def return_upgma(seq_list, names_list, df, cfd_dict=None):
'''input: a list of names and a list of sequences, calibrated
output: an upgma instance.
'''
if df == Metric.CRISTA:
base = list(map(lambda sg: sg[3:-6], seq_list)) # seq_list
seq_list = list(
map(lambda t: Metric.pos_in_metric_general(t, df, base, cfd_dict),
seq_list))
df = Metric.find_dist_np
if df == Metric.cfd_funct: # to uncomment
#base = random.sample(seq_list, int(math.log(len(seq_list))))
#base = random.sample(seq_list, 80)
#base = random.sample(seq_list, int(len(seq_list)**0.9))
#base = seq_list
#seq_list = list(map(lambda t: Metric.pos_in_metric_general(t,df,base, cfd_dict), seq_list))
seq_list = list(
map(lambda t: Metric.pos_in_metric_cfd_np(t, cfd_dict),
seq_list)) #to uncomment
# df = Metric.find_dist_t #if prev line is not is use #to uncomment
df = Metric.find_dist_np
matrix = UPGMA.make_initiale_matrix(df, seq_list)
m2 = UPGMA.make_distance_matrix(
names_list,
matrix) #shuold be m2 = UPGMA.make_distance_matrix(names_list, matrix)
upgma1 = UPGMA.make_UPGMA(m2)
return upgma1
def return_upgma(seq_list, names_list, df): '''input: a list of names and a list of sequences, calibrated output: an upgma instance. ''' matrix = UPGMA.make_initiale_matrix(df,seq_list) m2 = UPGMA.make_distance_matrix(names_list, matrix) #m3 = m2.__repr__() upgma1 = UPGMA.make_UPGMA(m2) return upgma1
def test_compre_to_shirans():
Nuc = ["A", "G", "C", "T"]
seq_lst = [ ''.join(random.choice(Nuc) for _ in range(20)) for i in range(200)]
for s1 in seq_lst:
for s2 in seq_lst:
if cfd_funct(s1, s2) != UPGMA.cfd_func(s1, s2):
print("different: ", s1, s2)
print("scores :",cfd_funct(s1, s2), UPGMA.cfd_func(s1, s2))
def Load_File_Internal(self, tfile):
"""Load file with error checking"""
self.aligned_file = tfile.replace(
'/', os.sep) #the file to find the protein distance matrix
af = self.aligned_file
index, slash = af.rfind('.'), af.rfind(os.sep)
if (index == -1 or index < slash):
index = len(af)
self.distance_file = af[0:index] + ".dst"
print "trying to open treesystem with aligned %s distance %s" % (
self.aligned_file, self.distance_file)
if not os.path.isfile(self.aligned_file):
print "no aligned file %s found" % (self.aligned_file)
try:
print 'treesystem opening %s' % (self.aligned_file)
#Sequencer.Clustalw_Protein(self.aligned_file) #Create protein distance matrix
print "sending %s off to UPGMA" % (self.distance_file)
self.tree = UPGMA.UPGMA(
self.distance_file) #root tree is the base tree
except IOError:
print "File must be a FASTA formatted file with more than one sequence"
return
self.Grab_Info(
) #Create a dictionary by GI of the titles and sequences
def test2_compre_to_shirans(): t1 = "ACGTACGTACGTACGTACGG" t2 = "GCGTACGTACGTACGTACGG" s1, s2 = 1-cfd_funct(t1, t2), 1- UPGMA.cfd_func(t1, t2) print(s1, s2)
def Make_Tree(self, file):
if (len(self.gi_list) > 0):
self.tree = UPGMA.UPGMAFiltered(file, self.gi_list)
else:
self.tree = TreeParse.Tree(0)
self.changed = 0
return self.tree
def test_fill_distance():
a = "aret"
b = "ardw"
c = "brdw"
seq_list = [a, b, c]
names = ["a", "b", "c"]
matrix = UPGMA.make_initiale_matrix(UPGMA.p_distance, seq_list)
m2 = UPGMA.make_distance_matrix(names, matrix)
print("names")
print(m2.names)
m3 = m2.__repr__()
upgma1 = UPGMA.make_UPGMA(m2)
fill_leaves_sets(upgma1)
fill_distance_from_leaves(upgma1)
node = list(upgma1.root.leaves_DS)[0]
while (node):
node = node.parent
def return_upgma(seq_list, names_list, df, cfd_dict=None):
'''input: a list of names and a list of sequences, calibrated
output: an upgma instance.
'''
if df == Metric.cfd_funct:
#base = seq_list
#metric_seq_list = list(map(lambda t: Metric.pos_in_metric_general(t,df,base, cfd_dict), seq_list))
seq_list = list(
map(lambda t: Metric.pos_in_metric_cfd_np(t, cfd_dict),
seq_list)) #to uncomment
# df = Metric.find_dist_t #if prev line is not is use #to uncomment
df = Metric.find_dist_np
matrix = UPGMA.make_initiale_matrix(df, seq_list)
m2 = UPGMA.make_distance_matrix(
names_list,
matrix) #shuold be m2 = UPGMA.make_distance_matrix(names_list, matrix)
upgma1 = UPGMA.make_UPGMA(m2)
return upgma1
def main(arg1, arg2):
start_time = time.time()
with open(arg1) as f:
content = f.readlines()
# you may also want to remove whitespace characters like `\n` at the end of each line
content = [x.strip() for x in content]
###print(content)
if (arg2 == "common"):
leaf_lists = {}
for i in range(len(content)):
t1 = Tree(content[i])
leaf_lists[i] = []
for leaf in t1:
leaf_lists[i].append(leaf.name)
##print(leaf_lists)
distance_mat = []
for x in range(0, len(content)):
distance_mat.append([])
for y in range(0, x):
lev_dist = len(intersection(leaf_lists[x], leaf_lists[y]))
distance_mat[x].append(lev_dist)
#.pop(0)
M_labels = number_labels(0, len(content))
tree, order = UPGMA_inc.UPGMA(distance_mat, M_labels)
##print(tree)
tree = tree + ';'
t_order = Tree(tree)
order_list = []
for node in t_order.traverse("postorder"):
# Do some analysis on node
if node.is_leaf():
order_list.append(node.name)
###print(t_order)
###print(order_list)
#min_x=distance_mat.index(min(distance_mat))
#min_y=distance_mat[min_x].index(min(distance_mat[min_x]))
###print(min_x,min_y)
###print(distance_mat[min_x][min_y])
t2 = Tree(content[int(order_list[0])])
for i in range(0, len(order_list) - 1):
t1 = Tree(content[int(order_list[i + 1])])
tree1_copy = t1.copy()
t2 = Tree(scm(t1, t2))
#splits1=rf_dist_list.main(tree1_copy.copy(),tree2_copy.copy())
###print("splits 1: ", splits1)
###print("splits 2: ",splits2)
###print(t2.write(format=9))
#t2.show()
elif (arg2 == "uncommon"):
leaf_lists = {}
for i in range(len(content)):
t1 = Tree(content[i])
leaf_lists[i] = []
for leaf in t1:
leaf_lists[i].append(leaf.name)
###print(leaf_lists)
distance_mat = []
for x in range(0, len(content)):
distance_mat.append([])
for y in range(0, x):
lev_dist = get_unique(leaf_lists[x], leaf_lists[y])
distance_mat[x].append(lev_dist)
#.pop(0)
M_labels = number_labels(0, len(content))
tree, order = UPGMA.UPGMA(distance_mat, M_labels)
###print(tree)
tree = tree + ';'
t_order = Tree(tree)
order_list = []
for node in t_order.traverse("postorder"):
# Do some analysis on node
if node.is_leaf():
order_list.append(node.name)
###print(t_order)
##print(order_list)
#min_x=distance_mat.index(min(distance_mat))
#min_y=distance_mat[min_x].index(min(distance_mat[min_x]))
###print(min_x,min_y)
###print(distance_mat[min_x][min_y])
t2 = Tree(content[int(order_list[0])])
for i in range(0, len(order_list) - 1):
t1 = Tree(content[int(order_list[i + 1])])
tree1_copy = t1.copy()
t2 = Tree(scm(t1, t2))
leaf_list1 = []
leaf_list2 = []
for leaf in t1:
leaf_list1.append(leaf.name)
for leaf in t2:
leaf_list2.append(leaf.name)
###print(leaf_list1)
overlap = intersection(leaf_list1, leaf_list2)
###print("overlap is: ",overlap)
tree2_copy = t2.copy()
###print(tree1_copy,tree2_copy)
tree1_copy.prune(overlap)
tree2_copy.prune(overlap)
#t.write(format=1
splits2 = rf_dist_list.main(tree2_copy.copy(), tree1_copy.copy())
#splits1=rf_dist_list.main(tree1_copy.copy(),tree2_copy.copy())
###print("splits 1: ", splits1)
###print("splits 2: ",splits2)
else:
t2 = Tree(content[0])
for i in range(0, len(content) - 1):
t1 = Tree(content[i + 1])
tree1_copy = t1.copy()
t2 = Tree(scm(t1, t2))
leaf_list1 = []
leaf_list2 = []
for leaf in t1:
leaf_list1.append(leaf.name)
for leaf in t2:
leaf_list2.append(leaf.name)
###print(leaf_list1)
#overlap=intersection(leaf_list1,leaf_list2)
###print("overlap is: ",overlap)
#tree2_copy=t2.copy()
###print(tree1_copy,tree2_copy)
#tree1_copy.prune(overlap)
#tree2_copy.prune(overlap)
#t.write(format=1
#splits2=rf_dist_list.main(tree2_copy.copy(),tree1_copy.copy())
#splits1=rf_dist_list.main(tree1_copy.copy(),tree2_copy.copy())
###print("splits 1: ", splits1)
###print("splits 2: ",splits2)
###print(time.time()-start_time)
###print(t2.write(format=9))
#t2.show()
return t2
dist_map[(d1,d2)] = dist
# 输出similarity 到文件
file1 = "similarity.txt"
with open(file1,"w") as f:
for row in score_matrix:
f.write(','.join(str(e) for e in row))
f.write('\n')
# 输出距离矩阵到distance 文件
file2 = "distance.txt"
with open(file2,"w") as f:
for row in dist_matrix:
f.write(','.join(str(e) for e in row))
f.write('\n')
# # 打印距离map
# print(dist_map)
#
# 打印upgma树
tree = UPGMA.upgma(dist_map,len(sequences),len(sequences))
MSAseqs = Needleman.MSA(tree,sequences,score_matrix,s_matrix)
# again create msa_dist_map according the msaseqs
msa_dist_map = {}
for d1 in range(len(MSAseqs)):
for d2 in range(len(MSAseqs)):
dist = Needleman.distance(MSAseqs[d1], MSAseqs[d2], s_matrix)
msa_dist_map[(d1,d2)] = dist
finaltree = UPGMA.upgma(msa_dist_map,len(MSAseqs),len(MSAseqs))