def trn_stats(genes, trn, t_factors, version):
LOGGER.info("Computing TRN statistics")
nodes = sorted(trn.nodes_iter())
node2id = {n: i for (i, n) in enumerate(nodes)}
id2node = {i: n for (i, n) in enumerate(nodes)}
(grn, node2id) = to_simple(trn.to_grn(), return_map=True)
nodes = sorted(grn.nodes_iter())
regulating = {node for (node, deg) in grn.out_degree_iter() if deg > 0}
regulated = set(nodes) - regulating
components = sorted(nx.weakly_connected_components(grn), key=len,
reverse=True)
data = dict()
for (a, b) in itertools.product(("in", "out"), repeat=2):
data["{a}_{b}_ass".format(a=a, b=b)] = nx.degree_assortativity_coefficient(grn, x=a, y=b)
census = triadic_census(grn)
forward = census["030T"]
feedback = census["030C"]
num_cycles = sum(1 for cyc in nx.simple_cycles(grn) if len(cyc) > 2)
in_deg = [grn.in_degree(node) for node in regulated]
out_deg = [grn.out_degree(node) for node in regulating]
data["version"] = version,
data["release"] = pd.to_datetime(RELEASE[version]),
data["num_genes"] = len(genes),
data["num_tf"] = len(t_factors),
data["num_nodes"] = len(nodes),
data["num_regulating"] = len(regulating),
data["num_regulated"] = len(regulated),
data["num_links"] = grn.size(),
data["density"] = nx.density(grn),
data["num_components"] = len(components),
data["largest_component"] = len(components[0]),
data["feed_forward"] = forward,
data["feedback"] = feedback,
data["fis_out"] = trn.out_degree(TranscriptionFactor[FIS_ID, version]),
data["hns_out"] = trn.out_degree(TranscriptionFactor[HNS_ID, version]),
data["cycles"] = num_cycles,
data["regulated_in_deg"] = mean(in_deg),
data["regulating_out_deg"] = mean(out_deg),
data["hub_out_deg"] = max(out_deg)
stats = pd.DataFrame(data, index=[1])
in_deg = [grn.in_degree(node) for node in nodes]
out_deg = [grn.out_degree(node) for node in nodes]
bc = nx.betweenness_centrality(grn)
bc = [bc[node] for node in nodes]
dists = pd.DataFrame({
"version": version,
"release": [pd.to_datetime(RELEASE[version])] * len(nodes),
"node": [id2node[node].unique_id for node in nodes],
"regulated_in_degree": in_deg,
"regulating_out_degree": out_deg,
"betweenness": bc
})
return (stats, dists)
def main_random(args):
locations = sorted(glob(os.path.join(args.in_path, args.glob)))
locations = [os.path.abspath(loc) for loc in locations]
pool = multiprocessing.Pool(args.nproc)
bar = ProgressBar(maxval=args.rnd_num, widgets=[Timer(), " ",
SimpleProgress(), " ", Percentage(), " ", Bar(), " ", ETA()])
rewire_name = "grn_rewired_{0:.1f}.pkl".format(args.prob)
switch_name = "grn_switched_{0:d}.pkl".format(args.flip_num)
for path in locations:
filename = os.path.join(path, "trn.pkl")
if not os.path.exists(filename):
continue
ver = version_from_path(path)
base_path = os.path.join(args.out_path, ver)
if not os.path.isdir(base_path):
os.makedirs(base_path)
LOGGER.info(ver)
trn = pyorg.read_pickle(filename)
# we consider null-models on the projected level since that is the level
# on which we evaluate topological quantities
net = pyreg.to_simple(trn.to_grn())
if args.run_rewire:
LOGGER.info("Rewiring with probability %.1f", args.prob)
tasks = [(net, args.prob)] * args.rnd_num
res_it = pool.imap_unordered(rewire, tasks)
rands = list()
bar.start()
for rnd in res_it:
rands.append(rnd)
bar += 1
bar.finish()
pyorg.write_pickle(rands, os.path.join(base_path, rewire_name))
if args.run_switch:
LOGGER.info("Switch-randomizing each edge %d times", args.flip_num)
tasks = [(net, args.flip_num)] * args.rnd_num
res_it = pool.imap_unordered(switch, tasks)
success = list()
rands = list()
bar.start()
for (rnd, rate) in res_it:
rands.append(rnd)
success.append(rate)
bar += 1
bar.finish()
pyorg.write_pickle(rands, os.path.join(base_path, switch_name))
LOGGER.info("mean flip success rate: %.3G +/- %.3G", np.mean(success),
np.std(success))
pool.close()
