def init_leafs(G, H, k, H_number_of_nodes, sigma, nodes_table):
for leaf in G.leaf_nodes():
if not tree_operations.isolated(leaf):
H.add_node(H_number_of_nodes,
s=leaf.label,
t=sigma[leaf.label],
l=list())
big_node = H_number_of_nodes
H_number_of_nodes += 1
i = 0
for i in range(0, k):
if i == 0:
cost = 0
else:
cost = math.inf
new_item = {
's': leaf.label,
't': sigma[leaf.label],
'cost': cost,
'event': "leaf",
'list_place': i
}
H.nodes[big_node]['l'].insert(i, new_item)
nodes_table[sigma[leaf.label]][leaf.label] = big_node
return H, H_number_of_nodes, nodes_table
def init_leafs_efficient(G, H, k, H_number_of_nodes, sigma, nodes_table):
for leaf in G.leaf_nodes():
if not tree_operations.isolated(leaf):
target = ''
if leaf.label in sigma:
target = sigma[leaf.label]
else:
for species in sigma:
if leaf.label.find(species) != -1 or species.find(
leaf.label) != -1:
target = sigma[species]
H.add_node(H_number_of_nodes, s=leaf.label, t=target, l=list())
big_node = H_number_of_nodes
H_number_of_nodes += 1
for i in range(0, k):
if i == 0:
cost_no_losses = 0
cost_with_losses = 0
else:
cost_no_losses = math.inf
cost_with_losses = math.inf
new_item = {
's': leaf.label,
't': target,
'cost_without_losses': cost_no_losses,
'cost_with_losses': cost_with_losses,
'event': "leaf",
'list_place': i
}
H.nodes[big_node]['l'].insert(i, new_item)
nodes_table[target][leaf.label] = big_node
return H, H_number_of_nodes, nodes_table
def main(path, create_sigma, res):
if create_sigma:
with open(path + '/FASTA.txt', 'r') as fp:
res = ''
for line in fp:
if line[0] == '>':
start = line.find('[') + 1
end = line.find(']')
while start < end:
if line[start] == ' ':
res += ' '
else:
res += line[start]
start += 1
res += '\n'
file = open(path + "/taxa_names.txt", 'w')
file.write(str(res))
file.close()
else:
try:
S = tr.Tree.get_from_path(path + "/S.txt", schema="newick")
except:
res['error'] += "\nSpecies tree '/data/S.txt' was not found.\n" \
"In order to create it, please go to https://www.ncbi.nlm.nih.gov/Taxonomy/CommonTree/wwwcmt.cgi\n" \
"and follow the instructions:\n" \
" -> Choose File -> select the file 'NCBI_tax_ID.txt' from the folder data/your_data \n" \
"-> Add from file: -> select the subtree you want (e.i. Proteobacteria) and press Choose ->\n" \
"Expand All -> Save As phylip tree.\n " \
"Finally you need to rename the file 'S.txt' and move it to the data/your_data/ directory."
return
res = ''
for leaf in S.leaf_nodes():
if not tree_operations.isolated(leaf):
res += leaf.taxon.label + ','
file = open(path + '' + "/taxa_names.txt", 'w')
file.write(str(res))
file.close()
def main (path,create_form_fasta,res_map):
if create_form_fasta:
res = '{ '
try:
S_text = open(path + '/S.txt', 'r').read()
except:
res_map['error'] += "\nSpecies tree '/data/S.txt' was not found.\n" \
"In order to create it, please go to https://www.ncbi.nlm.nih.gov/Taxonomy/CommonTree/wwwcmt.cgi\n" \
"and follow the instructions:\n" \
" -> Choose File -> select the file 'NCBI_tax_ID.txt' from the folder data/your_data \n" \
"-> Add from file: -> select the subtree you want (e.i. Proteobacteria) and press Choose ->\n" \
"Expand All -> Save As phylip tree.\n " \
"Finally you need to rename the file 'S.txt' and move it to the data/your_data/ directory."
return
input = open(path+"/old_new_names.txt", 'r')
old_new_names = []
for line in input:
old_new_names.append(eval(line))
old_new_names = old_new_names[0]
S_text = S_text.replace(' ','').replace('\n','')
with open(path+'/FASTA.txt','r') as fp:
for line in fp:
if line[0] == '>':
start = 1
end = line.find(' ')
gene = ''
while start < end :
gene += line[start]
start += 1
gene = gene.replace("_"," ")
start = line.find('[')+1
end = line.find(']')
specie = ''
while start < end :
specie += line[start]
start += 1
if S_text.find(old_new_names[specie].replace(' ','')) != -1:
res += "'"+gene+"' : '"+old_new_names[specie].replace(' ','')+"',"
res += ' }'
file = open(path + "/sigma.txt", 'w')
file.write(str(res))
file.close()
else:
try:
G = tr.Tree.get_from_path(path + "/G.txt", schema="newick")
except:
res_map['error'] += "\nGene tree '/data/G.txt' was not found.\n" \
"In order to create it, go to https://www.ebi.ac.uk/Tools/msa/clustalo/\n" \
"and follow the instructions:\n" \
"Choose File -> select 'FASTA.txt' from data/your_data/ directory\n" \
"-> select OUTPUT FORMAT: -> wait until job is done..\n" \
""
return
res = '{ '
for leaf in G.leaf_nodes():
if not tree_operations.isolated(leaf):
res += " '"+leaf.taxon.label+"' "+':'+" '"+leaf.taxon.label[0:1]+"'"+','
res += ' }'
file = open(path + '' + "/sigma.txt", 'w')
file.write(str(res))
file.close()
def draw_S_and_G(S, G, old_sigma, colors, sigma, path, sol, ext, to_color):
plt.clf()
S_to_draw = nx.DiGraph()
G_to_draw = nx.DiGraph()
index = 1
nodes_color_S = []
nodes_color_G = []
##FOR S
for u in S.postorder_node_iter():
S_to_draw.add_node(index, label=u.label)
if not tree_operations.is_a_leaf(u):
child = u.child_nodes()
i = 0
while i < len(child):
if len(child) >= i + 1:
S_to_draw.add_edge(
index,
list(S.postorder_node_iter()).index(child[i]) + 1)
i = i + 1
index += 1
labels_S = nx.get_node_attributes(S_to_draw, 'label')
for k, l in labels_S.items():
for x in S.postorder_node_iter():
if x.taxon != None:
if x.label == l:
l = l + "\n (" + str(x.taxon) + ")"
labels_S.update({k: l})
for u in S.postorder_node_iter():
if u.label != None and u.label in colors and to_color:
if colors[u.label] == 'red':
nodes_color_S.append('red')
elif colors[u.label] == 'black':
nodes_color_S.append('grey')
else:
nodes_color_S.append('pink')
else:
nodes_color_S.append('white')
## FOR G
index = 1
for u in G.postorder_node_iter():
G_to_draw.add_node(index, label=u.label)
if not tree_operations.is_a_leaf(u):
child = u.child_nodes()
i = 0
while i < len(child):
if len(child) >= i + 1:
G_to_draw.add_edge(
index,
list(G.postorder_node_iter()).index(child[i]) + 1)
i = i + 1
index += 1
labels_G = nx.get_node_attributes(G_to_draw, 'label')
for k, l in labels_G.items():
for x in G.postorder_node_iter():
if x.taxon != None:
if x.label == l and (x.taxon.label in old_sigma):
l = l + "\n (" + str(x.taxon) + ")"
l = l + '\n' + str(old_sigma[x.taxon.label])
labels_G.update({k: l})
for u in G.postorder_node_iter():
degel = False
if sol != None:
for int, temp_sol in sol.items():
for p in range(0, len(temp_sol['list_of_couples'])):
if (u.label == temp_sol['Marked']
or u.label == temp_sol['list_of_couples'][p][0]
or u.label == temp_sol['list_of_couples'][p][1]
) and not degel:
nodes_color_G.append('blue')
degel = True
if not degel and tree_operations.is_a_leaf(
u) and u.label in sigma and not tree_operations.isolated(
u) and sigma[u.label] in colors and to_color:
if colors[sigma[u.label]] == 'red':
nodes_color_G.append('red')
elif colors[sigma[u.label]] == 'black':
nodes_color_G.append('grey')
else:
nodes_color_G.append('pink')
elif not degel:
nodes_color_G.append('white')
postree_S = graphviz_layout(S_to_draw, prog='dot')
postree_G = graphviz_layout(G_to_draw, prog='dot')
for k, v in postree_G.items():
# Shift the x values of every node by 10 to the right
lst = list(v)
lst[0] = lst[0] + 100
postree_G.update({k: tuple(lst)})
fig, axes = plt.subplots(1, 2, figsize=(90, 50))
ax = axes.flatten()
ax[0].set_title('Species tree',
fontsize=50,
rotation='vertical',
x=-0.1,
y=0.5)
ax[1].set_title('Gene tree',
fontsize=50,
rotation='vertical',
x=-0.1,
y=0.5)
nx.draw(S_to_draw,
postree_S,
arrows=True,
node_color=nodes_color_S,
ax=ax[0])
nx.draw(G_to_draw,
postree_G,
arrows=True,
node_color=nodes_color_G,
ax=ax[1])
t1 = nx.draw_networkx_labels(S_to_draw,
postree_S,
labels_S,
font_size=7,
ax=ax[0])
t2 = nx.draw_networkx_labels(G_to_draw,
postree_G,
labels_G,
font_size=7,
ax=ax[1])
for _, t in t1.items():
t.set_rotation('vertical')
for _, t in t2.items():
t.set_rotation('vertical')
nx.draw_networkx_edges(S_to_draw, postree_S, ax=ax[0])
nx.draw_networkx_edges(G_to_draw, postree_G, ax=ax[1])
to_create = path + '/figures/'
os.makedirs(os.path.dirname(to_create), exist_ok=True)
plt.savefig(path + '/figures/S+G' + ext + '.png')
def draw_tree(tree, name, old_sigma, colors, sigma, path, color_tree, x_axis,
y_axis, label_flag):
tree_to_draw = nx.DiGraph()
index = 1
nodes_color = []
for u in tree.postorder_node_iter():
tree_to_draw.add_node(index, label=u.label)
if not tree_operations.is_a_leaf(u):
child = u.child_nodes()
i = 0
while i < len(child):
if len(child) >= i + 1:
tree_to_draw.add_edge(
index,
list(tree.postorder_node_iter()).index(child[i]) + 1)
i = i + 1
index += 1
labels = nx.get_node_attributes(tree_to_draw, 'label')
for k, l in labels.items():
for x in tree.postorder_node_iter():
if x.taxon != None:
if x.label == l:
l = l + "\n (" + str(x.taxon) + ")"
if name == 'G':
l = l + '\n' + str(old_sigma[x.taxon.label])
labels.update({k: l})
else:
labels.update({k: l})
if name == 'S':
for u in tree.postorder_node_iter():
if color_tree:
if u.label != None and u.label in colors:
if colors[u.label] == 'red':
nodes_color.append('red')
elif colors[u.label] == 'black':
nodes_color.append('grey')
else:
nodes_color.append('pink')
else:
nodes_color.append('white')
else:
nodes_color.append('white')
else:
for u in tree.postorder_node_iter():
if tree_operations.is_a_leaf(u) and not tree_operations.isolated(
u) and sigma[u.label] in colors:
if colors[sigma[u.label]] == 'red':
nodes_color.append('red')
else:
nodes_color.append('grey')
else:
nodes_color.append('white')
postree = graphviz_layout(tree_to_draw, prog='dot')
plt.figure(12, figsize=(x_axis, y_axis)) # size of fig
nx.draw(tree_to_draw, postree, arrows=True, node_color=nodes_color)
if label_flag:
text = nx.draw_networkx_labels(tree_to_draw,
postree,
labels,
font_size=7)
for _, t in text.items():
t.set_rotation('vertical')
nx.draw_networkx_edges(tree_to_draw, postree)
plt.savefig(path + name + '.png')
print('Drawing' + name)