def get_seeds_from_node_scores_file(node_scores_file, default_non_seed_score):
nodes, dummy, initial_node_to_score, dummy = network_utilities.get_nodes_and_edges_from_sif_file(file_name = node_scores_file, store_edge_type = False)
seeds = set()
for node in initial_node_to_score:
if initial_node_to_score[node] > default_non_seed_score:
seeds.add(node)
return seeds, nodes
def convert_ids_using_mapping_file(input_file, mapping_file, output_file, one_gene_per_node=True, delim="\t"):
nodes, dummy, node_to_data, dummy = network_utilities.get_nodes_and_edges_from_sif_file(file_name = input_file, store_edge_type = False)
id_to_mapped_ids = get_id_to_mapped_id_mapping(mapping_file, delim=delim)
values = []
#for node, d in node_to_data.iteritems():
for node in nodes:
if node not in id_to_mapped_ids:
continue
if one_gene_per_node:
genes = [ id_to_mapped_ids[node][0] ]
else:
genes = id_to_mapped_ids[node]
for gene in genes:
#values.append((d, gene))
values.append(gene)
values.sort()
values.reverse()
#i = 1
f = open(output_file, 'w')
#f2 = open(output_file + ".ranks", 'w')
#for d, gene in values:
for gene in values:
f.write("%s\n" % (gene))
#f.write("%s\t%s\n" % (gene, str(score)))
#f2.write("%s\t%d\n" % (gene, i))
#i += 1
f.close()
#f2.close()
return
def get_seeds_from_node_scores_file(node_scores_file, default_non_seed_score):
nodes, dummy, initial_node_to_score, dummy = network_utilities.get_nodes_and_edges_from_sif_file(
file_name=node_scores_file, store_edge_type=False)
seeds = set()
for node in initial_node_to_score:
if initial_node_to_score[node] > default_non_seed_score:
seeds.add(node)
return seeds, nodes
def get_scores(score_file):
"""
Parses scores from a scoring file created by GUILD (node <whitespace> score), returns a dictionary where the values are floats.
"""
nodes, dummy, node_to_score, dummy = network_utilities.get_nodes_and_edges_from_sif_file(
file_name=score_file,
store_edge_type=False,
delim=None,
data_to_float=True)
return node_to_score
def output_mapped_node_id_scores(output_scores_file,
node_mapping_file,
one_gene_per_node=True,
output_file=None):
"""
Output mapped ids of nodes
"""
dummy, dummy, node_to_score, dummy = network_utilities.get_nodes_and_edges_from_sif_file(
file_name=output_scores_file, store_edge_type=False)
id_to_mapped_ids = get_id_to_mapped_id_mapping(node_mapping_file)
values = []
for node, score in node_to_score.iteritems():
if node not in id_to_mapped_ids:
continue
if one_gene_per_node:
genes = [id_to_mapped_ids[node][0]]
else:
genes = id_to_mapped_ids[node]
for gene in genes:
values.append((score, gene))
values.sort()
values.reverse()
included = set()
i = 1
if output_file is not None:
f = open(output_file, 'w')
f2 = open(output_file + ".ranks", 'w')
f3 = open(output_file + ".unique", 'w')
for score, gene in values:
f.write("%s\t%s\n" % (gene, str(score)))
f2.write("%s\t%d\n" % (gene, i))
if gene not in included:
f3.write("%s\t%s\n" % (gene, str(score)))
included.add(gene)
i += 1
f.close()
f2.close()
f3.close()
else:
print "%s\t%f" % (gene, score)
return
def output_mapped_node_id_scores(output_scores_file, node_mapping_file, one_gene_per_node=True, output_file=None):
"""
Output mapped ids of nodes
"""
dummy, dummy, node_to_score, dummy = network_utilities.get_nodes_and_edges_from_sif_file(file_name = output_scores_file, store_edge_type = False)
id_to_mapped_ids = get_id_to_mapped_id_mapping(node_mapping_file)
values = []
for node, score in node_to_score.iteritems():
if node not in id_to_mapped_ids:
continue
if one_gene_per_node:
genes = [ id_to_mapped_ids[node][0] ]
else:
genes = id_to_mapped_ids[node]
for gene in genes:
values.append((score, gene))
values.sort()
values.reverse()
included = set()
i = 1
if output_file is not None:
f = open(output_file, 'w')
f2 = open(output_file + ".ranks", 'w')
f3 = open(output_file + ".unique", 'w')
for score, gene in values:
f.write("%s\t%s\n" % (gene, str(score)))
f2.write("%s\t%d\n" % (gene, i))
if gene not in included:
f3.write("%s\t%s\n" % (gene, str(score)))
included.add(gene)
i += 1
f.close()
f2.close()
f3.close()
else:
print "%s\t%f" % (gene, score)
return
def convert_ids_using_mapping_file(input_file,
mapping_file,
output_file,
one_gene_per_node=True,
delim="\t"):
nodes, dummy, node_to_data, dummy = network_utilities.get_nodes_and_edges_from_sif_file(
file_name=input_file, store_edge_type=False)
id_to_mapped_ids = get_id_to_mapped_id_mapping(mapping_file, delim=delim)
values = []
#for node, d in node_to_data.iteritems():
for node in nodes:
if node not in id_to_mapped_ids:
continue
if one_gene_per_node:
genes = [id_to_mapped_ids[node][0]]
else:
genes = id_to_mapped_ids[node]
for gene in genes:
#values.append((d, gene))
values.append(gene)
values.sort()
values.reverse()
#i = 1
f = open(output_file, 'w')
#f2 = open(output_file + ".ranks", 'w')
#for d, gene in values:
for gene in values:
f.write("%s\n" % (gene))
#f.write("%s\t%s\n" % (gene, str(score)))
#f2.write("%s\t%d\n" % (gene, i))
#i += 1
f.close()
#f2.close()
return
def get_scores(score_file):
"""
Parses scores from a scoring file created by GUILD (node <whitespace> score), returns a dictionary where the values are floats.
"""
nodes, dummy, node_to_score, dummy = network_utilities.get_nodes_and_edges_from_sif_file(file_name = score_file, store_edge_type = False, delim=None, data_to_float=True)
return node_to_score
