def _build_tree(self, tree_file, tree_format):
if tree_format == 'newick_string':
self.tree_str = tree_file
return ete3.Tree(self.tree_str, format=1)
elif tree_format == 'newick':
with open(tree_file, 'r') as nwk_file:
self.tree_str = nwk_file.read()
return ete3.Tree(self.tree_str, format=1)
elif tree_format == 'phyloxml':
from ete3 import Phyloxml
project = Phyloxml()
project.build_from_file(tree_file)
self.tree_str = None
tree = project.get_phylogeny()[0]
for node in tree.traverse():
# assign name to extant species
if node.is_leaf():
node.name = self._get_name_phyloxml(
node, self.phyloxml_leaf_name_tag)
# assign name to ancestral species
elif self.use_internal_name:
node.name = self._get_name_phyloxml(
node, self.phyloxml_internal_name_tag)
return tree
def getTreeFromPhyloxml(xml, saveToFile="default.xml", delFile=True):
"""
Read a phylogeny tree from a phyloxml string and return a TreeClass object
or a list of TreeClass object
"""
project = Phyloxml()
fo = open(saveToFile, "w+")
fo.write(xml)
fo.close()
project.build_from_file(saveToFile)
treeList = []
for tree in project.get_phylogeny():
treeList.append(TreeClass.import_from_PhyloxmlTree(tree))
if (delFile):
os.remove(saveToFile)
if len(treeList) == 1:
return treeList[0]
return treeList
def getTreeFromPhyloxml(xml, saveToFile="default.xml", delFile=True):
"""
Read a phylogeny tree from a phyloxml string and return a TreeClass object
or a list of TreeClass object
"""
project = Phyloxml()
fo = open(saveToFile, "w+")
fo.write(xml)
fo.close()
project.build_from_file(saveToFile)
treeList = []
for tree in project.get_phylogeny():
treeList.append(TreeClass.import_from_PhyloxmlTree(tree))
if(delFile):
os.remove(saveToFile)
if len(treeList) == 1:
return treeList[0]
return treeList
def get_ete_tree(filename):
from ete3 import Tree, Phyloxml
p = Phyloxml()
p.build_from_file(filename)
t = p.get_phylogeny()[0]
return t
def _generate_internal_node_name(self, tree):
if self.use_internal_name is False:
for node in tree.traverse("postorder"):
if node.is_leaf() is False:
self.set_taxon_name(node)
if self.tree_format == 'phyloxml':
#### IMPORTANT ####
'''
This code section is an horrible fix due to incompatibility of Phyloxml().export() with python3.
We overwrite the export module (and its functions) here to deal with both byte and unicode.
TODO: this should be replace as ASAP
'''
def showIndent(outfile, level):
for idx in range(level):
g = ' '
g = g.encode('UTF-8')
outfile.write(g)
namespace_ = 'phy:'
name_ = 'Phyloxml'
namespacedef_ = ''
outfile = BytesIO()
level = 0
def export(xxxx,
outfile,
level,
namespace_='phy:',
name_='Phyloxml',
namespacedef_=''):
showIndent(outfile, level)
x = '<%s%s%s' % (
namespace_,
name_,
namespacedef_ and ' ' + namespacedef_ or '',
)
x = x.encode('UTF-8')
outfile.write(x)
already_processed = []
exportAttributes(xxxx,
outfile,
level,
already_processed,
namespace_,
name_='Phyloxml')
if hasContent_(xxxx):
y = '>\n'
y = y.encode('UTF-8')
outfile.write(y)
exportChildren(xxxx, outfile, level + 1, namespace_, name_)
showIndent(outfile, level)
z = '</%s%s>\n' % (namespace_, name_)
z = z.encode('UTF-8')
outfile.write(z)
else:
v = '/>\n'
v = v.encode('UTF-8')
outfile.write(v)
def exportAttributes(xxxx,
outfile,
level,
already_processed,
namespace_='phy:',
name_='Phyloxml'):
pass
def exportChildren(xxxx,
outfile,
level,
namespace_='phy:',
name_='Phyloxml',
fromsubclass_=False):
for phylogeny_ in xxxx.phylogeny:
export(phylogeny_,
outfile,
level,
namespace_,
name_='phylogeny')
def hasContent_(xxxx):
if hasattr(xxxx, 'phylogeny'):
return True
else:
return False
#### IMPORTANT ####
# build phyloxml project
project = Phyloxml()
project.add_phylogeny(tree)
# Export phyloxml document
export(project,
outfile,
level,
namespace_='phy:',
name_='Phyloxml',
namespacedef_='')
OUTPUT = outfile
# Some ad-hoc changes to the phyloxml formatted document to meet the schema definition
text = OUTPUT.read().decode('UTF-8')
text = text.replace('phy:', '')
text = re.sub('branch_length_attr="[^"]+"', "", text)
header = """
<phyloxml xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://www.phyloxml.org" xsi:schemaLocation="http://www.phyloxml.org http://www.phyloxml.org/1.20/phyloxml.xsd">
"""
text = re.sub('<Phyloxml[^>]+>', header, text)
text = text.replace('Phyloxml', 'phyloxml')
text = text.replace('\n', '').replace("'", '')
self.tree_str = text
else:
self.tree_str = self.tree.write(format=8, format_root_node=True)
from ete3 import Phyloxml, phyloxml
import random
project = Phyloxml()
# Creates a random tree
phylo = phyloxml.PhyloxmlTree()
phylo.populate(5, random_branches=True)
phylo.phyloxml_phylogeny.set_name("test_tree")
# Add the tree to the phyloxml project
project.add_phylogeny(phylo)
print project.get_phylogeny()[0]
# /-iajom
# /---|
# | \-wiszh
#----|
# | /-xrygw
# \---|
# | /-gjlwx
# \---|
# \-ijvnk
# Trees can be operated as normal ETE trees
phylo.show()
# Export the project as phyloXML format
project.export()
# <phy:Phyloxml xmlns:phy="http://www.phyloxml.org/1.10/phyloxml.xsd">
# <phy:phylogeny>
from ete3 import Phyloxml
project = Phyloxml()
project.build_from_file("apaf.xml")
# Each tree contains the same methods as a PhyloTree object
for tree in project.get_phylogeny():
print tree
# you can even use rendering options
tree.show()
# PhyloXML features are stored in the phyloxml_clade attribute
for node in tree:
print "Node name:", node.name
for seq in node.phyloxml_clade.get_sequence():
for domain in seq.domain_architecture.get_domain():
domain_data = [domain.valueOf_, domain.get_from(), domain.get_to()]
print " Domain:", '\t'.join(map(str, domain_data))
from ete3 import Phyloxml, phyloxml
import random
project = Phyloxml()
# Creates a random tree
phylo = phyloxml.PhyloxmlTree()
phylo.populate(5, random_branches=True)
phylo.phyloxml_phylogeny.set_name("test_tree")
# Add the tree to the phyloxml project
project.add_phylogeny(phylo)
print project.get_phylogeny()[0]
# /-iajom
# /---|
# | \-wiszh
#----|
# | /-xrygw
# \---|
# | /-gjlwx
# \---|
# \-ijvnk
# Trees can be operated as normal ETE trees
phylo.show()
# Export the project as phyloXML format
project.export()
# <phy:Phyloxml xmlns:phy="http://www.phyloxml.org/1.10/phyloxml.xsd">