def split_randomly_into_two_sets(list_of_child):
left_tree = tr.Tree()
right_tree = tr.Tree()
left_subtree_size = random.choice(range(0,len(list_of_child)))
for i in range(0,len(list_of_child)):
if i < left_subtree_size:
left_tree.seed_node.add_child(list_of_child[i])
else:
right_tree.seed_node.add_child(list_of_child[i])
if left_subtree_size == 0:
left_tree = None
if left_subtree_size == len(list_of_child):
right_tree = None
return tree_operations.collapse_edges(left_tree),tree_operations.collapse_edges(right_tree)
def create_tree_for_color_noise(parameters):
print('Creating noise in colors')
noise = parameters[0]
G_internal_colors = parameters[2]
S_colors = parameters[3]
number_of_leaves = parameters[6]
number_of_random_changes = number_of_leaves * (noise / 100)
random_for_prec = random_for_precentage
for rand_num in range(0, random_for_prec):
input = open(path + '/0/sigma0.0' + '.txt', 'r')
sigma = []
for line in input:
sigma.append(eval(line))
sigma = sigma[0]
input = open(path + '/0/colors0.0' + '.txt', 'r')
colors = []
for line in input:
colors.append(eval(line))
colors = colors[0]
S = tr.Tree.get_from_path(path + "/phyliptree(binary,all).phy", schema="newick")
G = tr.Tree.get_from_path(path + "/GeneTree(binary)_local.txt", schema="newick")
S = utiles.init_internal_labels(S, 'x', sigma, path)
G = utiles.init_internal_labels(G, 'u', sigma, path)
G = tree_operations.collapse_edges(G)
S = tree_operations.collapse_edges(S)
S_labels_table, G_labels_table,sigma = inits.init_taxon_to_label_table(S, G, sigma)
sigma, old_sigma = inits.update_sigma(S, G, 0, sigma, False, path, True, S_labels_table, G_labels_table)
colors, old_colors = inits.update_colors(S, colors, True)
i = 0
while i < number_of_random_changes:
G_internal_colors = tree_operations.color_tree(G, 'G', G_internal_colors, colors, sigma)
S_colors = tree_operations.color_tree(S, 'S', S_colors, colors, sigma)
number_of_nodes = tree_operations.number_of_leafs(G, 'G')
random_vertex_to_change_color = randome_leave_from_tree(G, number_of_nodes, True)
colors = change_color_of_vertex(random_vertex_to_change_color, colors, None, sigma, True)
i += 1
old_colors = return_color_to_taxon(S, colors)
save_data(old_sigma, old_colors, {}, noise, rand_num,compare,path+'/color')
def init_internal_labels(tree, char, old_sigma, path):
counter = 1
dic = ''
for nd in tree.postorder_node_iter():
nd.label = char + str(counter)
counter += 1
if nd.taxon:
dic = dic + nd.label + ' : ' + nd.taxon.label
if char == 'u':
dic = dic + ' (' + old_sigma[nd.taxon.label] + ') '
dic += '\n'
to_create = path + '/saved_data/'
os.makedirs(os.path.dirname(to_create), exist_ok=True)
tree_operations.collapse_edges(tree)
if char == 'u':
file = open(path + '/saved_data/G_keys.txt', 'w')
file.write(str(dic))
file.close()
if char == 'x':
file = open(path + '/saved_data/S_keys.txt', 'w')
file.write(str(dic))
file.close()
return tree
def RSAM_finder_multithread(parameters):
noise_in = ''
list_of_scores_for_rand_num = {}
max_score_p1_list = []
max_score_p1_and_p2_list = []
random_for_prec_curr = random_for_prec
for rand_num in range(0, random_for_prec_curr):
noise_level, noise_in, p1, p2 = parameters
path_change_in = path + '/' + noise_in
os.makedirs(os.path.dirname(path_change_in), exist_ok=True)
path_change_in = path_change_in + '/saved_data'
os.makedirs(os.path.dirname(path_change_in), exist_ok=True)
path_change_in = path + '/' + noise_in
S_dis_matrix = {}
nodes_table = {}
S_colors = {}
all_vertices = {}
new_G = nx.DiGraph()
nCr_lookup_table = {}
fact_lookup_table = {}
G = tr.Tree.get_from_path(path + "/GeneTree(binary," + geneExt +
")_local.txt",
schema="newick")
S = tr.Tree.get_from_path(path + "/phyliptree(binary," +
speciesTreespecification + ").phy",
schema="newick")
input = open(
path_change_in + '/' + str(noise_level) + '/sigma' +
str(noise_level) + '.' + str(rand_num) + '.txt', 'r')
sigma = []
for line in input:
sigma.append(eval(line))
sigma = sigma[0]
input = open(
path_change_in + '/' + str(noise_level) + '/colors' +
str(noise_level) + '.' + str(rand_num) + '.txt', 'r')
colors = []
for line in input:
colors.append(eval(line))
colors = colors[0]
G.prune_taxa_with_labels(
tree_operations.remove_unsigma_genes(G, sigma, True))
S = utiles.init_internal_labels(S, 'x', sigma, path)
G = utiles.init_internal_labels(G, 'u', sigma, path)
G = tree_operations.collapse_edges(G)
S = tree_operations.collapse_edges(S)
S_labels_table, G_labels_table, sigma = inits.init_taxon_to_label_table(
S, G, sigma)
sigma, old_sigma = inits.update_sigma(S, G, k, sigma, test,
path_change_in, exact_names,
S_labels_table, G_labels_table)
G.prune_taxa_with_labels(
tree_operations.remove_unsigma_genes(G, sigma, False))
colors, old_colors = inits.update_colors(S, colors, exact_names)
S_dis_matrix = inits.init_distance_S(S_dis_matrix, k, test, path,
speciesTreespecification)
nodes_table = inits.init_nodes_table(S, G, nodes_table)
H, H_number_of_nodes, nodes_table = hypergraph.build_hyper_garph(
S, G, test, k, nodes_table, D_cost, S_cost, HT_cost,
path_change_in, alpha, sigma, save_data)
H, max_prob = hypergraph.assign_probabilities(S, G, H, gamma)
if H is None:
list_of_scores_for_rand_num.update({rand_num: {}})
else:
## PROBABILITIES, COLORS, PATTERN ##
S_colors = tree_operations.color_tree(S, 'S', S_colors, colors,
sigma)
interesting_vertices_p1, nCr_lookup_table, fact_lookup_table = find_Pattern(
H, S, S_dis_matrix, nCr_lookup_table, fact_lookup_table, p1,
S_colors)
interesting_vertices_p2, nCr_lookup_table, fact_lookup_table = find_Pattern(
H, S, S_dis_matrix, nCr_lookup_table, fact_lookup_table, p2,
S_colors)
max_S_d_of_HT = tree_operations.find_max_d_of_HT(
S_dis_matrix, interesting_vertices_p1, p1)
new_G = tree_operations.weight_G_based_on_same_color_HT(
G, new_G, interesting_vertices_p1, interesting_vertices_p2,
max_S_d_of_HT, p1, p2, False)
new_G = tree_operations.number_of_edges_in_subtree(new_G)
new_G = tree_operations.normlize_weights(new_G, k, p1, 'p1')
new_G = tree_operations.normlize_weights(new_G, k, p2, 'p2')
if p2[0] is None:
max_score_p1_list = tree_operations.find_max_scores(
new_G, number_of_planted_vertices, 'p1', p1[3])
else:
max_score_p1_and_p2_list = tree_operations.find_max_scores(
new_G, number_of_planted_vertices, 'p2', p1[3])
marked_nodes, all_vertices = pattern_identify.find_signi_distance(
new_G, all_vertices, p1, p2, max_score_p1_list,
max_score_p1_and_p2_list, False)
list_of_scores_for_rand_num.update({rand_num: all_vertices})
return (utiles.average_of_list(list_of_scores_for_rand_num,
random_for_prec_curr), noise_in)
schema="newick")
print(" Reading file " + path_curr + "/sigma.txt'...")
input = open(path_curr + '/0/sigma0.0.txt', 'r')
sigma = []
for line in input:
sigma.append(eval(line))
sigma = sigma[0]
print(" Finished reading file " + path_curr + "0/sigma0.0.txt'")
G.prune_taxa_with_labels(
tree_operations.remove_unsigma_genes(G, sigma, True))
S = utiles.init_internal_labels(S, 'x', sigma, path_curr)
G = utiles.init_internal_labels(G, 'u', sigma, path_curr)
G = tree_operations.collapse_edges(G)
S = tree_operations.collapse_edges(S)
S_labels_table, G_labels_table, sigma = inits.init_taxon_to_label_table(
S, G, sigma)
sigma, old_sigma = inits.update_sigma(S, G, k, sigma, False, path_curr,
True, S_labels_table,
G_labels_table)
G.prune_taxa_with_labels(
tree_operations.remove_unsigma_genes(G, sigma, False))
S_dis_matrix = inits.init_distance_S({}, k, False, path_curr,
speciesTreespecification)
nodes_table = inits.init_nodes_table(S, G, {})
start = datetime.now()
effi.build_hyper_garph(S, G, False, k, nodes_table, D_cost, S_cost,
def main(S,G,number_of_leaves,path,k,running_time,number_of_planted_vertices):
global random_for_precentage,all_edges,TH_edges_in_subtree,compare_subtrees,TH_pattern_in_subtree,TH_compare_subtrees,both,TH_both,accur
starting_time = datetime.now()
new_G = nx.DiGraph()
noise = 0
number_of_HT_under_planted = 10
S = Tree()
sigma = {}
nCr_lookup_table = {}
fact_lookup_table = {}
colors = {}
S_dis_matrix = {}
names = []
S_colors = {}
G_internal_colors = {}
sol = {}
for i in range(0, number_of_leaves):
names.append(sym + str(i))
S.populate(number_of_leaves, names_library=names)
count_nodes_and_update_internal_names(S)
#S = random_again(S, number_of_leaves / 4)
colors = random_colors(S, colors)
G = S.copy("newick")
for leaf in G.iter_leaves():
if leaf.name[:6] == 'Specie':
leaf.name = "Gene" + leaf.name[6:]
else:
leaf.name = "GeneI" + leaf.name[8:]
print_tree(G,'G',path)
print_tree(S,'S',path)
sigma = create_sigme(number_of_leaves, sigma)
utils.newick2edgelist.main(path)
save_edgelist(S_dis_matrix,path)
S = tr.Tree.get_from_path(path + "/phyliptree(binary,all).phy", schema="newick")
G = tr.Tree.get_from_path(path + "/GeneTree(binary)_local.txt", schema="newick")
S = utiles.init_internal_labels(S, 'x', sigma, path)
G = utiles.init_internal_labels(G, 'u', sigma, path)
G = tree_operations.collapse_edges(G)
S = tree_operations.collapse_edges(S)
S_labels_table, G_labels_table,sigma = inits.init_taxon_to_label_table(S, G, sigma)
sigma, old_sigma = inits.update_sigma(S, G, 0, sigma, False, path, True, S_labels_table, G_labels_table)
colors, old_colors = inits.update_colors(S, colors, True)
max_dis = tree_operations.max_dis(S_dis_matrix)
flag = True
j = 0
all_random_sources_red_to_red = []
all_random_sources_black_to_black = []
all_random_nutral = []
all_random_sources = (all_random_sources_red_to_red, all_random_sources_black_to_black, all_random_nutral)
new_G = tree_operations.weight_G_based_on_same_color_HT(G, new_G, [],
[],[],[], 0, False,
'HT', False, k)
new_G = tree_operations.number_of_edges_in_subtree(new_G)
S_colors = tree_operations.color_tree(S, 'S', S_colors, colors, sigma)
G_internal_colors = tree_operations.color_tree(G, 'G', G_internal_colors, colors, sigma)
if not on_lab:
draw.draw_S_and_G(S, G, old_sigma, colors, sigma, path, None, '_rand_before')
if not running_time:
while j < number_of_planted_vertices:
print(
' ***** %sth vertex ******' % str(
j))
sol[j] = {}
nCr_lookup_table, fact_lookup_table, (
sol[j]['Marked'], sol[j]['list_of_couples']), colors = choose_planted_vertex(S_dis_matrix,new_G, S, G,
G_internal_colors,
TH_edges_in_subtree,
compare_subtrees,
TH_compare_subtrees,
sigma,
k,
both,
TH_both, j, sol, accur,
nCr_lookup_table,
fact_lookup_table,
all_random_sources,
colors,
S_colors, max_dis)
if sol[j]['Marked'] == False:
flag = flag and sol[j]['Marked']
else:
sigma, old_sigma, y = change_sigma(sigma, old_sigma, S, G, sol[j]['list_of_couples'],
number_of_HT_under_planted,S_labels_table,G_labels_table)
S_colors = tree_operations.color_tree(S, 'S', S_colors, colors, sigma)
G_internal_colors = tree_operations.color_tree(G, 'G', G_internal_colors, colors, sigma)
j += 1
if not flag:
if not on_lab:
draw.draw_S_and_G(S, G, old_sigma, colors, sigma, path, None, '_rand')
old_colors = return_color_to_taxon(S, colors)
save_data(old_sigma, old_colors, sol, noise, 0, compare,path)
if not running_time:
quit()
print('Planted vertices:%s' % str(sol))
if not on_lab:
draw.draw_S_and_G(S, G, old_sigma, colors, sigma, path, sol, '_rand' + str(noise) + '.' + str(0))
old_colors = return_color_to_taxon(S, colors)
save_data(old_sigma, old_colors, sol, noise, 0,compare,path)
return_planted_nodes_new_name(sol,G,path)
p = Pool(15)
parameters = [(noise_level[i],number_of_HT_under_planted,G_internal_colors,S_colors,nCr_lookup_table,fact_lookup_table,number_of_leaves) for i in range(0,len(noise_level))]
p.map(create_tree_for_HT_and_colors_noise, parameters)
p.map(create_tree_for_color_noise, parameters)
p.map(create_tree_for_HT_noise, parameters)
else:
save_data(old_sigma, old_colors, sol, noise, 0, compare, path)
print('Running time: %s' % str(datetime.now() - starting_time))
def create_tree_for_HT_and_colors_noise(parameters):
print('Creating noise in HT and colors')
noise = parameters[0]
number_of_HT_under_planted = parameters[1]
G_internal_colors = parameters[2]
S_colors = parameters[3]
nCr_lookup_table = parameters[4]
fact_lookup_table = parameters[5]
number_of_leaves = parameters[6]
number_of_random_changes = number_of_leaves * (noise / 100)
random_for_prec = random_for_precentage
for rand_num in range(0, random_for_prec):
input = open(path + '/0/sigma0.0' + '.txt', 'r')
sigma = []
for line in input:
sigma.append(eval(line))
sigma = sigma[0]
input = open(path + '/0/colors0.0' + '.txt', 'r')
colors = []
for line in input:
colors.append(eval(line))
colors = colors[0]
S = tr.Tree.get_from_path(path + "/phyliptree(binary,all).phy", schema="newick")
G = tr.Tree.get_from_path(path + "/GeneTree(binary)_local.txt", schema="newick")
S = utiles.init_internal_labels(S, 'x', sigma, path)
G = utiles.init_internal_labels(G, 'u', sigma, path)
G = tree_operations.collapse_edges(G)
S = tree_operations.collapse_edges(S)
S_labels_table, G_labels_table,sigma = inits.init_taxon_to_label_table(S, G, sigma)
sigma, old_sigma = inits.update_sigma(S, G, 0, sigma, False, path, True, S_labels_table, G_labels_table)
colors, old_colors = inits.update_colors(S, colors, True)
i = 0
all_random_sources_red_to_red = []
all_random_sources_black_to_black = []
all_random_nutral = []
while i < number_of_random_changes:
G_internal_colors = tree_operations.color_tree(G, 'G', G_internal_colors, colors, sigma)
S_colors = tree_operations.color_tree(S, 'S', S_colors, colors, sigma)
number_of_nodes = tree_operations.number_of_leafs(G, 'G')
random_source = random_vertex_in_tree(number_of_nodes, G)
random_target = random_vertex_in_tree(number_of_nodes, G)
random_vertex_to_change_color = randome_leave_from_tree(G, number_of_nodes, True)
sigma, old_sigma, changed = change_sigma(sigma, old_sigma, S, G,
[(random_source.label, random_target.label)],
number_of_HT_under_planted,S_labels_table,G_labels_table)
colors = change_color_of_vertex(random_vertex_to_change_color, colors, None, sigma, True)
nCr_lookup_table, fact_lookup_table, enriched = check_if_enriched(S,G,random_source, random_target,
nCr_lookup_table, fact_lookup_table,
accur, G_internal_colors,S_colors)
if enriched == 'red-to-red':
all_random_sources_red_to_red.append(random_source)
elif enriched == 'black_to_balck':
all_random_sources_black_to_black.append(random_source)
else:
all_random_nutral.append(random_source)
i += changed
old_colors = return_color_to_taxon(S, colors)
save_data(old_sigma, old_colors, {}, noise, rand_num,compare,path+"/colors_and_HT")