def distances_to_tree(
id_filename: str,
distance_filename: str,
output_filename: str,
method: str = "nj",
fmt: str = "newick",
) -> None:
r"""Read IDs and distances from files, build tree and write to a file.
Parameters
----------
id_filename : str
File containing a list of sequence IDs, one per line.
distance_filename : str
File containing distances in f"{id1}\t{id12}\t{dist}\n" format.
output_filename : str
File to write output tree.
method : str
Tree-building method. One of "nj" (default) or "upgma"
fmt : str
Output format (default = "newick")
Returns
-------
None
"""
with open(id_filename, "r") as idfile:
ids = idfile.read().split()
with open(distance_filename, "r") as distfile:
dm = build_distance_matrix(ids, distfile)
tree = build_tree(dm, method)
write(tree, output_filename, fmt)
import logging
import os
from Bio.Phylo import NexusIO, write
if '__main__' == __name__:
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('--trees', required=True, type=str)
parser.add_argument('--pattern', required=True, type=str)
params = parser.parse_args()
logging.basicConfig(level=logging.INFO, format='%(asctime)s: %(message)s', datefmt="%Y-%m-%d %H:%M:%S")
i = 0
for tree in NexusIO.parse(params.trees):
os.makedirs(os.path.dirname(params.pattern % i), exist_ok=True)
write([tree], params.pattern % i, 'newick', plain=True)
i += 1
logging.info('Converted %d trees to newick' % i)
n.name = 'n{}'.format(i)
tree_ids = [_.name for _ in tree]
df = pd.read_csv(params.tab, sep='\t', index_col=0)
df = df.loc[df.index.isin(tree_ids), :]
cdf = df[['country', 'host']].groupby(['country']).count().to_dict()['host']
for c, n in cdf.items():
print(c, n)
c2ids = defaultdict(set)
for t in tree:
if t.name in df.index:
c2ids[df.loc[t.name, 'country']].add(t.name)
to_keep = set()
for c, ids in c2ids.items():
if not pd.isna(c):
if len(ids) <= params.threshold:
to_keep |= ids
else:
to_keep |= set(pd.np.random.choice(list(ids), size=params.threshold, replace=False))
tree = remove_certain_leaves(tree, lambda _: _.name not in to_keep)
features = [DATE, DATE_CI]
nwk = tree.write(format_root_node=True, features=features, format=3)
write(NewickIO.parse(StringIO(nwk)), params.out_tree, 'nexus')
with open(params.out_tree, 'r') as f:
nexus_str = f.read().replace('&&NHX:', '&')
for feature in features:
nexus_str = nexus_str.replace(':{}='.format(feature), ',{}='.format(feature))
with open(params.out_tree, 'w') as f:
f.write(nexus_str)
def newick(args, trees, lang=None):
p = args.module_dir.joinpath(
'static', 'trees', 'tree-%s-newick.txt' % (lang.id if lang else 'glottolog',))
with codecs.open(p, 'w', 'utf8') as fp:
write(trees, fp, 'newick')
def newick(args, trees, lang=None):
p = args.module_dir.joinpath(
'static', 'trees',
'tree-%s-newick.txt' % (lang.id if lang else 'glottolog', ))
with codecs.open(p, 'w', 'utf8') as fp:
write(trees, fp, 'newick')