def get_sum_of_branches(treepath):
fin = open(treepath, "r")
newick = fin.readline().strip()
t = Tree()
t.read_from_string(newick.__str__(), "newick")
fin.close()
return t.length()
def __init__(self, **kwargs):
'''
Parameters
----------
reference_tree_path: str
Path to the file containing the reference tree, which is used to
retroot the tree tree provided to tree
tree_path: str
Path to the file containing the tree to be re-rooted. This tree will
be rerooted at the same position as the tree porovided to the
reference_tree
'''
reference_tree_path = kwargs.pop('reference_tree_path', None)
tree_path = kwargs.pop('tree_path')
logging.debug("Importing old tree from file: %s"
% tree_path)
self.tree = Tree.get(path=tree_path,
schema='newick')
if reference_tree_path:
logging.debug("Importing reference tree from file: %s"
% reference_tree_path)
self.reference_tree = Tree.get(path=reference_tree_path,
schema='newick')
else:
self.reference_tree = reference_tree_path
if len(kwargs) > 0:
raise Exception("Unexpected arguments provided to Decorator class: %s" % kwargs)
def __bisect__(t,e):
# e = __find_centroid_edge__(t)
u = e.tail_node
v = e.head_node
u.remove_child(v)
t1 = Tree(seed_node = v)
if u.num_child_nodes() == 1:
p = u.parent_node
v = u.child_nodes()[0]
l_v = v.edge_length
u.remove_child(v)
if p is None: # u is the seed_node; this means the tree runs out of all but one side
t.seed_node = v
return t,t1
l_u = u.edge_length
p.remove_child(u)
p.add_child(v)
v.edge_length = l_u+l_v
u = p
while u is not None:
__updateNode__(u)
u = u.parent_node
t.annotated = True
t1.annotated = True
return t,t1
def generate_ATT_from_files(seqaln,
mattype,
workdir,
treefile,
otu_json,
ingroup_mrca=None):
"""Build an ATT object without phylesystem.
If no ingroup mrca ott_id is provided, will use all taxa in tree to calc mrca."""
aln = DnaCharacterMatrix.get(path=seqaln, schema=mattype)
for tax in aln.taxon_namespace:
tax.label = tax.label.replace(" ", "_") #Forcing all spaces to underscore UGH
tre = Tree.get(path=treefile,
schema="newick",
preserve_underscores=True,
taxon_namespace=aln.taxon_namespace)
with open(otu_json) as data_file:
otu_dict = json.load(data_file)
for tax in aln:
assert tax.label in otu_dict
tre = Tree.get(path=treefile,
schema="newick",
preserve_underscores=True,
taxon_namespace=aln.taxon_namespace)
otu_newick = tre.as_string(schema="newick")
if ingroup_mrca:
ott_mrca = int(ingroup_mrca)
else:
ott_ids = [otu_dict[otu].get['^ot:ottId'] for otu in otu_dict]
ott_mrca = get_mrca_ott(ott_ids)
return AlignTreeTax(otu_newick, otu_dict, aln, ingroup_mrca=ott_mrca, workdir=workdir)
def get_subtree(self, taxa):
if len(taxa) == 0:
return None
tree = Tree(self._tree)
if isinstance(taxa[0],str):
tree.prune_taxa_with_labels(taxa)
elif isinstance(taxa[0],Taxon):
tree.prune_taxa(taxa)
return PhylogeneticTree(tree)
def scale_tree_branch(tree, format="newick"):
tree_obj = None
if os.path.exists(tree):
tree_obj = Tree.get_from_path(tree, format)
elif isinstance(tree, str):
tree_obj = Tree(stream=StringIO(tree), schema=format)
elif isinstance(tree, Tree):
tree_obj = Tree
if sum([ e.length > 1 for e in tree_obj.postorder_edge_iter()]):
for e in tree_obj.postorder_edge_iter():
if e.length is not None:
e.length = e.length/100
return tree_obj.as_newick_string()
def test_bootstraps_in_annotated_tree_alongside_empty_taxa(self):
self.assertEquals({u'a': [],
u'b': [],
u'c': ['tax'],
u'd': ['tax']},
TaxonomyExtractor().taxonomy_from_annotated_tree(\
Tree.get(data="(a,(b,(c,d:0.2)'0.2:tax')0.01973:0.9)root;", schema='newick')))
def __init__(self, workDir, resultsFile, inFile, coreId, seqType, seedNum, bootNum, method, interLeaved):
'''
Data Fields:
work_dir = temproray directory
inFile = data file,
id = core id (int),
seqType = d (dna); p (protein); r (rna),
bootNum = number of replicates,
seedNum = Random number seed between 1 and 32767
method =b (Bootstrap) Default,
j (Jackknife)
c (Permute species for each character)
o (Permute character order)
s (Permute within species)
r (Rewrite data)),
interLeaved=True if sequence data is interleaved otherwise False
'''
self.work_dir = workDir
self.resultsFile = resultsFile
self.inFile = inFile
self.coreId = coreId
self.seqType = seqType
self.seedNum = seedNum
self.bootNum = bootNum
self.method = method
self.n = bootNum
self.nt = False
self.interLeaved = interLeaved
self.outFile = "bootstrap_"+str(coreId)+".out"
self.newSpeciesTree = Tree()
self.leafLabelStree = []
self.internalExRootSpeceLabels= []
if self.seqType in ['r', 'd']:
self.nt = True
def readTreeFromFile( treePath):
'''
input: path to the file containing newick tree
return Tree object
'''
myTree= Tree.get_from_path(treePath, 'newick', annotations_as_nhx=True, extract_comment_metadata=True , suppress_annotations=False)
return myTree
def get_bls(tree_path):
# clean the tree of any support values, so we're left only with BLs
bls = []
t = Tree()
t.read_from_path( tree_path, "newick" )
i = t.level_order_edge_iter()
while True:
try:
e = i.next() # in Python 2.x
len = e.length
if len != None:
bls.append( len )
except StopIteration:
break
return bls
def main():
cpu = sys.argv[1]
job_name = sys.argv[2]
try:
alnfile = sys.argv[3]
except:
assert(restart is True), "Specified alignment file does not exist. Path?"
try:
treefile = sys.argv[4]
except:
assert(restart is True), "Specified tree file does not exist. Path?"
# Rewrite tree to create trifurcating root, as needed by phylobayes mpi
tree = Tree.get_from_path(treefile, "newick", rooting = "force-unrooted")
tree.resolve_polytomies() # in case of polytomies.
tree.update_bipartitions() # this will create a trifurcating root on an unrooted tree
tstring = str(tree).replace('[&U] ', '')
with open('temp.tre', 'w') as tf:
tf.write(tstring + ';\n')
# Phylobayes is run to chain length 5500, sampling every 5 to yield 1100. Later, burnin of 100 is removed to get a final posterior n=1000 (same procedure as Rodrigue 2013 Genetics)
pb_call = "mpirun -np " + str(cpu) + " ./pb_mpi -mutsel -cat -d " + alnfile + " -T temp.tre -x 5 1100 " + job_name
run_pb_call = subprocess.call(pb_call, shell = True)
assert( run_pb_call == 0 ), "pb_mpi didn't run!"
# Parse output with readpb_mpi, using a burnin of 100 and saving everything else (posterior size = 1000)
readpb_call = "mpirun -np " + str(cpu) + " ./readpb_mpi -x 100 1 -1 " + job_name + "\n"
run_readpb_call = subprocess.call(readpb_call, shell = True)
assert( run_readpb_call == 0 ), "readpb_mpi didn't run!"
def get_tree_lines(Tname): stringlist =[] from dendropy import Tree tree = Tree.get_from_path(Tname,"newick") for nd in tree.postorder_internal_node_iter(): for child in nd.child_nodes(): stringlist.append(child.as_newick_string()) return (stringlist)
def ete_to_dendropy(tree):
from dendropy import Tree as DTree
char_matrix = ete_to_dendropy_cm(tree)
taxon_namespace = char_matrix.taxon_namespace
dendro_tree = DTree.get(data=tree.write(format=1),
schema='newick',
taxon_namespace=taxon_namespace)
return dendro_tree, char_matrix
def bipartition_by_edge(self, e):
"""Prunes the subtree that attached to the head_node of edge e and returns them as a separate tree."""
t = self._tree
nr = e.head_node
assert e.tail_node is not None
assert e.head_node is not None
assert nr.parent_node is e.tail_node
is_valid_tree(t)
n = self.n_leaves
potentially_deleted_nd = e.tail_node
grandparent_nd = potentially_deleted_nd.parent_node
e.tail_node.remove_child(nr, suppress_unifurcations=True)
nr.edge.length = None
nr.parent_node = None
convert_node_to_root_polytomy(nr)
t1 = PhylogeneticTree(Tree(seed_node=nr))
n1 = t1.n_leaves # temp we could speed this up, by telling the Phylogenetic tree how many leaves it has
if hasattr(e, "num_leaves_below"):
if grandparent_nd is None:
old_root = potentially_deleted_nd
if old_root.edge:
old_root.edge.num_leaves_below -= n1
else:
if potentially_deleted_nd in grandparent_nd.child_nodes():
potentially_deleted_nd.edge.num_leaves_below -= n1
old_root = grandparent_nd
if old_root.edge:
old_root.edge.num_leaves_below -= n1
while old_root.parent_node:
old_root = old_root.parent_node
if old_root.edge:
old_root.edge.num_leaves_below -= n1
else:
old_root = grandparent_nd or potentially_deleted_nd
while old_root.parent_node:
old_root = old_root.parent_node
t2 = PhylogeneticTree(Tree(seed_node=old_root))
is_valid_tree(t1._tree)
is_valid_tree(t2._tree)
return t1, t2
def readTreeFromString(self, treeString):
'''
input: string containing newick tree
return Tree object
'''
myTree= Tree()
myTree= Tree.get_from_string( treeString, 'newick', annotations_as_nhx=True, extract_comment_metadata=True , suppress_annotations=False)
return myTree
def remove_internal_labels(strtree):
tree = Tree.get_from_string(strtree, schema='newick')
for node in tree.postorder_node_iter():
if not node.label is None:
if (int(node.label) >= tips_number):
node.label = None
return tree.as_string(schema="newick")
def read_lsd_results(inputDir):
# suppose LSD was run on the "mytree.newick" and all the outputs are placed inside inputDir
log_file = normpath(join(inputDir, "mytree.tre.result"))
input_tree_file = normpath(join(inputDir, "mytree.tre"))
result_tree_file = normpath(join(inputDir, "mytree.tre.result.newick"))
s = open(log_file,'r').read()
i = s.find("Tree 1 rate ") + 12
mu = ""
found_dot = False
while (s[i] == '.' and not found_dot) or (s[i] in [str(x) for x in range(10)]):
mu += s[i]
if s[i] == '.':
found_dot = True
i += 1
mu = float(mu)
taxa = TaxonNamespace()
tree = Tree.get_from_path(input_tree_file,schema="newick",taxon_namespace=taxa,rooting="force-rooted")
tree.encode_bipartitions()
n = len(list(tree.leaf_node_iter()))
N = 2*n-2
x0 = [10**-10]*N + [mu]
idx = 0
brlen_map = {}
for node in tree.postorder_node_iter():
if not node is tree.seed_node:
key = node.bipartition
brlen_map[key] = (idx,node.edge_length)
idx += 1
tree2 = Tree.get_from_path(result_tree_file,schema="newick",taxon_namespace=taxa,rooting="force-rooted")
tree2.encode_bipartitions()
for node in tree2.postorder_node_iter():
if not node is tree2.seed_node:
key = node.bipartition
idx,el = brlen_map[key]
if el > 0 and node.edge_length>0:
x0[idx] = node.edge_length/float(el)
return x0
def test_branch_lengths(self):
'''https://github.com/geronimp/graftM/issues/192'''
taxes = TaxonomyExtractor().taxonomy_from_annotated_tree(
Tree.get(path=os.path.join(path_to_data, 'create', 'sulfitereductase.ben.tree'), schema='newick'))
self.assertEquals([u'Aanerobic sulfite reductase asrC',
u'Anaerobic sulfite reductase asrC Group 3',
u'Unknown alpha and beta subunits',
u'0.856_PFAM_NIR_SIR,NIR_SIR_ferr'], # number is actually in the clade name
taxes['T506DRAFT_scaffold00010.10_60~2561511230'])
def index_mutations(con):
"""Builds an index of all mutations"""
cur = con.cursor()
for msaid in get_alignment_method_ids(con):
for modelid in get_phylo_modelids(con):
newick = get_anc_cladogram(con, msaid, modelid)
t = Tree()
t.read_from_string(newick, "newick")
for edge in t.preorder_edge_iter():
if edge.head_node == None or edge.tail_node == None:
continue
if edge.head_node.label == None or edge.tail_node.label == None:
continue
print msaid, modelid, edge.head_node.label, edge.tail_node.label
anc1name = "Node" + edge.head_node.label.__str__()
anc2name = "Node" + edge.tail_node.label.__str__()
index_mutations_helper(con, msaid, modelid, anc1name, anc2name)
def test_remove_sequences_with_named_internal_nodes(self):
tc = DendropyTreeCleaner()
tree = Tree.get(data="('Asulf_Archaeoglobus.1_2280~2522125074':7.17,(('Afulgi_764~2528311132':0.0,'CP006577_764~2588253768':0.0):0.0,'AE000782_746~638154502':0.0)'s__Archaeoglobus fulgidus':7.555):1.461;\n",
schema='newick')
tc.remove_sequences(tree,
['CP006577_764~2588253768',
'Afulgi_764~2528311132'])
self.assertEqual("(Asulf_Archaeoglobus.1_2280~2522125074:7.17,AE000782_746~638154502:7.555):1.461",
str(tree))
def check_list_against_tree(treepath, checklist):
'''take a path to a newick tree file and look for any taxa that correspond to keys in the "keep" dictionary,
incrementing the value of each one found'''
with open(treepath, 'r', encoding='UTF-8') as treefile:
check_list_against_taxa(
Tree.get_from_stream(treefile,
schema="newick",
preserve_underscores=True,
rooting='default-rooted'), checklist)
def test_yule(script_runner, execution_number, datadir):
backbone = os.path.join(datadir, "stem2.backbone.tre")
taxonomy = os.path.join(datadir, "stem2.taxonomy.tre")
taxed = Tree.get(path=taxonomy, schema="newick")
bbone = Tree.get(path=backbone, schema="newick", rooting="default-rooted")
result = script_runner.run("tact_add_taxa", "--taxonomy", taxonomy,
"--backbone", backbone, "--output",
".tact-pytest-yule", "-vv", "--yule")
assert result.returncode == 0
output = ".tact-pytest-yule.newick.tre"
tacted = Tree.get(path=output, schema="newick", rooting="default-rooted")
ss = tacted.as_ascii_plot()
sys.stderr.write(ss)
result = script_runner.run("tact_check_results", output, "--taxonomy",
taxonomy, "--backbone", backbone, "--output",
".tact-pytest-yule.check.csv", "--cores=1")
assert result.returncode == 0
return (tacted, taxed, bbone)
def tree_compare(tempdir):
# CHANGE to tempdir
tns = dendropy.TaxonNamespace()
tree1 = Tree.get_from_path(tempdir + "/ref.tree",
"newick",
taxon_namespace=tns)
tree2 = Tree.get_from_path(tempdir + "/normal_tree",
"newick",
taxon_namespace=tns)
tree3 = Tree.get_from_path(tempdir + "/red_tree",
"newick",
taxon_namespace=tns)
tree1.encode_bipartitions()
tree2.encode_bipartitions()
tree3.encode_bipartitions()
distance_normal = treecompare.symmetric_difference(tree1, tree2)
distance_reduced = treecompare.symmetric_difference(tree1, tree3)
return distance_normal, distance_reduced
def scale_tree(f_name, n):
t = Tree.get(file=open(f_name, 'r'), schema="newick", tree_offset=0)
for e in t.edges():
if e.length is not None:
e.length = float(n*float(e.length))
t.write(file=open(f_name.replace('.mt', '') + '_' + str(n).replace('.', '_') + '.mt', 'w+'), schema="newick")
def remove_branch_lengths(f, out):
t = Tree.get(file=open(f, 'r'), schema="newick")
new = open(out, 'w+')
for e in t.edges():
e.length = None
t.write(file=new, schema="newick")
def get_tree_and_OTT_list(tree_filehandle, sources, verbosity=0):
"""
Takes a base tree and creates objects for each node and leaf, attaching them as 'data' dictionaries
to each node in the DendroPy tree. Nodes and leaves with an OTT id also have pointers to their data
dicts stored in an OTT-keyed dict, so that mappings to other databases (ncbi id, etc etc) can be created.
We can easily have duplicate leaf names, so for the entire procedure we ignore the Dendropy concept
of a taxon list and simply use labels.
Returns the Dendropy tree and the OTT dict.
"""
#these variables are all pointers into the same data
ordered_leaves=[]
ordered_nodes=[]
indexed_by_ott={}
try:
tree = Tree.get_from_stream(tree_filehandle, schema="newick", preserve_underscores=True, suppress_leaf_node_taxa=True)
except:
sys.exit("Problem reading tree from " + treefile.name)
info("-> read tree from " + tree_filehandle.name)
ott_node = re.compile(r"(.*) ott(\d+)(@\d*)?$") #matches the OTT number
mrca_ott_node = re.compile(r"(.*) (mrcaott\d+ott\d+)(@\d*)?$") #matches a node with an "mrca" node number (no unique OTT)
for i, node in enumerate(tree.preorder_node_iter()):
node.data = {'parent':node.parent_node or None}
if node.label:
node.label = node.label.replace("_"," ")
m = ott_node.search(node.label)
if m is not None:
if m.group(3):
warn("Node has an @ sign at the end ({}), meaning it has probably not been substituted by an OpenTree equivalent. You may want to provide an alternative subtree from this node downwards, as otherwise it will probably be deleted from the main tree.".format(node.label))
node.label = m.group(1)
node.data['ott'] = int(m.group(2))
indexed_by_ott[node.data['ott']] = node.data
node.data['sources']={k:None for k in sources}
else:
m = mrca_ott_node.search(node.label)
if m is not None:
if m.group(3):
warn("Node has an @ sign at the end ({}), meaning it has probably not been substituted by an OpenTree equivalent. You may want to provide an alternative subtree from this node downwards, as otherwise it will probably be deleted from the main tree.".format(node.label))
node.label = m.group(1)
#this is an 'mrca' node, so we want to save sources but *not* save the ott number in node.data
indexed_by_ott[m.group(2)] = node.data
node.data['sources']={k:None for k in sources}
elif node.is_leaf():
warn("Leaf without an OTT id: '{}'. This will not be associated with any other data".format(node.label))
#finally, put underscores at the start or the end of the new label back
#as these denote "fake" names that are hidden and only used for mapping
#we could keep them as spaces, but leading/trailing underscores are easier to see by eye
if node.label[0]==" ":
node.label = "_" + node.label[1:]
if node.label[-1]==" ":
node.label = node.label[:-1] + "_"
info("-> extracted {} otts from among {} leaves and nodes".format(len(indexed_by_ott), i))
return tree, indexed_by_ott
def main():
d1 = sys.argv[1]
d2 = sys.argv[2]
d1_name = basename(d1)
d2_name = basename(d2)
print('og {} {}'.format(d1_name, d2_name))
d1_files = list(sorted(glob(join(d1, '*', 'RAxML_bipartitions.bipart'))))
d2_files = list(sorted(glob(join(d2, '*', 'RAxML_bipartitions.bipart'))))
assert len(d1_files) == len(d2_files)
for fn1, fn2 in zip(d1_files, d2_files):
t1 = Tree.get(path=fn1, schema='newick')
t2 = Tree.get(path=fn2, schema='newick')
assert tostr(t1) == tostr(t2)
t1_og = basename(dirname(fn1))
t2_og = basename(dirname(fn2))
assert t1_og == t2_og
labs = zip(get_node_labels(t1), get_node_labels(t2))
for l1, l2 in labs:
print(t1_og, l1, l2)
def evaluate(ref, file_name):
# To store the data during the process, we create two temporary files.
tmp1 = tempfile.mkstemp()
tmp2 = tempfile.mkstemp()
# Use the commands of fastprot and fnj.
# The output of the FastPhylo programs is in file 'tmp2'.
os.system("fastprot -m -o " + tmp1[1] + " " + file_name)
os.system("fnj -O newick -m FNJ -o " + tmp2[1] + " " + tmp1[1])
#Use Dendropy to compare the trees.
in_tree = Tree.get_from_stream(os.fdopen(tmp2[0]),
schema='newick',
taxon_namespace=tns)
ref_tree = Tree.get_from_path(ref, schema='newick', taxon_namespace=tns)
sym_diff = treecompare.symmetric_difference(ref_tree, in_tree)
return sym_diff
def test_ben_bug(self):
new_tree_newick = '(646366661:0.00571,(646777089:0.01427,(2556226606:0.0,2517129521:0.0):0.04312)0.377:0.01170,((650856936:0.01153,(((((646367708:0.01465,(638201361:0.00187,646622935:0.00573)0.940:0.01352)0.988:0.02634,(2519841469:0.06952,(650856136:0.01840,2506713669:0.02486)0.774:0.00888)0.893:0.01193)0.981:0.03778,((649738338:0.07504,(638155665:0.00613,648151945:0.00304)0.995:0.05973)0.884:0.02836,((650752390:0.11644,(2516847065:0.01707,2520801411:0.03442)0.993:0.04619)0.940:0.03278,(640592705:0.14347,637846211:0.11851)0.971:0.04593)0.940:0.03067)0.943:0.03401)0.998:0.06483,(638168675:0.17080,((649738388:0.09935,((((2540854716:0.00325,2553937573:0.00406)1.000:0.09930,(646533023:0.09868,640592823:0.06908)0.951:0.03770)1.000:0.07636,(650872422:0.05527,(650750471:0.05106,(2516847513:0.01440,2520803234:0.02517)0.998:0.05067)0.947:0.03589)0.074:0.01784)0.786:0.03804,(638155700:0.00445,648151981:0.00284)0.894:0.02131)0.995:0.08448)0.999:0.10690,((KYC55281.1:0.28954,(2540666849:0.26647,(2555938320:0.04589,2518907621:0.04631)0.970:0.05624)1.000:0.12340)0.993:0.09723,(((2515321874:0.26529,((637699780:0.01317,(2540563143:0.01361,(638165755:0.01099,638179449:0.01674)0.558:0.00611)0.964:0.01965)1.000:0.10518,(2502870849:0.06989,(648055573:0.14431,(646706666:0.11338,(637960147:0.03570,(2509663319:0.04930,(2519472088:0.03452,2515107634:0.07709)0.639:0.02134)0.957:0.03004)0.316:0.01755)0.809:0.02055)0.323:0.01213)0.991:0.07286)0.974:0.06071)0.997:0.09000,(650797088:0.06590,(639699575:0.03533,2512008957:0.12951)0.779:0.03900)1.000:0.21062)0.685:0.04985,((((640867801:0.08102,(2507462304:0.07476,(643570914:0.08474,((637897753:0.11959,((2509037835:0.14386,(648194984:0.08665,(648195418:0.04239,2506476786:0.04237)0.993:0.03477)0.668:0.01876)0.510:0.00983,((((640115295:0.06428,2540643958:0.01655)1.000:0.05043,2540643737:0.02645)0.502:0.01269,640115052:0.02482)0.987:0.04272,(2507147269:0.04181,2507146024:0.06962)0.615:0.01449)0.611:0.01456)0.992:0.03807)0.542:0.02193,((2525334810:0.02116,640099739:0.01544)0.785:0.00549,(640100248:0.00446,2525335778:0.02444)0.750:0.00227)1.000:0.12583)0.944:0.03489)0.962:0.04171)0.986:0.04499)0.793:0.02738,2509039570:0.05560)1.000:0.18840,(2505968448:0.05750,(2505971857:0.03133,2512783668:0.02305)0.185:0.01848)0.998:0.08344)0.875:0.04885,2518787893:0.16350)0.868:0.04436)1.000:0.14016)0.957:0.05998)0.998:0.08120)0.984:0.05479)0.999:0.07664,(2506713165:0.01408,((650917784:0.03595,640788680:0.07226)0.510:0.02178,(2519842728:0.03972,(646859549:0.04217,(2511672461:0.01672,(640786544:0.03901,(640793336:0.00334,(640165512:0.02037,641283602:0.00189)0.147:0.00210)0.175:0.00497)0.641:0.01093)0.991:0.02914)1.000:0.05940)0.323:0.02509)0.977:0.02843)0.960:0.02127)0.499:0.01743)0.998:0.03986,(638202197:0.00190,(644970377:0.01516,646623830:0.00752)0.678:0.00364)0.903:0.00939)0.626:0.01605);'
old_tree_newick = '(((((646366661:0.00564,((2517129521:0,2556226606:0):0.04302,646777089:0.01412)0.499:0.01173)0.999:0.07494,(638202197:0.0019,(644970377:0.01507,646623830:0.0075)0.738:0.00362)0.872:0.00931)0.635:0.01598,650856936:0.01308)0.995:0.04,(2506713165:0.01171,((640788680:0.07255,650917784:0.03571)0.466:0.02189,(2519842728:0.03945,(646859549:0.04217,(2511672461:0.01668,(640786544:0.03894,(640793336:0.00335,(640165512:0.02038,641283602:0.0019)0.155:0.00211)0.174:0.00496)0.668:0.01095)0.987:0.02908)1.000:0.05973)0.285:0.02499)0.985:0.02844)0.967:0.02183)0.668:0.01914,(((646367708:0.01473,(638201361:0.00188,646622935:0.00578)0.947:0.01381)0.981:0.02381,(2519841469:0.06809,(650856136:0.0182,2506713669:0.02508)0.727:0.0089)0.915:0.01182)0.971:0.03729,((649738338:0.07412,(648151945:0.00339,638155665:0.00581)0.999:0.05834)0.847:0.02714,((650752390:0.11368,(2516847065:0.01707,2520801411:0.03449)0.997:0.04731)0.943:0.033,(640592705:0.14071,637846211:0.11886)0.974:0.04714)0.907:0.02899)0.938:0.03341)0.999:0.06584,(638168675:0.16751,((649738388:0.09339,((((2540854716:0.00327,2553937573:0.00411)1.000:0.1001,(640592823:0.06966,646533023:0.10017)0.945:0.03786)0.999:0.07732,(650872422:0.0565,(650750471:0.05131,(2516847513:0.01447,2520803234:0.02528)0.998:0.05086)0.932:0.03598)0.014:0.01864)0.823:0.03947,(648151981:0.00285,638155700:0.0045)0.891:0.01979)0.998:0.08667)0.999:0.11839,((2540666849:0.25749,(2518907621:0.04615,2555938320:0.04332)0.979:0.0624)1.000:0.20869,(((2515321874:0.27886,((637699780:0.01253,(2540563143:0.01408,(638165755:0.01119,638179449:0.01933)0.559:0.0062)0.973:0.01906)1.000:0.10181,(((2509663319:0.05476,(2515107634:0.07727,2519472088:0.03736)0.549:0.02018)0.970:0.02691,(637960147:0.03454,646706666:0.12022)0.328:0.01393)0.935:0.02456,(2502870849:0.07124,648055573:0.13944)0.419:0.01578)0.997:0.07265)0.976:0.05902)0.992:0.09155,(650797088:0.06773,(639699575:0.03844,2512008957:0.12921)0.700:0.03684)1.000:0.19382)0.774:0.0559,((2518787893:0.1617,(2512783668:0.01562,(2505971857:0.02991,2505968448:0.06931)0.820:0.01544)1.000:0.10132)0.000:0.03917,((640867801:0.07687,(2507462304:0.07769,(((637897753:0.11989,((2509037835:0.14075,(648194984:0.08661,(648195418:0.04254,2506476786:0.04232)0.986:0.0348)0.722:0.0191)0.553:0.00998,((((640115295:0.06424,2540643958:0.01643)1.000:0.05042,2540643737:0.02653)0.542:0.01245,640115052:0.0251)0.986:0.04265,(2507146024:0.06963,2507147269:0.0417)0.641:0.01435)0.611:0.01449)0.989:0.03824)0.424:0.02187,((640099739:0.01547,2525334810:0.02122)0.833:0.00545,(640100248:0.00445,2525335778:0.02442)0.761:0.0023)1.000:0.12528)0.944:0.03961,643570914:0.0938)0.959:0.03885)0.984:0.04627)0.758:0.02972,2509039570:0.05614)1.000:0.19872)0.185:0.04422)0.999:0.13795)0.646:0.06267)0.977:0.07517)0.979:0.05715);'
old_tree = Tree.get(schema='newick', data=old_tree_newick)
tree_to_reroot = Tree.get(schema='newick', data=new_tree_newick)
r = Rerooter()
reann = Reannotator()
new_tree = r.reroot_by_tree(
r.reroot(old_tree),
r.reroot(tree_to_reroot))
expected_lefts = old_tree.seed_node.child_nodes()[0].leaf_nodes()
expected_rights = old_tree.seed_node.child_nodes()[1].leaf_nodes()
for tip in expected_lefts:
self.assertTrue(tip.taxon.label in [t.taxon.label for t in new_tree.seed_node.child_nodes()[1].leaf_nodes()])
for tip in expected_rights:
self.assertTrue(tip.taxon.label in [t.taxon.label for t in new_tree.seed_node.child_nodes()[0].leaf_nodes()])
self.assertEqual(len(tree_to_reroot.leaf_nodes()), len(new_tree.leaf_nodes()))
def return_trees_from_trace(path):
print "Parsing trace:", path
trees = []
lnls = []
fin = open(path, "r")
last_tree = None
last_lnl = 0.0
count_unique_trees = 0
for line in fin.xreadlines():
treestring = ""
lnlstring = ""
found_tree = False
for c in line:
if found_tree == False and c != "]" and c != "[" and c != "(":
lnlstring += c
if c == "(":
found_tree = True
if found_tree == True:
treestring += c
lnl = float(lnlstring)
t = Tree()
t.read_from_string(line, "newick")
if last_tree != None: #2nd->nth trees in the list
#sd = last_tree.symmetric_difference(t)
#sd = t.symmetric_difference(last_tree)
if last_lnl < lnl:
trees.append(t)
lnls.append("%.2f"%lnl)
count_unique_trees += 1
else:
trees[trees.__len__()-1] = t
lnls[lnls.__len__()-1] = "%.2f"%lnl
else: #first tree in the list
trees.append(t)
lnls.append("%.2f"%lnl)
count_unique_trees += 1
last_tree = t
last_lnl = lnl
print count_unique_trees, lnl
trees.append(last_tree)
lnls.append("%.2f"%lnl)
fin.close()
return [trees, lnls]
def __init__(self,ddpTree=None,tree_file=None,schema="newick",Tree_records=[]): if tree_file: self.ddpTree = Tree.get_from_path(tree_file,schema) else: #self.ddpTree = copy.deepcopy(ddpTree) self.ddpTree = ddpTree self.Tree_records = Tree_records self.opt_score = None self.opt_root = self.ddpTree.seed_node self.opt_x = 0
def assert_tree_equal_no_labels_deprecated(self, expected_newick, observed_tree):
expected = Tree.get(schema='newick', data=expected_newick)
for node in expected.nodes():
if not node.is_leaf():
node.label = None
for node in observed_tree.nodes():
if not node.is_leaf():
node.label = None
self.assertEqual(str(expected), str(observed_tree))
def test_ben_bug(self):
new_tree_newick = u'(646366661:0.00571,(646777089:0.01427,(2556226606:0.0,2517129521:0.0):0.04312)0.377:0.01170,((650856936:0.01153,(((((646367708:0.01465,(638201361:0.00187,646622935:0.00573)0.940:0.01352)0.988:0.02634,(2519841469:0.06952,(650856136:0.01840,2506713669:0.02486)0.774:0.00888)0.893:0.01193)0.981:0.03778,((649738338:0.07504,(638155665:0.00613,648151945:0.00304)0.995:0.05973)0.884:0.02836,((650752390:0.11644,(2516847065:0.01707,2520801411:0.03442)0.993:0.04619)0.940:0.03278,(640592705:0.14347,637846211:0.11851)0.971:0.04593)0.940:0.03067)0.943:0.03401)0.998:0.06483,(638168675:0.17080,((649738388:0.09935,((((2540854716:0.00325,2553937573:0.00406)1.000:0.09930,(646533023:0.09868,640592823:0.06908)0.951:0.03770)1.000:0.07636,(650872422:0.05527,(650750471:0.05106,(2516847513:0.01440,2520803234:0.02517)0.998:0.05067)0.947:0.03589)0.074:0.01784)0.786:0.03804,(638155700:0.00445,648151981:0.00284)0.894:0.02131)0.995:0.08448)0.999:0.10690,((KYC55281.1:0.28954,(2540666849:0.26647,(2555938320:0.04589,2518907621:0.04631)0.970:0.05624)1.000:0.12340)0.993:0.09723,(((2515321874:0.26529,((637699780:0.01317,(2540563143:0.01361,(638165755:0.01099,638179449:0.01674)0.558:0.00611)0.964:0.01965)1.000:0.10518,(2502870849:0.06989,(648055573:0.14431,(646706666:0.11338,(637960147:0.03570,(2509663319:0.04930,(2519472088:0.03452,2515107634:0.07709)0.639:0.02134)0.957:0.03004)0.316:0.01755)0.809:0.02055)0.323:0.01213)0.991:0.07286)0.974:0.06071)0.997:0.09000,(650797088:0.06590,(639699575:0.03533,2512008957:0.12951)0.779:0.03900)1.000:0.21062)0.685:0.04985,((((640867801:0.08102,(2507462304:0.07476,(643570914:0.08474,((637897753:0.11959,((2509037835:0.14386,(648194984:0.08665,(648195418:0.04239,2506476786:0.04237)0.993:0.03477)0.668:0.01876)0.510:0.00983,((((640115295:0.06428,2540643958:0.01655)1.000:0.05043,2540643737:0.02645)0.502:0.01269,640115052:0.02482)0.987:0.04272,(2507147269:0.04181,2507146024:0.06962)0.615:0.01449)0.611:0.01456)0.992:0.03807)0.542:0.02193,((2525334810:0.02116,640099739:0.01544)0.785:0.00549,(640100248:0.00446,2525335778:0.02444)0.750:0.00227)1.000:0.12583)0.944:0.03489)0.962:0.04171)0.986:0.04499)0.793:0.02738,2509039570:0.05560)1.000:0.18840,(2505968448:0.05750,(2505971857:0.03133,2512783668:0.02305)0.185:0.01848)0.998:0.08344)0.875:0.04885,2518787893:0.16350)0.868:0.04436)1.000:0.14016)0.957:0.05998)0.998:0.08120)0.984:0.05479)0.999:0.07664,(2506713165:0.01408,((650917784:0.03595,640788680:0.07226)0.510:0.02178,(2519842728:0.03972,(646859549:0.04217,(2511672461:0.01672,(640786544:0.03901,(640793336:0.00334,(640165512:0.02037,641283602:0.00189)0.147:0.00210)0.175:0.00497)0.641:0.01093)0.991:0.02914)1.000:0.05940)0.323:0.02509)0.977:0.02843)0.960:0.02127)0.499:0.01743)0.998:0.03986,(638202197:0.00190,(644970377:0.01516,646623830:0.00752)0.678:0.00364)0.903:0.00939)0.626:0.01605);'
old_tree_newick = u'(((((646366661:0.00564,((2517129521:0,2556226606:0):0.04302,646777089:0.01412)0.499:0.01173)0.999:0.07494,(638202197:0.0019,(644970377:0.01507,646623830:0.0075)0.738:0.00362)0.872:0.00931)0.635:0.01598,650856936:0.01308)0.995:0.04,(2506713165:0.01171,((640788680:0.07255,650917784:0.03571)0.466:0.02189,(2519842728:0.03945,(646859549:0.04217,(2511672461:0.01668,(640786544:0.03894,(640793336:0.00335,(640165512:0.02038,641283602:0.0019)0.155:0.00211)0.174:0.00496)0.668:0.01095)0.987:0.02908)1.000:0.05973)0.285:0.02499)0.985:0.02844)0.967:0.02183)0.668:0.01914,(((646367708:0.01473,(638201361:0.00188,646622935:0.00578)0.947:0.01381)0.981:0.02381,(2519841469:0.06809,(650856136:0.0182,2506713669:0.02508)0.727:0.0089)0.915:0.01182)0.971:0.03729,((649738338:0.07412,(648151945:0.00339,638155665:0.00581)0.999:0.05834)0.847:0.02714,((650752390:0.11368,(2516847065:0.01707,2520801411:0.03449)0.997:0.04731)0.943:0.033,(640592705:0.14071,637846211:0.11886)0.974:0.04714)0.907:0.02899)0.938:0.03341)0.999:0.06584,(638168675:0.16751,((649738388:0.09339,((((2540854716:0.00327,2553937573:0.00411)1.000:0.1001,(640592823:0.06966,646533023:0.10017)0.945:0.03786)0.999:0.07732,(650872422:0.0565,(650750471:0.05131,(2516847513:0.01447,2520803234:0.02528)0.998:0.05086)0.932:0.03598)0.014:0.01864)0.823:0.03947,(648151981:0.00285,638155700:0.0045)0.891:0.01979)0.998:0.08667)0.999:0.11839,((2540666849:0.25749,(2518907621:0.04615,2555938320:0.04332)0.979:0.0624)1.000:0.20869,(((2515321874:0.27886,((637699780:0.01253,(2540563143:0.01408,(638165755:0.01119,638179449:0.01933)0.559:0.0062)0.973:0.01906)1.000:0.10181,(((2509663319:0.05476,(2515107634:0.07727,2519472088:0.03736)0.549:0.02018)0.970:0.02691,(637960147:0.03454,646706666:0.12022)0.328:0.01393)0.935:0.02456,(2502870849:0.07124,648055573:0.13944)0.419:0.01578)0.997:0.07265)0.976:0.05902)0.992:0.09155,(650797088:0.06773,(639699575:0.03844,2512008957:0.12921)0.700:0.03684)1.000:0.19382)0.774:0.0559,((2518787893:0.1617,(2512783668:0.01562,(2505971857:0.02991,2505968448:0.06931)0.820:0.01544)1.000:0.10132)0.000:0.03917,((640867801:0.07687,(2507462304:0.07769,(((637897753:0.11989,((2509037835:0.14075,(648194984:0.08661,(648195418:0.04254,2506476786:0.04232)0.986:0.0348)0.722:0.0191)0.553:0.00998,((((640115295:0.06424,2540643958:0.01643)1.000:0.05042,2540643737:0.02653)0.542:0.01245,640115052:0.0251)0.986:0.04265,(2507146024:0.06963,2507147269:0.0417)0.641:0.01435)0.611:0.01449)0.989:0.03824)0.424:0.02187,((640099739:0.01547,2525334810:0.02122)0.833:0.00545,(640100248:0.00445,2525335778:0.02442)0.761:0.0023)1.000:0.12528)0.944:0.03961,643570914:0.0938)0.959:0.03885)0.984:0.04627)0.758:0.02972,2509039570:0.05614)1.000:0.19872)0.185:0.04422)0.999:0.13795)0.646:0.06267)0.977:0.07517)0.979:0.05715);'
old_tree = Tree.get(schema='newick', data=old_tree_newick)
tree_to_reroot = Tree.get(schema='newick', data=new_tree_newick)
r = Rerooter()
reann = Reannotator()
new_tree = r.reroot_by_tree(
r.reroot(old_tree),
r.reroot(tree_to_reroot))
expected_lefts = old_tree.seed_node.child_nodes()[0].leaf_nodes()
expected_rights = old_tree.seed_node.child_nodes()[1].leaf_nodes()
for tip in expected_lefts:
self.assertTrue(tip.taxon.label in [t.taxon.label for t in new_tree.seed_node.child_nodes()[1].leaf_nodes()])
for tip in expected_rights:
self.assertTrue(tip.taxon.label in [t.taxon.label for t in new_tree.seed_node.child_nodes()[0].leaf_nodes()])
self.assertEqual(len(tree_to_reroot.leaf_nodes()), len(new_tree.leaf_nodes()))
def run_tact(script_runner, datadir, stem):
backbone = os.path.join(datadir, stem + ".backbone.tre")
taxonomy = os.path.join(datadir, stem + ".taxonomy.tre")
taxed = Tree.get(path=taxonomy, schema="newick")
bbone = Tree.get(path=backbone, schema="newick")
result = script_runner.run("tact_add_taxa", "--taxonomy", taxonomy,
"--backbone", backbone, "--output",
".tact-pytest-" + stem, "-vv")
assert result.returncode == 0
output = ".tact-pytest-" + stem + ".newick.tre"
tacted = Tree.get(path=output, schema="newick")
ss = tacted.as_ascii_plot()
sys.stderr.write(ss)
result = script_runner.run("tact_check_results", output, "--taxonomy",
taxonomy, "--backbone", backbone, "--output",
".tact-pytest-" + stem + ".check.csv",
"--cores=1")
assert result.returncode == 0
return (tacted, taxed, bbone)
def assert_tree_equal_no_labels_deprecated(self, expected_newick, observed_tree):
expected = Tree.get(schema='newick', data=expected_newick)
for node in expected.nodes():
if not node.is_leaf():
node.label = None
for node in observed_tree.nodes():
if not node.is_leaf():
node.label = None
self.assertEqual(str(expected), str(observed_tree))
def pretty_print_trees():
print "\n. OK, I'm reformatting the RAxML results for nice printing..."
"""Reformats the phylogeny, such that each taxon label looks like this:
trna12-AlaTCT[6/7]
. . . where 6 is the number of sequences collapsed into this sequence, and 7 is the number of total tRNAs in the databse."""
species_list = species_trna_seq.keys()
species_list.sort()
for species in species_list:
#print species_trna_dups[species]
treepath = RAXMLDIR + "/RAxML_result." + species
if False == os.path.exists( treepath ):
continue
newtreepath = TREEDIR + "/" + species + ".tree"
t = Tree()
t.read_from_path(treepath, "newick")
print " -->", treepath
trna_count = count_trna_types(species)
#print trna_count
newts = t.__str__()
for taxon in t.taxon_set:
#print "372:", taxon.label
#thisac = get_ac_from_name(taxon.label)
thisac = species_trna_mtrip[species][taxon.label]
count_this_type = trna_count[thisac]
count_dups = 0
if taxon.label in species_trna_dups[species]:
count_dups = species_trna_dups[species][taxon.label].__len__() + 1
if count_dups <= 1:
count_dups = ""
else:
count_dups = "(" + count_dups.__str__() + ")"
mark = ""
if species in species_switchedtrnas:
print "534:", species_switchedtrnas[species]
if species_switchedtrnas[species].__contains__(taxon.label):
mark = "***"
newts = re.sub( taxon.label, (taxon.label + count_dups + "[" + count_this_type.__str__()+ "]" + mark), newts)
fout = open(newtreepath, "w")
fout.write( newts + "\n" )
fout.close()
def write_and_read_nexus(filename, header, tree_id, tree_str):
tns = TaxonNamespace(is_case_sensitive=True)
# write a temp file containing tree
with open(filename, "w") as f:
for line in header + ["tree " + tree_id + " " + tree_str]:
f.write(line + "\n");
# read tree as dendropy tree
tree = Tree.get(path=filename, schema="nexus",
taxon_namespace=tns, case_sensitive_taxon_labels=True,
suppress_internal_node_taxa=False)
return tree
def main():
from sys import argv
treefile = argv[1]
t = Tree.get_from_path(treefile, "newick")
R = resolve_tree(t)
for s in R:
print(s)
def main(OT_filehandle, OTTs_to_keep, outfile):
#read in tree, but don't create taxa (faster)\
tree = Tree.get(stream=OT_filehandle, schema="newick", suppress_leaf_node_taxa=True)
for node in tree.postorder_node_iter():
if hasattr(node, 'keep') or node_label_in(node, OTTs_to_keep):
if node.parent_node: #this is not the root
node.parent_node.keep=True
else:
if not hasattr(node, 'keep'):
node.parent_node.remove_child(node, suppress_unifurcations=False)
tree.write(file=outfile, schema='newick', suppress_leaf_node_labels=False)
def compute_tree_distances(con):
cur = con.cursor()
cur.execute("insert or replace into TreeDistanceMetrics(metricid, name) values(1, 'symmetric')")
cur.execute("insert or replace into TreeDistanceMetrics(metricid, name) values(2, 'euclidean')")
con.commit()
treeid_dendropytree = {}
sql = "select id, almethod, phylomodelid, newick from UnsupportedMlPhylogenies"
con.execute(sql)
x = cur.fetchall()
for ii in x:
treeid = ii[0]
t = Tree()
t.read_from_string(newick, "newick")
treeid_dendropytree[treeid] = t
for ii in treeid_dendropytree:
treeii = treeid_dendropytree[ii]
this_row = []
for jj in treeid_dendropytree:
treejj = treeid_dendropytree[jj]
"""Symmetric Distance"""
distance = treeii.symmetric_difference(treejj)
"""Store the computed distance in the database."""
sql = "insert into TreeDistances(metricid, treeida, treeidb, distance) values("
sql += "1," + ii.__str__() + "," + jj.__str__() + "," + distance.__str__() + ")"
cur.execute(sql)
"""Euclidean Distance"""
distance = treeii.euclidean_distance(treejj)
"""Store the computed distance in the database."""
sql = "insert into TreeDistances(metricid, treeida, treeidb, distance) values("
sql += "2," + ii.__str__() + "," + jj.__str__() + "," + distance.__str__() + ")"
cur.execute(sql)
con.commit()
def get_bipart(ts, species):
t = Tree.get(data=ts, schema='newick')
hash_node = t.find_node(lambda n: n.label == '#1')
sub_nodes = set(n.taxon.label for n in hash_node.leaf_iter())
all_nodes = set(n.taxon.label for n in t.leaf_node_iter())
b1 = ''.join('1' if l in sub_nodes else ('0' if l in all_nodes else '?')
for l in species)
b2 = ''.join(neg(v) for v in b1)
assert b1 != b2
assert len(b1) == len(b2) and len(b1) == len(species)
return min(b1, b2)
def assert_tree_equal_no_labels(self, expected_newick, observed_tree):
'''should include some tree ordering because ordering of children is not relevant, but eh for now'''
expected = Tree.get(data=expected_newick, schema='newick', rooting='force-rooted')
def prep_tree(tree):
for n in tree.internal_nodes():
n.label = None
if n.edge.length is None: n.edge.length=0.0
tree = self.sort_tree(tree)
prep_tree(expected)
prep_tree(observed_tree)
self.assertEqual(str(self.sort_tree(expected)), str(self.sort_tree(observed_tree)))
def root_tree(f_name, out):
t = Tree.get(path=f_name, schema="newick", rooting='force-rooted')
t.reroot_at_midpoint()
f = open(out, "w+")
t.write(path=out,
schema="newick",
suppress_rooting=True,
real_value_format_specifier="12.8f")
f.close()
def assert_tree_equal_no_labels(self, expected_newick, observed_tree):
'''should include some tree ordering because ordering of children is not relevant, but eh for now'''
expected = Tree.get(data=expected_newick, schema='newick', rooting='force-rooted')
def prep_tree(tree):
for n in tree.internal_nodes():
n.label = None
if n.edge.length is None: n.edge.length=0.0
tree = self.sort_tree(tree)
prep_tree(expected)
prep_tree(observed_tree)
self.assertEqual(str(self.sort_tree(expected)), str(self.sort_tree(observed_tree)))
def test_write_fasttree_newick(self):
tc = DendropyTreeCleaner()
tree = Tree.get(data="((a,b),(d,e))root;", schema='newick')
self.assertEqual("((a,b),(d,e));\n", self.clean(tc, tree))
# Internal labels should be removed.
tree = Tree.get(data="((a_2,b)c,(d,e)f)root;", schema='newick')
self.assertEqual("((a_2,b),(d,e));\n", self.clean(tc, tree))
# Quoted spaces should become underscores.
tree = Tree.get(data="(('a 2',b),(d,e))root;", schema='newick')
self.assertEqual("((a_2,b),(d,e));\n", self.clean(tc, tree))
# Test underscores that are quoted.
tree = Tree.get(data="(('a_2',b),(d,e))root;", schema='newick')
self.assertEqual("((a_2,b),(d,e));\n", self.clean(tc, tree))
# Test dashes
tree = Tree.get(data="((ANME-2dV10_01644,b),(d,e))root;",
schema='newick')
self.assertEqual("((ANME-2dV10_01644,b),(d,e));\n",
self.clean(tc, tree))
# A more real world example with '~' characters (which never mattered actually).
tree = Tree.get(
data=
"('Asulf_Archaeoglobus.1_2280~2522125074':7.17,(('Afulgi_764~2528311132':0.0,'CP006577_764~2588253768':0.0):0.0,'AE000782_746~638154502':0.0)'s__Archaeoglobus fulgidus':7.555):1.461;\n",
schema='newick')
self.assertEqual(
"(Asulf_Archaeoglobus.1_2280~2522125074:7.17,((Afulgi_764~2528311132:0.0,CP006577_764~2588253768:0.0):0.0,AE000782_746~638154502:0.0):7.555):1.461;\n",
self.clean(tc, tree))
def test_reroot_trifurcated_tree_at_longest_child(self):
test_tree_1 = Tree.get(schema='newick',
data=u'(A:0.1,B:0.2,(C:0.3,D:0.4):0.5);')
test_tree_2 = Tree.get(schema='newick',
data=u'(A:0.5,B:0.2,(C:0.3,D:0.4):0.1);')
test_tree_3 = Tree.get(schema='newick',
data=u'(A:0.2,B:0.5,(C:0.3,D:0.4):0.1);')
expected_test_tree_1 = str(
Tree.get(schema='newick',
data=u"((C:0.3,D:0.4):0.25,(A:0.1,B:0.2):0.25);"))
expected_test_tree_2 = str(
Tree.get(schema='newick',
data=u"(A:0.25,(B:0.2,(C:0.3,D:0.4):0.1):0.25);"))
expected_test_tree_3 = str(
Tree.get(schema='newick',
data=u"(B:0.25,(A:0.2,(C:0.3,D:0.4):0.1):0.25);"))
rerooted_test_tree_1 = str(Rerooter().reroot(test_tree_1)).strip()
rerooted_test_tree_2 = str(Rerooter().reroot(test_tree_2)).strip()
rerooted_test_tree_3 = str(Rerooter().reroot(test_tree_3)).strip()
self.assertEqual(rerooted_test_tree_1, expected_test_tree_1)
self.assertEqual(rerooted_test_tree_2, expected_test_tree_2)
self.assertEqual(rerooted_test_tree_3, expected_test_tree_3)
def runProgram(referenceTreeFile,
sampleTreeList,
bootstrap_cutoff_value=80,
output_tree="output_tree.tre",
verbose=False,
quiet=False,
timing=False):
if verbose:
print("Reference Tree: ", referenceTreeFile)
print("Sample Tree List: ", sampleTreeList)
print("Bootstrap Cutoff Value: ", bootstrap_cutoff_value)
print("Output Tree File: ", output_tree)
if timing:
verbose = False
try:
reference_tree = Tree.get(path=referenceTreeFile,
schema="newick",
preserve_underscores=True)
except:
print(
"Error with file '{}': please only use files with newick tree format"
.format(referenceTreeFile))
sys.exit()
reference_tree_namespace = reference_tree.taxon_namespace
sample_tree_list = readTrees(sampleTreeList, reference_tree_namespace,
quiet)
# Check if gene tree taxon namespace matches reference tree
for s in sample_tree_list:
if not reference_tree_namespace.has_taxa_labels(
s.taxon_namespace.labels()):
print(
'Error: reference tree is of a different taxon namespace as the sample trees'
)
return
full_quartet_dictionary = buildFullSupport(sample_tree_list,
bootstrap_cutoff_value, verbose,
quiet, timing)
if verbose:
print("Full quartet dictionary with support values")
[
print(quartet, full_quartet_dictionary[quartet])
for quartet in full_quartet_dictionary
]
print()
buildLabeledTree(referenceTreeFile, full_quartet_dictionary, output_tree,
quiet, timing)
def recom_resultFig_dm(recom_prob, mixtureProb):
output = np.zeros((alignment_len, nodes_number))
for i in range(len(recom_prob)):
if (recom_prob['recom_nodes'][i] < tips_num):
for j in range(alignment_len):
if (recom_prob['posterior'][i][j][1] >= mixtureProb):
output[j, recom_prob['recom_nodes'][i]] = 1
else:
# for j in range(alignment_len):
# if (recom_prob['posterior'][i][j][1] >= mixtureProb):
# output[j, recom_prob['target_node'][i]] = 1
for j in range(i + 1, len(recom_prob)):
if (recom_prob['recom_nodes'][i]
== recom_prob['target_node'][j]) and (
recom_prob['recom_nodes'][j]
== recom_prob['target_node'][i]):
for k in range(alignment_len):
if ((recom_prob['posterior'][i][k][1] >= mixtureProb)
and
(recom_prob['posterior'][j][k][1] >= mixtureProb)):
output[k, recom_prob['target_node'][i]] = 1
# if (recom_prob['posterior'][i][k] < recom_prob['posterior'][j][k]):
# recom_prob['posterior'][i][k] = recom_prob['posterior'][j][k]
# if (recom_prob['posterior'][i][k] >= mixtureProb):
# output[k, recom_prob['target_node'][i]] = 1
fig = plt.figure(figsize=(tips_num + 9, tips_num / 2))
color = ['red', 'green', 'purple', 'blue', 'black']
clonaltree = Tree.get_from_path(tree_path, 'newick')
set_index(clonaltree, alignment)
for i in range(nodes_number):
ax = fig.add_subplot(nodes_number, 1, i + 1)
if i >= tips_num:
desc = set()
d = give_descendents(clonaltree, i, desc)
ax.plot(output[:, i],
label=str(i) + ' is mrca:' + str(d),
color=color[i % 5])
else:
ax.plot(output[:, i],
label=give_taxon(clonaltree, i),
color=color[i % 5])
ax.legend(bbox_to_anchor=(0.045, 1.5), prop={'size': 10})
ax.set_frame_on(False)
ax.axis('off')
ax.axis('on')
ax.set_yticklabels([])
plt.savefig("PhyloHMM_Recombination_two.jpeg")
# plt.show()
return output
def test_joel_bug(self):
tree67 = u'''[
Thu Sep 10 15:55:28 2015: Loaded from /srv/projects/graftm/testing_files/testing_graftM/tmp_01_decorate/67_otus.tree
Thu Sep 10 15:56:18 2015: tree_67_otus saved to /srv/projects/graftm/testing_files/testing_graftM/tmp_01_decorate/67_otus.rerooted.tree
]
((((1928988:0.10866,2909029:0.15809):0.03546,((801940:0.10703,(3825327:0.12686,4298210:0.09398):0.07480):0.02560,729293:0.21465):0.01982):0.02058,((426860:0.16275,219508:0.12556):0.02403,((1128285:0.06200,4455990:0.07954):0.07525,(815912:0.12348,(3770699:0.23707,823009:0.09955):0.04225):0.01489):0.01849):0.01531):0.09184,(((2361381:0.22741,(3779572:0.06720,4363260:0.07438):0.01460):0.04187,(((((((734152:0.13251,4091454:0.12251):0.03552,((576962:0.14097,(1145804:0.14124,3106714:0.14895):0.01964):0.01668,(2014493:0.15560,(3192744:0.11018,(202294:0.07263,1138804:0.08032):0.05015):0.01277):0.01187):0.01016):0.01486,4323734:0.15004):0.00053,(759363:0.05430,4459468:0.04835):0.03216):0.01531,4322265:0.12041):0.01024,(4391683:0.11058,(229854:0.07735,(4336814:0.09937,((150571:0.07911,2730777:0.10930):0.04404,((4042859:0.25381,(717487:0.13914,4363563:0.19585):0.02281):0.02587,(((3190878:0.16480,4452949:0.07312):0.05029,(4015030:0.10339,(4438491:0.04779,(2286116:0.08699,(4251079:0.03657,4349225:0.02256):0.01189):0.01091):0.04963):0.01748):0.02917,(3014179:0.16455,(2170497:0.16101,(2107103:0.22406,951205:0.11633):0.02436):0.02574):0.03041):0.01561):0.02862):0.02589):0.01914):0.01811):0.01347):0.01451,((182569:0.14758,4363259:0.07793):0.04894,696036:0.14901):0.01514):0.01624):0.02659,(3761685:0.11278,4423155:0.16503):0.03965):0.09184);
'''
tree70 = u'((4423550:0.17275,((4091454:0.108,4427993:0.1045)50:0.01575,((123662:0.06599,(3269889:0.12737,(104534:0.06041,734152:0.09136)20:0.00526)80:0.01669)90:0.01398,(300695:0.10755,225636:0.1317)100:0.0405)0:0.01073)40:0.0128)20:0.00782,(4377103:0.09243,((172946:0.08097,1145804:0.08645)100:0.02986,(1941303:0.0953,4332975:0.09505)90:0.00838)100:0.02206)90:0.0272,((((1931714:0.07012,(4322265:0.10071,4343117:0.13235)100:0.01842)100:0.03116,(((759363:0.05402,4459468:0.0433)100:0.02405,(294612:0.14484,2679839:0.1009)90:0.02132)70:0.01331,((((((730039:0.15444,((4015030:0.11176,(4438491:0.04568,(4349225:0.02406,(2286116:0.08501,(4251079:0.02026,4386156:0.01582)80:0.01016)40:0.0097)80:0.0168)100:0.03826)50:0.01397,(4308961:0.10766,4452949:0.05355)90:0.06215)40:0.01455)50:0.01325,(((1718272:0.12738,(150571:0.08502,(699249:0.03117,2730777:0.03253)100:0.06302)70:0.02174)60:0.03847,(((2107103:0.20025,3190878:0.14435)40:0.03601,(1824285:0.10892,3014179:0.14706)30:0.02039)0:0.01309,((3366304:0.09202,951205:0.07509)100:0.05732,2170497:0.16332)90:0.02722)10:0.01937)0:0.01868,(3064426:0.20791,((1837676:0.14477,(4363563:0.14803,4479774:0.10823)90:0.04638)90:0.03766,(4042859:0.2295,717487:0.15674)40:0.01749)20:0.01416)0:0.01063)0:0.03387)100:0.04795,4336814:0.08037)0:0.02958,(346735:0.11193,4391683:0.07639)60:0.00894)0:0.01312,1142178:0.07594)0:0.01881,(229854:0.0646,4460175:0.09289)90:0.02422)20:0.01731)0:0.01339)0:0.00777,(((2984017:0.05634,4340384:0.07722)80:0.03016,(((4371218:0.13005,(1133483:0.08797,3106714:0.09717)90:0.02053)80:0.02174,(3256066:0.08328,4022282:0.11841)90:0.03619)100:0.03392,((202294:0.06795,1138804:0.07777)100:0.05296,(3192744:0.09608,(2014493:0.11684,(180127:0.06532,4417185:0.0713)100:0.03824)100:0.0368)40:0.01663)70:0.00787)50:0.01733)10:0.0083,(222095:0.1391,(288404:0.13004,(4323734:0.07601,4446882:0.06844)60:0.01661)100:0.02863)40:0.01639)0:0.00846)0:0.0135,(((((1133369:0.07769,4336154:0.07979)100:0.11778,(((708774:0.0822,((114724:0.047,82092:0.04936)100:0.11526,(201206:0.10329,4423155:0.14181)60:0.03138)40:0.01886)80:0.03209,(202302:0.11673,3761685:0.09059)100:0.02325)90:0.02946,(((576962:0.11188,202459:0.09918)90:0.033,(213358:0.0989,(3390949:0.09853,3726184:0.09836)90:0.03298)90:0.02315)20:0.01425,202949:0.15903)0:0.01188)20:0.02709)10:0.01609,((4323100:0.0982,4409929:0.10612)60:0.01386,((696036:0.11283,(203529:0.18615,202449:0.08377)10:0.02209)30:0.02916,((2361381:0.18808,203220:0.10905)100:0.04166,(4363260:0.07208,(3779572:0.04977,114015:0.13268)70:0.02151)70:0.01055)100:0.04229)0:0.01717)0:0.01634)0:0.00519,(539547:0.12233,(4409453:0.14784,(4363259:0.05689,((268769:0.0594,266521:0.05311)100:0.04977,(182569:0.10314,4463866:0.07165)70:0.01505)100:0.04024)80:0.01602)100:0.05088)20:0.02162)0:0.0112,((573196:0.11279,((((3825327:0.11767,4298210:0.09472)100:0.07495,(836195:0.11165,801940:0.09002)100:0.02232)90:0.0347,((1928988:0.1129,(1129716:0.13293,2909029:0.13959)50:0.01858)70:0.02572,(((815912:0.12176,((219508:0.13512,(426860:0.12643,(202758:0.04748,4344033:0.03692)100:0.11429)90:0.0487)20:0.00791,((823117:0.10669,823009:0.0888)90:0.0381,3770699:0.24911)50:0.02136)40:0.02309)30:0.01326,(4455990:0.05381,(1128285:0.06585,4271527:0.03794)70:0.02727)100:0.06911)10:0.01546,4097115:0.09311)30:0.02142)20:0.01039)20:0.02855,(729293:0.18117,3871866:0.11553)90:0.03599)100:0.15854)20:0.02836,150700:0.13922)20:0.02787)0:0.00717)0:0.00859)100;'
old_tree = Tree.get(schema='newick', data=tree67)
tree_to_reroot = Tree.get(schema='newick', data=tree70)
new_tree = Rerooter().reroot_by_tree(
old_tree,
tree_to_reroot)
expected_lefts = old_tree.seed_node.child_nodes()[0].leaf_nodes()
expected_rights = old_tree.seed_node.child_nodes()[1].leaf_nodes()
for tip in expected_lefts:
self.assertTrue(tip.taxon.label in [t.taxon.label for t in new_tree.seed_node.child_nodes()[1].leaf_nodes()])
for tip in expected_rights:
self.assertTrue(tip.taxon.label in [t.taxon.label for t in new_tree.seed_node.child_nodes()[0].leaf_nodes()])
self.assertEqual(len(tree_to_reroot.leaf_nodes()), len(new_tree.leaf_nodes()))
def summary_to_nw_str(mcmc_tree_filename):
calc_summary_tree(mcmc_tree_filename)
# convert summary nexus tree to newick for ete3
tns = TaxonNamespace(is_case_sensitive=True)
filename = mcmc_tree_filename + "_summary.tree"
dp_tree = Tree.get(path=filename,
schema="nexus",
taxon_namespace=tns,
case_sensitive_taxon_labels=True,
suppress_internal_node_taxa=False)
# drop all annotations and illegal characters
return dp_tree.as_string('newick', suppress_annotations=True)[5:].rstrip("\n")
def bipartition_by_root(self):
if (self.n_leaves == 1):
return (None, None, None)
root = self._tree.seed_node
t1_root = root._child_nodes[0]
t = self._tree
t.prune_subtree(t1_root, update_splits=True, delete_outdegree_one=True)
t1 = PhylogeneticTree(t)
t2 = PhylogeneticTree(Tree(t1_root))
# Reroot if there's more than node left
if (t2.n_leaves > 1):
t2._tree.reroot_at_node(t1_root)
return t1, t2, root
def getBalancedTreeByHeight(self, size, th):
clades = int(math.log(size,2))
unit = (th*1.0) / clades
self.taxCtr = 0;
self.bal_newick = ''
self.buildBalancedString(1,clades,unit)
self.bal_newick += ';'
#print(self.bal_newick)
tree = Tree.get_from_string(self.bal_newick,"newick")
#print(tree)
tree.deroot()
return tree
def sample_with_outgroups(a_tree, n_ingroups, n_outgroups=1, n_reps=1):
# sample n_reps trees from a large tree, each has n_ingroups and n_outgroups taxa
samples = []
for i in range(n_reps):
t = Tree(a_tree)
check, igs, ogs = sample_and_prune(t,
n_ingroups,
n_outgroups=n_outgroups)
if not check:
return False, samples
samples.append((t, igs, ogs))
return True, samples
def get_dendropy_tree_from_break_tree(self, break_tree):
nodes = self._extract_break_tree_leaves(break_tree)
sorted_break_tree_leaves_sets, max_leaves_set_size = self._sort_break_tree_leaves_sets(break_tree)
for leave_set_size in range(max_leaves_set_size):
if leave_set_size not in sorted_break_tree_leaves_sets:
continue
for leave_set in sorted_break_tree_leaves_sets[leave_set_size]:
one_step_parents = []
for leaf in leave_set:
node = self._find_node_with_same_taxon(nodes, leaf)
oldest_parent = self._get_oldest_parent(node)
if oldest_parent not in one_step_parents:
one_step_parents.append(oldest_parent)
new_oldest_parent = Node()
if len(one_step_parents) > 1:
for parent in one_step_parents:
parent.parent_node = new_oldest_parent
oldest_parents = []
for node in nodes:
oldest_parent = self._get_oldest_parent(node)
if oldest_parent not in oldest_parents:
oldest_parents.append(oldest_parent)
if len(oldest_parents) > 1:
seed = Node()
for oldest_parent in oldest_parents:
oldest_parent.parent_node = seed
elif len(oldest_parents) == 1:
seed = oldest_parents[0]
else:
seed = Node()
tree = Tree(seed_node=seed)
tree.deroot()
return tree
def generate_ATT_from_phylesystem(aln,
workdir,
study_id,
tree_id,
phylesystem_loc='api'):
"""gathers together tree, alignment, and study info - forces names to otu_ids.
Outputs AlignTreeTax object.
an alignemnt, a
Input can be either a study ID and tree ID from OpenTree
Alignemnt need to be a Dendropy DNA character matrix!"""
#TODO CHECK ARGS
assert(isinstance(aln, datamodel.charmatrixmodel.DnaCharacterMatrix))
for tax in aln.taxon_namespace:
tax.label = tax.label.replace(" ", "_") #Forcing all spaces to underscore UGH
nexson = get_nexson(study_id, phylesystem_loc)
ott_ids = get_subtree_otus(nexson,
tree_id=tree_id,
subtree_id="ingroup",
return_format="ottid")
ott_mrca = get_mrca_ott(ott_ids)
newick = extract_tree(nexson,
tree_id,
PhyloSchema('newick',
output_nexml2json='1.2.1',
content="tree",
tip_label="ot:originalLabel"))
newick = newick.replace(" ", "_") #UGH Very heavy handed, need to make sure happens on alignement side as well.
tre = Tree.get(data=newick,
schema="newick",
preserve_underscores=True,
taxon_namespace=aln.taxon_namespace)
otus = get_subtree_otus(nexson, tree_id=tree_id)
otu_dict = {}
orig_lab_to_otu = {}
treed_taxa = {}
for otu_id in otus:
otu_dict[otu_id] = extract_otu_nexson(nexson, otu_id)[otu_id]
otu_dict[otu_id]['^physcraper:status'] = "original"
otu_dict[otu_id]['^physcraper:last_blasted'] = "1900/01/01"
orig = otu_dict[otu_id].get(u'^ot:originalLabel').replace(" ", "_")
orig_lab_to_otu[orig] = otu_id
treed_taxa[orig] = otu_dict[otu_id].get(u'^ot:ottId')
for tax in aln.taxon_namespace:
try:
tax.label = orig_lab_to_otu[tax.label].encode('ascii')
except KeyError:
sys.stderr.write("{} doesn't have an otu id. It is being removed from the alignement. This may indicate a mismatch between tree and alignement\n".format(tax.label))
#need to prune tree to seqs and seqs to tree...
otu_newick = tre.as_string(schema="newick")
return AlignTreeTax(otu_newick, otu_dict, aln, ingroup_mrca=ott_mrca, workdir=workdir) #newick should be bare, but alignement should be DNACharacterMatrix
def returnRootOfTree( infile, filePrefix, ext):
'''
input: path to the file containing newick tree
return root of the Tree
'''
directory=os.path.dirname(os.path.realpath(infile))
treePath= directory+'/'+filePrefix+'.'+ ext
rootNode=''
myTree= Tree.get_from_path(treePath, 'newick', annotations_as_nhx=True, extract_comment_metadata=True , suppress_annotations=False)
for i in myTree.internal_nodes():
if i.level() == 0:
rootNode=i.get_node_str()
break
return rootNode
def test_input_unrooted_tree(self):
otu61 = os.path.join(path_to_data, '61_otus.gpkg','61_otus.refpkg')
with tempfile.NamedTemporaryFile(suffix='.fa') as bad_alignment:
with tempdir.TempDir() as tmp:
Create(prerequisites).main(
taxtastic_taxonomy=os.path.join(otu61,'61_otus_taxonomy.csv'),
taxtastic_seqinfo=os.path.join(otu61,'61_otus_seqinfo.csv'),
# created with newick_utils:
# nw_prune test/data/61_otus.gpkg/61_otus.refpkg/61_otus.tre 4459468 >test/data/61_otus.without_4459468.tre
unrooted_tree=os.path.join(path_to_data,'create','61_otus.without_4459468.tre'),
sequences=os.path.join(path_to_data,'create','61_otus.without_4459468.fasta'),
alignment=os.path.join(path_to_data,'create','61_otus.without_4459468.aln.fasta'),
prefix=tmp, force=True)
gpkg = GraftMPackage.acquire(tmp)
tree=Tree.get(schema='newick', data=open(gpkg.reference_package_tree_path()).readline())
self.assertEqual(21, len(tree.leaf_nodes()))
def read_matrix_and_tree(char_file_path,
tree_file_path,
char_type=DnaCharacterMatrix,
char_schema='fasta',
tree_schema='newick'):
if char_file_path:
d = char_type.get(path=char_file_path, schema=char_schema)
tn = d.taxon_namespace
tn.is_mutable = False
else:
d, tn = None, None
tree = Tree.get(path=tree_file_path,
schema=tree_schema,
preserve_underscores=True,
taxon_namespace=tn)
return d, tree
