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):
output_f = open(args.hotnet_output_json)
output_blob = json.load(output_f)
output_f.close()
heat_parameters = output_blob["heat_parameters"]
if heat_parameters["heat_fn"] != "load_mutation_heat":
raise ValueError(
"Heat scores must have been calculated from mutation data to annotate output."
)
components = output_blob["components"]
genes = hnio.load_genes(heat_parameters["gene_file"])
samples = hnio.load_samples(heat_parameters["sample_file"])
snvs = hnio.load_snvs(heat_parameters["snv_file"], genes, samples)
cnas = hnio.load_cnas(heat_parameters["cna_file"], genes, samples)
if not samples:
samples = set([snv.sample
for snv in snvs] + [cna.sample for cna in cnas])
gene2mutsam = defaultdict(set)
for mut in snvs + cnas:
gene2mutsam[mut.gene].add(mut.sample)
annotated_ccs = list()
for component in components:
annotated_cc = list()
annotated_ccs.append(annotated_cc)
cc_mutated_samples = set()
for gene in component:
cc_mutated_samples.update(gene2mutsam[gene])
annotated_cc.append("%s(%s)" % (gene, len(gene2mutsam[gene])))
annotated_cc.insert(
0,
"%s(%s%%)" % (len(cc_mutated_samples),
len(cc_mutated_samples) / float(len(samples)) * 100))
output_directory = output_blob["parameters"]["output_directory"]
output_file = os.path.abspath(output_directory) + "/" + ANNOTATION_TSV
hnio.write_components_as_tsv(output_file, annotated_ccs)
def run(args):
output_f = open(args.hotnet_output_json)
output_blob = json.load(output_f)
output_f.close()
heat_parameters = output_blob["heat_parameters"]
if heat_parameters["heat_fn"] != "load_mutation_heat":
raise ValueError("Heat scores must have been calculated from mutation data to annotate output.")
components = output_blob["components"]
genes = hnio.load_genes(heat_parameters["gene_file"])
samples = hnio.load_samples(heat_parameters["sample_file"])
snvs = hnio.load_snvs(heat_parameters["snv_file"], genes, samples)
cnas = hnio.load_cnas(heat_parameters["cna_file"], genes, samples)
if not samples:
samples = set([snv.sample for snv in snvs] + [cna.sample for cna in cnas])
gene2mutsam = defaultdict(set)
for mut in snvs + cnas:
gene2mutsam[mut.gene].add(mut.sample)
annotated_ccs = list()
for component in components:
annotated_cc = list()
annotated_ccs.append(annotated_cc)
cc_mutated_samples = set()
for gene in component:
cc_mutated_samples.update(gene2mutsam[gene])
annotated_cc.append("%s(%s)" % (gene, len(gene2mutsam[gene])))
annotated_cc.insert(0, "%s(%s%%)" % (len(cc_mutated_samples),
len(cc_mutated_samples) / float(len(samples)) * 100))
output_directory = output_blob["parameters"]["output_directory"]
output_file = os.path.abspath(output_directory) + "/" + ANNOTATION_TSV
hnio.write_components_as_tsv(output_file, annotated_ccs)
def run_helper(args, infmat_name, get_deltas_fn, extra_delta_args):
"""Helper shared by simpleRun and simpleRunClassic.
"""
# 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 = hnio.load_infmat(args.infmat_file, infmat_name)
full_index2gene = hnio.load_index(args.infmat_index_file)
using_json_heat = os.path.splitext(args.heat_file.lower())[1] == '.json'
if using_json_heat:
heat = json.load(open(args.heat_file))['heat']
else:
heat = hnio.load_heat_tsv(args.heat_file)
print "* Loaded heat scores for %s genes" % len(heat)
# filter out genes not in the network
heat = hnheat.filter_heat_to_network_genes(heat, set(full_index2gene.values()))
# genes with score 0 cannot be in output components, but are eligible for heat in permutations
heat, addtl_genes = hnheat.filter_heat(heat, None, False, 'There are ## genes with heat score 0')
deltas = get_deltas_fn(full_index2gene, heat, args.delta_permutations, args.num_cores, infmat, addtl_genes, *extra_delta_args)
sim, index2gene = hn.similarity_matrix(infmat, full_index2gene, heat, True)
results_files = []
for delta in 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, index2gene, delta, directed=True)
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, full_index2gene.values(),
args.significance_permutations, addtl_genes,
args.num_cores)
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, full_index2gene,
heat_permutations, delta, sizes, True,
args.num_cores)
real_counts = stats.num_components_min_size(G, sizes)
size2real_counts = dict(zip(sizes, real_counts))
sizes2stats = stats.compute_statistics(size2real_counts, sizes2counts,
args.significance_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
if not using_json_heat:
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 # include delta in parameters section of output JSON
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()
results_files.append( os.path.abspath(delta_out_dir) + "/" + JSON_OUTPUT )
hnio.write_components_as_tsv(os.path.abspath(delta_out_dir) + "/" + COMPONENTS_TSV, ccs)
# create the hierarchy if necessary
if args.output_hierarchy:
from bin import createDendrogram as CD
hierarchy_out_dir = '{}/hierarchy/'.format(args.output_directory)
if not os.path.isdir(hierarchy_out_dir): os.mkdir(hierarchy_out_dir)
params = vars(args)
CD.createDendrogram( sim, index2gene.values(), hierarchy_out_dir, params, verbose=False)
hierarchyFile = '{}/viz_files/{}'.format(str(hn.__file__).rsplit('/', 1)[0], HIERARCHY_WEB_FILE)
shutil.copy(hierarchyFile, '{}/index.html'.format(hierarchy_out_dir))
# write visualization output if edge file given
if args.edge_file:
from bin import makeResultsWebsite as MRW
viz_args = [ "-r" ] + results_files
viz_args += ["-ef", args.edge_file, "-o", args.output_directory + "/viz" ]
if args.network_name: viz_args += [ "-nn", args.network_name ]
if args.display_score_file: viz_args += [ "-dsf", args.display_score_file ]
if args.display_name_file: viz_args += [ "-dnf", args.display_name_file ]
MRW.run( MRW.get_parser().parse_args(viz_args) )
def run_helper(args, infmat_name, get_deltas_fn, extra_delta_args):
"""Helper shared by simpleRun and simpleRunClassic.
"""
# 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]
full_index2gene = hnio.load_index(args.infmat_index_file)
using_json_heat = os.path.splitext(args.heat_file.lower())[1] == '.json'
if using_json_heat:
heat = json.load(open(args.heat_file))['heat']
else:
heat = hnio.load_heat_tsv(args.heat_file)
print "* Loaded heat scores for %s genes" % len(heat)
# filter out genes not in the network
heat = hnheat.filter_heat_to_network_genes(heat, set(full_index2gene.values()))
# genes with score 0 cannot be in output components, but are eligible for heat in permutations
heat, addtl_genes = hnheat.filter_heat(heat, None, False, 'There are ## genes with heat score 0')
deltas = get_deltas_fn(full_index2gene, heat, args.delta_permutations, args.num_cores, infmat, addtl_genes, *extra_delta_args)
sim, index2gene = hn.similarity_matrix(infmat, full_index2gene, heat, True)
results_files = []
for delta in 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, index2gene, delta, directed=True)
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, full_index2gene.values(),
args.significance_permutations, addtl_genes,
args.num_cores)
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, full_index2gene,
heat_permutations, delta, sizes, True,
args.num_cores)
real_counts = stats.num_components_min_size(G, sizes)
size2real_counts = dict(zip(sizes, real_counts))
sizes2stats = stats.compute_statistics(size2real_counts, sizes2counts,
args.significance_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
if not using_json_heat:
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 # include delta in parameters section of output JSON
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()
results_files.append( os.path.abspath(delta_out_dir) + "/" + JSON_OUTPUT )
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:
from bin import makeResultsWebsite as MRW
viz_args = [ "-r" ] + results_files
viz_args += ["-ef", args.edge_file, "-o", args.output_directory + "/viz" ]
if args.network_name: viz_args += [ "-nn", args.network_name ]
if args.display_score_file: viz_args += [ "-dsf", args.display_score_file ]
MRW.run( MRW.get_parser().parse_args(viz_args) )
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)