def setUp(self):
self.tree = self.mock_tree_from_nwk()
self.bp_tree = from_skbio_treenode(self.tree)
self.table = biom.Table(
np.array([[1, 2, 0, 4], [8, 7, 0, 5], [1, 0, 0, 0], [0, 0, 0,
0]]).T,
list('abed'), ['Sample1', 'Sample2', 'Sample3', 'Sample4'])
self.sample_metadata = pd.DataFrame(
{
"Metadata1": [0, 0, 0, 1],
"Metadata2": [0, 0, 0, 0],
"Metadata3": [1, 2, 3, 4],
"Metadata4": ["abc", "def", "ghi", "jkl"]
},
index=list(self.table.ids()))
# (These are some Greengenes taxonomy annotations I took from the
# moving pictures taxonomy.qza file. I made up the confidences.)
self.feature_metadata = pd.DataFrame(
{
"Taxonomy":
[("k__Bacteria; p__Bacteroidetes; c__Bacteroidia; "
"o__Bacteroidales; f__Bacteroidaceae; g__Bacteroides; "
"s__"),
("k__Bacteria; p__Proteobacteria; "
"c__Gammaproteobacteria; o__Pasteurellales; "
"f__Pasteurellaceae; g__; s__"),
("k__Bacteria; p__Bacteroidetes; c__Bacteroidia; "
"o__Bacteroidales; f__Bacteroidaceae; g__Bacteroides; "
"s__uniformis")],
"Confidence": [0.95, 0.8, 0]
},
index=["e", "h", "a"])
self.split_tax_fm, self.taxcols = split_taxonomy(self.feature_metadata)
self.tip_md = self.split_tax_fm.loc[["a", "e"]]
self.int_md = self.split_tax_fm.loc[["h"]]
# This is designed to match the shearing that's done in the core test
# for --p-shear-to-table
self.shorn_tree = parse_newick(
"(((a:1)EmpressNode0:1,b:2)g:1,(d:3)h:2)EmpressNode1:1;")
self.exp_split_fm_cols = [
"Level 1", "Level 2", "Level 3", "Level 4", "Level 5", "Level 6",
"Level 7", "Confidence"
]
eigvals = pd.Series([0.50, 0.25, 0.25], index=['PC1', 'PC2', 'PC3'])
samples = [[0.1, 0.2, 0.3], [0.2, 0.3, 0.4], [0.3, 0.4, 0.5],
[0.4, 0.5, 0.6]]
proportion_explained = pd.Series([15.5, 12.2, 8.8],
index=['PC1', 'PC2', 'PC3'])
samples_df = pd.DataFrame(
samples,
index=['Sample1', 'Sample2', 'Sample3', 'Sample4'],
columns=['PC1', 'PC2', 'PC3'])
self.ordination = OrdinationResults(
'PCoA',
'Principal Coordinate Analysis',
eigvals,
samples_df,
proportion_explained=proportion_explained)
def test_fm_filtering_post_shearing_with_moving_pictures_dataset(self):
# This particular tip can be problematic (it was the reason we found
# out about https://github.com/biocore/empress/issues/248), so we
# observe how it is handled in generating a visualization of the
# moving pictures dataset to verify that #248 does not recur.
funky_tip = "8406abe6d9a72018bf32d189d1340472"
tree, tbl, smd, fmd, pcoa = load_mp_data()
# Convert artifacts / metadata objects to "normal" types that we can
# pass to Empress
bp_tree = from_skbio_treenode(tree.view(TreeNode))
tbl_df = tbl.view(biom.Table)
pcoa_skbio = pcoa.view(skbio.OrdinationResults)
smd_df = smd.to_dataframe()
fmd_df = fmd.to_dataframe()
# Sanity check -- verify that the funky tip we're looking for is
# actually present in the data. (We haven't actually done anything
# specific to Empress yet. This just verifies the environment is ok.)
# https://stackoverflow.com/a/23549599/10730311
self.assertTrue(funky_tip in fmd_df.index)
# Generate an Empress visualization using this data
viz = Empress(bp_tree,
tbl_df,
smd_df,
feature_metadata=fmd_df,
ordination=pcoa_skbio,
filter_extra_samples=True,
shear_to_table=True)
# Check that tip 8406abe6d9a72018bf32d189d1340472 *isn't* in the tip
# metadata. All of the samples this tip is present in are filtered out
# when --p-filter-extra-samples is used with this particular PCoA, so
# we verify that this tip is removed from the tip metadata.
self.assertFalse(funky_tip in viz.tip_md.index)
def test_from_skbio_treenode(self):
obs_bp = from_skbio_treenode(self.sktn)
exp_bp = self.bp
npt.assert_equal(obs_bp.B, exp_bp.B)
for i in range(len(self.bp.B)):
self.assertEqual(exp_bp.name(i), obs_bp.name(i))
self.assertEqual(exp_bp.length(i), obs_bp.length(i))
def test_from_skbio_treenode(self):
obs_bp = from_skbio_treenode(self.sktn)
exp_bp = self.bp
npt.assert_equal(obs_bp.B, exp_bp.B)
for i in range(len(self.bp.B)):
self.assertEqual(exp_bp.name(i), obs_bp.name(i))
self.assertEqual(exp_bp.length(i), obs_bp.length(i))
def setUp(self):
self.tree = self.mock_tree_from_nwk()
self.bp_tree = from_skbio_treenode(self.tree)
# Test table/metadata (mostly) adapted from Qurro:
# https://github.com/biocore/qurro/blob/b9613534b2125c2e7ee22e79fdff311812f4fefe/qurro/tests/test_df_utils.py#L178
self.table = pd.DataFrame(
{
"Sample1": [1, 2, 0, 4],
"Sample2": [8, 7, 0, 5],
"Sample3": [1, 0, 0, 0],
"Sample4": [0, 0, 0, 0]
},
index=["a", "b", "e", "d"]
)
self.sample_metadata = pd.DataFrame(
{
"Metadata1": [0, 0, 0, 1],
"Metadata2": [0, 0, 0, 0],
"Metadata3": [1, 2, 3, 4],
"Metadata4": ["abc", "def", "ghi", "jkl"]
},
index=list(self.table.columns)[:]
)
# (These are some Greengenes taxonomy annotations I took from the
# moving pictures taxonomy.qza file. I made up the confidences.)
self.feature_metadata = pd.DataFrame(
{
"Taxonomy": [
(
"k__Bacteria; p__Bacteroidetes; c__Bacteroidia; "
"o__Bacteroidales; f__Bacteroidaceae; g__Bacteroides; "
"s__"
),
(
"k__Bacteria; p__Proteobacteria; "
"c__Gammaproteobacteria; o__Pasteurellales; "
"f__Pasteurellaceae; g__; s__"
),
(
"k__Bacteria; p__Bacteroidetes; c__Bacteroidia; "
"o__Bacteroidales; f__Bacteroidaceae; g__Bacteroides; "
"s__uniformis"
)
],
"Confidence": [0.95, 0.8, 0]
},
index=["e", "h", "a"]
)
self.split_tax_fm = split_taxonomy(self.feature_metadata)
self.exp_split_fm_cols = [
"Level 1", "Level 2", "Level 3", "Level 4", "Level 5", "Level 6",
"Level 7", "Confidence"
]
def from_tree(cls, tree, use_lengths=True):
""" Creates an Tree object from a skbio tree.
Parameters
----------
tree : skbio.TreeNode
Input skbio tree
use_lengths: Boolean
Specify if the branch length should be incorporated into
the geometry calculations for visualization.
Returns
-------
Tree: bp.BP
"""
bp_tree = from_skbio_treenode(tree)
if sum(bp_tree.B) <= 1:
raise ValueError("Tree must contain at least 2 nodes.")
# While traversing the tree, record tip / internal node names
# (Nodes without names are ignored, since we'll assign those later
# using tools.fill_missing_node_names())
tip_names = []
internal_node_names = []
max_branch_length = 0
for i in range(sum(bp_tree.B)):
node_idx = bp_tree.postorderselect(i)
name = bp_tree.name(node_idx)
length = bp_tree.length(node_idx)
if name is not None:
# NOTE: This should eventually be taken out when
# fill_missing_node_names() is refactored. However, for now,
# this makes sure that users can't accidentally break things by
# naming nodes identical to our default names for missing nodes
if name.startswith("EmpressNode"):
raise ValueError(
'Node names can\'t start with "EmpressNode".')
if isleaf(bp_tree, node_idx):
tip_names.append(name)
else:
internal_node_names.append(name)
if length is None:
raise ValueError(
"Non-root branches of the tree must have lengths.")
if length < 0:
raise ValueError(
"Non-root branches of the tree must have nonnegative "
"lengths.")
max_branch_length = max(length, max_branch_length)
# We didn't consider the root node in the above traversal since we
# don't care about its length. However, we do care about its name,
# so we add the root's name to internal_node_names.
if max_branch_length == 0:
raise ValueError(
"At least one non-root branch of the tree must have a "
"positive length.")
unique_tip_name_set = set(tip_names)
if len(unique_tip_name_set) != len(tip_names):
raise ValueError("Tip names in the tree must be unique.")
unique_internal_node_name_set = set(internal_node_names)
if len(unique_tip_name_set & unique_internal_node_name_set) > 0:
raise ValueError(
"Tip names in the tree cannot overlap with internal node "
"names.")
if len(unique_internal_node_name_set) != len(internal_node_names):
warnings.warn("Internal node names in the tree are not unique.",
TreeFormatWarning)
bp_tree = Tree(bp_tree)
bp_tree.update_geometry(use_lengths)
return bp_tree
