def check_if_enriched(S,G,source, target,nCr_lookup_table,fact_lookup_table, accur,G_internal_colors,S_colors):
reds_under_source = G_internal_colors[source.label][0]
blacks_under_source = G_internal_colors[source.label][1]
reds_under_target = G_internal_colors[target.label][0]
blacks_under_target = G_internal_colors[target.label][1]
total_source = reds_under_source + blacks_under_source
total_target = reds_under_target + blacks_under_target
total_red = S_colors[S.seed_node.label][0]
total_black = S_colors[S.seed_node.label][1]
num_of_leafs = tree_operations.number_of_leafs(S, 'S')
Pr_red = total_red / num_of_leafs
Pr_black = total_black / num_of_leafs
#print('source: %s, target: %s, reds_under_source: %s, blacks_under_source: %s, reds_under_target: %s, blacks_under_target: %s' % (str(source),str(target),str(reds_under_source), str(blacks_under_source),str(reds_under_target),str(blacks_under_target)))
p_value_source_red, nCr_lookup_table, fact_lookup_table = utiles.p_value_calculation(reds_under_source, total_source,
nCr_lookup_table,
fact_lookup_table, accur,
Pr_red,
Pr_black, source.label)
p_value_source_black, nCr_lookup_table, fact_lookup_table = utiles.p_value_calculation(blacks_under_source,
total_source,
nCr_lookup_table,
fact_lookup_table,
accur, Pr_black,
Pr_red,
source.label)
p_value_target_red, nCr_lookup_table, fact_lookup_table = utiles.p_value_calculation(reds_under_target,
total_target,
nCr_lookup_table,
fact_lookup_table, accur,
Pr_red,
Pr_black, target.label)
p_value_target_black, nCr_lookup_table, fact_lookup_table = utiles.p_value_calculation(blacks_under_target,
total_target,
nCr_lookup_table,
fact_lookup_table, accur,
Pr_black,
Pr_red,
target.label)
#print(' p_value_source_red: %s\n p_value_target_red:%s' % (
#str(p_value_source_red), str(p_value_target_red)))
#print(' p_value_source_black: %s\n p_value_target_black:%s' % (
#str(p_value_source_black), str(p_value_target_black)))
if p_value_source_red < p and p_value_target_red < p:
return nCr_lookup_table,fact_lookup_table,'red-to-red'
if p_value_source_black < p and p_value_target_black < p:
return nCr_lookup_table,fact_lookup_table,'black-to-black'
else: return nCr_lookup_table,fact_lookup_table,'nothing-to-nothing'
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 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,vertex_number,sol,accur,nCr_lookup_table,fact_lookup_table,all_random_sources,colors,S_colors,max_dis):
total_red = S_colors[S.seed_node.label][0]
total_black = S_colors[S.seed_node.label][1]
num_of_leafs = tree_operations.number_of_leafs(S,'S')
Pr_red = total_red / num_of_leafs
Pr_black = total_black / num_of_leafs
for u in list(reversed(list(nx.topological_sort(new_G)))):
old_colors = colors.copy()
old_internal_G_colors = G_internal_colors.copy()
old_S = S
old_S_colors = S_colors.copy()
##this is the random vertex
outgoing_edges = new_G.out_edges([u], data=True)
outgoing_edges = [e for e in outgoing_edges]
u = new_G.nodes(data=True)[u]
if len(outgoing_edges) == 2:
if compare_subtrees:
if u['edges_in_subtree'] > TH_edges_in_subtree and not check_if_vertex_was_chosen(vertex_number,sol,u['label']):
print('\n***\nVertex ' + str(u) + ' was chosen to be marked.')
if not both:
number_of_HT = number_of_HT_needed(G,u, all_random_sources, TH_compare_subtrees, 'red')
nCr_lookup_table, fact_lookup_table,ans = create_good_HT(G, S, nCr_lookup_table,fact_lookup_table,number_of_HT, u, u, Pr_red, Pr_black, 'red',
max_dis,S_dis_matrix,new_G,G_internal_colors)
if ans[0] == u['label']:
return nCr_lookup_table,fact_lookup_table,ans,colors
else:
number_of_HT = number_of_HT_needed(G, u, all_random_sources, TH_compare_subtrees, 'black')
nCr_lookup_table, fact_lookup_table, ans = create_good_HT(G, S, nCr_lookup_table,
fact_lookup_table, number_of_HT,
u, u, Pr_red, Pr_black, 'black',
max_dis, S_dis_matrix, new_G,
G_internal_colors)
colors = old_colors
G_internal_colors = old_internal_G_colors
S = old_S
S_colors = old_S_colors
print('No vertex could be planted.')
return nCr_lookup_table,fact_lookup_table,(False,False),colors
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")
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(sigma, True, 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, True)
new_G = nx.DiGraph()
new_G = tree_operations.copy_G(G,new_G)
if draw_S:
draw.draw_tree(S, 'S', old_sigma, colors, sigma,path,color,x_axis,y_axis,lables_flag)
quit()
if 'D' in p1[0]:
draw_new_doup(marked_nodes, colors, sigma, new_G, G, old_sigma, 0, 0,
path, True, False, ext, pattern_name,
big_size, ['D'], True, 1,S_labels_table)
else:
draw_new_HT(marked_nodes, colors, sigma, new_G, G, old_sigma, 0, 0,
path, True, False, ext, pattern_name,
big_size, ['HT'], True, 1,S_labels_table)
print('Number of leafs of S: '+str(tree_operations.number_of_leafs(S,'S')))
print('Number of leafs of G: '+str(tree_operations.number_of_leafs(G,'G')))