help='Number of samples')
parser.add_argument('--N_per_bin',
type=int,
default=30,
help='Minimum number of nodes per degree bin')
parser.add_argument('--rdmseed', type=int, default=None, help='RNG seed')
args = parser.parse_args()
logging.basicConfig(level=logging.INFO,
format='%(module)s:%(levelname)s:%(asctime)s:%(message)s',
handlers=[
logging.FileHandler("../logs/report.log"),
logging.StreamHandler()
])
logging.info(args)
files = listdir(args.in_genesets_dir)
net = utils.read_network(args.net_path)
#def gen_samples(file):
for file in tqdm(files):
genes = utils.read_gene_list(join(args.in_genesets_dir, file))
samples = gen.gen_degree_preserved_sets(genes,
net,
args.N_samples,
args.N_per_bin,
rdmseed=args.rdmseed)
utils.write_genesets_list(join(args.out_samples_dir, file), samples)
#utils.parallel_process(gen_samples, files, n_jobs=8)
default=100,
help='Number of samples')
parser.add_argument('--N_cores', type=int, default=1, help='Number of cores')
parser.add_argument('--seed', type=int, default=100, help='Random seed')
args = parser.parse_args()
logging.basicConfig(level=logging.INFO,
format='%(module)s:%(levelname)s:%(asctime)s:%(message)s',
handlers=[
logging.FileHandler("../logs/report.log"),
logging.StreamHandler()
])
logging.info(args)
random.seed(args.seed)
net = utils.read_network(args.net_path)
srcnodes = utils.read_gene_list(args.srcnodes_file)
destnodes = utils.read_gene_list(args.destnodes_file)
srcnodes_samples = gen.gen_degree_preserved_sets(srcnodes,
net,
n_samples=args.N_samples,
rdmseed=args.seed)
destnodes_samples = gen.gen_degree_preserved_sets(destnodes,
net,
n_samples=args.N_samples,
rdmseed=args.seed)
flows = utils.read_flows(args.flows_file)
fcnodes = flows[(flows.FCS >= args.fc_thresh)
& (flows.N_paths >= args.npath_thresh)].index.tolist()
def main(args):
logging.basicConfig(
level=logging.INFO,
format='%(module)s:%(levelname)s:%(asctime)s:%(message)s',
handlers=[
logging.FileHandler("../logs/report.log"),
logging.StreamHandler()
])
logging.info(args)
random.seed(args.seed)
net = utils.read_network(args.net_path)
srcnodes = utils.read_gene_list(args.srcnodes_file)
destnodes = utils.read_gene_list(args.destnodes_file)
flows = utils.read_flows(args.flows_file)
fcnodes = flows[(flows.FCS >= args.fc_thresh)
& (flows.N_paths >= args.npath_thresh)].index.tolist()
logging.info('Num of FC nodes: {}'.format(len(fcnodes)))
all_paths = []
for src_gene in tqdm(srcnodes):
for dest_gene in tqdm(destnodes, leave=False):
paths = list(nx.all_shortest_paths(net, src_gene, dest_gene))
all_paths += paths
logging.info('Num of all paths: {}'.format(len(all_paths)))
fc_paths = []
for i in trange(len(all_paths)):
fullpath = all_paths[i]
if len(fullpath) > 2:
path = all_paths[i][1:-1]
if np.all([node in fcnodes for node in path]):
fc_paths.append(fullpath)
logging.info('Num of FC paths: {}'.format(len(fc_paths)))
rdm_paths_A = []
for i in trange(args.N_samples):
path = random.choice(fc_paths)
tries = 0
newpath = []
while tries < 100:
newpath = [random.choice(list(net.nodes()))]
while len(newpath) < len(path):
possible_nodes = [
gene for gene in net[newpath[-1]] if gene not in newpath
]
if len(possible_nodes) > 0:
newpath.append(random.choice(possible_nodes))
else:
tries += 1
break
if len(newpath) == len(path):
break
assert tries < 100
rdm_paths_A.append(newpath)
rdm_paths_B = random.sample(all_paths, args.N_samples)
utils.write_paths(args.out_allpaths, all_paths)
utils.write_paths(args.out_fcpaths, fc_paths)
utils.write_paths(args.out_rdmpaths_A, rdm_paths_A)
utils.write_paths(args.out_rdmpaths_B, rdm_paths_B)