data_outs.addStream(sys.stdout)
# Write out parameters
data_outs.write("# Run started {}\n".format(util.timestamp()))
data_outs.write("# Command: {}\n".format(' '.join(sys.argv)))
data_outs.write("# Parameters:\n")
optdict = vars(options)
for (k,v) in optdict.items():
data_outs.write("#\t{k}: {v}\n".format(k=k, v=v))
# Read input
fname =os.path.expanduser(options.in_fname)
if not os.path.isfile(fname):
raise IOError("# Error: file {} does not exist".format(fname))
tree_root = Newick.Clade()
tree_root.parent = None
tree_root.name = "cellular organisms"
# Get directory of guide file
path = os.path.dirname(fname)
curwd = os.getcwd()
species_names = []
with open(fname,'r') as inf:
os.chdir(path)
tab = util.readTable(inf, header=True)
rows = tab.dictrows
if options.debug:
rows = [x for x in tab.dictrows][:2]
def taxid2tree(self, taxid_list, out_fmt="newick"):
""" This function take a list of gi as input, will generate a path for
for each gi, then construct a newick or phyloxml tree based on these
gi pathes.
out_fmt = newick / phyloxml ...
"""
treeFile = StringIO()
# get pathes for a list of taxid
path_list = [
";".join([str(item) for item in self.get_path(taxid)])
for taxid in taxid_list
]
# read in pathFile, and store node info into nodes
nodes = {} # data format {"node_name": Clade_object}
root = None
# to parese path iterately
for i, path in enumerate(path_list):
line = path.strip().split(";")
if root is None:
root = line[0]
else:
assert root == line[
0], "The %d-th line is from a different root" % (i + 1)
# check node iterately, first reverse list, to from leaf to root
# to make sure every node has a parent node
leaf2root = line[::-1]
for j, item in enumerate(leaf2root):
# find child_node and parent_node, root node's parent is itself
if j == len(line) - 1:
child_node = item
parent_node = item
else:
child_node = item
parent_node = leaf2root[j + 1]
if nodes.has_key(child_node):
continue
else:
# add this node
nodes[child_node] = Newick.Clade(name=child_node)
# add its parent info
nodes[child_node].parent = parent_node
for node_name, node_clade in nodes.iteritems():
# find the root node, its parent is itself
if node_name == node_clade.parent:
root_node = node_clade
print "root node is %s, constructing tree ..." % (
str(node_name))
# if node is not root, then find its parent, and add to its parent's clades
else:
parent_node = nodes[node_clade.parent]
parent_node.clades.append(node_clade)
del node_clade.parent
tree = Newick.Tree(root=root_node)
bp.write(tree, treeFile, out_fmt)
treeStr = treeFile.getvalue()
return treeStr
def new_clade(self, parent=None):
"""Return new Newick.Clade, optionally with temporary reference to parent."""
clade = Newick.Clade()
if parent:
clade.parent = parent
return clade
def path2newick(self, path2pathFile, node_fmt="taxid", out_fmt="newick"):
""" This function take taxonomic path file as input, path should be consist
of taxonomic id, not scitific name, because some scientific name are the
same in different rank, but ids are unique.
node_fmt = taxid / sciName
out_fmt = newick / phyloxml ...
"""
path, fileName = os.path.split(path2pathFile)
basename = os.path.splitext(fileName)[0]
outFile = os.path.join(path,
basename + "2tree_" + node_fmt + "." + out_fmt)
with open(path2pathFile, "r") as pathFile:
# read in pathFile, and store node info into nodes
nodes = {} # data format {"node_name": Clade_object}
root = None
# open file to parese line iterately
for i, line in enumerate(pathFile):
line = line.strip()
if line.endswith(";"):
line = line.rstrip(";")
line = line.strip().split(";")
if root is None:
root = line[1]
else:
assert root == line[
1], "The %d-th line is from a different root" % (i + 1)
# check node iterately, first reverse list, to from leaf to root
# to make sure every node has a parent node
leaf2root = line[::-1]
for j, item in enumerate(leaf2root):
# find child_node and parent_node, root node's parent is itself
if j == len(line) - 1:
child_node = item
parent_node = item
else:
child_node = item
parent_node = leaf2root[j + 1]
if nodes.has_key(child_node):
continue
else:
# add this node
nodes[child_node] = Newick.Clade(name=child_node)
# add its parent info
nodes[child_node].parent = parent_node
for node_name, node_clade in nodes.iteritems():
# find the root node, its parent is itself
if node_name == node_clade.parent:
root_node = node_clade
print node_clade
print "root node found!! "
# if node is not root, then find its parent, and add to its parent's clades
else:
parent_node = nodes[node_clade.parent]
parent_node.clades.append(node_clade)
del node_clade.parent
# transform between output node format
if node_fmt == "taxid":
tree = Newick.Tree(root=root_node)
else:
assert node_fmt == "sciName", "The node_fmt should be taxid or sciName"
# convert taxid to sciName
for node_name, node in nodes.iteritems():
node_name = self.get_sciName(node_name)
for child in node.clades:
if child:
child.name = self.get_sciName(child.name)
root_node.name = self.get_sciName(root_node.name)
tree = Newick.Tree(root=root_node)
# write tree to file
print 'Writing %s tree to %s...' % (out_fmt, outFile)
bp.write(tree, outFile, out_fmt)