def significance_wrapper((infmat, index2gene, heat_permutation, delta, sizes)):
M, index2gene = hn.induce_infmat(infmat, index2gene,
sorted(heat_permutation.keys()))
h = hn.heat_vec(heat_permutation, index2gene)
sim_mat = hn.similarity_matrix(M, h)
G = hn.weighted_graph(sim_mat, index2gene, delta)
return num_components_min_size(G, sizes)
def run(args):
infmat = scipy.io.loadmat(args.infmat_file)[args.infmat_name]
infmat_index = hnio.load_index(args.infmat_index_file)
heat, heat_params = hnio.load_heat_json(args.heat_file)
if args.perm_type == "heat":
addtl_genes = hnio.load_genes(args.permutation_genes_file) if args.permutation_genes_file else None
deltas = get_deltas_for_heat(infmat, infmat_index, heat, addtl_genes,
args.num_permutations, args.parallel)
elif args.perm_type == "mutations":
deltas = get_deltas_for_mutations(args, infmat, infmat_index, heat_params)
else:
raise ValueError("Invalid mutation permutation type: %s" % args.perm_type)
#find the multiple of the median delta s.t. the size of the largest CC in the real data
#is <= MAX_CC_SIZE
medianDelta = np.median(deltas[MIN_CC_SIZE])
M, gene_index = hn.induce_infmat(infmat, infmat_index, sorted(heat.keys()))
h = hn.heat_vec(heat, gene_index)
sim = hn.similarity_matrix(M, h)
for i in range(1, 11):
G = hn.weighted_graph(sim, gene_index, i*medianDelta)
max_cc_size = max([len(cc) for cc in hn.connected_components(G)])
if max_cc_size <= MAX_CC_SIZE:
break
#and recommend running HotNet with that multiple and the next 4 multiples
recommended_deltas = [i*medianDelta for i in range(i, i+5)]
output_file = open(args.output_file, 'w') if args.output_file else sys.stdout
json.dump({"parameters": vars(args), "heat_parameters": heat_params,
"recommended_deltas": recommended_deltas}, output_file, indent=4)
if (args.output_file): output_file.close()
def run(args):
# create output directory if doesn't exist; warn if output files already exist
if not os.path.exists(args.output_directory):
os.makedirs(args.output_directory)
dir_contents = os.listdir(args.output_directory)
if JSON_OUTPUT in dir_contents or COMPONENTS_TSV in dir_contents or SIGNIFICANCE_TSV in dir_contents:
print("WARNING: Output directory already contains HotNet results file(s), which will be "
"overwritten. (Ctrl-c to cancel).")
# load data
infmat = scipy.io.loadmat(args.infmat_file)[args.infmat_name]
infmat_index = hnio.load_index(args.infmat_index_file)
heat, heat_params = hnio.load_heat_json(args.heat_file)
# compute similarity matrix and extract connected components
M, gene_index = hn.induce_infmat(infmat, infmat_index, sorted(heat.keys()), quiet=False)
h = hn.heat_vec(heat, gene_index)
sim = hn.similarity_matrix(M, h)
G = hn.weighted_graph(sim, gene_index, args.delta)
ccs = hn.connected_components(G, args.min_cc_size)
# calculate significance
if args.permutation_type != "none":
if args.permutation_type == "heat":
sizes2stats = heat_permutation_significance(args, heat, infmat, infmat_index, G)
elif args.permutation_type == "mutations":
if heat_params["heat_fn"] != "load_mutation_heat":
raise RuntimeError("Heat scores must be based on mutation data to perform\
significance testing based on mutation data permutation.")
sizes2stats = mutation_permutation_significance(args, infmat, infmat_index, G, heat_params)
else:
raise ValueError("Unrecognized permutation type %s" % (args.permutation_type))
#sort ccs list such that genes within components are sorted alphanumerically, and components
#are sorted first by length, then alphanumerically by name of the first gene in the component
ccs = [sorted(cc) for cc in ccs]
ccs.sort(key=lambda comp: comp[0])
ccs.sort(key=len, reverse=True)
# write output
output_dict = {"parameters": vars(args), "heat_parameters": heat_params,
"sizes": hn.component_sizes(ccs), "components": ccs}
if args.permutation_type != "none":
output_dict["statistics"] = sizes2stats
hnio.write_significance_as_tsv(os.path.abspath(args.output_directory) + "/" + SIGNIFICANCE_TSV,
sizes2stats)
json_out = open(os.path.abspath(args.output_directory) + "/" + JSON_OUTPUT, 'w')
json.dump(output_dict, json_out, indent=4)
json_out.close()
hnio.write_components_as_tsv(os.path.abspath(args.output_directory) + "/" + COMPONENTS_TSV, ccs)
def run(args):
infmat = scipy.io.loadmat(args.infmat_file)[args.infmat_name]
infmat_index = hnio.load_index(args.infmat_index_file)
heat, heat_params = hnio.load_heat_json(args.heat_file)
if args.perm_type == "heat":
addtl_genes = hnio.load_genes(
args.permutation_genes_file
) if args.permutation_genes_file else None
deltas = get_deltas_for_heat(infmat, infmat_index, heat, addtl_genes,
args.num_permutations, args.parallel)
elif args.perm_type == "mutations":
deltas = get_deltas_for_mutations(args, infmat, infmat_index,
heat_params)
else:
raise ValueError("Invalid mutation permutation type: %s" %
args.perm_type)
#find the multiple of the median delta s.t. the size of the largest CC in the real data
#is <= MAX_CC_SIZE
medianDelta = np.median(deltas[MIN_CC_SIZE])
M, gene_index = hn.induce_infmat(infmat, infmat_index, sorted(heat.keys()))
h = hn.heat_vec(heat, gene_index)
sim = hn.similarity_matrix(M, h)
for i in range(1, 11):
G = hn.weighted_graph(sim, gene_index, i * medianDelta)
max_cc_size = max([len(cc) for cc in hn.connected_components(G)])
if max_cc_size <= MAX_CC_SIZE:
break
#and recommend running HotNet with that multiple and the next 4 multiples
recommended_deltas = [i * medianDelta for i in range(i, i + 5)]
output_file = open(args.output_file,
'w') if args.output_file else sys.stdout
json.dump(
{
"parameters": vars(args),
"heat_parameters": heat_params,
"recommended_deltas": recommended_deltas
},
output_file,
indent=4)
if (args.output_file):
output_file.close()
def significance_wrapper((infmat, index2gene, heat_permutation, delta, sizes)):
M, index2gene = hn.induce_infmat(infmat, index2gene, sorted(heat_permutation.keys()))
h = hn.heat_vec(heat_permutation, index2gene)
sim_mat = hn.similarity_matrix(M, h)
G = hn.weighted_graph(sim_mat, index2gene, delta)
return num_components_min_size(G, sizes)
def run(args):
# create output directory if doesn't exist; warn if it exists and is not empty
if not os.path.exists(args.output_directory):
os.makedirs(args.output_directory)
if len(os.listdir(args.output_directory)) > 0:
print("WARNING: Output directory is not empty. Any conflicting files will be overwritten. ")
print("(Ctrl-c to cancel).")
infmat = scipy.io.loadmat(args.infmat_file)[INFMAT_NAME]
infmat_index = hnio.load_index(args.infmat_index_file)
heat = hnio.load_heat_tsv(args.heat_file)
# filter out genes with heat score less than min_heat_score
heat, addtl_genes, args.min_heat_score = hnheat.filter_heat(heat, args.min_heat_score)
# find delta that maximizes # CCs of size >= MIN_SIZE for each permuted data set
deltas = ft.get_deltas_for_heat(infmat, infmat_index, heat, addtl_genes, args.num_permutations,
args.parallel)
#find the multiple of the median delta s.t. the size of the largest CC in the real data
#is <= MAX_CC_SIZE
medianDelta = np.median(deltas[MIN_CC_SIZE])
M, gene_index = hn.induce_infmat(infmat, infmat_index, sorted(heat.keys()), quiet=False)
h = hn.heat_vec(heat, gene_index)
sim = hn.similarity_matrix(M, h)
for i in range(1, 11):
G = hn.weighted_graph(sim, gene_index, i*medianDelta)
max_cc_size = max([len(cc) for cc in hn.connected_components(G)])
if max_cc_size <= MAX_CC_SIZE:
break
# load interaction network edges and determine location of static HTML files for visualization
edges = hnio.load_ppi_edges(args.edge_file) if args.edge_file else None
index_file = '%s/viz_files/%s' % (os.path.realpath(__file__).rsplit('/', 1)[0], VIZ_INDEX)
subnetworks_file = '%s/viz_files/%s' % (os.path.realpath(__file__).rsplit('/', 1)[0], VIZ_SUBNETWORKS)
gene2index = dict([(gene, index) for index, gene in list(infmat_index.items())])
#and run HotNet with that multiple and the next 4 multiples
run_deltas = [i*medianDelta for i in range(i, i+5)]
for delta in run_deltas:
# create output directory
delta_out_dir = args.output_directory + "/delta_" + str(delta)
if not os.path.isdir(delta_out_dir):
os.mkdir(delta_out_dir)
# find connected components
G = hn.weighted_graph(sim, gene_index, delta)
ccs = hn.connected_components(G, args.min_cc_size)
# calculate significance (using all genes with heat scores)
print("* Performing permuted heat statistical significance...")
heat_permutations = p.permute_heat(heat, args.num_permutations, addtl_genes, args.parallel)
sizes = list(range(2, 11))
print("\t- Using no. of components >= k (k \\in")
print("[%s, %s]) as statistic" % (min(sizes), max(sizes)))
sizes2counts = stats.calculate_permuted_cc_counts(infmat, infmat_index, heat_permutations,
delta, sizes, args.parallel)
real_counts = stats.num_components_min_size(G, sizes)
size2real_counts = dict(list(zip(sizes, real_counts)))
sizes2stats = stats.compute_statistics(size2real_counts, sizes2counts, args.num_permutations)
# sort ccs list such that genes within components are sorted alphanumerically, and components
# are sorted first by length, then alphanumerically by name of the first gene in the component
ccs = [sorted(cc) for cc in ccs]
ccs.sort(key=lambda comp: comp[0])
ccs.sort(key=len, reverse=True)
# write output
heat_dict = {"heat": heat, "parameters": {"heat_file": args.heat_file}}
heat_out = open(os.path.abspath(delta_out_dir) + "/" + HEAT_JSON, 'w')
json.dump(heat_dict, heat_out, indent=4)
heat_out.close()
args.heat_file = os.path.abspath(delta_out_dir) + "/" + HEAT_JSON
args.delta = delta
output_dict = {"parameters": vars(args), "sizes": hn.component_sizes(ccs),
"components": ccs, "statistics": sizes2stats}
hnio.write_significance_as_tsv(os.path.abspath(delta_out_dir) + "/" + SIGNIFICANCE_TSV,
sizes2stats)
json_out = open(os.path.abspath(delta_out_dir) + "/" + JSON_OUTPUT, 'w')
json.dump(output_dict, json_out, indent=4)
json_out.close()
hnio.write_components_as_tsv(os.path.abspath(delta_out_dir) + "/" + COMPONENTS_TSV, ccs)
# write visualization output if edge file given
if args.edge_file:
viz_data = {"delta": delta, 'subnetworks': list()}
for cc in ccs:
viz_data['subnetworks'].append(viz.get_component_json(cc, heat, edges, gene2index, args.network_name))
delta_viz_dir = '%s/viz/delta%s' % (args.output_directory, delta)
if not os.path.isdir(delta_viz_dir):
os.makedirs(delta_viz_dir)
viz_out = open('%s/subnetworks.json' % delta_viz_dir, 'w')
json.dump(viz_data, viz_out, indent=4)
viz_out.close()
shutil.copy(subnetworks_file, delta_viz_dir)
if args.edge_file:
viz.write_index_file(index_file, '%s/viz/%s' % (args.output_directory, VIZ_INDEX), run_deltas)
def run(args):
# create output directory if doesn't exist; warn if output files already exist
if not os.path.exists(args.output_directory):
os.makedirs(args.output_directory)
dir_contents = os.listdir(args.output_directory)
if JSON_OUTPUT in dir_contents or COMPONENTS_TSV in dir_contents or SIGNIFICANCE_TSV in dir_contents:
print(
"WARNING: Output directory already contains HotNet results file(s), which will be "
"overwritten. (Ctrl-c to cancel).")
# load data
infmat = scipy.io.loadmat(args.infmat_file)[args.infmat_name]
infmat_index = hnio.load_index(args.infmat_index_file)
heat, heat_params = hnio.load_heat_json(args.heat_file)
# compute similarity matrix and extract connected components
M, gene_index = hn.induce_infmat(infmat,
infmat_index,
sorted(heat.keys()),
quiet=False)
h = hn.heat_vec(heat, gene_index)
sim = hn.similarity_matrix(M, h)
G = hn.weighted_graph(sim, gene_index, args.delta)
ccs = hn.connected_components(G, args.min_cc_size)
# calculate significance
if args.permutation_type != "none":
if args.permutation_type == "heat":
sizes2stats = heat_permutation_significance(
args, heat, infmat, infmat_index, G)
elif args.permutation_type == "mutations":
if heat_params["heat_fn"] != "load_mutation_heat":
raise RuntimeError(
"Heat scores must be based on mutation data to perform\
significance testing based on mutation data permutation."
)
sizes2stats = mutation_permutation_significance(
args, infmat, infmat_index, G, heat_params)
else:
raise ValueError("Unrecognized permutation type %s" %
(args.permutation_type))
#sort ccs list such that genes within components are sorted alphanumerically, and components
#are sorted first by length, then alphanumerically by name of the first gene in the component
ccs = [sorted(cc) for cc in ccs]
ccs.sort(key=lambda comp: comp[0])
ccs.sort(key=len, reverse=True)
# write output
output_dict = {
"parameters": vars(args),
"heat_parameters": heat_params,
"sizes": hn.component_sizes(ccs),
"components": ccs
}
if args.permutation_type != "none":
output_dict["statistics"] = sizes2stats
hnio.write_significance_as_tsv(
os.path.abspath(args.output_directory) + "/" + SIGNIFICANCE_TSV,
sizes2stats)
json_out = open(
os.path.abspath(args.output_directory) + "/" + JSON_OUTPUT, 'w')
json.dump(output_dict, json_out, indent=4)
json_out.close()
hnio.write_components_as_tsv(
os.path.abspath(args.output_directory) + "/" + COMPONENTS_TSV, ccs)
def run(args):
# create output directory if doesn't exist; warn if it exists and is not empty
if not os.path.exists(args.output_directory):
os.makedirs(args.output_directory)
if len(os.listdir(args.output_directory)) > 0:
print("WARNING: Output directory is not empty. Any conflicting files will be overwritten. "
"(Ctrl-c to cancel).")
infmat = scipy.io.loadmat(args.infmat_file)[INFMAT_NAME]
infmat_index = hnio.load_index(args.infmat_index_file)
heat = hnio.load_heat_tsv(args.heat_file)
#filter out genes with heat score less than min_heat_score
heat, addtl_genes, args.min_heat_score = hnheat.filter_heat(heat, args.min_heat_score)
#find delta that maximizes # CCs of size >= MIN_SIZE for each permuted data set
deltas = ft.get_deltas_for_heat(infmat, infmat_index, heat, addtl_genes, args.num_permutations,
args.parallel)
#find the multiple of the median delta s.t. the size of the largest CC in the real data
#is <= MAX_CC_SIZE
medianDelta = np.median(deltas[MIN_CC_SIZE])
M, gene_index = hn.induce_infmat(infmat, infmat_index, sorted(heat.keys()), quiet=False)
h = hn.heat_vec(heat, gene_index)
sim = hn.similarity_matrix(M, h)
for i in range(1, 11):
G = hn.weighted_graph(sim, gene_index, i*medianDelta)
max_cc_size = max([len(cc) for cc in hn.connected_components(G)])
if max_cc_size <= MAX_CC_SIZE:
break
#and run HotNet with that multiple and the next 4 multiples
run_deltas = [i*medianDelta for i in range(i, i+5)]
for delta in run_deltas:
#create output directory
delta_out_dir = args.output_directory + "/delta_" + str(delta)
if not os.path.isdir(delta_out_dir):
os.mkdir(delta_out_dir)
#find connected components
G = hn.weighted_graph(sim, gene_index, delta)
ccs = hn.connected_components(G, args.min_cc_size)
# calculate significance (using all genes with heat scores)
print "* Performing permuted heat statistical significance..."
heat_permutations = p.permute_heat(heat, args.num_permutations, addtl_genes, args.parallel)
sizes = range(2, 11)
print "\t- Using no. of components >= k (k \\in",
print "[%s, %s]) as statistic" % (min(sizes), max(sizes))
sizes2counts = stats.calculate_permuted_cc_counts(infmat, infmat_index, heat_permutations,
delta, sizes, args.parallel)
real_counts = stats.num_components_min_size(G, sizes)
size2real_counts = dict(zip(sizes, real_counts))
sizes2stats = stats.compute_statistics(size2real_counts, sizes2counts, args.num_permutations)
#sort ccs list such that genes within components are sorted alphanumerically, and components
#are sorted first by length, then alphanumerically by name of the first gene in the component
ccs = [sorted(cc) for cc in ccs]
ccs.sort(key=lambda comp: comp[0])
ccs.sort(key=len, reverse=True)
# write output
output_dict = {"parameters": vars(args), "sizes": hn.component_sizes(ccs),
"components": ccs, "statistics": sizes2stats}
hnio.write_significance_as_tsv(os.path.abspath(delta_out_dir) + "/" + SIGNIFICANCE_TSV,
sizes2stats)
json_out = open(os.path.abspath(delta_out_dir) + "/" + JSON_OUTPUT, 'w')
json.dump(output_dict, json_out, indent=4)
json_out.close()
hnio.write_components_as_tsv(os.path.abspath(delta_out_dir) + "/" + COMPONENTS_TSV, ccs)
def run(args):
# create output directory if doesn't exist; warn if it exists and is not empty
if not os.path.exists(args.output_directory):
os.makedirs(args.output_directory)
if len(os.listdir(args.output_directory)) > 0:
print("WARNING: Output directory is not empty. Any conflicting files will be overwritten. "
"(Ctrl-c to cancel).")
infmat = scipy.io.loadmat(args.infmat_file)[INFMAT_NAME]
infmat_index = hnio.load_index(args.infmat_index_file)
heat = hnio.load_heat_tsv(args.heat_file)
# filter out genes with heat score less than min_heat_score
heat, addtl_genes, args.min_heat_score = hnheat.filter_heat(heat, args.min_heat_score)
# find delta that maximizes # CCs of size >= MIN_SIZE for each permuted data set
deltas = ft.get_deltas_for_heat(infmat, infmat_index, heat, addtl_genes, args.num_permutations,
args.parallel)
#find the multiple of the median delta s.t. the size of the largest CC in the real data
#is <= MAX_CC_SIZE
medianDelta = np.median(deltas[MIN_CC_SIZE])
M, gene_index = hn.induce_infmat(infmat, infmat_index, sorted(heat.keys()), quiet=False)
h = hn.heat_vec(heat, gene_index)
sim = hn.similarity_matrix(M, h)
for i in range(1, 11):
G = hn.weighted_graph(sim, gene_index, i*medianDelta)
max_cc_size = max([len(cc) for cc in hn.connected_components(G)])
if max_cc_size <= MAX_CC_SIZE:
break
# load interaction network edges and determine location of static HTML files for visualization
edges = hnio.load_ppi_edges(args.edge_file) if args.edge_file else None
index_file = '%s/viz_files/%s' % (os.path.realpath(__file__).rsplit('/', 1)[0], VIZ_INDEX)
subnetworks_file = '%s/viz_files/%s' % (os.path.realpath(__file__).rsplit('/', 1)[0], VIZ_SUBNETWORKS)
gene2index = dict([(gene, index) for index, gene in infmat_index.iteritems()])
#and run HotNet with that multiple and the next 4 multiples
run_deltas = [i*medianDelta for i in range(i, i+5)]
for delta in run_deltas:
# create output directory
delta_out_dir = args.output_directory + "/delta_" + str(delta)
if not os.path.isdir(delta_out_dir):
os.mkdir(delta_out_dir)
# find connected components
G = hn.weighted_graph(sim, gene_index, delta)
ccs = hn.connected_components(G, args.min_cc_size)
# calculate significance (using all genes with heat scores)
print "* Performing permuted heat statistical significance..."
heat_permutations = p.permute_heat(heat, args.num_permutations, addtl_genes, args.parallel)
sizes = range(2, 11)
print "\t- Using no. of components >= k (k \\in",
print "[%s, %s]) as statistic" % (min(sizes), max(sizes))
sizes2counts = stats.calculate_permuted_cc_counts(infmat, infmat_index, heat_permutations,
delta, sizes, args.parallel)
real_counts = stats.num_components_min_size(G, sizes)
size2real_counts = dict(zip(sizes, real_counts))
sizes2stats = stats.compute_statistics(size2real_counts, sizes2counts, args.num_permutations)
# sort ccs list such that genes within components are sorted alphanumerically, and components
# are sorted first by length, then alphanumerically by name of the first gene in the component
ccs = [sorted(cc) for cc in ccs]
ccs.sort(key=lambda comp: comp[0])
ccs.sort(key=len, reverse=True)
# write output
heat_dict = {"heat": heat, "parameters": {"heat_file": args.heat_file}}
heat_out = open(os.path.abspath(delta_out_dir) + "/" + HEAT_JSON, 'w')
json.dump(heat_dict, heat_out, indent=4)
heat_out.close()
args.heat_file = os.path.abspath(delta_out_dir) + "/" + HEAT_JSON
args.delta = delta
output_dict = {"parameters": vars(args), "sizes": hn.component_sizes(ccs),
"components": ccs, "statistics": sizes2stats}
hnio.write_significance_as_tsv(os.path.abspath(delta_out_dir) + "/" + SIGNIFICANCE_TSV,
sizes2stats)
json_out = open(os.path.abspath(delta_out_dir) + "/" + JSON_OUTPUT, 'w')
json.dump(output_dict, json_out, indent=4)
json_out.close()
hnio.write_components_as_tsv(os.path.abspath(delta_out_dir) + "/" + COMPONENTS_TSV, ccs)
# write visualization output if edge file given
if args.edge_file:
viz_data = {"delta": delta, 'subnetworks': list()}
for cc in ccs:
viz_data['subnetworks'].append(viz.get_component_json(cc, heat, edges, gene2index,
args.network_name))
delta_viz_dir = '%s/viz/delta%s' % (args.output_directory, delta)
if not os.path.isdir(delta_viz_dir):
os.makedirs(delta_viz_dir)
viz_out = open('%s/subnetworks.json' % delta_viz_dir, 'w')
json.dump(viz_data, viz_out, indent=4)
viz_out.close()
shutil.copy(subnetworks_file, delta_viz_dir)
if args.edge_file:
viz.write_index_file(index_file, '%s/viz/%s' % (args.output_directory, VIZ_INDEX), run_deltas)