def generate_skbio_tree(classification, existing_tree=None):
from skbio.tree import MissingNodeError, TreeNode
otus = classification.results()['table']
if existing_tree is None:
tree = TreeNode(name='1', length=1)
tree.tax_name = 'Root'
tree.rank = 'no rank'
else:
tree = existing_tree
# we use this to keep track of nodes that haven't had their parent added yet
unlinked = defaultdict(list)
for otu in otus:
tax_id = otu['tax_id']
# skip nodes already in the tree
try:
tree.find(tax_id)
continue
except MissingNodeError:
pass
# try to find a parent (if it exists)
parent_id = otu['parent_tax_id']
try:
parent = tree.find(parent_id)
# the children are merged out here (only if we have a parent) to
# make sure we're not creating trees inside unlinked itself
children = _merge_unlinked(tax_id, unlinked)
except MissingNodeError:
parent = None
children = None
# create the node
node = TreeNode(name=tax_id, length=1, children=children)
node.tax_name = otu.get('name', '')
node.rank = otu.get('rank', 'no rank')
# either add the node to its parent or keep track of it until its
# parent is "in tree" too
if parent is not None:
parent.append(node)
else:
unlinked[parent_id].append(node)
assert len(
unlinked) == 0, 'some unlinked nodes were not included in the tree'
return tree
def unifrac(classifications, weighted=True,
field='readcount_w_children', rank='species', strict=False):
"""
A beta diversity metric that takes into account the relative relatedness of community members.
Weighted UniFrac looks at abundances, unweighted UniFrac looks at presence
"""
assert field in ACCEPTABLE_FIELDS
counts, tax_ids, ids = beta_counts(classifications, field=field, rank=rank)
tree = None
for c in classifications:
if strict and c.job.id != classifications[0].job.id:
raise OneCodexException('All Classifications must have the same Job for Unifrac')
tree = generate_skbio_tree(c, existing_tree=tree)
# there's a bug (?) in skbio where it expects the root to only have
# one child, so we do a little faking here
new_tree = TreeNode(name='fake root')
new_tree.rank = 'no rank'
new_tree.append(tree)
# prune low-level nodes off the tree so the tips are what we're comparing
prune_to_rank(new_tree, rank=rank)
if weighted:
return skbio.diversity.beta_diversity('weighted_unifrac', counts, ids,
tree=new_tree, otu_ids=tax_ids)
else:
return skbio.diversity.beta_diversity('unweighted_unifrac', counts, ids,
tree=new_tree, otu_ids=tax_ids)
def unifrac(self, weighted=True, rank="auto"):
"""Calculate the UniFrac beta diversity metric.
UniFrac takes into account the relatedness of community members. Weighted UniFrac considers
abundances, unweighted UniFrac considers presence.
Parameters
----------
weighted : `bool`
Calculate the weighted (True) or unweighted (False) distance metric.
rank : {'auto', 'kingdom', 'phylum', 'class', 'order', 'family', 'genus', 'species'}, optional
Analysis will be restricted to abundances of taxa at the specified level.
Returns
-------
skbio.stats.distance.DistanceMatrix, a distance matrix.
"""
# needs read counts, not relative abundances
import skbio.diversity
if self._guess_normalized():
raise OneCodexException("UniFrac requires unnormalized read counts.")
df = self.to_df(rank=rank, normalize=False)
counts = []
for c_id in df.index:
counts.append(df.loc[c_id].tolist())
tax_ids = df.keys().tolist()
tree = self.tree_build()
tree = self.tree_prune_rank(tree, rank=df.ocx_rank)
# there's a bug (?) in skbio where it expects the root to only have
# one child, so we do a little faking here
from skbio.tree import TreeNode
new_tree = TreeNode(name="fake root")
new_tree.rank = "no rank"
new_tree.append(tree)
# then finally run the calculation and return
if weighted:
return skbio.diversity.beta_diversity(
"weighted_unifrac", counts, df.index.tolist(), tree=new_tree, otu_ids=tax_ids
)
else:
return skbio.diversity.beta_diversity(
"unweighted_unifrac", counts, df.index.tolist(), tree=new_tree, otu_ids=tax_ids
)
def unifrac(self, weighted=True, rank="auto"):
"""A beta diversity metric that takes into account the relative relatedness of community
members. Weighted UniFrac looks at abundances, unweighted UniFrac looks at presence.
Parameters
----------
weighted : `bool`
Calculate the weighted (True) or unweighted (False) distance metric.
rank : {'auto', 'kingdom', 'phylum', 'class', 'order', 'family', 'genus', 'species'}, optional
Analysis will be restricted to abundances of taxa at the specified level.
Returns
-------
skbio.stats.distance.DistanceMatrix, a distance matrix.
"""
# needs read counts, not relative abundances
if self._guess_normalized():
raise OneCodexException("UniFrac requires unnormalized read counts.")
df = self.to_df(rank=rank, normalize=False)
counts = []
for c_id in df.index:
counts.append(df.loc[c_id].tolist())
tax_ids = df.keys().tolist()
tree = self.tree_build()
tree = self.tree_prune_rank(tree, rank=df.ocx_rank)
# there's a bug (?) in skbio where it expects the root to only have
# one child, so we do a little faking here
from skbio.tree import TreeNode
new_tree = TreeNode(name="fake root")
new_tree.rank = "no rank"
new_tree.append(tree)
# then finally run the calculation and return
if weighted:
return skbio.diversity.beta_diversity(
"weighted_unifrac", counts, df.index.tolist(), tree=new_tree, otu_ids=tax_ids
)
else:
return skbio.diversity.beta_diversity(
"unweighted_unifrac", counts, df.index.tolist(), tree=new_tree, otu_ids=tax_ids
)
def tree_build(self):
"""Build a tree from the taxonomy data present in this object.
This is designed for use with `ClassificationsDataFrame` or `SampleCollection`.
Returns
-------
`skbio.tree.TreeNode`, the root node of a tree that contains all the taxa in the current
analysis and their parents leading back to the root node.
"""
from skbio.tree import TreeNode
# build all the nodes
nodes = {}
for tax_id in self.taxonomy.index:
node = TreeNode(name=tax_id, length=1)
node.tax_name = self.taxonomy["name"][tax_id]
node.rank = self.taxonomy["rank"][tax_id]
node.parent_tax_id = self.taxonomy["parent_tax_id"][tax_id]
nodes[tax_id] = node
# generate all the links
for tax_id in self.taxonomy.index:
try:
parent = nodes[nodes[tax_id].parent_tax_id]
except KeyError:
if tax_id != "1":
warnings.warn(
"tax_id={} has parent_tax_id={} which is not in tree"
"".format(tax_id, nodes[tax_id].parent_tax_id))
continue
parent.append(nodes[tax_id])
return nodes["1"]
def tree_build(self):
"""Build a tree from the taxonomy data present in this `ClassificationsDataFrame` or
`SampleCollection`.
Returns
-------
`skbio.tree.TreeNode`, the root node of a tree that contains all the taxa in the current
analysis and their parents leading back to the root node.
"""
from skbio.tree import TreeNode
# build all the nodes
nodes = {}
for tax_id in self.taxonomy.index:
node = TreeNode(name=tax_id, length=1)
node.tax_name = self.taxonomy["name"][tax_id]
node.rank = self.taxonomy["rank"][tax_id]
node.parent_tax_id = self.taxonomy["parent_tax_id"][tax_id]
nodes[tax_id] = node
# generate all the links
for tax_id in self.taxonomy.index:
try:
parent = nodes[nodes[tax_id].parent_tax_id]
except KeyError:
if tax_id != "1":
warnings.warn(
"tax_id={} has parent_tax_id={} which is not in tree"
"".format(tax_id, nodes[tax_id].parent_tax_id)
)
continue
parent.append(nodes[tax_id])
return nodes["1"]
def unifrac(self, weighted=True, rank=Rank.Auto):
"""Calculate the UniFrac beta diversity metric.
UniFrac takes into account the relatedness of community members. Weighted UniFrac considers
abundances, unweighted UniFrac considers presence.
Parameters
----------
weighted : `bool`
Calculate the weighted (True) or unweighted (False) distance metric.
rank : {'auto', 'kingdom', 'phylum', 'class', 'order', 'family', 'genus', 'species'}, optional
Analysis will be restricted to abundances of taxa at the specified level.
Returns
-------
skbio.stats.distance.DistanceMatrix, a distance matrix.
"""
import skbio.diversity
df = self.to_df(rank=rank, normalize=self._guess_normalized())
ocx_rank = df.ocx_rank
# The scikit-bio implementations of phylogenetic metrics require integer counts
if self._guess_normalized():
df = df * 10e9
tax_ids = df.keys().tolist()
tree = self.tree_build()
tree = self.tree_prune_rank(tree, rank=ocx_rank)
# `scikit-bio` requires that the tree root has no more than 2
# children, otherwise it considers it "unrooted".
#
# https://github.com/biocore/scikit-bio/blob/f3ae1dcfe8ea88e52e19f6693d79e529d05bda04/skbio/diversity/_util.py#L89
#
# Our taxonomy root regularly has more than 2 children, so we
# add a fake parent of `root` to the tree here.
from skbio.tree import TreeNode
new_tree = TreeNode(name="fake root")
new_tree.rank = "no rank"
new_tree.append(tree)
# then finally run the calculation and return
if weighted:
return skbio.diversity.beta_diversity(
BetaDiversityMetric.WeightedUnifrac,
df,
df.index,
tree=new_tree,
otu_ids=tax_ids,
normalized=True,
)
else:
return skbio.diversity.beta_diversity(
BetaDiversityMetric.UnweightedUnifrac,
df,
df.index,
tree=new_tree,
otu_ids=tax_ids,
)
