def test_parse_newick_with_commas(self):
# bug: comma is getting interpreted even if in quotes
in_ = "(('foo,bar':1,baz:2)x:3)r;"
exp = skbio.TreeNode.read([in_])
obs = to_skbio_treenode(parse_newick(in_))
print(obs.ascii_art())
print(exp.ascii_art())
self.assertEqual(obs.compare_subsets(exp), 0.0)
def test_parse_newick_with_commas(self):
# bug: comma is getting interpreted even if in quotes
in_ = "(('foo,bar':1,baz:2)x:3)r;"
exp = skbio.TreeNode.read([in_])
obs = to_skbio_treenode(parse_newick(in_))
print(obs.ascii_art())
print(exp.ascii_art())
self.assertEqual(obs.compare_subsets(exp), 0.0)
def test_write_newick_edges(self):
test_a = '((foo"bar":1{0},baz:2{1})x:3{2})r;'
test_b = "(((a)b)c,((d)e)f)r;"
buf = io.StringIO()
obs = write_newick(parse_newick(test_a), buf, True)
buf.seek(0)
obs = to_skbio_treenode(parse_newick(buf.read()))
self.assertEqual(obs.find('foo"bar"').edge_num, 0)
self.assertEqual(obs.find('baz').edge_num, 1)
self.assertEqual(obs.find('x').edge_num, 2)
buf = io.StringIO()
obs = write_newick(parse_newick(test_b), buf, True)
buf.seek(0)
obs = to_skbio_treenode(parse_newick(buf.read()))
for o in obs.traverse():
self.assertEqual(o.edge_num, 0)
def test_parse_jplace_multiple_per_fragment(self):
columns = [
'fragment', 'edge_num', 'likelihood', 'like_weight_ratio',
'distal_length', 'pendant_length'
]
exp_df = [
[
"82", 361, 0.01013206496780672, 1, 0.02652932626620403,
0.039354548684623215
],
[
"99", 308, 0.04520741687623886, 1, 0.11020044356641526,
0.06550337922097477
],
# tied on like_weight_ratio but lower pendant
[
"99", 309, 0.04520741687623886, 1, 0.11020044356641526,
0.00550337922097477
],
[
"55", 139, 0.09563944060686769, 1, 0.014593217782258146,
0.04537214236560885
],
# tied higher like_weight_ratio
[
"55", 138, 0.09563944060686769, 10, 0.014593217782258146,
0.04537214236560885
]
]
exp_df = pd.DataFrame(exp_df, columns=columns)
# ...adjust jplace data
data = json.loads(self.jplacedata)
keep = []
for placement in data['placements']:
if placement['n'][0] == '82':
keep.append(placement)
elif placement['n'][0] == '99':
placement['p'].append([
309, 0.04520741687623886, 1, 0.11020044356641526,
0.00550337922097477
])
keep.append(placement)
elif placement['n'][0] == '55':
placement['p'].append([
138, 0.09563944060686769, 10, 0.014593217782258146,
0.04537214236560885
])
keep.append(placement)
data['placements'] = keep
data = json.dumps(data)
exp_tree = self.tree
obs_df, obs_tree = parse_jplace(data)
obs_tree = to_skbio_treenode(obs_tree)
pdt.assert_frame_equal(obs_df, exp_df)
self.assertEqual(obs_tree.compare_rfd(exp_tree), 0)
def test_to_skbio_treenode(self):
obs = to_skbio_treenode(self.bp)
for o, e in zip(obs.traverse(), self.sktn.traverse()):
if e.length is None:
self.assertEqual(o.length, None if e.is_root() else 0.0)
else:
self.assertEqual(o.length, e.length)
self.assertEqual(o.name, e.name)
self.assertEqual(obs.ascii_art(), self.sktn.ascii_art())
def test_to_skbio_treenode(self):
obs = to_skbio_treenode(self.bp)
for o, e in zip(obs.traverse(), self.sktn.traverse()):
if e.length is None:
self.assertEqual(o.length, None if e.is_root() else 0.0)
else:
self.assertEqual(o.length, e.length)
self.assertEqual(o.name, e.name)
self.assertEqual(obs.ascii_art(), self.sktn.ascii_art())
def test_to_skbio_treenode_with_edge_numbers(self):
# from https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0031009
# but without edge labels
# 0 1 2 3 4 5 6 7 8 9
# 1 1 1 0 1 0 0 1 0 0
in_ = '((A:.01{0}, B:.01{1})D:.01{3}, C:.01{4}) {5};'
obs = parse_newick(in_)
obs_sk = to_skbio_treenode(obs)
self.assertEqual(obs_sk.find('A').edge_num, 0)
self.assertEqual(obs_sk.find('B').edge_num, 1)
self.assertEqual(obs_sk.find('D').edge_num, 3)
self.assertEqual(obs_sk.find('C').edge_num, 4)
self.assertEqual(obs_sk.edge_num, 5)
def test_place_jplace_square_braces(self):
self.jplacedata = json.loads(self.jplacedata)
treestr = self.jplacedata['tree']
treestr = re.sub(r"{(\d+)}", r"[\1]", treestr)
self.jplacedata['tree'] = treestr
self.jplacedata = json.dumps(self.jplacedata)
exp_tree = self.tree
obs_df, obs_tree = parse_jplace(self.jplacedata)
obs_tree = to_skbio_treenode(obs_tree)
self.assertEqual(obs_tree.compare_rfd(exp_tree), 0)
for n in obs_tree.traverse(include_self=False):
self.assertTrue(n.edge_num >= 0)
def test_parse_jplace_simple(self):
columns = [
'fragment', 'edge_num', 'likelihood', 'like_weight_ratio',
'distal_length', 'pendant_length'
]
exp_df = [[
"82", 361, 0.01013206496780672, 1, 0.02652932626620403,
0.039354548684623215
],
[
"99", 308, 0.04520741687623886, 1, 0.11020044356641526,
0.06550337922097477
],
[
"43", 309, 0.04054866161921744, 1, 0.010712923050783987,
0.020946988900520196
],
[
"195", 277, 0.01918907908397749, 1, 0.03065741838803451,
0.04513513498399864
],
[
"162", 55, 0.01758935282545493, 1, 0.0033199487685078776,
0.05388735804976052
],
[
"56", 81, 0.2366882303770561, 1, 0.04172580852519453,
0.0007060238727097983
],
[
"91", 105, 0.0001863393767883581, 1, 0.04578898721138839,
0.08655004339151215
],
[
"174", 89, 0.01216463967379211, 1, 0.04707020642820376,
0.045206727542450205
],
[
"5", 143, 0.012162345471765756, 1, 0.023797389484252734,
0.10447375403452556
],
[
"55", 139, 0.09563944060686769, 1, 0.014593217782258146,
0.04537214236560885
]]
exp_df = pd.DataFrame(exp_df, columns=columns)
exp_tree = self.tree
obs_df, obs_tree = parse_jplace(self.jplacedata)
obs_tree = to_skbio_treenode(obs_tree)
pdt.assert_frame_equal(obs_df, exp_df)
self.assertEqual(obs_tree.compare_rfd(exp_tree), 0)
def subset_and_write_table_tree(
otu_size: int,
sample_size: int,
density: float,
rep: int,
seed: int,
table: biom.Table,
tree: bp.BP,
output_dir: str,
) -> None:
"""Given parameters for a single subset, filter the table and tree and
write to file
"""
# prepare output info
file_start = 'otu_size-{}--sample_size-{}--rep-{}--seed-{}--density-{}' \
.format(otu_size, sample_size, rep, seed, density)
full_file_start = os.path.join(output_dir, file_start)
# get subset of table
table_subset = get_random_subtable(table,
otu_size=otu_size,
sample_size=sample_size,
seed=seed,
density=density)
table_subset.table_id = file_start
# write out biom table
with biom_open(full_file_start + '.biom', 'w') as fp:
table_subset.to_hdf5(fp, "subset: " + file_start)
# create a sheared tree based off the table
otu_ids = table_subset.ids('observation')
# TODO: change bp_tree to tree
bp_tree = tree # bp.from_skbio_treenode(tree)
sheared_bp = bp_tree.shear(set(otu_ids))
tree_subset = bp.to_skbio_treenode(sheared_bp)
# tree_subset = tree.shear(otu_ids)
for node in tree_subset.traverse():
if node.length is None:
node.length = 0
tree_subset.write(full_file_start + '.newick')
def _validate_and_match_data(self, ignore_missing_samples,
filter_missing_features,
filter_unobserved_features_from_phylogeny):
# remove unobserved features from the phylogeny
if filter_unobserved_features_from_phylogeny:
self.tree = self.tree.shear(set(self.table.columns))
# extract balance parenthesis
self._bp_tree = list(self.tree.B)
self.tree = Tree.from_tree(to_skbio_treenode(self.tree))
fill_missing_node_names(self.tree)
# Note that the feature_table we get from QIIME 2 (as an argument to
# this function) is set up such that the index describes sample IDs and
# the columns describe feature IDs. We transpose this table before
# sending it to tools.match_inputs() and keep using the transposed
# table for the rest of this visualizer.
self.table, self.samples, self.tip_md, self.int_md = match_inputs(
self.tree, self.table.T, self.samples, self.features,
ignore_missing_samples, filter_missing_features)
def test_parse_newick_simple_edge_numbers(self):
# from https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0031009
# but without edge labels
# 0 1 2 3 4 5 6 7 8 9
# 1 1 1 0 1 0 0 1 0 0
in_ = '((A:.01{0}, B:.01{1})D:.01{3}, C:.01{4}) {5};'
exp_sk = '((A:.01, B:.01)D:.01, C:.01);' # skbio doesn't know about edge numbers
obs = parse_newick(in_)
obs_sk = to_skbio_treenode(obs)
exp_sk = skbio.TreeNode.read([exp_sk])
self.assertEqual(obs_sk.compare_rfd(exp_sk), 0)
self.assertEqual(obs.edge(2), 0)
self.assertEqual(obs.edge(4), 1)
self.assertEqual(obs.edge(1), 3)
self.assertEqual(obs.edge(7), 4)
self.assertEqual(obs.edge(0), 5)
self.assertEqual(obs.edge_from_number(0), 2)
self.assertEqual(obs.edge_from_number(1), 4)
self.assertEqual(obs.edge_from_number(3), 1)
self.assertEqual(obs.edge_from_number(4), 7)
self.assertEqual(obs.edge_from_number(5), 0)
def test_parse_newick_nested_quotes(self):
# bug: quotes are removed
in_ = '((foo"bar":1,baz:2)x:3)r;'
exp = skbio.TreeNode.read([in_])
obs = to_skbio_treenode(parse_newick(in_))
self.assertEqual(obs.compare_subsets(exp), 0.0)
def test_parse_newick_with_parens(self):
# bug: parens are getting interpreted even if in quotes
in_ = "(('foo(b)ar':1,baz:2)x:3)r;"
exp = skbio.TreeNode.read([in_])
obs = to_skbio_treenode(parse_newick(in_))
self.assertEqual(obs.compare_subsets(exp), 0.0)
def test_parse_newick_nested_quotes(self):
# bug: quotes are removed
in_ = '((foo"bar":1,baz:2)x:3)r;'
exp = skbio.TreeNode.read([in_])
obs = to_skbio_treenode(parse_newick(in_))
self.assertEqual(obs.compare_subsets(exp), 0.0)
def test_parse_newick_with_parens(self):
# bug: parens are getting interpreted even if in quotes
in_ = "(('foo(b)ar':1,baz:2)x:3)r;"
exp = skbio.TreeNode.read([in_])
obs = to_skbio_treenode(parse_newick(in_))
self.assertEqual(obs.compare_subsets(exp), 0.0)