def test_make_consensus_tree(self):
"""correctly gets parent consensus counts"""
input = [['a','b','c','d','e','f','g'],
['a','b','c',None,None,'x','y'],
['h','i','j','k','l','m','n'],
['h','i','j','k','l','m','q'],
['h','i','j','k','l','m','n']]
exp_str = "(((((((g)f)e)d,(((y)x)))c)b)a,((((((n,q)m)l)k)j)i)h);"
obs_root, lookup = make_consensus_tree(input, check_for_rank=False)
self.assertEqual(obs_root.getNewick(with_distances=False), exp_str)
self.assertNotContains(None, lookup)
def test_make_consensus_tree_withtips(self):
"""correctly constructs the taxonomy tree with tip info"""
input = [['a','b','c','d','e','f','g'],
['a','b','c',None,None,'x','y'],
['h','i','j','k','l','m','n'],
['h','i','j','k','l','m','q'],
['h','i','j','k','l','m','n']]
input_ids = ['1','2','3','4','5']
exp_str = "((((((((1)g)f)e)d,((((2)y)x)))c)b)a,(((((((3,5)n,(4)q)m)l)k)j)i)h);"
obs_root, lookup = make_consensus_tree(input, check_for_rank=False, tips=input_ids)
self.assertEqual(obs_root.getNewick(with_distances=False), exp_str)
self.assertNotContains(None, lookup)
def test_make_consensus_tree(self):
"""correctly gets parent consensus counts"""
data = [['a', 'b', 'c', 'd', 'e', 'f', 'g'],
['a', 'b', 'c', None, None, 'x', 'y'],
['h', 'i', 'j', 'k', 'l', 'm', 'n'],
['h', 'i', 'j', 'k', 'l', 'm', 'q'],
['h', 'i', 'j', 'k', 'l', 'm', 'n']]
exp_str = "(((((((g)f)e)d,(((y)x)))c)b)a,((((((n,q)m)l)k)j)i)h);"
obs_root, lookup = make_consensus_tree(data, check_for_rank=False)
self.assertEqual(str(obs_root).strip(), exp_str)
self.assertNotIn(None, lookup)
def test_make_consensus_tree(self):
"""correctly gets parent consensus counts"""
input = [['a', 'b', 'c', 'd', 'e', 'f', 'g'],
['a', 'b', 'c', None, None, 'x', 'y'],
['h', 'i', 'j', 'k', 'l', 'm', 'n'],
['h', 'i', 'j', 'k', 'l', 'm', 'q'],
['h', 'i', 'j', 'k', 'l', 'm', 'n']]
exp_str = "(((((((g)f)e)d,(((y)x)))c)b)a,((((((n,q)m)l)k)j)i)h);"
obs_root, lookup = make_consensus_tree(input, check_for_rank=False)
self.assertEqual(obs_root.to_newick(with_distances=False), exp_str)
self.assertNotIn(None, lookup)
def get_polyphyletic(cons):
"""get polyphyletic groups and a representative tip"""
tips, taxonstrings = unzip(cons.items())
tree, lookup = make_consensus_tree(taxonstrings, False, tips=tips)
cache_tipnames(tree)
names = {}
for n in tree.non_tips():
if n.name is None:
continue
if (n.name, n.Rank) not in names:
names[(n.name, n.Rank)] = {}
if n.parent is not None:
names[(n.name, n.Rank)][n.parent.name] = n.tip_names[0]
return names
def get_polyphyletic(cons):
"""get polyphyletic groups and a representative tip"""
tips, taxonstrings = unzip(cons.items())
tree, lookup = make_consensus_tree(taxonstrings, False, tips=tips)
cache_tipnames(tree)
names = {}
for n in tree.non_tips():
if n.name is None:
continue
if (n.name, n.Rank) not in names:
names[(n.name, n.Rank)] = {}
if n.parent is not None:
names[(n.name, n.Rank)][n.parent.name] = n.tip_names[0]
return names
def test_make_consensus_tree_withtips(self):
"""correctly constructs the taxonomy tree with tip info"""
data = [['a', 'b', 'c', 'd', 'e', 'f', 'g'],
['a', 'b', 'c', None, None, 'x', 'y'],
['h', 'i', 'j', 'k', 'l', 'm', 'n'],
['h', 'i', 'j', 'k', 'l', 'm', 'q'],
['h', 'i', 'j', 'k', 'l', 'm', 'n']]
input_ids = ['1', '2', '3', '4', '5']
exp_str = ("((((((((1)g)f)e)d,((((2)y)x)))c)b)a,(((((((3,5)n,"
"(4)q)m)l)k)j)i)h);")
obs_root, lookup = make_consensus_tree(
data, check_for_rank=False, tips=input_ids)
self.assertEqual(str(obs_root).strip(), exp_str)
self.assertNotIn(None, lookup)
def test_walk_consensus_tree(self):
"""correctly walk consensus tree"""
input = [['a','b','c','d','e','f','g'],
['a','b','c',None,None,'x','y'],
['h','i','j','k','l','m','n'],
['h','i','j','k','l','m','q'],
['h','i','j','k','l','m','n']]
root, lookup = make_consensus_tree(input, check_for_rank=False)
exp1 = ['n','m','l']
exp2 = ['a']
exp3 = ['x','f__','o__','c']
obs1 = walk_consensus_tree(lookup, 'n', 3, reverse=False)
obs2 = walk_consensus_tree(lookup, 'a', 3, reverse=False)
obs3 = walk_consensus_tree(lookup, 'x', 4, reverse=False)
self.assertEqual(obs1, exp1)
self.assertEqual(obs2, exp2)
self.assertEqual(obs3, exp3)
def test_walk_consensus_tree(self):
"""correctly walk consensus tree"""
data = [['a', 'b', 'c', 'd', 'e', 'f', 'g'],
['a', 'b', 'c', None, None, 'x', 'y'],
['h', 'i', 'j', 'k', 'l', 'm', 'n'],
['h', 'i', 'j', 'k', 'l', 'm', 'q'],
['h', 'i', 'j', 'k', 'l', 'm', 'n']]
_, lookup = make_consensus_tree(data, check_for_rank=False)
exp1 = ['n', 'm', 'l']
exp2 = ['a']
exp3 = ['x', 'f__', 'o__', 'c']
obs1 = walk_consensus_tree(lookup, 'n', 3, reverse=False)
obs2 = walk_consensus_tree(lookup, 'a', 3, reverse=False)
obs3 = walk_consensus_tree(lookup, 'x', 4, reverse=False)
self.assertEqual(obs1, exp1)
self.assertEqual(obs2, exp2)
self.assertEqual(obs3, exp3)
def generate_constrings(tree, tipname_map, verbose=False):
"""Assigns taxonomy to unidentified sequences in tree.
Returns all sequence IDs on tree."""
counts = nlevel.collect_names_at_ranks_counts(tree)
min_count = 2
nlevel.decorate_ntips(tree)
nlevel.decorate_name_relative_freqs(tree, counts, min_count)
nlevel.set_ranksafe(tree)
nlevel.pick_names(tree)
nlevel.name_node_score_fold(tree)
if verbose:
print "Tree score: ", nlevel.score_tree(tree)
nlevel.set_preliminary_name_and_rank(tree)
contree, contree_lookup = nlevel.make_consensus_tree(tipname_map.values())
nlevel.backfill_names_gap(tree, contree_lookup)
nlevel.commonname_promotion(tree)
nlevel.make_names_unique(tree, append_suffix=False)
constrings = nlevel.pull_consensus_strings(tree)
return constrings
