import argparse
import re
import sys
from errors import filecheck_and_quit, directorycheck_and_quit
progname = re.compile('[A-Za-z0-9.-_]+').search(sys.argv[0]).group()
desc = 'Read in a SequenceCollection from disk and print scores'
input_help = 'Filepath+name of gzipped SequenceCollection object'
category_choices = ['Observed', 'Randomised', 'Simulated', 'NA']
parser = argparse.ArgumentParser(prog=progname, description=desc)
parser.add_argument('-i', dest='input_file', help=input_help, type=str)
parser.add_argument('-t', dest='phyml_dir', help=input_help, type=str)
args = parser.parse_args()
input_file = args.input_file
phyml_dir = args.phyml_dir.rstrip('/')
filecheck_and_quit(input_file)
directorycheck_and_quit(phyml_dir)
from sequence_collection import SequenceCollection
sc = SequenceCollection.gunzip(input_file)
cluster_records = sc.get_cluster_records()
sc.load_phyml_results(phyml_dir, records=cluster_records,
use_hashname=True)
sc.update_scores()
sc.gzip(input_file)
type=str, help=datatype_help)
parser.add_argument('-score', dest='score', action='store_true')
args = vars(parser.parse_args())
input_dir = args['input'].rstrip('/')
output = args['output']
tmpdir = args['tmpdir'].rstrip('/')
min_clusters = args['min_clusters']
max_clusters = args['max_clusters']
distance = args['distance']
method = args['cluster_method']
delete = args['delete']
datatype = args['datatype']
score = args['score']
directorycheck_and_quit(input_dir)
directorycheck_and_make(tmpdir)
gtp_path = os.environ['GTP_PATH']
helper = os.environ['DARWINHELPER']
from sequence_collection import SequenceCollection
sc = SequenceCollection(
input_dir,
file_format='phylip',
datatype=datatype,
helper=helper,
gtp_path=gtp_path,
tmpdir=tmpdir,
overwrite=True,
################################################################################
import argparse
import re
import sys
from errors import filecheck_and_quit, directorycheck_and_quit
progname = re.compile('[A-Za-z0-9.-_]+').search(sys.argv[0]).group()
desc = 'Read in a SequenceCollection from disk and print scores'
input_help = 'Filepath+name of gzipped SequenceCollection object'
category_choices = ['Observed', 'Randomised', 'Simulated', 'NA']
parser = argparse.ArgumentParser(prog=progname, description=desc)
parser.add_argument('-i', dest='input_file', help=input_help, type=str)
parser.add_argument('-t', dest='phyml_dir', help=input_help, type=str)
args = parser.parse_args()
input_file = args.input_file
phyml_dir = args.phyml_dir.rstrip('/')
filecheck_and_quit(input_file)
directorycheck_and_quit(phyml_dir)
from sequence_collection import SequenceCollection
sc = SequenceCollection.gunzip(input_file)
cluster_records = sc.get_cluster_records()
sc.load_phyml_results(phyml_dir, records=cluster_records, use_hashname=True)
sc.update_scores()
sc.gzip(input_file)
def simulate_from_record_WAG(
cls,
record,
output_dir,
name='tempsim',
tmpdir='/tmp',
allow_nonsense=False,
split_lengths=None,
gene_names=None,
):
length = record.seqlength
tree = record.tree
directorycheck_and_quit(tmpdir)
gamma = tree.extract_gamma_parameter()
param_dir = '{0}/alf_parameter_dir'.format(tmpdir)
working_dir = '{0}/alf_working_dir'.format(tmpdir)
directorycheck_and_make(param_dir, verbose=False)
directorycheck_and_make(working_dir, verbose=False)
treefile = '{0}/treefile.nwk'.format(tmpdir)
tree.pam2sps('sps2pam').write_to_file(treefile)
directorycheck_and_make(param_dir)
directorycheck_and_make(working_dir)
sim = cls(simulation_name=name, working_directory=working_dir,
outfile_path=param_dir, unit_is_pam=True)
sim.indels()
sim.rate_variation(gamma)
sim.root_genome(number_of_genes=1, min_length=length)
sim.one_word_model('WAG')
sim.custom_tree(treefile)
params = sim.write_parameters()
sim.runALF(params, quiet=True)
tree_newick = tree.newick
alf_newick = \
open('{0}/alf_working_dir/{1}/RealTree.nwk'.format(tmpdir,
name)).read()
replacement_dict = dict(zip(re.findall(r'(\w+)(?=:)',
alf_newick), re.findall(r'(\w+)(?=:)',
tree_newick))) # bug correction
alignment = \
glob.glob('{0}/alf_working_dir/{1}/MSA/*aa.fa'.format(tmpdir,
name))[0]
new_record = TCSeqRec(alignment)
new_record.sequences = [seq[:length] for seq in
new_record.sequences]
new_record._update()
print new_record.seqlength
new_record.headers = [replacement_dict[x[:x.rindex('/')]]
for x in new_record.headers] # bug should be fixed
new_record._update()
new_record.sort_by_name()
if split_lengths and gene_names:
with open('{0}/trees.txt'.format(output_dir), 'a') as trf:
trf.write('{0}\t{1}\n'.format('-'.join(gene_names), tree.newick))
for rec in new_record.split_by_lengths(split_lengths,
gene_names):
rec.write_phylip('{0}/{1}.phy'.format(output_dir,
rec.name))
else:
with open('{0}/trees.txt'.format(output_dir), 'a') as trf:
trf.write('{0}\t{1}\n'.format(new_record.name, tree.newick))
new_record.write_phylip('{0}/{1}.phy'.format(output_dir,
name))
shutil.rmtree(param_dir)
shutil.rmtree(working_dir)
help=datatype_help)
parser.add_argument('-score', dest='score', action='store_true')
args = vars(parser.parse_args())
input_dir = args['input'].rstrip('/')
output = args['output']
tmpdir = args['tmpdir'].rstrip('/')
min_clusters = args['min_clusters']
max_clusters = args['max_clusters']
distance = args['distance']
method = args['cluster_method']
delete = args['delete']
datatype = args['datatype']
score = args['score']
directorycheck_and_quit(input_dir)
directorycheck_and_make(tmpdir)
gtp_path = os.environ['GTP_PATH']
helper = os.environ['DARWINHELPER']
from sequence_collection import SequenceCollection
sc = SequenceCollection(
input_dir,
file_format='phylip',
datatype=datatype,
helper=helper,
gtp_path=gtp_path,
tmpdir=tmpdir,
overwrite=True,
def simulate_from_record_WAG(
cls,
record,
output_dir,
name='tempsim',
tmpdir='/tmp',
allow_nonsense=False,
split_lengths=None,
gene_names=None,
):
length = record.seqlength
tree = record.tree
directorycheck_and_quit(tmpdir)
gamma = tree.extract_gamma_parameter()
param_dir = '{0}/alf_parameter_dir'.format(tmpdir)
working_dir = '{0}/alf_working_dir'.format(tmpdir)
directorycheck_and_make(param_dir, verbose=False)
directorycheck_and_make(working_dir, verbose=False)
treefile = '{0}/treefile.nwk'.format(tmpdir)
tree.pam2sps('sps2pam').write_to_file(treefile)
directorycheck_and_make(param_dir)
directorycheck_and_make(working_dir)
sim = cls(simulation_name=name,
working_directory=working_dir,
outfile_path=param_dir,
unit_is_pam=True)
sim.indels()
sim.rate_variation(gamma)
sim.root_genome(number_of_genes=1, min_length=length)
sim.one_word_model('WAG')
sim.custom_tree(treefile)
params = sim.write_parameters()
sim.runALF(params, quiet=True)
tree_newick = tree.newick
alf_newick = \
open('{0}/alf_working_dir/{1}/RealTree.nwk'.format(tmpdir,
name)).read()
replacement_dict = dict(
zip(re.findall(r'(\w+)(?=:)', alf_newick),
re.findall(r'(\w+)(?=:)', tree_newick))) # bug correction
alignment = \
glob.glob('{0}/alf_working_dir/{1}/MSA/*aa.fa'.format(tmpdir,
name))[0]
new_record = TCSeqRec(alignment)
new_record.sequences = [seq[:length] for seq in new_record.sequences]
new_record._update()
print new_record.seqlength
new_record.headers = [
replacement_dict[x[:x.rindex('/')]] for x in new_record.headers
] # bug should be fixed
new_record._update()
new_record.sort_by_name()
if split_lengths and gene_names:
with open('{0}/trees.txt'.format(output_dir), 'a') as trf:
trf.write('{0}\t{1}\n'.format('-'.join(gene_names),
tree.newick))
for rec in new_record.split_by_lengths(split_lengths, gene_names):
rec.write_phylip('{0}/{1}.phy'.format(output_dir, rec.name))
else:
with open('{0}/trees.txt'.format(output_dir), 'a') as trf:
trf.write('{0}\t{1}\n'.format(new_record.name, tree.newick))
new_record.write_phylip('{0}/{1}.phy'.format(output_dir, name))
shutil.rmtree(param_dir)
shutil.rmtree(working_dir)