def main(dataset_name=constants.DATASET_NAME, disease_name=None, expected_genes = None, score_method=constants.DEG_EDGER, network_file_name="dip.sif"):
constants.update_dirs(DATASET_NAME_u=dataset_name)
search_method = "sa"
network_file_name, score_file_name, score_method, bg_genes= server.init_common_params(network_file_name, score_method)
results_file_name = init_specific_params(search_method)
script_file_name=format_script(os.path.join(constants.SH_DIR, "run_{}.sh".format(ALGO_NAME)), BASE_FOLDER=constants.BASE_PROFILE,
DATASET_DIR=constants.DATASET_DIR,
ALGO_DIR=ALGO_DIR, NETWORK_NAME=network_file_name, SCORE_FILE_NAME=score_file_name,
IS_GREEDY=str(search_method == "greedy"), OUTPUT_FILE=results_file_name, NUM_OF_MODULES=10, OVERLAP_THRESHOLD=0)
subprocess.Popen("bash {}".format(script_file_name), shell=True,
stdout=subprocess.PIPE, cwd=ALGO_DIR).stdout.read()
os.remove(script_file_name)
modules_genes_file_name = os.path.join(constants.OUTPUT_DIR, "{}_{}_module_genes.txt".format(ALGO_NAME, search_method))
all_bg_genes, modules = extract_modules_and_bg(bg_genes, results_file_name, modules_genes_file_name)
output_base_dir = ""
if constants.REPORTS:
output_base_dir = build_all_reports(ALGO_NAME + "_" + search_method, dataset_name, modules, all_bg_genes, score_file_name, network_file_name, disease_name, expected_genes)
output_file_name=os.path.join(constants.OUTPUT_DIR,
"{}_{}_client_output.txt".format(ALGO_NAME, search_method))
output_modules(output_file_name, modules, score_file_name, output_base_dir)
def main(dataset_name=constants.DATASET_NAME,
disease_name=None,
expected_genes=None,
score_method=constants.DEG_EDGER,
network_file_name="dip.sif"):
constants.update_dirs(DATASET_NAME_u=dataset_name)
network_file_name, score_file_name, score_method, bg_genes = server.init_common_params(
network_file_name, score_method)
heat_file_name, network_file_name = init_specific_params(
score_file_name, score_method, network_file_name)
script_file_name = format_script(
os.path.join(constants.SH_DIR, "run_{}.sh".format(ALGO_NAME)),
ALGO_DIR=ALGO_DIR,
CACHE_DIR=constants.CACHE_DIR,
OUTPUT_DIR=constants.OUTPUT_DIR,
NETWORK_NAME=os.path.splitext(os.path.basename(network_file_name))[0])
print subprocess.Popen(
"bash {}".format(script_file_name), shell=True,
stdout=subprocess.PIPE).stdout.read() # cwd=dir_path
os.remove(script_file_name)
modules, all_bg_genes = extract_modules_and_bg(bg_genes)
output_base_dir = ""
if constants.REPORTS:
output_base_dir = build_all_reports(ALGO_NAME, dataset_name, modules,
all_bg_genes, score_file_name,
network_file_name, disease_name,
expected_genes)
output_file_name = os.path.join(constants.OUTPUT_DIR,
"{}_client_output.txt".format(ALGO_NAME))
output_modules(output_file_name, modules, score_file_name, output_base_dir)
def main(dataset_name=constants.DATASET_NAME, disease_name=None, expected_genes = None, score_method=constants.DEG_EDGER, network_file_name="dip.sif", fdr=0.05):
constants.update_dirs(DATASET_NAME_u=dataset_name)
network_file_name, score_file_name, score_method, bg_genes = server.init_common_params(network_file_name , score_method)
all_bg_genes, modules = run_bionet_for_all_modules(fdr, network_file_name, score_file_name, constants.IS_PVAL_SCORES)
output_base_dir = ""
if constants.REPORTS:
output_base_dir = build_all_reports(ALGO_NAME, dataset_name, modules, all_bg_genes, score_file_name, network_file_name, disease_name, expected_genes)
output_file_name = os.path.join(constants.OUTPUT_DIR,
"{}_client_output.txt".format(ALGO_NAME))
output_modules(output_file_name, modules, score_file_name, output_base_dir)
def main(dataset_name=constants.DATASET_NAME,
disease_name=None,
expected_genes=None):
global NETWORK_NAME
constants.update_dirs(DATASET_NAME_u=dataset_name)
network_file_name, score_file_name, score_method, bg_genes = server.init_common_params(
NETWORK_NAME)
STRATEGY = "INES"
algorithm = "OPTIMAL"
omitted_genes = []
modules = []
all_bg_genes = []
cur_network_name = NETWORK_NAME
for cur_i_module in range(40):
binary_score_file_name, cur_network_file_name = init_specific_params(
score_file_name, score_method, omitted_genes, network_file_name,
str(cur_i_module))
format_scripts(algo_name=ALGO_NAME,
score_file_name=binary_score_file_name,
network_name=cur_network_file_name,
STRATEGY=STRATEGY,
algorithm=algorithm)
print subprocess.Popen("bash {}/run_{}.sh".format(
constants.SH_DIR, ALGO_NAME),
shell=True,
stdout=subprocess.PIPE,
cwd=ALGO_DIR).stdout.read()
module, all_bg_gene = extract_module_genes(bg_genes, STRATEGY,
algorithm)
if len(module[0]) > 3:
modules.append(module[0])
all_bg_genes.append(all_bg_gene[0])
omitted_genes += list(module[0])
output_base_dir = ""
if constants.REPORTS:
output_base_dir = build_all_reports(
ALGO_NAME + "_" + STRATEGY + "_" + algorithm, modules,
all_bg_genes, score_file_name, network_file_name, disease_name,
expected_genes)
output_file_name = os.path.join(
constants.OUTPUT_DIR,
"{}_{}_{}_client_output.txt".format(ALGO_NAME, STRATEGY, algorithm))
output_modules(output_file_name, modules, score_file_name, output_base_dir)
def main(dataset_name=constants.DATASET_NAME, disease_name=None, expected_genes = None):
global NETWORK_NAME
constants.update_dirs(DATASET_NAME_u=dataset_name)
network_file_name, score_file_name, score_method, bg_genes = server.init_common_params(NETWORK_NAME)
STRATEGY = "GLONE"
binary_score_file_name = init_common_params(score_file_name, score_method)
format_scripts(algo_name=ALGO_NAME, score_file_name=binary_score_file_name, network_name=NETWORK_NAME, STRATEGY=STRATEGY)
print subprocess.Popen("bash {}/run_{}.sh".format(constants.SH_DIR, ALGO_NAME), shell=True,
stdout=subprocess.PIPE, cwd=ALGO_DIR).stdout.read()
modules, all_bg_genes = extract_module_genes(bg_genes, STRATEGY)
output_base_dir = ""
if constants.REPORTS:
output_base_dir = build_all_reports(ALGO_NAME + "_" + STRATEGY, modules, all_bg_genes, score_file_name, network_file_name, disease_name, expected_genes)
output_file_name = os.path.join(constants.OUTPUT_DIR,
"{}_client_output.txt".format(ALGO_NAME))
output_modules(output_file_name, modules, score_file_name, output_base_dir )
def main(dataset_name=constants.DATASET_NAME, disease_name=None, expected_genes = None, score_method=constants.DEG_EDGER, network_file_name="dip.sif"):
constants.update_dirs(DATASET_NAME_u=dataset_name)
network_file_name, score_file_name, score_method, bg_genes = server.init_common_params(network_file_name, score_method)
strategy = "INES"
algorithm = "GREEDY"
omitted_genes = []
modules = []
all_bg_genes = []
dest_algo_dir = "{}_{}".format(ALGO_DIR, random.random())
shutil.copytree(ALGO_DIR, dest_algo_dir)
empty_counter = 0
for cur_i_module in range(40):
binary_score_file_name, cur_network_file_name = init_specific_params(score_file_name, score_method, omitted_genes,
network_file_name, str(random.random()), dest_algo_dir)
script_file_name=format_scripts(score_file_name=binary_score_file_name, network_name=cur_network_file_name,
STRATEGY=strategy, algorithm=algorithm, algo_dir=dest_algo_dir, dataset_name=dataset_name)
print subprocess.Popen("bash {}".format(script_file_name), shell=True,
stdout=subprocess.PIPE, cwd=dest_algo_dir).stdout.read()
module, all_bg_gene = extract_module_genes(bg_genes, strategy, algorithm, dest_algo_dir)
if len(module[0]) > 3:
empty_counter=0
modules.append(module[0])
all_bg_genes.append(all_bg_gene[0])
else:
empty_counter+=1
omitted_genes += list(module[0])
os.remove(script_file_name)
if empty_counter>3:
print "got more that 3 smalle modules in row. continue..."
break
shutil.rmtree(dest_algo_dir)
output_base_dir = ""
if constants.REPORTS:
output_base_dir = build_all_reports("{}_{}_{}".format(ALGO_NAME,strategy, algorithm), dataset_name, modules, all_bg_genes, score_file_name, network_file_name, disease_name, expected_genes)
output_file_name = os.path.join(constants.OUTPUT_DIR,
"{}_client_output.txt".format("{}_{}_{}".format(ALGO_NAME,strategy, algorithm)))
output_modules(output_file_name, modules, score_file_name, output_base_dir )
def main(dataset_name=constants.DATASET_NAME,
disease_name=None,
expected_genes=None,
score_method=constants.DEG_EDGER):
global NETWORK_NAME
constants.update_dirs(DATASET_NAME_u=dataset_name)
network_file_name, score_file_name, score_method, bg_genes = server.init_common_params(
NETWORK_NAME, score_method)
ge_file_name, network_file_name, output_file_name = init_specific_params(
ge_file_name=os.path.join(constants.DATA_DIR, "ge.tsv"),
network_file_name=os.path.join(constants.NETWORKS_DIR,
NETWORK_NAME + ".sif"))
format_script(os.path.join(constants.SH_DIR,
"run_{}.sh".format(ALGO_NAME)),
ALGO_BASE_DIR=constants.ALGO_BASE_DIR,
GE_FILE_NAME=ge_file_name,
NETWORK_FILE_NAME=network_file_name,
BETA=0.95,
MINIMAL_MODULE_SIZE=4,
MAXIMAL_MODULE_SIZE=1000,
OUTPUT_FILE_NAME=output_file_name)
subprocess.Popen("bash {}/run_{}.sh".format(constants.SH_DIR, ALGO_NAME),
shell=True,
stdout=subprocess.PIPE,
cwd=ALGO_DIR).stdout.read()
modules, all_bg_genes = extract_modules_and_bg(bg_genes, output_file_name)
output_base_dir = ""
if constants.REPORTS:
output_base_dir = build_all_reports(ALGO_NAME, modules, all_bg_genes,
score_file_name, network_file_name,
disease_name, expected_genes)
output_file_name = os.path.join(constants.OUTPUT_DIR,
"{}_client_output.txt".format(ALGO_NAME))
output_modules(output_file_name, modules, score_file_name, output_base_dir)
def main(dataset_name=constants.DATASET_NAME, disease_name=None, expected_genes = None, score_method=constants.DEG_EDGER):
global NETWORK_NAME
constants.update_dirs(DATASET_NAME_u=dataset_name)
network_file_name, score_file_name, score_method, bg_genes = server.init_common_params(NETWORK_NAME, score_method)
if score_method == constants.PREDEFINED_SCORE:
raise Exception("Cannot run this algo on scor-based metrics. please provide gene expression file")
bg_genes, network_file_name = init_specific_params(NETWORK_NAME)
format_script(os.path.join(constants.SH_DIR, "run_{}.sh".format(ALGO_NAME)), BASE_FOLDER=constants.BASE_PROFILE,
DATASET_DIR=constants.DATASET_DIR, ALGO_DIR=ALGO_DIR, NETWORK_NAME=NETWORK_NAME)
subprocess.Popen("bash {}/run_{}.sh".format(constants.SH_DIR, ALGO_NAME), shell=True,
stdout=subprocess.PIPE, cwd=ALGO_DIR).stdout.read()
modules, all_bg_genes = extract_modules_and_bg(bg_genes)
output_base_dir = ""
if constants.REPORTS:
output_base_dir = build_all_reports(ALGO_NAME, modules, all_bg_genes, score_file_name, network_file_name, disease_name, expected_genes)
output_file_name = os.path.join(constants.OUTPUT_DIR,
"{}_client_output.txt".format(ALGO_NAME))
output_modules(output_file_name, modules, score_file_name, output_base_dir )
def main(dataset_name=constants.DATASET_NAME,
disease_name=None,
expected_genes=None,
score_method=constants.DEG_EDGER,
network_file_name="dip.sif"):
constants.update_dirs(DATASET_NAME_u=dataset_name)
network_file_name, score_file_name, score_method, bg_genes = server.init_common_params(
network_file_name, score_method)
script_name = "run_{}.sh".format(ALGO_NAME)
dest_algo_dir = "{}_{}".format(ALGO_DIR, random.random())
shutil.copytree(ALGO_DIR, dest_algo_dir)
conf_file_name = init_specific_params(score_file_name, dest_algo_dir)
script_file_name = format_script(os.path.join(constants.SH_DIR,
script_name),
BASE_FOLDER=constants.BASE_PROFILE,
DATASET_DIR=constants.DATASET_DIR,
CONFIG_FILE_NAME=conf_file_name,
NETBOX_DIR=dest_algo_dir)
print subprocess.Popen("bash {}".format(script_file_name),
shell=True,
stdout=subprocess.PIPE,
cwd=dest_algo_dir).stdout.read()
modules, all_bg_genes = extract_modules_and_bg(bg_genes, dest_algo_dir)
os.remove(script_file_name)
os.remove(conf_file_name)
shutil.rmtree(dest_algo_dir)
output_base_dir = ""
if constants.REPORTS:
output_base_dir = build_all_reports(ALGO_NAME, dataset_name, modules,
all_bg_genes, score_file_name,
network_file_name, disease_name,
expected_genes)
output_file_name = os.path.join(constants.OUTPUT_DIR,
"{}_client_output.txt".format(ALGO_NAME))