def get_fam(rfid):
'''Get a family including tree and sequence information
from an Rfam data dump stored in data/rfam
inputs:
rfid: rfam family id.
outputs:
ali: a biopython alignment
tree: a biopython tree from a newick file.
info: information parsed from the original stockholm file.
'''
fmeta = open(cfg.dataPath('rfam/family_metas/{0}.pickle'.format(rfid)))
fali = open(cfg.dataPath('rfam/family_alis/{0}.fa'.format(rfid)))
ali = aio.parse(fali, 'fasta').next()
info = pickle.load(fmeta)
fname = cfg.dataPath('rfam/Rfam.seed_tree/{0}.seed_tree'.format(rfid))
tree = nio.parse(
open(cfg.dataPath(
'rfam/Rfam.seed_tree/{0}.seed_tree'.format(rfid)))).next()
return ali, tree, info
def test_phylotree(self):
sample_names = [
s["sample_name"] for s in self.common_inputs["samples"]
]
res = self.run_miniwdl()
outputs = res["outputs"]
self.assertCountEqual(outputs.keys(), [
"phylotree.clustermap_png",
"phylotree.clustermap_svg",
"phylotree.ncbi_metadata_json",
"phylotree.phylotree_newick",
"phylotree.ska_distances",
"phylotree.variants",
])
with open(outputs["phylotree.phylotree_newick"]) as f:
tree = next(NewickIO.parse(f))
nodes = [
n.name for n in tree.get_terminals() + tree.get_nonterminals()
if n.name
]
self.assertCountEqual(nodes, sample_names + self.accession_ids)
identifiers = sorted(sample_names + self.accession_ids)
with open(outputs["phylotree.ska_distances"]) as f:
pairs = [
sorted([r["Sample 1"], r["Sample 2"]])
for r in DictReader(f, delimiter="\t")
]
expected = [[a, b] for a in identifiers for b in identifiers
if a < b]
self.assertCountEqual(pairs, expected)
with open(outputs["phylotree.variants"]) as f:
self.assertCountEqual(identifiers,
[r.id for r in SeqIO.parse(f, "fasta")])
with open(outputs["phylotree.ncbi_metadata_json"]) as f:
self.assertEqual(
json.load(f), {
"NC_012532.1": {
"name": "Zika virus, complete genome",
"country": "Uganda",
},
"NC_035889.1": {
"name":
"Zika virus isolate ZIKV/H. sapiens/Brazil/Natal/2015, complete genome",
"country": "Brazil: Rio Grande do Norte, Natal",
"collection_date": "2015",
},
})
with open(outputs["phylotree.clustermap_svg"]) as f:
full_text = "\n".join(f.readlines())
for name in sample_names + self.accession_ids:
self.assertEqual(full_text.count(name), 2, name)
def readOneTree(stream): """Reads a Newick-formatted tree, permitting lines with comments denoted by leading '#'.""" tree_string = "" lines = stream.readlines() for line in lines: if not line.strip()[0] == '#': tree_string += line.strip() trees = NewickIO.parse(StringIO(tree_string)) tree = next(trees) return tree
def readOneTree(stream): """Reads a Newick-formatted tree, permitting lines with comments denoted by leading '#'.""" tree_string = "" lines = stream.readlines() for line in lines: if not line.strip()[0] == '#': tree_string += line.strip() trees = NewickIO.parse(StringIO(tree_string)) tree = next(trees) return tree
def main(newick: str, output_newick: str, samples: Iterable[Sample]):
sample_name_by_workflow_run_id = {
str(s["workflow_run_id"]): s["sample_name"]
for s in samples
}
with open(newick) as i, open(output_newick, "w") as o:
tree = next(NewickIO.parse(i))
for node in tree.find_clades(order="level"):
node.name = sample_name_by_workflow_run_id.get(
node.name, node.name)
NewickIO.write([tree], o)
def read_fasta_or_newick_and_return_tree(path, nwk_path=None, patt=None):
global NUM_OF_VIRIONS
if any(path.name.endswith(x) for x in FASTA_EXTENSIONS):
seqs = AlignIO.read(path, FASTA)
seqs._records = [x for x in seqs if get_count(x, patt) > MIN_COUNT]
NUM_OF_VIRIONS = int(sum(get_count(x, patt) for x in seqs))
if len(seqs) <= 2: return None
tree = build_phylogenetic_tree(seqs)
if nwk_path is not None and tree is not None:
NewickIO.write([tree], nwk_path)
elif any(path.name.endswith(x) for x in NEWICK_EXTENSIONS):
tree = NewickIO.parse(path).next()
# Root the tree if necessary
if not tree.rooted:
tree.root_at_midpoint()
return tree
def get_fam(rfid):
'''Get a family including tree and sequence information
from an Rfam data dump stored in data/rfam
inputs:
rfid: rfam family id.
outputs:
ali: a biopython alignment
tree: a biopython tree from a newick file.
info: information parsed from the original stockholm file.
'''
fmeta = open( cfg.dataPath('rfam/family_metas/{0}.pickle'.format(rfid)))
fali = open( cfg.dataPath('rfam/family_alis/{0}.fa'.format(rfid)))
ali = aio.parse(fali,'fasta').next()
info= pickle.load(fmeta)
fname = cfg.dataPath('rfam/Rfam.seed_tree/{0}.seed_tree'.format(rfid))
tree = nio.parse(open(cfg.dataPath('rfam/Rfam.seed_tree/{0}.seed_tree'.format(rfid)))).next()
return ali, tree, info
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)
if not os.path.isfile(fname):
raise IOError("# Error: file {} does not exist".format(fname))
with open(fname, 'r') as inf:
# Read a FASTA file?
(headers, seqs) = biofile.readFASTA(inf)
# Read tree
tree_fname = os.path.expanduser(options.tree_in_fname)
if not os.path.isfile(tree_fname):
raise IOError("# Error: file {} does not exist".format(tree_fname))
tree_string = ""
with open(tree_fname, 'r') as inf:
lines = inf.readlines()
for line in lines:
if not line.strip()[0] == '#':
tree_string += line.strip()
trees = NewickIO.parse(StringIO(tree_string))
tree = next(trees)
# Read mapping file
map_fname = os.path.expanduser(options.mapping_in_fname)
if not os.path.isfile(map_fname):
raise IOError("# Error: file {} does not exist".format(map_fname))
with open(map_fname, 'r') as inf:
map_table = util.readTable(inf, header=True)
# Create mapping
mapping_dict = dict(zip(map_table['species'],
map_table['updated.species']))
# Update the FASTA headers
#new_headers = []
#new_seqs = []