def fetch(tree):
t = TreeNode.from_newick(open(tree))
ranks = set(nl.RANK_ORDER)
res = []
error = True
failed_nodes = []
for n in t.non_tips():
if n.name and n.name[0] not in ranks:
failed_nodes.append(n)
if failed_nodes:
for n in failed_nodes:
tip = list(n.tips())[0]
tip_id = tip.name
path = [a.name for a in tip.ancestors() if a.name is not None]
res.append("Unknown rank: %s" % n.name)
res.append("\tA tip ID from the clade: %s" % tip_id)
res.append("\tCurrent lineage in tree: %s" % '; '.join(path[::-1]))
else:
res = nl.pull_consensus_strings(t)
error = False
return res, error
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