##########################################################################################
# Get support value for the evolutionary events
##########################################################################################
evts = file('%s' '/' '%s' '.temp' % (events_dir, tree), "r")
#events_and_support = file('%s''/''%s''.para.events' %(events_dir,tree), "w")
output_count = 0
for row in evts:
pair = row.split("<===>")
left = "".join(pair[0].split())
right = "".join(pair[1].split())
if (len(left) > 0 and len(right) > 0):
child_left = left.split(",")
child_right = right.split(",")
ancestor_1 = t.get_common_ancestor(child_left[0],
child_right[0])
#print child_left[0] + "\t" + child_right[0]
#print ancestor_1
#a counter to score the number of monocots genes
mono_left = 0
mono_right = 0
Cpent_left = 0
Cpent_right = 0
rosid_left = 0
rosid_right = 0
asterid_left = 0
asterid_right = 0
other_left = 0
other_right = 0
#para_list = list()
rosid_list = list()
##########################################################################################
# Get support value for the evolutionary events
##########################################################################################
evts = file('%s''/''%s''.temp' %(events_dir,tree), "r")
#events_and_support = file('%s''/''%s''.para.events' %(events_dir,tree), "w")
output_count =0
for row in evts:
pair = row.split("<===>" )
left = "".join(pair[0].split())
right = "".join(pair[1].split())
if (len(left) > 0 and len(right) > 0):
child_left = left.split(",")
child_right = right.split(",")
ancestor_1 = t.get_common_ancestor(child_left[0], child_right[0])
#print child_left[0] + "\t" + child_right[0]
#print ancestor_1
#a counter to score the number of monocots genes
mono_left =0
mono_right = 0
#para_left = 0
#para_right= 0
Cpent_left = 0
Cpent_right =0
Cpent_list = list()
rosid_left = 0
rosid_right=0
asterid_left=0
asterid_right =0
evts.write(",".join(ev.out_seqs))
evts.write("\n")
evts.close()
evts = file('%s' '/' '%s' '.temp' % (events_dir, tree), "r")
output_count = 0
for row in evts:
pair = row.split("<===>")
left = "".join(pair[0].split())
right = "".join(pair[1].split())
if (len(left) > 0 and len(right) > 0):
child_left = left.split(",")
child_right = right.split(",")
ancestor_1 = t.get_common_ancestor(child_left[0],
child_right[0])
#print child_left[0] + "\t" + child_right[0]
#print ancestor_1
#a counter to score the number of monocots genes
mono_left = 0
mono_right = 0
para_left = 0
para_right = 0
rosid_left = 0
rosid_right = 0
asterid_left = 0
asterid_right = 0
other_left = 0
other_right = 0
para_list = list()
def run(args):
from ete2 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 = map(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 = map(strip, line.split('\t'))
nodenames = map(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)
def run(args):
from ete2 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 = map(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 = map(strip, line.split('\t'))
nodenames = map(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)
# 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
" 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:
print t.write(features=[args.evoltype_attr], format_root_node=True)
# 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
