import random
from ete_dev import Tree
# Creates a normal tree
t = Tree(
'((H:0.3,I:0.1):0.5, A:1, (B:0.4,(C:0.5,(J:1.3, (F:1.2, D:0.1):0.5):0.5):0.5):0.5);'
)
print t
# Let's locate some nodes using the get common ancestor method
ancestor = t.get_common_ancestor("J", "F", "C")
# the search_nodes method (I take only the first match )
A = t.search_nodes(name="A")[0]
# and using the shorcut to finding nodes by name
C = t & "C"
H = t & "H"
I = t & "I"
# Let's now add some custom features to our nodes. add_features can be
# used to add many features at the same time.
C.add_features(vowel=False, confidence=1.0)
A.add_features(vowel=True, confidence=0.5)
ancestor.add_features(nodetype="internal")
# Or, using the oneliner notation
(t & "H").add_features(vowel=False, confidence=0.2)
# But we can automatize this. (note that i will overwrite the previous
# values)
for leaf in t.traverse():
if leaf.name in "AEIOU":
leaf.add_features(vowel=True, confidence=random.random())
else:
leaf.add_features(vowel=False, confidence=random.random())
# Now we use these information to analyze the tree.
print "This tree has", len(t.search_nodes(vowel=True)), "vowel nodes"
def get_rooting(tol, seed_species, agename=False):
'''
returns dict of species age for a given TOL and a given seed
**Example:**
::
tol = "((((((((Drosophila melanogaster,(Drosophila simulans,Drosophila secchellia)),(Drosophila yakuba,Drosophila erecta))[&&NHX:name=melanogaster subgroup],Drosophila ananassae)[&&NHX:name=melanogaster group],(Drosophila pseudoobscura,Drosophila persimilis)[&&NHX:name=obscura group])[&&NHX:name=Sophophora Old World],Drosophila willistoni)[&&NHX:name=subgenus Sophophora],(Drosophila grimshawi,(Drosophila virilis,Drosophila mojavensis))[&&NHX:name=subgenus Drosophila])[&&NHX:name=genus Drosophila],(Anopheles gambiae,Aedes aegypti)[&&NHX:name=Culicidae])[&&NHX:name=Arthropoda],Caenorhabditis elegans)[&&NHX:name=Animalia];"
seed = "Drosophila melanogaster"
ROOTING, age2name = get_rooting (tol, seed, True)
ROOTING == {"Aedes aegypti" : 7,
"Anopheles gambiae" : 7,
"Caenorhabditis elegans" : 8,
"Drosophila ananassae" : 3,
"Drosophila erecta" : 2,
"Drosophila grimshawi" : 6,
"Drosophila melanogaster" : 1,
"Drosophila mojavensis" : 6,
"Drosophila persimilis" : 4,
"Drosophila pseudoobscura": 4,
"Drosophila secchellia" : 1,
"Drosophila simulans" : 1,
"Drosophila virilis" : 6,
"Drosophila willistoni" : 5,
"Drosophila yakuba" : 2}
age2name == {1: "Drosophila melanogaster. Drosophila simulans. Drosophila secchellia",
2: "melanogaster subgroup",
3: "melanogaster group",
4: "Sophophora Old World",
5: "subgenus Sophophora",
6: "genus Drosophila",
7: "Arthropoda",
8: "Animalia"}
:argument seed_species: species name
:argument False agename: if True, also returns the inverse dictionary
:returns: ROOTING dictionary with age of each species
'''
tol = Tree(tol)
try:
node = tol.search_nodes(name=seed_species)[0]
except IndexError:
exit('ERROR: Seed species not found in tree\n')
age = 1
ROOTING = {}
if agename:
age2name = {}
while not node.is_root():
node = node.up
for leaf in node.get_leaf_names():
if agename:
if node.name == 'NoName':
nam = '.'.join(node.get_leaf_names())
else:
nam = node.name
age2name.setdefault(age, nam)
ROOTING.setdefault(leaf, age)
age += 1
if agename:
return ROOTING, age2name
return ROOTING
# /A-------| \G-------| # | | \-I # | | # | \-E #-NoName--| # | /-L # | /J-------| # | | | /-N # | | \O-------| # \C-------| \-Q # | # | /-P # \M-------| # \-S # Get pointers to specific nodes G = t.search_nodes(name="G")[0] J = t.search_nodes(name="J")[0] C = t.search_nodes(name="C")[0] # If we remove J from the tree, the whole partition under J node will # be detached from the tree and it will be considered an independent # tree. We can do the same thing using two approaches: J.detach() or # C.remove_child(J) removed_node = J.detach() # = C.remove_child(J) # if we know print the original tree, we will see how J partition is # no longer there. print "Tree after REMOVING the node J" print t.get_ascii(show_internal=True) # /-H # /D-------| # | \-K # /B-------|
def main(argv):
parser = argparse.ArgumentParser(description=__DESCRIPTION__,
formatter_class=argparse.RawDescriptionHelpFormatter)
input_args = parser.add_argument_group("INPUT OPTIONS")
input_args.add_argument("source_trees", metavar='source_trees', type=str, nargs="*",
help='a list of source tree files')
input_args.add_argument("--source_file", dest="source_file",
type=str,
help="""path to a file containing many source trees, one per line""")
input_args.add_argument("-r", dest="reftree",
type=str, required=True,
help="""Reference tree""")
input_args.add_argument("--ref_tree_attr", dest="ref_tree_attr",
type=str, default="name",
help=("attribute in ref tree used as leaf name"))
input_args.add_argument("--src_tree_attr", dest="src_tree_attr",
type=str, default="name",
help=("attribute in source tree used as leaf name"))
input_args.add_argument("--min_support_ref",
type=float, default=0.0,
help=("min support for branches to be considered from the ref tree"))
input_args.add_argument("--min_support_src",
type=float, default=0.0,
help=("min support for branches to be considered from the source tree"))
output_args = parser.add_argument_group("OUTPUT OPTIONS")
output_args.add_argument("-o", dest="output",
type=str,
help="""Path to the tab delimited report file""")
opt_args = parser.add_argument_group("DISTANCE OPTIONS")
opt_args.add_argument("--outgroup", dest="outgroup",
nargs = "+",
help="""outgroup used to root reference and source trees before distance computation""")
opt_args.add_argument("--expand_polytomies", dest="polytomies",
action = "store_true",
help="""expand politomies if necessary""")
opt_args.add_argument("--unrooted", dest="unrooted",
action = "store_true",
help="""compare trees as unrooted""")
opt_args.add_argument("--min_support", dest="min_support",
type=float, default=0.0,
help=("min support value for branches to be counted in the distance computation (RF, treeko and refTree/targeGene compatibility)"))
opt_args = parser.add_argument_group("PHYLOGENETICS OPTIONS")
opt_args.add_argument("--extract_species",
action = "store_true",
help="When used, leaf names in the reference and source trees are assumed to represent species."
" If target trees are gene-trees whose species information is encoded as a part of the leaf sequence name,"
" it can be automatically extracted by providing a Perl regular expression that extract a "
" valid species code (see --sp_regexp). Such information will be also used to detect duplication"
" events. ")
opt_args.add_argument("--sp_regexp",
type=str,
help=("Specifies a Perl regular expression to automatically extract species names"
" from the name string in source trees. If not used, leaf names are assumed to represent species names."
" Example: use this expression '[^_]+_(.+)' to extract HUMAN from the string 'P53_HUMAN'."))
opt_args.add_argument("--collateral",
action='store_true',
help=(""))
args = parser.parse_args(argv)
print __DESCRIPTION__
reftree = args.reftree
if args.source_file and args.source_trees:
print >>sys.stderr, 'The use of targets_file and targets at the same time is not supported.'
sys.exit(1)
if args.source_file:
source_trees = tree_iterator(args.source_file)
else:
source_trees = args.source_trees
ref_tree = Tree(reftree)
if args.ref_tree_attr:
for lf in ref_tree.iter_leaves():
lf._origname = lf.name
if args.ref_tree_attr not in lf.features:
print lf
lf.name = getattr(lf, args.ref_tree_attr)
if args.outgroup:
if len(args.outgroup) > 1:
out = ref_tree.get_common_ancestor(args.outgroup)
else:
out = ref_tree.search_nodes(name=args.outgroup[0])[0]
ref_tree.set_outgroup(out)
HEADER = ("source tree", 'ref tree', 'common\ntips', 'normRF', 'RF', 'maxRF', "%reftree", "%genetree", "subtrees", "treeko\ndist")
if args.output:
OUT = open(args.output, "w")
print >>OUT, '# ' + ctime()
print >>OUT, '# ' + ' '.join(sys.argv)
print >>OUT, '#'+'\t'.join(HEADER)
else:
print '# ' + ctime()
print '# ' + ' '.join(sys.argv)
COL_WIDTHS = [20, 20] + [9] * 10
print_table([HEADER], fix_col_width=COL_WIDTHS, wrap_style='wrap')
prev_tree = None
ref_fname = os.path.basename(args.reftree)
for counter, tfile in enumerate(source_trees):
if args.source_file:
seedid, tfile = tfile
else:
seedid = None
if args.extract_species:
if args.sp_regexp:
SPMATCHER = re.compile(args.sp_regexp)
get_sp_name = lambda x: re.search(SPMATCHER, x).groups()[0]
else:
get_sp_name = lambda x: x
tt = PhyloTree(tfile, sp_naming_function = get_sp_name)
else:
tt = Tree(tfile)
if args.src_tree_attr:
for lf in tt.iter_leaves():
lf._origname = lf.name
lf.name = getattr(lf, args.src_tree_attr)
if args.outgroup:
if len(args.outgroup) > 1:
out = tt.get_common_ancestor(args.outgroup)
else:
out = tt.search_nodes(name=args.outgroup[0])[0]
tt.set_outgroup(out)
if args.source_trees:
fname = os.path.basename(tfile)
else:
fname = '%05d' %counter
r = tt.compare(ref_tree,
ref_tree_attr=args.ref_tree_attr,
source_tree_attr=args.src_tree_attr,
min_support_ref=args.min_support_ref,
min_support_source = args.min_support_src,
unrooted=args.unrooted,
has_duplications=args.extract_species)
print_table([map(istr, [fname[-30:], ref_fname[-30:], r['effective_tree_size'], r['norm_rf'],
r['rf'], r['max_rf'], r["source_edges_in_ref"],
r["ref_edges_in_source"], r['source_subtrees'], r['treeko_dist']])],
fix_col_width = COL_WIDTHS, wrap_style='cut')
if args.output:
OUT.close()
import random
from ete_dev import Tree
# Creates a normal tree
t = Tree( '((H:0.3,I:0.1):0.5, A:1, (B:0.4,(C:0.5,(J:1.3, (F:1.2, D:0.1):0.5):0.5):0.5):0.5);' )
print t
# Let's locate some nodes using the get common ancestor method
ancestor=t.get_common_ancestor("J", "F", "C")
# the search_nodes method (I take only the first match )
A = t.search_nodes(name="A")[0]
# and using the shorcut to finding nodes by name
C= t&"C"
H= t&"H"
I= t&"I"
# Let's now add some custom features to our nodes. add_features can be
# used to add many features at the same time.
C.add_features(vowel=False, confidence=1.0)
A.add_features(vowel=True, confidence=0.5)
ancestor.add_features(nodetype="internal")
# Or, using the oneliner notation
(t&"H").add_features(vowel=False, confidence=0.2)
# But we can automatize this. (note that i will overwrite the previous
# values)
for leaf in t.traverse():
if leaf.name in "AEIOU":
leaf.add_features(vowel=True, confidence=random.random())
else:
leaf.add_features(vowel=False, confidence=random.random())
# Now we use these information to analyze the tree.
print "This tree has", len(t.search_nodes(vowel=True)), "vowel nodes"
print "Which are", [leaf.name for leaf in t.iter_leaves() if leaf.vowel==True]
# But features may refer to any kind of data, not only simple
# ---------| # | /-F # \--------| # \-G print "Tree3:", t3 # /-H # | # ---------| /-I # | /--------| # | | \-J # \--------| # | /-K # \--------| # \-L # Locates a terminal node in the first tree A = t1.search_nodes(name='A')[0] # and adds the two other trees as children. A.add_child(t2) A.add_child(t3) print "Resulting concatenated tree:", t1 # /-D # /--------| # | \-E # /--------| # | | /-F # | \--------| # /--------| \-G # | | # | | /-H # | | | # | \--------| /-I
from ete_dev import Tree
t = Tree( '(A:1,(B:1,(C:1,D:1):0.5):0.5);' )
# Browse the tree from a specific leaf to the root
node = t.search_nodes(name="C")[0]
while node:
print node
node = node.up
# --C
# /-C
# ---------|
# \-D
#
# /-B
# ---------|
# | /-C
# \--------|
# \-D
#
# /-A
# ---------|
# | /-B
# \--------|
# | /-C
# \--------|
# \-D
def main(argv):
parser = argparse.ArgumentParser(
description=__DESCRIPTION__,
formatter_class=argparse.RawDescriptionHelpFormatter)
input_args = parser.add_argument_group("INPUT OPTIONS")
input_args.add_argument("source_trees",
metavar='source_trees',
type=str,
nargs="*",
help='a list of source tree files')
input_args.add_argument(
"--source_file",
dest="source_file",
type=str,
help="""path to a file containing many source trees, one per line""")
input_args.add_argument("-r",
dest="reftree",
type=str,
required=True,
help="""Reference tree""")
input_args.add_argument("--ref_tree_attr",
dest="ref_tree_attr",
type=str,
default="name",
help=("attribute in ref tree used as leaf name"))
input_args.add_argument(
"--src_tree_attr",
dest="src_tree_attr",
type=str,
default="name",
help=("attribute in source tree used as leaf name"))
input_args.add_argument(
"--min_support_ref",
type=float,
default=0.0,
help=("min support for branches to be considered from the ref tree"))
input_args.add_argument(
"--min_support_src",
type=float,
default=0.0,
help=(
"min support for branches to be considered from the source tree"))
output_args = parser.add_argument_group("OUTPUT OPTIONS")
output_args.add_argument("-o",
dest="output",
type=str,
help="""Path to the tab delimited report file""")
opt_args = parser.add_argument_group("DISTANCE OPTIONS")
opt_args.add_argument(
"--outgroup",
dest="outgroup",
nargs="+",
help=
"""outgroup used to root reference and source trees before distance computation"""
)
opt_args.add_argument("--expand_polytomies",
dest="polytomies",
action="store_true",
help="""expand politomies if necessary""")
opt_args.add_argument("--unrooted",
dest="unrooted",
action="store_true",
help="""compare trees as unrooted""")
opt_args.add_argument(
"--min_support",
dest="min_support",
type=float,
default=0.0,
help=
("min support value for branches to be counted in the distance computation (RF, treeko and refTree/targeGene compatibility)"
))
opt_args = parser.add_argument_group("PHYLOGENETICS OPTIONS")
opt_args.add_argument(
"--extract_species",
action="store_true",
help=
"When used, leaf names in the reference and source trees are assumed to represent species."
" If target trees are gene-trees whose species information is encoded as a part of the leaf sequence name,"
" it can be automatically extracted by providing a Perl regular expression that extract a "
" valid species code (see --sp_regexp). Such information will be also used to detect duplication"
" events. ")
opt_args.add_argument(
"--sp_regexp",
type=str,
help=
("Specifies a Perl regular expression to automatically extract species names"
" from the name string in source trees. If not used, leaf names are assumed to represent species names."
" Example: use this expression '[^_]+_(.+)' to extract HUMAN from the string 'P53_HUMAN'."
))
opt_args.add_argument("--collateral", action='store_true', help=(""))
args = parser.parse_args(argv)
print __DESCRIPTION__
reftree = args.reftree
if args.source_file and args.source_trees:
print >> sys.stderr, 'The use of targets_file and targets at the same time is not supported.'
sys.exit(1)
if args.source_file:
source_trees = tree_iterator(args.source_file)
else:
source_trees = args.source_trees
ref_tree = Tree(reftree)
if args.ref_tree_attr:
for lf in ref_tree.iter_leaves():
lf._origname = lf.name
if args.ref_tree_attr not in lf.features:
print lf
lf.name = getattr(lf, args.ref_tree_attr)
if args.outgroup:
if len(args.outgroup) > 1:
out = ref_tree.get_common_ancestor(args.outgroup)
else:
out = ref_tree.search_nodes(name=args.outgroup[0])[0]
ref_tree.set_outgroup(out)
HEADER = ("source tree", 'ref tree', 'common\ntips', 'normRF', 'RF',
'maxRF', "%reftree", "%genetree", "subtrees", "treeko\ndist")
if args.output:
OUT = open(args.output, "w")
print >> OUT, '# ' + ctime()
print >> OUT, '# ' + ' '.join(sys.argv)
print >> OUT, '#' + '\t'.join(HEADER)
else:
print '# ' + ctime()
print '# ' + ' '.join(sys.argv)
COL_WIDTHS = [20, 20] + [9] * 10
print_table([HEADER], fix_col_width=COL_WIDTHS, wrap_style='wrap')
prev_tree = None
ref_fname = os.path.basename(args.reftree)
for counter, tfile in enumerate(source_trees):
if args.source_file:
seedid, tfile = tfile
else:
seedid = None
if args.extract_species:
if args.sp_regexp:
SPMATCHER = re.compile(args.sp_regexp)
get_sp_name = lambda x: re.search(SPMATCHER, x).groups()[0]
else:
get_sp_name = lambda x: x
tt = PhyloTree(tfile, sp_naming_function=get_sp_name)
else:
tt = Tree(tfile)
if args.src_tree_attr:
for lf in tt.iter_leaves():
lf._origname = lf.name
lf.name = getattr(lf, args.src_tree_attr)
if args.outgroup:
if len(args.outgroup) > 1:
out = tt.get_common_ancestor(args.outgroup)
else:
out = tt.search_nodes(name=args.outgroup[0])[0]
tt.set_outgroup(out)
if args.source_trees:
fname = os.path.basename(tfile)
else:
fname = '%05d' % counter
r = tt.compare(ref_tree,
ref_tree_attr=args.ref_tree_attr,
source_tree_attr=args.src_tree_attr,
min_support_ref=args.min_support_ref,
min_support_source=args.min_support_src,
unrooted=args.unrooted,
has_duplications=args.extract_species)
print_table([
map(istr, [
fname[-30:], ref_fname[-30:], r['effective_tree_size'],
r['norm_rf'], r['rf'], r['max_rf'], r["source_edges_in_ref"],
r["ref_edges_in_source"], r['source_subtrees'],
r['treeko_dist']
])
],
fix_col_width=COL_WIDTHS,
wrap_style='cut')
if args.output:
OUT.close()
from ete_dev import Tree
t = Tree('(A:1,(B:1,(C:1,D:1):0.5):0.5);')
# Browse the tree from a specific leaf to the root
node = t.search_nodes(name="C")[0]
while node:
print node
node = node.up
# --C
# /-C
# ---------|
# \-D
#
# /-B
# ---------|
# | /-C
# \--------|
# \-D
#
# /-A
# ---------|
# | /-B
# \--------|
# | /-C
# \--------|
# \-D
from ete_dev import Tree #Loads a tree t = Tree( '((H:1,I:1):0.5, A:1, (B:1,(C:1,D:1):0.5):0.5);' ) print t # /-H # /--------| # | \-I # | #---------|--A # | # | /-B # \--------| # | /-C # \--------| # \-D # I get D D = t.search_nodes(name="D") # I get all nodes with distance=0.5 nodes = t.search_nodes(dist=0.5) print len(nodes), "nodes have distance=0.5"
from ete_dev import Tree
#Loads a tree
t = Tree('((H:1,I:1):0.5, A:1, (B:1,(C:1,D:1):0.5):0.5);')
print t
# /-H
# /--------|
# | \-I
# |
#---------|--A
# |
# | /-B
# \--------|
# | /-C
# \--------|
# \-D
# I get D
D = t.search_nodes(name="D")
# I get all nodes with distance=0.5
nodes = t.search_nodes(dist=0.5)
print len(nodes), "nodes have distance=0.5"
def get_rooting(tol, seed_species, agename = False):
'''
returns dict of species age for a given TOL and a given seed
**Example:**
::
tol = "((((((((Drosophila melanogaster,(Drosophila simulans,Drosophila secchellia)),(Drosophila yakuba,Drosophila erecta))[&&NHX:name=melanogaster subgroup],Drosophila ananassae)[&&NHX:name=melanogaster group],(Drosophila pseudoobscura,Drosophila persimilis)[&&NHX:name=obscura group])[&&NHX:name=Sophophora Old World],Drosophila willistoni)[&&NHX:name=subgenus Sophophora],(Drosophila grimshawi,(Drosophila virilis,Drosophila mojavensis))[&&NHX:name=subgenus Drosophila])[&&NHX:name=genus Drosophila],(Anopheles gambiae,Aedes aegypti)[&&NHX:name=Culicidae])[&&NHX:name=Arthropoda],Caenorhabditis elegans)[&&NHX:name=Animalia];"
seed = "Drosophila melanogaster"
ROOTING, age2name = get_rooting (tol, seed, True)
ROOTING == {"Aedes aegypti" : 7,
"Anopheles gambiae" : 7,
"Caenorhabditis elegans" : 8,
"Drosophila ananassae" : 3,
"Drosophila erecta" : 2,
"Drosophila grimshawi" : 6,
"Drosophila melanogaster" : 1,
"Drosophila mojavensis" : 6,
"Drosophila persimilis" : 4,
"Drosophila pseudoobscura": 4,
"Drosophila secchellia" : 1,
"Drosophila simulans" : 1,
"Drosophila virilis" : 6,
"Drosophila willistoni" : 5,
"Drosophila yakuba" : 2}
age2name == {1: "Drosophila melanogaster. Drosophila simulans. Drosophila secchellia",
2: "melanogaster subgroup",
3: "melanogaster group",
4: "Sophophora Old World",
5: "subgenus Sophophora",
6: "genus Drosophila",
7: "Arthropoda",
8: "Animalia"}
:argument seed_species: species name
:argument False agename: if True, also returns the inverse dictionary
:returns: ROOTING dictionary with age of each species
'''
tol = Tree (tol)
try:
node = tol.search_nodes (name=seed_species)[0]
except IndexError:
exit ('ERROR: Seed species not found in tree\n')
age = 1
ROOTING = {}
if agename:
age2name = {}
while not node.is_root():
node = node.up
for leaf in node.get_leaf_names():
if agename:
if node.name == 'NoName':
nam = '.'.join (node.get_leaf_names())
else:
nam = node.name
age2name.setdefault (age, nam)
ROOTING.setdefault (leaf, age)
age += 1
if agename:
return ROOTING, age2name
return ROOTING
# /A-------| \G-------| # | | \-I # | | # | \-E #-NoName--| # | /-L # | /J-------| # | | | /-N # | | \O-------| # \C-------| \-Q # | # | /-P # \M-------| # \-S # Get pointers to specific nodes G = t.search_nodes(name="G")[0] J = t.search_nodes(name="J")[0] C = t.search_nodes(name="C")[0] # If we remove J from the tree, the whole partition under J node will # be detached from the tree and it will be considered an independent # tree. We can do the same thing using two approaches: J.detach() or # C.remove_child(J) removed_node = J.detach() # = C.remove_child(J) # if we know print the original tree, we will see how J partition is # no longer there. print "Tree after REMOVING the node J" print t.get_ascii(show_internal=True) # /-H # /D-------| # | \-K # /B-------|
