def get_deltas_for_mutations(args, infmat, index2gene, heat_params):
print "* Performing permuted mutation data delta selection..."
index2gene = hnio.load_index(args.infmat_index_file)
heat_permutations = permutations.generate_mutation_permutation_heat(
heat_params["heat_fn"], heat_params["sample_file"],
heat_params["gene_file"], index2gene.values(), heat_params["snv_file"],
args.gene_length_file, args.bmr, args.bmr_file, heat_params["cna_file"],
args.gene_order_file, heat_params["cna_filter_threshold"],
heat_params["min_freq"], args.num_permutations, args.num_cores)
return get_deltas_from_heat_permutations(infmat, index2gene, heat_permutations, args.test_statistic,
args.sizes, args.classic, args.num_cores)
def get_deltas_for_mutations(args, infmat, index2gene, heat_params):
print "* Performing permuted mutation data delta selection..."
index2gene = hnio.load_index(args.infmat_index_file)
heat_permutations = permutations.generate_mutation_permutation_heat(
heat_params["heat_fn"],
heat_params["sample_file"],
heat_params["gene_file"],
index2gene.values(),
heat_params["snv_file"],
args.gene_length_file,
args.bmr,
args.bmr_file,
heat_params["cna_file"],
args.gene_order_file,
heat_params["cna_filter_threshold"],
heat_params["min_freq"],
args.num_permutations,
args.num_cores,
)
return get_deltas_from_heat_permutations(
infmat, index2gene, heat_permutations, args.test_statistic, args.sizes, args.classic, args.num_cores
)
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).")
# load data
infmat = hnio.load_infmat(args.infmat_file, args.infmat_name)
full_index2gene = hnio.load_index(args.infmat_index_file)
heat, heat_params = hnio.load_heat_json(args.heat_file)
# compute similarity matrix
sim, index2gene = hn.similarity_matrix(infmat, full_index2gene, heat,
not args.classic)
# only calculate permuted data sets for significance testing once
if args.permutation_type != "none":
if args.permutation_type == "heat":
print "* Generating heat permutations for statistical significance testing"
extra_genes = hnio.load_genes(args.permutation_genes_file) \
if args.permutation_genes_file else None
heat_permutations = p.permute_heat(heat, full_index2gene.values(),
args.num_permutations,
extra_genes, args.num_cores)
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."
)
print "* Generating mutation permutations for statistical significance testing"
heat_permutations = p.generate_mutation_permutation_heat(
heat_params["heat_fn"],
heat_params["sample_file"], heat_params["gene_file"],
full_index2gene.values(), heat_params["snv_file"],
args.gene_length_file, args.bmr, args.bmr_file,
heat_params["cna_file"], args.gene_order_file,
heat_params["cna_filter_threshold"], heat_params["min_freq"],
args.num_permutations, args.num_cores)
elif args.permutation_type == "network":
pass #nothing to do right now
elif args.permutation_type == "precomputed":
heat_file_paths = [
args.datasets_path.replace(ITERATION_REPLACEMENT_TOKEN, str(i))
for i in range(1, args.num_permutations + 1)
]
heat_permutations = [
hnio.load_heat_tsv(heat_file) for heat_file in heat_file_paths
]
else:
raise ValueError("Unrecognized permutation type %s" %
(args.permutation_type))
for delta in args.deltas:
delta_out_dir = args.output_directory + "/delta_" + str(delta)
if not os.path.isdir(delta_out_dir):
os.mkdir(delta_out_dir)
G = hn.weighted_graph(sim, index2gene, delta, not args.classic)
ccs = hn.connected_components(G, args.min_cc_size)
# calculate significance
if args.permutation_type != "none":
if args.permutation_type == "network":
sizes2stats = calculate_significance_network(
args, args.permuted_networks_path, full_index2gene, G,
heat, delta, args.num_permutations)
else:
sizes2stats = calculate_significance(args, infmat,
full_index2gene, G, delta,
heat_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
hnio.write_components_as_tsv(
os.path.abspath(delta_out_dir) + "/" + COMPONENTS_TSV, ccs)
args.delta = delta # include delta in parameters section of output JSON
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(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()
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).")
# load data
infmat = np.array(scipy.io.loadmat(args.infmat_file)[args.infmat_name])
full_index2gene = hnio.load_index(args.infmat_index_file)
heat, heat_params = hnio.load_heat_json(args.heat_file)
# compute similarity matrix
sim, index2gene = hn.similarity_matrix(infmat, full_index2gene, heat, not args.classic)
# only calculate permuted data sets for significance testing once
if args.permutation_type != "none":
if args.permutation_type == "heat":
print "* Generating heat permutations for statistical significance testing"
extra_genes = hnio.load_genes(args.permutation_genes_file) \
if args.permutation_genes_file else None
heat_permutations = p.permute_heat(heat, full_index2gene.values(),
args.num_permutations, extra_genes, args.num_cores)
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.")
print "* Generating mutation permutations for statistical significance testing"
heat_permutations = p.generate_mutation_permutation_heat(
heat_params["heat_fn"], heat_params["sample_file"],
heat_params["gene_file"], full_index2gene.values(),
heat_params["snv_file"], args.gene_length_file, args.bmr,
args.bmr_file, heat_params["cna_file"], args.gene_order_file,
heat_params["cna_filter_threshold"], heat_params["min_freq"],
args.num_permutations, args.num_cores)
elif args.permutation_type == "network":
pass #nothing to do right now
elif args.permutation_type == "precomputed":
heat_file_paths = [args.datasets_path.replace(ITERATION_REPLACEMENT_TOKEN, str(i))
for i in range(1, args.num_permutations+1)]
heat_permutations = [hnio.load_heat_tsv(heat_file) for heat_file in heat_file_paths]
else:
raise ValueError("Unrecognized permutation type %s" % (args.permutation_type))
for delta in args.deltas:
delta_out_dir = args.output_directory + "/delta_" + str(delta)
if not os.path.isdir(delta_out_dir):
os.mkdir(delta_out_dir)
G = hn.weighted_graph(sim, index2gene, delta, not args.classic)
ccs = hn.connected_components(G, args.min_cc_size)
# calculate significance
if args.permutation_type != "none":
if args.permutation_type == "network":
sizes2stats = calculate_significance_network(args, args.permuted_networks_path,
full_index2gene, G, heat, delta,
args.num_permutations)
else:
sizes2stats = calculate_significance(args, infmat, full_index2gene, G, delta,
heat_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
hnio.write_components_as_tsv(os.path.abspath(delta_out_dir) + "/" + COMPONENTS_TSV, ccs)
args.delta = delta # include delta in parameters section of output JSON
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(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()
