def build_bid_taxonomy_map(self):
self.bid_taxonomy_map = {}
self.ranks_set = set([])
for node in self.tax_tree.traverse("postorder"):
if not node.is_root() and hasattr(node, "B"):
parent = node.up
branch_rdiff = Taxonomy.lowest_assigned_rank_level(node.ranks) - Taxonomy.lowest_assigned_rank_level(
parent.ranks
)
branch_rank_id = Taxonomy.get_rank_uid(node.ranks)
branch_len = node.dist
self.bid_taxonomy_map[node.B] = (branch_rank_id, branch_rdiff, branch_len)
self.ranks_set.add(branch_rank_id)
def build_bid_taxonomy_map(self):
self.bid_taxonomy_map = {}
self.ranks_set = set([])
for node in self.tax_tree.traverse("postorder"):
if not node.is_root() and hasattr(node, "B"):
parent = node.up
branch_rdiff = Taxonomy.lowest_assigned_rank_level(
node.ranks) - Taxonomy.lowest_assigned_rank_level(
parent.ranks)
branch_rank_id = Taxonomy.get_rank_uid(node.ranks)
branch_len = node.dist
self.bid_taxonomy_map[node.B] = (branch_rank_id, branch_rdiff,
branch_len)
self.ranks_set.add(branch_rank_id)
def strip_missing_ranks(self, ranks):
rank_level = len(ranks)
while not Taxonomy.get_rank_uid(
ranks[0:rank_level]) in self.ranks_set and rank_level > 0:
rank_level -= 1
return ranks[0:rank_level]
def get_seq_ranks_from_tree(self, seq_name):
if seq_name not in self.name2taxnode:
errmsg = "FATAL ERROR: Sequence %s is not found in the taxonomic tree!" % seq_name
self.cfg.exit_fatal_error(errmsg)
seq_node = self.name2taxnode[seq_name]
ranks = Taxonomy.split_rank_uid(seq_node.up.name)
return ranks
def get_seq_ranks_from_tree(self, seq_name):
if seq_name not in self.name2taxnode:
errmsg = "FATAL ERROR: Sequence %s is not found in the taxonomic tree!" % seq_name
self.cfg.exit_fatal_error(errmsg)
seq_node = self.name2taxnode[seq_name]
ranks = Taxonomy.split_rank_uid(seq_node.up.name)
return ranks
def label_bf_tree_with_ranks(self):
"""labeling inner tree nodes with taxonomic ranks"""
if not self.bf_rooted_tree:
raise AssertionError(
"self.bf_rooted_tree is not set: TaxTreeHelper.set_bf_unrooted_tree() must be called before!"
)
for node in self.bf_rooted_tree.traverse("postorder"):
if node.is_leaf():
seq_ranks = self.origin_taxonomy[node.name]
rank_level = Taxonomy.lowest_assigned_rank_level(seq_ranks)
node.add_feature("rank_level", rank_level)
node.add_feature("ranks", seq_ranks)
node.name += "__" + seq_ranks[rank_level]
else:
if len(node.children) != 2:
raise AssertionError(
"FATAL ERROR: tree is not bifurcating!")
lchild = node.children[0]
rchild = node.children[1]
rank_level = min(lchild.rank_level, rchild.rank_level)
while rank_level >= 0 and lchild.ranks[
rank_level] != rchild.ranks[rank_level]:
rank_level -= 1
node.add_feature("rank_level", rank_level)
node_ranks = [Taxonomy.EMPTY_RANK] * max(
len(lchild.ranks), len(rchild.ranks))
if rank_level >= 0:
node_ranks[0:rank_level + 1] = lchild.ranks[0:rank_level +
1]
node.name = lchild.ranks[rank_level]
else:
node.name = "Undefined"
if hasattr(node, "B"):
self.cfg.log.debug(
"INFO: empty taxonomic annotation for branch %s (child nodes have no common ranks)",
node.B)
node.add_feature("ranks", node_ranks)
self.tax_tree = self.bf_rooted_tree
self.init_taxnode_map()
def label_bf_tree_with_ranks(self):
"""labeling inner tree nodes with taxonomic ranks"""
if not self.bf_rooted_tree:
raise AssertionError(
"self.bf_rooted_tree is not set: TaxTreeHelper.set_bf_unrooted_tree() must be called before!"
)
for node in self.bf_rooted_tree.traverse("postorder"):
if node.is_leaf():
seq_ranks = self.origin_taxonomy[node.name]
rank_level = Taxonomy.lowest_assigned_rank_level(seq_ranks)
node.add_feature("rank_level", rank_level)
node.add_feature("ranks", seq_ranks)
node.name += "__" + seq_ranks[rank_level]
else:
if len(node.children) != 2:
raise AssertionError("FATAL ERROR: tree is not bifurcating!")
lchild = node.children[0]
rchild = node.children[1]
rank_level = min(lchild.rank_level, rchild.rank_level)
while rank_level >= 0 and lchild.ranks[rank_level] != rchild.ranks[rank_level]:
rank_level -= 1
node.add_feature("rank_level", rank_level)
node_ranks = [Taxonomy.EMPTY_RANK] * max(len(lchild.ranks), len(rchild.ranks))
if rank_level >= 0:
node_ranks[0 : rank_level + 1] = lchild.ranks[0 : rank_level + 1]
node.name = lchild.ranks[rank_level]
else:
node.name = "Undefined"
if hasattr(node, "B"):
self.cfg.log.debug(
"INFO: empty taxonomic annotation for branch %s (child nodes have no common ranks)", node.B
)
node.add_feature("ranks", node_ranks)
self.tax_tree = self.bf_rooted_tree
self.init_taxnode_map()
def assign_taxonomy_maxsum(self, edges, minlw):
"""this function sums up all LH-weights for each rank and takes the rank with the max. sum """
# in EPA result, each placement(=branch) has a "weight"
# since we are interested in taxonomic placement, we do not care about branch vs. branch comparisons,
# but only consider rank vs. rank (e. g. G1 S1 vs. G1 S2 vs. G1)
# Thus we accumulate weights for each rank, there are to measures:
# "own" weight = sum of weight of all placements EXACTLY to this rank (e.g. for G1: G1 only)
# "total" rank = own rank + own rank of all children (for G1: G1 or G1 S1 or G1 S2)
rw_own = {}
rw_total = {}
ranks = [Taxonomy.EMPTY_RANK]
for edge in edges:
br_id = str(edge[0])
lweight = edge[2]
lowest_rank = None
lowest_rank_lvl = None
if lweight == 0.:
continue
# accumulate weight for the current sequence
br_rank_id, rdiff, brlen = self.bid_taxonomy_map[br_id]
ranks = Taxonomy.split_rank_uid(br_rank_id)
for i in range(len(ranks)):
rank = ranks[i]
rank_id = Taxonomy.get_rank_uid(ranks, i)
if rank != Taxonomy.EMPTY_RANK:
rw_total[rank_id] = rw_total.get(rank_id, 0) + lweight
lowest_rank_lvl = i
lowest_rank = rank_id
else:
break
if lowest_rank:
if rdiff > 0:
# if ranks of 'upper' and 'lower' adjacent nodes of a branch are non-equal, split LHW among them
parent_rank = Taxonomy.get_rank_uid(
ranks, lowest_rank_lvl - rdiff)
rw_own[lowest_rank] = rw_own.get(
lowest_rank, 0) + lweight * (1 - self.parent_lhw_coeff)
rw_own[parent_rank] = rw_own.get(
parent_rank, 0) + lweight * self.parent_lhw_coeff
# correct total lhw for all levels between "parent" and "lowest"
# NOTE: all those intermediate ranks are in fact indistinguishable, e.g. a family which contains a single genus
for r in range(rdiff):
interim_rank = Taxonomy.get_rank_uid(
ranks, lowest_rank_lvl - r)
rw_total[interim_rank] = rw_total.get(
interim_rank, 0) - lweight * self.parent_lhw_coeff
else:
rw_own[lowest_rank] = rw_own.get(lowest_rank, 0) + lweight
# else:
# self.cfg.log.debug("WARNING: no annotation for branch %s", br_id)
# if all branches have empty ranks only, just return this placement
if len(rw_total) == 0:
return ranks, [1.] * len(ranks)
# we assign the sequence to a rank, which has the max "own" weight AND
# whose "total" weight is greater than a confidence threshold
max_rw = 0.
ass_rank_id = None
for r in rw_own.iterkeys():
if rw_own[r] > max_rw and rw_total[r] >= minlw:
ass_rank_id = r
max_rw = rw_own[r]
if not ass_rank_id:
ass_rank_id = max(rw_total.iterkeys(),
key=(lambda key: rw_total[key]))
a_ranks = Taxonomy.split_rank_uid(ass_rank_id)
# "total" weight is considered as confidence value for now
a_conf = [0.] * len(a_ranks)
for i in range(len(a_conf)):
rank = a_ranks[i]
if rank != Taxonomy.EMPTY_RANK:
rank_id = Taxonomy.get_rank_uid(a_ranks, i)
a_conf[i] = rw_total[rank_id]
return a_ranks, a_conf
def get_branch_ranks(self, br_id):
br_rec = self.bid_taxonomy_map[br_id]
br_rank_id = br_rec[0]
ranks = Taxonomy.split_rank_uid(br_rank_id)
return ranks
def assign_taxonomy_maxsum(self, edges, minlw):
"""this function sums up all LH-weights for each rank and takes the rank with the max. sum """
# in EPA result, each placement(=branch) has a "weight"
# since we are interested in taxonomic placement, we do not care about branch vs. branch comparisons,
# but only consider rank vs. rank (e. g. G1 S1 vs. G1 S2 vs. G1)
# Thus we accumulate weights for each rank, there are to measures:
# "own" weight = sum of weight of all placements EXACTLY to this rank (e.g. for G1: G1 only)
# "total" rank = own rank + own rank of all children (for G1: G1 or G1 S1 or G1 S2)
rw_own = {}
rw_total = {}
ranks = [Taxonomy.EMPTY_RANK]
for edge in edges:
br_id = str(edge[0])
lweight = edge[2]
lowest_rank = None
lowest_rank_lvl = None
if lweight == 0.0:
continue
# accumulate weight for the current sequence
br_rank_id, rdiff, brlen = self.bid_taxonomy_map[br_id]
ranks = Taxonomy.split_rank_uid(br_rank_id)
for i in range(len(ranks)):
rank = ranks[i]
rank_id = Taxonomy.get_rank_uid(ranks, i)
if rank != Taxonomy.EMPTY_RANK:
rw_total[rank_id] = rw_total.get(rank_id, 0) + lweight
lowest_rank_lvl = i
lowest_rank = rank_id
else:
break
if lowest_rank:
if rdiff > 0:
# if ranks of 'upper' and 'lower' adjacent nodes of a branch are non-equal, split LHW among them
parent_rank = Taxonomy.get_rank_uid(ranks, lowest_rank_lvl - rdiff)
rw_own[lowest_rank] = rw_own.get(lowest_rank, 0) + lweight * (1 - self.parent_lhw_coeff)
rw_own[parent_rank] = rw_own.get(parent_rank, 0) + lweight * self.parent_lhw_coeff
# correct total lhw for all levels between "parent" and "lowest"
# NOTE: all those intermediate ranks are in fact indistinguishable, e.g. a family which contains a single genus
for r in range(rdiff):
interim_rank = Taxonomy.get_rank_uid(ranks, lowest_rank_lvl - r)
rw_total[interim_rank] = rw_total.get(interim_rank, 0) - lweight * self.parent_lhw_coeff
else:
rw_own[lowest_rank] = rw_own.get(lowest_rank, 0) + lweight
# else:
# self.cfg.log.debug("WARNING: no annotation for branch %s", br_id)
# if all branches have empty ranks only, just return this placement
if len(rw_total) == 0:
return ranks, [1.0] * len(ranks)
# we assign the sequence to a rank, which has the max "own" weight AND
# whose "total" weight is greater than a confidence threshold
max_rw = 0.0
ass_rank_id = None
for r in rw_own.iterkeys():
if rw_own[r] > max_rw and rw_total[r] >= minlw:
ass_rank_id = r
max_rw = rw_own[r]
if not ass_rank_id:
ass_rank_id = max(rw_total.iterkeys(), key=(lambda key: rw_total[key]))
a_ranks = Taxonomy.split_rank_uid(ass_rank_id)
# "total" weight is considered as confidence value for now
a_conf = [0.0] * len(a_ranks)
for i in range(len(a_conf)):
rank = a_ranks[i]
if rank != Taxonomy.EMPTY_RANK:
rank_id = Taxonomy.get_rank_uid(a_ranks, i)
a_conf[i] = rw_total[rank_id]
return a_ranks, a_conf
def get_branch_ranks(self, br_id):
br_rec = self.bid_taxonomy_map[br_id]
br_rank_id = br_rec[0]
ranks = Taxonomy.split_rank_uid(br_rank_id)
return ranks
def strip_missing_ranks(self, ranks):
rank_level = len(ranks)
while not Taxonomy.get_rank_uid(ranks[0:rank_level]) in self.ranks_set and rank_level > 0:
rank_level -= 1
return ranks[0:rank_level]