parser.add_option("-e", "--eventfile", dest="eventfile",
help="events file")
parser.add_option("-o", "--output", dest="output",
help="output file")
parser.add_option("-p", "--prune", dest="prune", type="float",default=0,help="Do not draw subs with probability less than this value")
parser.add_option("-s", "--scale", dest="scale", type="int",
help="8000 for little ksu, 3 for krya")
parser.add_option("-c", "--circle_size", dest="size", type="float",
help="20 for little ksu, ? for krya")
parser.add_option("-w", "--width", dest="width", type="int",
help="870 for little ksu, ? for krya")
parser.add_option("-l", "--large", dest="large",action="store_true", default=False,
help="do not set vertical margin between branches( branch margins used for scheme)")
(options, args) = parser.parse_args()
t = Tree(options.treefile, format=1) #flexible with internal node names
farthest, dist = t.get_farthest_node()
print ("The farthest node from root is", farthest.name, "with dist=", dist)
if not options.scale:
options.scale = int(1700/dist) #900/dist
#root = t.get_tree_root()
#farthest = root.get_farthest_leaf()
#print "The height is ", t.get_distance(root.name, farthest.name)
# Basic tree style
ts = TreeStyle()
ts.show_leaf_name = False
if options.large:
ts.show_scale = False
#ts.optimal_scale_level = "full"
ts.scale = options.scale #3 for krya # pixels per branch length unit
if not options.large:
class um_tree:
def __init__(self, tree, PATH):
self.tree = Tree(tree, format=1)
self.tree2 = open(tree)
self.tree.resolve_polytomy(default_dist=0.000001, recursive=True)
self.tree.dist = 0
self.tree.add_feature("age", 0)
self.nodes = self.tree.get_descendants()
self.PATH = PATH
internal_node = []
cnt = 0
for n in self.nodes:
node_age = n.get_distance(self.tree)
n.add_feature("age", node_age)
if not n.is_leaf():
n.add_feature("id", cnt)
cnt = cnt + 1
internal_node.append(n)
self.nodes = internal_node
one_leaf = self.tree.get_farthest_node()[0]
one_leaf.add_feature("id", cnt + 1)
if one_leaf.is_leaf():
self.nodes.append(one_leaf)
self.nodes.sort(key=self.__compare_node)
self.species_list = []
self.coa_roots = None
def __compare_node(self, node):
return node.age
def get_waiting_times(self, threshold_node=None, threshold_node_idx=0):
wt_list = []
reach_t = False
curr_age = 0.0
curr_spe = 2
curr_num_coa = 0
coa_roots = []
min_brl = 1000
num_spe = -1
if threshold_node == None:
threshold_node = self.nodes[threshold_node_idx]
last_coa_num = 0
tcnt = 0
for node in self.nodes:
num_children = len(node.get_children())
wt = None
times = node.age - curr_age
if times >= 0:
if times < min_brl and times > 0:
min_brl = times
curr_age = node.age
assert curr_spe >= 0
if reach_t:
if tcnt == 0:
last_coa_num = 2
fnode = node.up
coa_root = None
idx = 0
while not fnode.is_root():
idx = 0
for coa_r in coa_roots:
if coa_r.id == fnode.id:
coa_root = coa_r
break
idx = idx + 1
if coa_root != None:
break
else:
fnode = fnode.up
wt = waiting_time(length=times,
num_coas=curr_num_coa,
num_lines=curr_spe)
for coa_r in coa_roots:
coa = coalescent(num_individual=coa_r.curr_n)
wt.coas.add_coalescent(coa)
wt.coas.coas_idx = last_coa_num
wt.num_curr_coa = last_coa_num
if (coa_root == None
): # here can be modified to use multiple T
curr_spe = curr_spe - 1
curr_num_coa = curr_num_coa + 1
node.add_feature("curr_n", 2)
coa_roots.append(node)
last_coa_num = 2
else:
curr_n = coa_root.curr_n
coa_root.add_feature("curr_n", curr_n + 1)
last_coa_num = curr_n + 1
tcnt = tcnt + 1
else:
if node.id == threshold_node.id:
reach_t = True
tcnt = 0
wt = waiting_time(length=times,
num_coas=0,
num_lines=curr_spe)
num_spe = curr_spe
curr_spe = curr_spe - 1
curr_num_coa = 2
node.add_feature("curr_n", 2)
coa_roots.append(node)
else:
wt = waiting_time(length=times,
num_coas=0,
num_lines=curr_spe)
curr_spe = curr_spe + 1
if times > 0.00000001:
wt_list.append(wt)
for wt in wt_list:
wt.count_num_lines()
self.species_list = []
all_coa_leaves = []
self.coa_roots = coa_roots
for coa_r in coa_roots:
leaves = coa_r.get_leaves()
all_coa_leaves.extend(leaves)
self.species_list.append(leaves)
all_leaves = self.tree.get_leaves()
for leaf in all_leaves:
if leaf not in all_coa_leaves:
self.species_list.append([leaf])
return wt_list, num_spe
def show(self, wt_list):
cnt = 1
for wt in wt_list:
print(("Waitting interval " + repr(cnt)))
print(wt)
cnt = cnt + 1
def get_species(self):
sp_list = []
for sp in self.species_list:
spe = []
for taxa in sp:
spe.append(taxa.name)
sp_list.append(spe)
all_taxa_name = []
# self.tree.convert_to_ultrametric(tree_length = 1.0, strategy='balanced')
for leaf in self.tree.get_leaves():
all_taxa_name.append(leaf.name)
style0 = NodeStyle()
style0["fgcolor"] = "#000000"
# style2["shape"] = "circle"
style0["vt_line_color"] = "#0000aa"
style0["hz_line_color"] = "#0000aa"
style0["vt_line_width"] = 2
style0["hz_line_width"] = 2
style0["vt_line_type"] = 0 # 0 solid, 1 dashed, 2 dotted
style0["hz_line_type"] = 0
style0["size"] = 0
for node in self.tree.get_descendants():
node.set_style(style0)
node.img_style["size"] = 0
self.tree.set_style(style0)
self.tree.img_style["size"] = 0
style1 = NodeStyle()
style1["fgcolor"] = "#000000"
# style2["shape"] = "circle"
style1["vt_line_color"] = "#ff0000"
style1["hz_line_color"] = "#0000aa"
style1["vt_line_width"] = 2
style1["hz_line_width"] = 2
style1["vt_line_type"] = 0 # 0 solid, 1 dashed, 2 dotted
style1["hz_line_type"] = 0
style1["size"] = 0
style2 = NodeStyle()
style2["fgcolor"] = "#0f0f0f"
# style2["shape"] = "circle"
style2["vt_line_color"] = "#ff0000"
style2["hz_line_color"] = "#ff0000"
style2["vt_line_width"] = 2
style2["hz_line_width"] = 2
style2["vt_line_type"] = 0 # 0 solid, 1 dashed, 2 dotted
style2["hz_line_type"] = 0
style2["size"] = 0
for node in self.coa_roots:
node.set_style(style1)
node.img_style["size"] = 0
for des in node.get_descendants():
des.set_style(style2)
des.img_style["size"] = 0
return [all_taxa_name], sp_list
def print_species(self):
# tree_path = os.path.dirname(self.tree2.name)
sp_out = open(os.path.join(self.PATH, "GMYC/GMYC_MOTU.txt"), "w+")
cnt = 1
for sp in self.species_list:
# print("Species " + repr(cnt) + ":")
sp_out.write("Species " + repr(cnt) + "\n")
cnt = cnt + 1
taxas = ""
for taxa in sp:
taxas = taxas + taxa.name + ", "
# print(" " + taxas[:-1])
sp_out.write(" " + taxas[:-1] + "\n")
def output_species(self, taxa_order=[]):
"""taxa_order is a list of taxa names, the paritions will be output as the same order"""
if len(taxa_order) == 0:
taxa_order = self.tree.get_leaf_names()
num_taxa = 0
for sp in self.species_list:
for taxa in sp:
num_taxa = num_taxa + 1
if not len(taxa_order) == num_taxa:
print("error error, taxa_order != num_taxa!")
return None, None
else:
partion = [-1] * num_taxa
cnt = 1
for sp in self.species_list:
for taxa in sp:
idx = taxa_order.index(taxa.name)
partion[idx] = cnt
cnt = cnt + 1
return taxa_order, partion
def num_lineages(self, wt_list):
nl_list = []
times = []
last_time = 0.0
for wt in wt_list:
nl_list.append(wt.get_num_branches())
times.append(last_time)
last_time = wt.length + last_time
plt.plot(times, nl_list)
plt.ylabel("Number of lineages")
plt.xlabel("Time")
plt.savefig("Time_Lines")
plt.show()
class um_tree:
def __init__(self, tree):
self.tree = Tree(tree, format=1)
self.tree.resolve_polytomy(default_dist=0.000001, recursive=True)
self.tree.dist = 0
self.tree.add_feature("age", 0)
self.nodes = self.tree.get_descendants()
internal_node = []
cnt = 0
for n in self.nodes:
node_age = n.get_distance(self.tree)
n.add_feature("age", node_age)
if not n.is_leaf():
n.add_feature("id", cnt)
cnt = cnt + 1
internal_node.append(n)
self.nodes = internal_node
one_leaf = self.tree.get_farthest_node()[0]
one_leaf.add_feature("id", cnt + 1)
if one_leaf.is_leaf():
self.nodes.append(one_leaf)
self.nodes.sort(key=self.__compare_node)
self.species_list = []
self.coa_roots = None
def __compare_node(self, node):
return node.age
def get_waiting_times(self, threshold_node=None, threshold_node_idx=0):
wt_list = []
reach_t = False
curr_age = 0.0
curr_spe = 2
curr_num_coa = 0
coa_roots = []
min_brl = 1000
num_spe = -1
if threshold_node == None:
threshold_node = self.nodes[threshold_node_idx]
last_coa_num = 0
tcnt = 0
for node in self.nodes:
num_children = len(node.get_children())
wt = None
times = node.age - curr_age
if times >= 0:
if times < min_brl and times > 0:
min_brl = times
curr_age = node.age
assert curr_spe >= 0
if reach_t:
if tcnt == 0:
last_coa_num = 2
fnode = node.up
coa_root = None
idx = 0
while not fnode.is_root():
idx = 0
for coa_r in coa_roots:
if coa_r.id == fnode.id:
coa_root = coa_r
break
idx = idx + 1
if coa_root != None:
break
else:
fnode = fnode.up
wt = waiting_time(length=times,
num_coas=curr_num_coa,
num_lines=curr_spe)
for coa_r in coa_roots:
coa = coalescent(num_individual=coa_r.curr_n)
wt.coas.add_coalescent(coa)
wt.coas.coas_idx = last_coa_num
wt.num_curr_coa = last_coa_num
if coa_root == None: #here can be modified to use multiple T
curr_spe = curr_spe - 1
curr_num_coa = curr_num_coa + 1
node.add_feature("curr_n", 2)
coa_roots.append(node)
last_coa_num = 2
else:
curr_n = coa_root.curr_n
coa_root.add_feature("curr_n", curr_n + 1)
last_coa_num = curr_n + 1
tcnt = tcnt + 1
else:
if node.id == threshold_node.id:
reach_t = True
tcnt = 0
wt = waiting_time(length=times,
num_coas=0,
num_lines=curr_spe)
num_spe = curr_spe
curr_spe = curr_spe - 1
curr_num_coa = 2
node.add_feature("curr_n", 2)
coa_roots.append(node)
else:
wt = waiting_time(length=times,
num_coas=0,
num_lines=curr_spe)
curr_spe = curr_spe + 1
if times > 0.00000001:
wt_list.append(wt)
for wt in wt_list:
wt.count_num_lines()
self.species_list = []
all_coa_leaves = []
self.coa_roots = coa_roots
for coa_r in coa_roots:
leaves = coa_r.get_leaves()
all_coa_leaves.extend(leaves)
self.species_list.append(leaves)
all_leaves = self.tree.get_leaves()
for leaf in all_leaves:
if leaf not in all_coa_leaves:
self.species_list.append([leaf])
return wt_list, num_spe
def show(self, wt_list):
cnt = 1
for wt in wt_list:
print("Waitting interval " + repr(cnt))
print(wt)
cnt = cnt + 1
def get_species(self):
sp_list = []
for sp in self.species_list:
spe = []
for taxa in sp:
spe.append(taxa.name)
sp_list.append(spe)
all_taxa_name = []
for leaf in self.tree.get_leaves():
all_taxa_name.append(leaf.name)
style0 = NodeStyle()
style0["fgcolor"] = "#000000"
style0["vt_line_color"] = "#0000aa"
style0["hz_line_color"] = "#0000aa"
style0["vt_line_width"] = 2
style0["hz_line_width"] = 2
style0["vt_line_type"] = 0 # 0 solid, 1 dashed, 2 dotted
style0["hz_line_type"] = 0
style0["size"] = 0
for node in self.tree.get_descendants():
node.set_style(style0)
node.img_style["size"] = 0
self.tree.set_style(style0)
self.tree.img_style["size"] = 0
style1 = NodeStyle()
style1["fgcolor"] = "#000000"
style1["vt_line_color"] = "#ff0000"
style1["hz_line_color"] = "#0000aa"
style1["vt_line_width"] = 2
style1["hz_line_width"] = 2
style1["vt_line_type"] = 0 # 0 solid, 1 dashed, 2 dotted
style1["hz_line_type"] = 0
style1["size"] = 0
style2 = NodeStyle()
style2["fgcolor"] = "#0f0f0f"
style2["vt_line_color"] = "#ff0000"
style2["hz_line_color"] = "#ff0000"
style2["vt_line_width"] = 2
style2["hz_line_width"] = 2
style2["vt_line_type"] = 0 # 0 solid, 1 dashed, 2 dotted
style2["hz_line_type"] = 0
style2["size"] = 0
for node in self.coa_roots:
node.set_style(style1)
node.img_style["size"] = 0
for des in node.get_descendants():
des.set_style(style2)
des.img_style["size"] = 0
return [all_taxa_name], sp_list
def print_species(self, save_file):
cnt = 1
file3 = open(os.path.join(save_file, "partition.txt"), "w+")
for sp in self.species_list:
print("Species " + repr(cnt) + ":", file=file3)
cnt = cnt + 1
taxas = ""
for taxa in sp:
taxas = taxas + taxa.name + ", "
print("" + taxas[:-1], file=file3)
def print_species_spart(self, save_file):
cnt = 1
file3 = open(os.path.join(save_file, "partition.spart"), "w+")
# for sp in self.species_list:
# print("Species " + repr(cnt) + ":", file= file3)
# cnt = cnt + 1
# taxas = ""
# for taxa in sp:
# print(taxa)
# taxas = taxas + taxa.name + ", "
# print("" + taxas[:-1], file= file3)
file3.write("Filename=GMYC delimitation\n")
file3.write(f'{datetime.datetime.now().astimezone().isoformat()}\n\n')
file3.write(f"Npartition={1};GMYC\n")
file3.write(f'Nsamples={sum(len(sp) for sp in self.species_list)}\n')
file3.write(
f'Nsubsets={len(self.species_list)};{",".join(["?" for i in range(len(self.species_list))])}\n\n'
)
file3.write("#this is my first comment\n")
file3.write("#this is my second comment\n\n")
file3.write("Assignment\n")
cnt = 1
for sp in self.species_list:
print(repr(sp))
for taxa in sp:
print(repr(taxa))
xx = taxa.name + "\t" + repr(cnt) + ";" + "?"
file3.write(f"{xx}\n")
cnt += 1
file3.write("\nPartition_score=\n")
file3.close()
def output_species(self, taxa_order=[]):
if len(taxa_order) == 0:
taxa_order = self.tree.get_leaf_names()
num_taxa = 0
for sp in self.species_list:
for taxa in sp:
num_taxa = num_taxa + 1
if not len(taxa_order) == num_taxa:
print("error error, taxa_order != num_taxa!")
return None, None
else:
partion = [-1] * num_taxa
cnt = 1
for sp in self.species_list:
for taxa in sp:
idx = taxa_order.index(taxa.name)
partion[idx] = cnt
cnt = cnt + 1
return taxa_order, partion
def num_lineages(self, wt_list, save_file):
nl_list = []
times = []
last_time = 0.0
for wt in wt_list:
nl_list.append(wt.get_num_branches())
times.append(last_time)
last_time = wt.length + last_time
plt.plot(times, nl_list)
plt.ylabel('Number of lineages')
plt.xlabel('Time')
plt.savefig(os.path.join(save_file, "Time_Lines.png"))
else:
sys.exit("Invalid parent-daughter: %s, %s" % (parentloc, thisloc))
return 5 * base + add
def FindLocationOfParent(node):
parent = node.up
try:
return infodic[parent.name]["location"]
except AttributeError:
sys.exit("Error finding parent of %s" % node.name)
tree = Tree(sys.argv[1], format=1)
rootheight = tree.get_farthest_node()[1]
print("Tree height: %s" % rootheight)
infodic = {}
with open(sys.argv[2], "rU") as infofile:
csvreader = csv.reader(infofile, delimiter=",")
header = csvreader.next()
for row in csvreader:
infodic[row[0]] = {
"height": row[1],
"length": row[2],
"location": row[3]
}
calendar = [[0 for year in xrange(int(math.ceil(rootheight)) + 1)]
