def get_nodes(file_name):
"""
Parses nodes from a given file (e.g., seed file).
"""
nodes, dummy, dummy, dummy = network_utilities.get_nodes_and_edges_from_sif_file(file_name = file_name, store_edge_type = False)
#nodes = set([ line.strip() for line in open(file_name) ])
return nodes
def get_node_to_score(score_file):
"""
Parses scores from a scoring file created by GUILD.
"""
nodes, dummy, node_to_score, dummy = network_utilities.get_nodes_and_edges_from_sif_file(
file_name=score_file, store_edge_type=False)
return node_to_score
def get_nodes(file_name):
"""
Parses nodes from a given file (e.g., seed file).
"""
nodes, dummy, dummy, dummy = network_utilities.get_nodes_and_edges_from_sif_file(file_name = file_name, store_edge_type = False)
#nodes = set([ line.strip() for line in open(file_name) ])
return nodes
def get_node_to_score(score_file):
"""
Parses scores from a scoring file created by GUILD.
"""
nodes, dummy, node_to_score, dummy = network_utilities.get_nodes_and_edges_from_sif_file(file_name = score_file, store_edge_type = False)
return node_to_score
def 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=" ", name=None):
"""
Creates input files required by GUILD executable.
network_file: network in sif-like format where edge type is edge score (e.g., "A 0.5 B" or "A pp B")
seed_file: seeds in text format where nodes and their scores are given (e.g., "A 0.1" or "A")
scoring_folder: path to directory where the input/output files will be created
non_seed_score: initial scores of non-seeds (0.01, by default)
seed_score: initial scores of seeds (1.0, by default)
edge_score: weight of edges, in case the values in network_file is not convertable to float (1.0, by default)
n_sample: number of randomly generated graphs for netzcore (100, by default)
delim: delimiter that separates columns in input/output files (" ", by default)
name: optional name defining the phenotype, the scoring files will created under this dir (in case of multiple phenotype analysis)
"""
if not os.path.exists(scoring_folder):
os.mkdir(scoring_folder)
if name is not None:
if not os.path.exists(scoring_folder+name):
os.mkdir(scoring_folder+name)
name += os.sep
else:
name = ""
# Read node info from network file (use network file as edge file)
print "Creating edge score file"
edge_score_file = scoring_folder + "edge_scores.sif" #network_file.split("/")[-1] + ".converted"
if os.path.exists(edge_score_file):
print "\tEdge score file exists, overwriting!"
nodes, edges, dummy, edge_to_data = network_utilities.get_nodes_and_edges_from_sif_file(network_file, store_edge_type = True, delim = delim, data_to_float=False)
edge_to_weight = create_edge_score_file(edge_score_file, edges, edge_to_data, edge_score, delim)
# Create node file (ignore seeds that are not in the network and assign non-seed scores)
print "Creating node score file"
node_score_file = scoring_folder + name + "node_scores.sif" #seed_file.split("/")[-1] + ".converted"
seed_score_file = scoring_folder + name + "seed_scores.sif"
seeds, dummy, seed_to_data, dummy = network_utilities.get_nodes_and_edges_from_sif_file(seed_file, store_edge_type = False, delim = delim, data_to_float=True)
if seed_to_data is None:
seed_to_data = {}
for seed in seeds:
seed_to_data[seed] = seed_score
node_to_data = create_node_score_file(node_score_file, seed_score_file, nodes, seeds, seed_to_data, non_seed_score, seed_score, delim)
# Create background node file (selects k non-seeds randomly where k is the number of seeds)
print "Creating background node score file"
bg_node_file = scoring_folder + name + "node_scores_background.sif" #seed_file.split("/")[-1] + ".converted"
bg_seed_file = scoring_folder + name + "seed_scores_background.sif"
create_background_score_file(bg_node_file, bg_seed_file, nodes, seeds, seed_to_data, non_seed_score, delim)
# Create modified edge file using node scores for netshort
print "Creating node score converted edge file (for netshort)"
nd_edge_file = scoring_folder + name + "edge_scores_netshort.sif" #network_file.split("/")[-1] + ".converted_for_netshort"
create_node_score_converted_edge_score_file(nd_edge_file, edges, edge_to_weight, node_to_data, delim)
# Create random network files for netzcore
print "Creating random networks (for netzcore)"
sampling_prefix = scoring_folder + "../" + "sampled_graph."
if os.path.exists(sampling_prefix+"%s"%n_sample):
print "\tSampled networks exists, skipping this step!"
else:
g = network_utilities.create_network_from_sif_file(network_file_in_sif = edge_score_file, use_edge_data = True, delim = delim)
for i in xrange(1,n_sample+1):
g_sampled = network_utilities.randomize_graph(graph=g, randomization_type="preserve_topology_and_node_degree")
network_utilities.output_network_in_sif(g_sampled, sampling_prefix+"%s"%i)
return
def 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=" ",
name=None):
"""
Creates input files required by GUILD executable.
network_file: network in sif-like format where edge type is edge score (e.g., "A 0.5 B" or "A pp B")
seed_file: seeds in text format where nodes and their scores are given (e.g., "A 0.1" or "A")
scoring_folder: path to directory where the input/output files will be created
non_seed_score: initial scores of non-seeds (0.01, by default)
seed_score: initial scores of seeds (1.0, by default)
edge_score: weight of edges, in case the values in network_file is not convertable to float (1.0, by default)
n_sample: number of randomly generated graphs for netzcore (100, by default)
delim: delimiter that separates columns in input/output files (" ", by default)
name: optional name defining the phenotype, the scoring files will created under this dir (in case of multiple phenotype analysis)
"""
if not os.path.exists(scoring_folder):
os.mkdir(scoring_folder)
if name is not None:
if not os.path.exists(scoring_folder + name):
os.mkdir(scoring_folder + name)
name += os.sep
else:
name = ""
# Read node info from network file (use network file as edge file)
print "Creating edge score file"
edge_score_file = scoring_folder + "edge_scores.sif" #network_file.split("/")[-1] + ".converted"
if os.path.exists(edge_score_file):
print "\tEdge score file exists, overwriting!"
nodes, edges, dummy, edge_to_data = network_utilities.get_nodes_and_edges_from_sif_file(
network_file, store_edge_type=True, delim=delim, data_to_float=False)
edge_to_weight = create_edge_score_file(edge_score_file, edges,
edge_to_data, edge_score, delim)
# Create node file (ignore seeds that are not in the network and assign non-seed scores)
print "Creating node score file"
node_score_file = scoring_folder + name + "node_scores.sif" #seed_file.split("/")[-1] + ".converted"
seed_score_file = scoring_folder + name + "seed_scores.sif"
seeds, dummy, seed_to_data, dummy = network_utilities.get_nodes_and_edges_from_sif_file(
seed_file, store_edge_type=False, delim=delim, data_to_float=True)
if seed_to_data is None:
seed_to_data = {}
for seed in seeds:
seed_to_data[seed] = seed_score
node_to_data = create_node_score_file(node_score_file, seed_score_file,
nodes, seeds, seed_to_data,
non_seed_score, seed_score, delim)
# Create background node file (selects k non-seeds randomly where k is the number of seeds)
print "Creating background node score file"
bg_node_file = scoring_folder + name + "node_scores_background.sif" #seed_file.split("/")[-1] + ".converted"
bg_seed_file = scoring_folder + name + "seed_scores_background.sif"
create_background_score_file(bg_node_file, bg_seed_file, nodes, seeds,
seed_to_data, non_seed_score, delim)
# Create modified edge file using node scores for netshort
print "Creating node score converted edge file (for netshort)"
nd_edge_file = scoring_folder + name + "edge_scores_netshort.sif" #network_file.split("/")[-1] + ".converted_for_netshort"
create_node_score_converted_edge_score_file(nd_edge_file, edges,
edge_to_weight, node_to_data,
delim)
# Create random network files for netzcore
print "Creating random networks (for netzcore)"
sampling_prefix = scoring_folder + "../" + "sampled_graph."
if os.path.exists(sampling_prefix + "%s" % n_sample):
print "\tSampled networks exists, skipping this step!"
else:
g = network_utilities.create_network_from_sif_file(
network_file_in_sif=edge_score_file,
use_edge_data=True,
delim=delim)
for i in xrange(1, n_sample + 1):
g_sampled = network_utilities.randomize_graph(
graph=g,
randomization_type="preserve_topology_and_node_degree")
network_utilities.output_network_in_sif(g_sampled,
sampling_prefix + "%s" % i)
return
