def order_from_graph(graph):
result = []
marques = {}
for l in script_tree.getLeavesNames(tree):
marques[l] = 0
while len(result) < len(graph.keys()) - len(script_tree.getLeavesNames(tree)):
keys = graph.keys()
i = 0
while marques.has_key(keys[i]):
i = i + 1
current = keys[i]
suivant = True
while suivant:
suivant = False
for v in graph[current]:
if not marques.has_key(v):
suivant = True
current = v
result.append(current)
marques[current] = 0
result.reverse()
return result
while len(graph[current]) > 0:
current = graph[current][0]
result.append(current)
return result
def order_from_graph(graph):
result = []
marques = {}
for l in script_tree.getLeavesNames(tree):
marques[l] = 0
while len(result) < len(graph.keys()) - len(script_tree.getLeavesNames(tree)):
keys = graph.keys()
i = 0
while marques.has_key(keys[i]):
i = i + 1
current = keys[i]
suivant = True
while suivant:
suivant = False
for v in graph[current]:
if not marques.has_key(v):
suivant = True
current = v
result.append(current)
marques[current] = 0
result.reverse()
return result
while len(graph[current]) > 0:
current = graph[current][0]
result.append(current)
return result
def order_from_graph(graph):
result = []
leaves = script_tree.getLeavesNames(tree)
number_neighbors = {}
visited_neigbors = {}
keys = graph.keys()
# print "construction of the inverse graph",len(keys),len(keys)-len(leaves)
for k in keys:
number_neighbors[k] = []
visited_neigbors[k] = []
for k in keys:
for v in graph[k]:
# if k in number_neighbors[v]:
# print "error",k,v,graph[k]
number_neighbors[v].append(k)
# print "find roots"
queue = []
for k in keys:
if len(number_neighbors[k]) == 0:
queue.append(k)
# print "find order",len(queue)
while len(queue) > 0:
current = queue[0]
del queue[0]
result.append(current)
for v in graph[current]:
if not v in leaves:
visited_neigbors[v].append(current)
if len(visited_neigbors[v]) == len(number_neighbors[v]):
queue.append(v)
# i = 0
# while i < len(keys) and (not keys[i] in leaves) and len(number_neighbors[keys[i]]) != visited_neigbors[keys[i]]:
# i = i + 1
# if i < len(keys):
# current = keys[i]
# visited = []
# while not current in visited:
# print current,
# visited.append(current)
# for v in number_neighbors[current]:
# if not v in visited_neigbors[current]:
# suiv = v
# current = suiv
# print current
# print len(result),len(marked)
return result
species = mots[1].split("_")[0].title() + "_" + mots[1].split(
"_")[1]
genes[mots[2]] = [
species, mots[3],
int(mots[4]),
int(mots[5]), mots[6]
]
l = l + 1
adjacence_file = open(analysisDir + "/deco_adjacences_" + name, "w")
gene_file = open(analysisDir + "/deco_genes_" + name, "w")
restricted_genes = []
for line in tree_file:
tree = script_tree.readTree(line)
leaves = script_tree.getLeavesNames(tree)
for l in leaves:
restricted_genes.append(l)
print len(tree_file), len(restricted_genes)
#print restricted_genes
def compare(x, y):
#print x,y
if genes[x][0] != genes[y][0]:
return cmp(genes[x][0], genes[y][0])
elif genes[x][1] != genes[y][1]:
return cmp(genes[x][1], genes[y][1])
else:
order = []
nodes = script_tree.getNodes(tree)
root = script_tree.getRoot(tree)
for n in nodes:
if not script_tree.isLeaf(tree,n):
order.append(n)
#print order
order.sort(lambda x,y: cmp(script_tree.distanceFrom(tree,x,root),script_tree.distanceFrom(tree,y,root)))
for i in range(len(order)):
order[i] = script_tree.getBootstrap(tree,order[i])
return order
# useful variables
nodes1 = script_tree.getNodes(tree1)
leaves1 = script_tree.getLeavesNames(tree1)
root1 = script_tree.getRoot(tree1)
internal_nodes1 = []
nodes2 = script_tree.getNodes(tree2)
leaves2 = script_tree.getLeavesNames(tree2)
root2 = script_tree.getRoot(tree2)
internal_nodes2 = []
order_input1 = order_from_tree(tree1)
order_input2 = order_from_tree(tree2)
#value_input = value(order_input)
import sys, script_tree, random, time, math, string
MINIMUM_SUPPORT_WITHIN_A_FAMILY = 0.05
MINIMUM_FAMILY_SIZE = 5
#MAXIMUM_DIFFERENCE_WITH_PROFILE = 6000
OUTPUT_FILE_REC = "constraints_from_recs"
OUTPUT_FILE_TRF = "constraints_from_transfers"
parameters = sys.argv[1:]
species_tree = script_tree.readTree(open(parameters[0], "r").readline())
extant_species = script_tree.getLeavesNames(species_tree)
gene_tree_file = parameters[1]
gene_trees = []
for gt in open(gene_tree_file, "r").readlines():
gene_trees.append(gt.strip())
nodes = script_tree.getNodes(species_tree)
for n in nodes:
script_tree.setLength(species_tree, n, 1.0)
def distance_from(x, y):
nodes = script_tree.getNodes(species_tree)
for n in nodes:
if script_tree.isLeaf(species_tree, n):
name = script_tree.getName(species_tree, n)
else:
name = script_tree.getBootstrap(species_tree, n)
if name == x:
A = n
if name == y:
import sys,script_tree,random,time,math,string
MINIMUM_SUPPORT_WITHIN_A_FAMILY = 0.05
MINIMUM_FAMILY_SIZE = 5
#MAXIMUM_DIFFERENCE_WITH_PROFILE = 6000
OUTPUT_FILE_REC = "constraints_from_recs"
OUTPUT_FILE_TRF = "constraints_from_transfers"
parameters = sys.argv[1:]
species_tree = script_tree.readTree(open(parameters[0],"r").readline())
extant_species = script_tree.getLeavesNames(species_tree)
gene_tree_file = parameters[1]
gene_trees = []
for gt in open(gene_tree_file,"r").readlines():
gene_trees.append(gt.strip())
nodes = script_tree.getNodes(species_tree)
for n in nodes:
script_tree.setLength(species_tree,n,1.0)
def distance_from(x,y):
nodes = script_tree.getNodes(species_tree)
for n in nodes:
if script_tree.isLeaf(species_tree,n):
name = script_tree.getName(species_tree,n)
else:
name = script_tree.getBootstrap(species_tree,n)
if name == x:
A = n
genes = {}
l = 0
while l < len(fichier_ensembl):
if fichier_ensembl[l][:3] == "SEQ":
mots = fichier_ensembl[l].split()
species = mots[1].split("_")[0].title()+"_"+mots[1].split("_")[1]
genes[mots[2]] = [species,mots[3],int(mots[4]),int(mots[5]),mots[6]]
l = l + 1
adjacence_file = open(analysisDir+"/deco_adjacences_"+name,"w")
gene_file = open(analysisDir+"/deco_genes_"+name,"w")
restricted_genes = []
for line in tree_file:
tree = script_tree.readTree(line)
leaves = script_tree.getLeavesNames(tree)
for l in leaves:
restricted_genes.append(l)
print len(tree_file),len(restricted_genes)
#print restricted_genes
def compare(x,y):
#print x,y
if genes[x][0] != genes[y][0]:
return cmp(genes[x][0],genes[y][0])
elif genes[x][1] != genes[y][1]:
return cmp(genes[x][1],genes[y][1])
else:
return cmp(genes[x][2],genes[y][2])
