to, out_file, min_bin_size, n_random, n_seed = get_parameters_from_file(
parameter_file_prefix + "%s.txt" % i_start)
network = network_utilities.create_network_from_sif_file(
network_file,
use_edge_data=False,
delim=None,
include_unconnected=True)
bins = network_utilities.get_degree_binning(network,
min_bin_size,
lengths=None)
for i in xrange(i_start, i_end):
if not os.path.exists(parameter_file_prefix + "%s.txt" % i):
print "File does not exists for index (aborting):", i
break
network_file, nodes_from, nodes_to, out_file, min_bin_size, n_random, n_seed = get_parameters_from_file(
parameter_file_prefix + "%s.txt" % i)
if os.path.exists(out_file):
print "Skipping existing file for index:", i
continue
print network_file, nodes_from, nodes_to, n_random, min_bin_size, n_seed, out_file
values = wrappers.calculate_proximity(network,
nodes_from=nodes_from,
nodes_to=nodes_to,
bins=bins,
n_random=n_random,
min_bin_size=min_bin_size,
seed=n_seed)
if values is not None: # not in network
d, z, (m, s) = values
#print z, d, (m, s)
open(out_file, 'w').write("%f %f %f %f\n" % (z, d, m, s))
return
def get_network(network_file, only_lcc):
network = network_utilities.create_network_from_sif_file(network_file, use_edge_data = False, delim = None, include_unconnected=True)
#print len(network.nodes()), len(network.edges())
if only_lcc:
components = network_utilities.get_connected_components(network, False)
network = network_utilities.get_subgraph(network, components[0])
#print len(network.nodes()), len(network.edges())
return network
def get_network(network_file, only_lcc):
network = network_utilities.create_network_from_sif_file(network_file, use_edge_data = False, delim = None, include_unconnected=True)
#print len(network.nodes()), len(network.edges())
if only_lcc:
components = network_utilities.get_connected_components(network, False)
network = network_utilities.get_subgraph(network, components[0])
#print len(network.nodes()), len(network.edges())
network_lcc_file = network_file + ".lcc"
if not os.path.exists(network_lcc_file ):
f = open(network_lcc_file, 'w')
for u,v in network.edges():
f.write("%s 1 %s\n" % (u, v))
f.close()
return network
def get_network(network_file, only_lcc):
network = network_utilities.create_network_from_sif_file(network_file, use_edge_data = False, delim = None, include_unconnected=True)
#print len(network.nodes()), len(network.edges())
if only_lcc and not network_file.endswith(".lcc"):
print "Shrinking network to its LCC", len(network.nodes()), len(network.edges())
components = network_utilities.get_connected_components(network, False)
network = network_utilities.get_subgraph(network, components[0])
print "Final shape:", len(network.nodes()), len(network.edges())
#print len(network.nodes()), len(network.edges())
network_lcc_file = network_file + ".lcc"
if not os.path.exists(network_lcc_file ):
f = open(network_lcc_file, 'w')
for u,v in network.edges():
f.write("%s 1 %s\n" % (u, v))
f.close()
return network
def main():
"""
Get nodes that are top scoring w.r.t. GUILD scores.
Assumes that GUILD scores have been calculated already (i.e. python hello_world.py).
"""
# Set the seed and network files
data_dir = "../../DATA/guild_tutorial/"
seed_file = data_dir + "seeds.txt"
network_file = data_dir + "interactions.sif"
enrichment_file = data_dir + "enrichment.txt"
scoring_folder = data_dir + "test/"
pvalue_file = scoring_folder + "output_scores.sif.netcombo.pval"
subnetwork_file = scoring_folder + "subnetwork.sif"
# Get GUILD scores
node_to_vals = guild_utilities.get_values_from_pvalue_file(pvalue_file)
# Get top scoring, i.e. nodes that have p-value <= 0.05
top_nodes = set()
for node, vals in node_to_vals.iteritems():
score, pval = vals
if pval <= 0.05:
top_nodes.add(node)
# Load interaction network
g = network_utilities.create_network_from_sif_file(network_file,
use_edge_data=True)
# Get subnetwork induced by top scoring nodes
g_sub = network_utilities.get_subgraph(g, top_nodes)
# Output subnetwork along with the inverted p-value scores (z-scores) calculated for edges
f = open(subnetwork_file, 'w')
for u, v in g_sub.edges():
zscore_u = stat_utilities.convert_p_values_to_z_scores(
[node_to_vals[u][1]])[0]
zscore_v = stat_utilities.convert_p_values_to_z_scores(
[node_to_vals[v][1]])[0]
score = (zscore_u + zscore_v) / 2
f.write("%s\t%f\t%s\n" % (u, score, v))
f.close()
return
def calculate_proximity_multiple(parameter_file_prefix, i_start, i_end):
network_file, nodes_from, nodes_to, out_file, min_bin_size, n_random, n_seed = get_parameters_from_file(parameter_file_prefix + "%s.txt" % i_start)
network = network_utilities.create_network_from_sif_file(network_file, use_edge_data = False, delim = None, include_unconnected=True)
bins = network_utilities.get_degree_binning(network, min_bin_size, lengths=None)
for i in xrange(i_start, i_end):
if not os.path.exists(parameter_file_prefix + "%s.txt" % i):
print "File does not exists for index (aborting):", i
break
network_file, nodes_from, nodes_to, out_file, min_bin_size, n_random, n_seed = get_parameters_from_file(parameter_file_prefix + "%s.txt" % i)
if os.path.exists(out_file):
print "Skipping existing file for index:", i
continue
print network_file, nodes_from, nodes_to, n_random, min_bin_size, n_seed, out_file
values = wrappers.calculate_proximity(network, nodes_from = nodes_from, nodes_to = nodes_to, bins = bins, n_random = n_random, min_bin_size = min_bin_size, seed = n_seed)
if values is not None: # not in network
d, z, (m, s) = values
#print z, d, (m, s)
open(out_file, 'w').write("%f %f %f %f\n" % (z, d, m, s))
return
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-e', '--network_file') #, required=True)
parser.add_argument('-s', '--nodes_from') #, required=True)
parser.add_argument('-t', '--nodes_to') #, required=True)
parser.add_argument('-o', '--out_file') #, required=True)
parser.add_argument('-n', '--n_random', type=int, default=1000)
parser.add_argument('-m', '--min_bin_size', type=int, default=100)
parser.add_argument('-x', '--n_seed', type=int, default=452456)
parser.add_argument('-f', '--parameter_file', type=str, default=None)
parser.add_argument('-p', '--parameter_file_prefix', type=str, default=None)
parser.add_argument('-i', '--parameter_file_start_index', type=int, default=None)
parser.add_argument('-j', '--parameter_file_end_index', type=int, default=None)
args = parser.parse_args()
# Run more than once for given input files
if args.parameter_file_prefix is not None:
parameter_file_prefix = args.parameter_file_prefix
i_start = args.parameter_file_start_index
i_end = args.parameter_file_end_index
calculate_proximity_multiple(parameter_file_prefix, i_start, i_end)
return
# Run from input parameter file
elif args.parameter_file is not None:
network_file, nodes_from, nodes_to, out_file, min_bin_size, n_random, n_seed = get_parameters_from_file(parameter_file_prefix + "%s.txt" % n)
# Run once with provided arguments
else:
nodes_from = args.nodes_from.split(",")
nodes_to = args.nodes_to.split(",")
network_file = args.network_file
n_random = args.n_random
min_bin_size = args.min_bin_size
n_seed = args.n_seed
out_file = args.out_file
network = network_utilities.create_network_from_sif_file(network_file, use_edge_data = False, delim = None, include_unconnected=True)
#print args
print network_file, nodes_from, nodes_to, n_random, min_bin_size, n_seed, out_file
values = wrappers.calculate_proximity(network, nodes_from = nodes_from, nodes_to = nodes_to, n_random = n_random, min_bin_size = min_bin_size, seed = n_seed)
if values is not None: # not in network
d, z, (m, s) = values
#print z, d, (m, s)
open(out_file, 'w').write("%f %f %f %f\n" % (z, d, m, s))
return
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-e', '--network_file') #, required=True)
parser.add_argument('-s', '--nodes_from') #, required=True)
parser.add_argument('-t', '--nodes_to') #, required=True)
parser.add_argument('-o', '--out_file') #, required=True)
parser.add_argument('-n', '--n_random', type=int, default=1000)
parser.add_argument('-m', '--min_bin_size', type=int, default=100)
parser.add_argument('-x', '--n_seed', type=int, default=452456)
parser.add_argument('-f', '--parameter_file', type=str, default=None)
parser.add_argument('-p', '--parameter_file_prefix', type=str, default=None)
parser.add_argument('-i', '--parameter_file_start_index', type=int, default=None)
parser.add_argument('-j', '--parameter_file_end_index', type=int, default=None)
args = parser.parse_args()
# Run more than once for given input files
if args.parameter_file_prefix is not None:
parameter_file_prefix = args.parameter_file_prefix
i_start = args.parameter_file_start_index
i_end = args.parameter_file_end_index
calculate_proximity_multiple(parameter_file_prefix, i_start, i_end)
return
# Run from input parameter file
elif args.parameter_file is not None:
network_file, nodes_from, nodes_to, out_file, min_bin_size, n_random, n_seed = get_parameters_from_file(parameter_file_prefix + "%s.txt" % n)
# Run once with provided arguments
else:
nodes_from = args.nodes_from.split(",")
nodes_to = args.nodes_to.split(",")
network_file = args.network_file
n_random = args.n_random
min_bin_size = args.min_bin_size
n_seed = args.n_seed
out_file = args.out_file
network = network_utilities.create_network_from_sif_file(network_file, use_edge_data = False, delim = None, include_unconnected=True)
#print args
print network_file, nodes_from, nodes_to, n_random, min_bin_size, n_seed, out_file
values = wrappers.calculate_proximity(network, nodes_from = nodes_from, nodes_to = nodes_to, n_random = n_random, min_bin_size = min_bin_size, seed = n_seed)
if values is not None: # not in network
d, z, (m, s) = values
#print z, d, (m, s)
open(out_file, 'w').write("%f %f %f %f\n" % (z, d, m, s))
return
def score_mcl(node_scores_file, network_file, output_scores_file, module_file,
default_non_seed_score):
g = network_utilities.create_network_from_sif_file(network_file,
use_edge_data=True)
#modules = get_modules_of_graph(g, "mcl", inflation=2) # if edge weight based clustering is desired
seeds, nodes = get_seeds_from_node_scores_file(node_scores_file,
default_non_seed_score)
modules = get_modules_from_file(module_file)
f = open(output_scores_file, 'w')
node_to_score = {}
#selected = set()
for module in modules:
module = set(module)
#common = module&seeds
#if 100*float(len(common))/len(module) > threshold:
#selected |= module
#score = float(len(common))/len(module)
#n = len(module)-len(common)
#if n == 0:
# continue
#score = 1.0/n
for node in module:
#node_to_score[node] = score
neighbors = set(g.neighbors(node))
common = neighbors & module
if node in common:
common.remove(node)
#if len(common) == 0:
# continue
score = float(len(common & seeds)) / len(module)
node_to_score[node] = score
for node in nodes:
if node in node_to_score:
f.write("%s\t%f\n" % (node, node_to_score[node]))
else:
f.write("%s\t0.0\n" % node)
f.close()
return
def create_network_from_sif_file(network_file, **kwargs):
return network_utilities.create_network_from_sif_file(
network_file, **kwargs)
def create_network_from_sif_file(network_file, **kwargs):
return network_utilities.create_network_from_sif_file(network_file, **kwargs)
