def test_01tree_annotation(self):
t = PhyloTree( "((9598, 9606), 10090);", sp_naming_function=lambda name: name)
t.annotate_ncbi_taxa(dbfile=DATABASE_PATH)
self.assertEqual(t.sci_name, 'Euarchontoglires')
homi = (t&'9606').up
self.assertEqual(homi.sci_name, 'Homininae')
self.assertEqual(homi.taxid, 207598)
self.assertEqual(homi.rank, 'subfamily')
self.assertEqual(homi.named_lineage, [u'root', u'cellular organisms', u'Eukaryota', u'Opisthokonta', u'Metazoa', u'Eumetazoa', u'Bilateria', u'Deuterostomia', u'Chordata', u'Craniata', u'Vertebrata', u'Gnathostomata', u'Teleostomi', u'Euteleostomi', u'Sarcopterygii', u'Dipnotetrapodomorpha', u'Tetrapoda', u'Amniota', u'Mammalia', u'Theria', u'Eutheria', u'Boreoeutheria', u'Euarchontoglires', u'Primates', u'Haplorrhini', u'Simiiformes', u'Catarrhini', u'Hominoidea', u'Hominidae', u'Homininae'])
self.assertEqual(homi.lineage, [1, 131567, 2759, 33154, 33208, 6072, 33213, 33511, 7711, 89593, 7742, 7776, 117570, 117571, 8287, 1338369, 32523, 32524, 40674, 32525, 9347, 1437010, 314146, 9443, 376913, 314293, 9526, 314295, 9604, 207598] )
human = t&'9606'
self.assertEqual(human.sci_name, 'H**o sapiens')
self.assertEqual(human.taxid, 9606)
self.assertEqual(human.rank, 'species')
self.assertEqual(human.named_lineage, [u'root', u'cellular organisms', u'Eukaryota', u'Opisthokonta', u'Metazoa', u'Eumetazoa', u'Bilateria', u'Deuterostomia', u'Chordata', u'Craniata', u'Vertebrata', u'Gnathostomata', u'Teleostomi', u'Euteleostomi', u'Sarcopterygii', u'Dipnotetrapodomorpha', u'Tetrapoda', u'Amniota', u'Mammalia', u'Theria', u'Eutheria', u'Boreoeutheria', u'Euarchontoglires', u'Primates', u'Haplorrhini', u'Simiiformes', u'Catarrhini', u'Hominoidea', u'Hominidae', u'Homininae', u'H**o', u'H**o sapiens'])
self.assertEqual(human.lineage, [1, 131567, 2759, 33154, 33208, 6072, 33213, 33511, 7711, 89593, 7742, 7776, 117570, 117571, 8287, 1338369, 32523, 32524, 40674, 32525, 9347, 1437010, 314146, 9443, 376913, 314293, 9526, 314295, 9604, 207598, 9605, 9606])
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 test_ncbi_compare(self): t = PhyloTree( "((9606, (9598, 9606)), 10090);", sp_naming_function=lambda x: x.name ) t.annotate_ncbi_taxa(dbfile=DATABASE_PATH)
def test_01tree_annotation(self):
t = PhyloTree("((9598, 9606), 10090);", sp_naming_function=lambda name: name)
t.annotate_ncbi_taxa(dbfile=DATABASE_PATH)
self.assertEqual(t.sci_name, "Euarchontoglires")
homi = (t & "9606").up
self.assertEqual(homi.sci_name, "Homininae")
self.assertEqual(homi.taxid, 207598)
self.assertEqual(homi.rank, "subfamily")
self.assertEqual(
homi.named_lineage,
[
u"root",
u"cellular organisms",
u"Eukaryota",
u"Opisthokonta",
u"Metazoa",
u"Eumetazoa",
u"Bilateria",
u"Deuterostomia",
u"Chordata",
u"Craniata",
u"Vertebrata",
u"Gnathostomata",
u"Teleostomi",
u"Euteleostomi",
u"Sarcopterygii",
u"Dipnotetrapodomorpha",
u"Tetrapoda",
u"Amniota",
u"Mammalia",
u"Theria",
u"Eutheria",
u"Boreoeutheria",
u"Euarchontoglires",
u"Primates",
u"Haplorrhini",
u"Simiiformes",
u"Catarrhini",
u"Hominoidea",
u"Hominidae",
u"Homininae",
],
)
self.assertEqual(
homi.lineage,
[
1,
131567,
2759,
33154,
33208,
6072,
33213,
33511,
7711,
89593,
7742,
7776,
117570,
117571,
8287,
1338369,
32523,
32524,
40674,
32525,
9347,
1437010,
314146,
9443,
376913,
314293,
9526,
314295,
9604,
207598,
],
)
human = t & "9606"
self.assertEqual(human.sci_name, "H**o sapiens")
self.assertEqual(human.taxid, 9606)
self.assertEqual(human.rank, "species")
self.assertEqual(
human.named_lineage,
[
u"root",
u"cellular organisms",
u"Eukaryota",
u"Opisthokonta",
u"Metazoa",
u"Eumetazoa",
u"Bilateria",
u"Deuterostomia",
u"Chordata",
u"Craniata",
u"Vertebrata",
u"Gnathostomata",
u"Teleostomi",
u"Euteleostomi",
u"Sarcopterygii",
u"Dipnotetrapodomorpha",
u"Tetrapoda",
u"Amniota",
u"Mammalia",
u"Theria",
u"Eutheria",
u"Boreoeutheria",
u"Euarchontoglires",
u"Primates",
u"Haplorrhini",
u"Simiiformes",
u"Catarrhini",
u"Hominoidea",
u"Hominidae",
u"Homininae",
u"H**o",
u"H**o sapiens",
],
)
self.assertEqual(
human.lineage,
[
1,
131567,
2759,
33154,
33208,
6072,
33213,
33511,
7711,
89593,
7742,
7776,
117570,
117571,
8287,
1338369,
32523,
32524,
40674,
32525,
9347,
1437010,
314146,
9443,
376913,
314293,
9526,
314295,
9604,
207598,
9605,
9606,
],
)
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)
