## From a newick tree and a list of sample, find the TMRCA of these samples
from ete3 import PhyloTree
from optparse import OptionParser
parser = OptionParser()
parser.add_option("-f", "--file", dest="filename",
help="File containing newick tree", metavar="FILE")
parser.add_option("-s", "--species", dest="speciesList",
help="file containing list of wanted species, one per line", metavar="FILE")
(options, args) = parser.parse_args()
t= PhyloTree(options.filename, format=1)
with open(options.speciesList) as f:
liste = f.read().splitlines()
pp=t.get_common_ancestor(liste)
print pp.name
# \--------|
# \-Mmu_002
# Create a dictionary with relative ages for the species present in
# the phylogenetic tree. Note that ages are only relative numbers to
# define which species are older, and that different species can
# belong to the same age.
species2age = {
"Hsa": 1, # H**o sapiens (Hominids)
"Ptr": 2, # P. troglodytes (primates)
"Mmu": 2, # Macaca mulata (primates)
"Mms": 3, # Mus musculus (mammals)
"Cfa": 3, # Canis familiaris (mammals)
"Dme": 4, # Drosophila melanogaster (metazoa)
}
# We can translate each number to its correspondig taxonomic number
age2name = {1: "hominids", 2: "primates", 3: "mammals", 4: "metazoa"}
event1 = t.get_common_ancestor("Hsa_001", "Hsa_004")
event2 = t.get_common_ancestor("Hsa_001", "Hsa_002")
print
print "The duplication event leading to the human sequences Hsa_001 and " + "Hsa_004 is dated at: ", age2name[
event1.get_age(species2age)
]
print "The duplication event leading to the human sequences Hsa_001 and " + "Hsa_002 is dated at: ", age2name[
event2.get_age(species2age)
]
# The duplication event leading to the human sequences Hsa_001 and Hsa_004
# is dated at: primates
#
# The duplication event leading to the human sequences Hsa_001 and Hsa_002
# is dated at: mammals
help=("print the extended newick format for provided tree using"
" ASCII representation and all its evolutionary events"
" before orthoXML export"))
args = parser.parse_args()
newick = args.tree[0]
SPECIES_NAME_POS = args.species_field
SPECIES_NAME_DELIMITER = args.species_delimiter
# load a phylomeDB Tree provided as a newick file in the command line
t = PhyloTree(newick, sp_naming_function=extract_spname)
if args.root:
if len(args.root) > 1:
outgroup = t.get_common_ancestor(args.root)
else:
outgroup = t & args.root[0]
t.set_outgroup(outgroup)
if not args.skip_ortholog_detection:
# detect speciation and duplication events using the species overlap
# algorithm used in phylomeDB
t.get_descendant_evol_events()
if args.ascii:
print(
t.get_ascii(attributes=[args.evoltype_attr, "name"],
show_internal=True))
if args.newick:
File.write("\n".join(HomologySummary)+"\n")
EventSummary = []
i=0
for n in recon_tree.traverse("postorder"):
n.ND = i
if n.is_leaf():
n.S = sp_dict[n.species]
if "evoltype" in dir(n):
n.Ev = n.evoltype
if n.evoltype == "L":
EventSummary.append("event(%i,loss)" %(n.S))
elif n.evoltype == "D":
sp_dup = n.get_species()
oldest_sp = sptree.get_common_ancestor(sp_dup)
n.S = oldest_sp.S
logger.debug("sp_dup: %s ",sp_dup)
EventSummary.append("event(%i,duplication)" %(n.S))
else:
n.Ev = "S"
logger.debug("name: %s",n.name)
logger.debug("S: %s",n.S)
logger.debug("Ev: %s",n.Ev)
logger.debug("ND: %s",n.ND)
i+=1
EventsFile = OutPrefixName + ".events.txt"
with open(EventsFile,"w") as File:
File.write("\n".join(EventSummary)+"\n")
lambda node: node.name.split("_")[0]) # n.species, n.name
t.set_outgroup(t & outgroup)
#taxon1 = ["parensis", "longipalpusC", "vaneedeni"]
#taxon2 = ["funestus", "funestuscf", "vaneedeni"]
taxon = [["parensis", "longipalpusC", "vaneedeni"],
["funestus", "funestuscf", "vaneedeni"]]
taxdict = {}
for i, tax in enumerate(taxon):
nodesupport = []
nodeage = []
for t in treelist:
if t.check_monophyly(values=tax, target_attr="species"):
samples = []
for sp in tax:
samples.extend(t.search_nodes(species=sp))
ancnode = t.get_common_ancestor(samples)
nodeage.append(ancnode.dist)
nodesupport.append(ancnode.support)
taxdict[i] = (nodeage, nodesupport)
if not winlist:
winarray = np.ones(len(treelist), dtype=bool)
mtreelist, winarray = getMonophyletic(treelist, quart, winarray)
btreelist, winarray = supportFilt(mtreelist, quart, winarray)
if nodes:
nh1, nh2 = nodeHeights(btreelist, quart)
else:
nh1 = []
nh2 = []
return (treelist, winarray, nh1, nh2)
def run(args):
from ete3 import Tree, PhyloTree
features = set()
for nw in args.src_tree_iterator:
if args.ncbi:
tree = PhyloTree(nw)
features.update([
"taxid", "name", "rank", "bgcolor", "sci_name",
"collapse_subspecies", "named_lineage", "lineage"
])
tree.annotate_ncbi_taxa(args.taxid_attr)
else:
tree = Tree(nw)
type2cast = {
"str": str,
"int": int,
"float": float,
"set": set,
"list": list
}
for annotation in args.feature:
aname, asource, amultiple, acast = None, None, False, str
for field in annotation:
try:
key, value = list(map(str.strip, field.split(":")))
except Exception:
raise ValueError("Invalid feature option [%s]" % field)
if key == "name":
aname = value
elif key == "source":
asource = value
elif key == "multiple":
#append
amultiple = value
elif key == "type":
try:
acast = type2cast[value]
except KeyError:
raise ValueError("Invalid feature type [%s]" % field)
else:
raise ValueError("Unknown feature option [%s]" % field)
if not aname and not asource:
ValueError(
'name and source are required when annotating a new feature [%s]'
% annotation)
features.add(aname)
for line in open(asource, 'rU'):
line = line.strip()
if not line or line.startswith('#'):
continue
nodenames, attr_value = list(map(str.strip, line.split('\t')))
nodenames = list(map(str.strip, nodenames.split(',')))
relaxed_grouping = True
if nodenames[0].startswith('!'):
relaxed_grouping = False
nodenames[0] = nodenames[0][1:]
if len(nodenames) > 1:
target_node = tree.get_common_ancestor(nodenames)
if not relaxed_grouping:
pass
# do something
else:
target_node = tree & nodenames[0]
if hasattr(target_node, aname):
log.warning('Overwriting annotation for node" [%s]"' %
nodenames)
else:
target_node.add_feature(aname, acast(attr_value))
dump(tree, features=features)
# Of course, you can disable the automatic generation of species
# names. To do so, you can set the species naming function to
# None. This is useful to set the species names manually or for
# reading them from a newick file. Other wise, species attribute would
# be overwriten
mynewick = """
(((Hsa_001[&&NHX:species=Human],Ptr_001[&&NHX:species=Chimp]),
(Cfa_001[&&NHX:species=Dog],Mms_001[&&NHX:species=Mouse])),
(Dme_001[&&NHX:species=Fly],Dme_002[&&NHX:species=Fly]));
"""
t = PhyloTree(mynewick, sp_naming_function=None)
print "Disabled mode (manual set):"
for n in t.get_leaves():
print "node:", n.name, "Species name:", n.species
# node: Dme_001 Species name: Fly
# node: Dme_002 Species name: Fly
# node: Hsa_001 Species name: Human
# node: Ptr_001 Species name: Chimp
# node: Cfa_001 Species name: Dog
# node: Mms_001 Species name: Mouse
#
# Of course, once this info is available you can query any internal
# node for species covered.
human_mouse_ancestor = t.get_common_ancestor("Hsa_001", "Mms_001")
print "These are the species under the common ancestor of Human & Mouse"
print '\n'.join( human_mouse_ancestor.get_species() )
# Mouse
# Chimp
# Dog
# Human
#From a Newick tree and two list of samples, extract the first coalescent event between samples of this two groups
from ete3 import PhyloTree
from optparse import OptionParser
parser = OptionParser()
parser.add_option("-f", "--file", dest="filename",
help="File containing newick tree", metavar="FILE")
parser.add_option("-s", "--species1", dest="species1List",
help="file containing list of samples, group1, one per line", metavar="FILE")
parser.add_option("-p", "--species2", dest="species2List",
help="file containing list of samples, group2, one per line", metavar="FILE")
(options, args) = parser.parse_args()
t= PhyloTree(options.filename, format=1)
with open(options.species1List) as f:
liste1 = f.read().splitlines()
with open(options.species2List) as f:
liste2 = f.read().splitlines()
for s1 in liste1:
for s2 in liste2:
pp=t.get_common_ancestor(s1,s2)
print pp.name
default=1000)
args = ap.parse_args()
og_list = []
with open(args.outgroupf, "r") as ogf:
for line in ogf:
og_list.append(line.strip())
tr = PhyloTree(args.tree,
sp_naming_function=lambda node: node.name.split("@")[0])
og_in_tr = []
for l in tr.iter_leaves():
if l.name.split("@")[0] in og_list:
og_in_tr.append(l.name)
all_l = [b.name for b in tr.iter_leaves()]
ing = list(set(all_l) - set(og_in_tr))
tr.set_outgroup(tr.get_common_ancestor(*og_in_tr))
tr.prune(ing, preserve_branch_length=True)
all_l = list(set(all_l) - set(og_in_tr))
trlen = calc_trlen(tr)
sub_trlen = calc_sub_trlen(tr)
resamp_dict = resample(sub_trlen, args.iterate)
print([(k, v)
for k, v in sorted(resamp_dict.items(), key=lambda x: x[1])][-9][0])
# Of course, you can disable the automatic generation of species
# names. To do so, you can set the species naming function to
# None. This is useful to set the species names manually or for
# reading them from a newick file. Other wise, species attribute would
# be overwriten
mynewick = """
(((Hsa_001[&&NHX:species=Human],Ptr_001[&&NHX:species=Chimp]),
(Cfa_001[&&NHX:species=Dog],Mms_001[&&NHX:species=Mouse])),
(Dme_001[&&NHX:species=Fly],Dme_002[&&NHX:species=Fly]));
"""
t = PhyloTree(mynewick, sp_naming_function=None)
print "Disabled mode (manual set):"
for n in t.get_leaves():
print "node:", n.name, "Species name:", n.species
# node: Dme_001 Species name: Fly
# node: Dme_002 Species name: Fly
# node: Hsa_001 Species name: Human
# node: Ptr_001 Species name: Chimp
# node: Cfa_001 Species name: Dog
# node: Mms_001 Species name: Mouse
#
# Of course, once this info is available you can query any internal
# node for species covered.
human_mouse_ancestor = t.get_common_ancestor("Hsa_001", "Mms_001")
print "These are the species under the common ancestor of Human & Mouse"
print "\n".join(human_mouse_ancestor.get_species())
# Mouse
# Chimp
# Dog
# Human
