def extract_rand(input_path, suffix, alignment_file):
path_argv = [input_path._version, input_path._dataset + suffix]
output_path = common.Paths(path_argv, 0)
data_versioning.setup_new_dataset(output_path)
shutil.copy(alignment_file, output_path.alignment)
shutil.copy(input_path.outgroups_file, output_path.outgroups_file)
shutil.copy(input_path.duplicates_json, output_path.duplicates_json)
def extract_me(input_path, suffix, alignment_file):
print(
"Extracting alignment generated with the maximum entropy tree thinning technique..."
)
path_argv = [input_path._version, input_path._dataset + suffix]
output_path = common.Paths(path_argv, 0)
data_versioning.setup_new_dataset(output_path)
shutil.copy(alignment_file, output_path.alignment)
shutil.copy(input_path.outgroups_file, output_path.outgroups_file)
shutil.copy(input_path.duplicates_json, output_path.duplicates_json)
print("New version of the snapshot: " + output_path.path)
def extract_ss(input_path, suffix, tree_file):
tree = Tree(tree_file, format=1)
leaves_set = set(tree.get_leaf_names())
msa = SeqGroup(input_path.alignment, "fasta")
path_argv = [input_path._version, input_path._dataset + suffix]
output_path = common.Paths(path_argv, 0)
data_versioning.setup_new_dataset(output_path)
new_msa = SeqGroup()
for entry in msa.iter_entries():
label = entry[0]
sequence = entry[1]
if (label in leaves_set):
new_msa.set_seq(label, sequence)
open(output_path.alignment, "w").write(new_msa.write(format="fasta"))
shutil.copy(input_path.duplicates_json, output_path.duplicates_json)
shutil.copy(input_path.outgroups_file, output_path.outgroups_file)
def setup_new_version( date=datetime.datetime.now().strftime("%Y-%m-%d"),
datasets = ["fmsao", "fmsan", "smsao", "smsan"]):
version_id = get_current_version_id( date )
version = "{}_{}".format( date, version_id )
# make the base path for the version
util.make_path( util.versioned_path(version, "") )
# generate the appropriate paths
paths = []
for ds in datasets:
p = common.Paths([version, ds], 0)
setup_new_dataset(p)
paths.append(p)
print(version)
return paths
def extract_ss(input_path, suffix, tree_file):
print(
"Extracting alignment generated with the support selection tree thinning technique..."
)
tree = Tree(tree_file, format=1)
leaves_set = set(tree.get_leaf_names())
msa = SeqGroup(input_path.alignment, "fasta")
path_argv = [input_path._version, input_path._dataset + suffix]
output_path = common.Paths(path_argv, 0)
data_versioning.setup_new_dataset(output_path)
new_msa = SeqGroup()
for entry in msa.iter_entries():
label = entry[0]
sequence = entry[1]
if (label in leaves_set):
new_msa.set_seq(label, sequence)
open(output_path.alignment, "w").write(new_msa.write(format="fasta"))
shutil.copy(input_path.duplicates_json, output_path.duplicates_json)
shutil.copy(input_path.outgroups_file, output_path.outgroups_file)
print("New version of the snapshot: " + output_path.path)
#!/usr/bin/env python3
import os
import sys
sys.path.insert(0, 'scripts')
import common
import thinned_dataset_extraction
paths = common.Paths(sys.argv)
# Support Selection thinning
thinned_dataset_extraction.extract_ss(paths, "-ss_thinned",
paths.ss_mre_thinned_tree)
# Clade compression thinning
#thinned_dataset_extraction.extract_cc(paths, "-cc_thinned", paths.cc_thinned_alignment)
# Max entropy thinning
#thinned_dataset_extraction.extract_cc(paths, "-me_thinned", paths.me_thinned_alignment)
# Random thinning
thinned_dataset_extraction.extract_rand(paths, "-rand_thinned",
paths.rand_thinned_alignment)