def main():
ontology = dag.DAG(config.go_fpath)
#gene_annotation = utils.get_annotation(config.annotation_fpath, config.filtered_annotation_fpath, ontology.get_root())
gene_annotation = utils.get_annotation(config.annotation_fpath, config.filtered_annotation_fpath, ontology.get_root())
print "Number of annotated genes:%d" % len(gene_annotation)
network = utils.create_network(config.network_fpath)
print "Number of nodes in network:%d" % network.number_of_nodes()
'''
non_sim_avg = 0.0
for node in network.nodes():
if not node in neighbors:
count += 1
nterms = gene_annotation[node]
sim = compute_gene_sim_total(nterms, terms)
#sim = compute_gene_sim_max(nterms, terms)
non_sim_avg += sim
non_sim_avg /= count
print "%s, %f, %f" % (gene, sim_avg, non_sim_avg)
if __name__ == "__main__":
dag = DAG(config.go_fpath)
gene_annotation = utils.get_annotation(config.annotation_fpath, config.filtered_annotation_fpath, dag.get_root().id)
term_ic = utils.calculate_ic(gene_annotation, dag, config.ic_fpath)
network = utils.create_network(config.network_fpath)
# Remove unannotated gene from network
for node in network.nodes():
if not node in gene_annotation:
network.remove_node(node)
# Remove individual nodes by get the largest indepedent connected component
network = nx.connected_component_subgraphs(network)[0]
sim_cache = utils.read_sim(config.simcache_fpath)
#compute_term_in_neighbour_ratio()
#compute_avg_term_num()
else:
csv = pd.read_csv('data/{}_labels.csv'.format(args.phase))
x = np.array([
cv2.cvtColor(
cv2.imread('data/{}/{:.0f}_{:.0f}.tif'.format(
args.phase, j['slide'], j['rid'])), cv2.COLOR_BGR2RGB)
for _, j in csv.iterrows()
])
np.save('data/{}/y.npy'.format(args.phase),
np.array(csv['y'].tolist()))
np.save('data/{}/x.npy'.format(args.phase), x)
elif args.opt == 'get_annotation':
filelist = glob.glob('data/cells/Sedeen/*.session.xml')
filelist.sort()
annotations = get_annotation(filelist)
if not os.path.exists('segmentation&classification/cells'):
os.mkdir('segmentation&classification/cells')
np.save('segmentation&classification/cells/annotation.npy', annotations)
elif args.opt == 'get_centroid':
seg = np.load('segmentation&classification/{}/seg.npy'.format(args.phase))
def _add_data(region_prop):
tmp = []
for j in region_prop:
if j.major_axis_length / j.minor_axis_length < 3 and j.area < 1200:
tmp.append(j.centroid + (j.label, ))
tmp = np.array(tmp)
return tmp