def run_dnadiff_pairwise(fasta_files, fasta_names, output_folder):
"""Runs MUMmer's dnadiff pairwise for given fasta_files. Uses fasta_names
to organize output folders for dnadiff as fastaname1_vs_fastaname2."""
assert len(fasta_files) == len(fasta_names)
for i in range(len(fasta_files)):
for j in range(i + 1, len(fasta_files)):
out_dir = ospj(output_folder, "{fn1}_vs_{fn2}".format(
fn1=fasta_names[i], fn2=fasta_names[j]))
dir_utils.mkdir_p(out_dir)
run_dnadiff(fasta_files[i], fasta_files[j], ospj(out_dir, "out"))
def run_dnadiff_pairwise(fasta_files, fasta_names, output_folder):
"""Runs MUMmer's dnadiff pairwise for given fasta_files. Uses fasta_names
to organize output folders for dnadiff as fastaname1_vs_fastaname2."""
assert len(fasta_files) == len(fasta_names)
for i in range(len(fasta_files)):
for j in range(i + 1, len(fasta_files)):
out_dir = ospj(
output_folder, "{fn1}_vs_{fn2}".format(fn1=fasta_names[i],
fn2=fasta_names[j]))
dir_utils.mkdir_p(out_dir)
run_dnadiff(fasta_files[i], fasta_files[j], ospj(out_dir, "out"))
def parallel_run_dnadiff_pairwise(fasta_files, fasta_names, output_folder):
"""Runs MUMmer's dnadiff pairwise for given fasta_files using
multiprocessing. Uses fasta_names to organize output folders for dnadiff as
fastaname1_vs_fastaname2."""
assert len(fasta_files) == len(fasta_names)
pool = Pool()
args = []
for i in range(len(fasta_files)):
for j in range(i + 1, len(fasta_files)):
out_dir = ospj(output_folder, "{fn1}_vs_{fn2}".format(
fn1=fasta_names[i], fn2=fasta_names[j]))
dir_utils.mkdir_p(out_dir)
args.append((fasta_files[i], fasta_files[j], ospj(out_dir, "out")))
pool.map(run_dnadiff_star, args)
pool.close()
pool.join()
def write_approved_bins(app_binsdf, fasta_file, output_folder, prefix):
"""Write given approved bins from scg_tsv to given
output_folder/prefix_binid.fa"""
# get fasta dict
with open(fasta_file) as handle:
rdict = SeqIO.to_dict(SeqIO.parse(handle, "fasta"))
# print approved bins
dir_utils.mkdir_p(output_folder)
for bin_id, contigs in app_binsdf.loc[:, ["Cluster",
"Contigs"]].as_matrix():
contig_ids = contigs.split("|")
out_file = ospj(output_folder,
"{prefix}_bin{bin_id}.fa".format(bin_id=bin_id, prefix=prefix))
with open(out_file, "w") as handle:
for cid in contig_ids:
handle.write(">{}\n{}\n".format(cid, rdict[cid].seq))
def parallel_run_dnadiff_pairwise(fasta_files, fasta_names, output_folder):
"""Runs MUMmer's dnadiff pairwise for given fasta_files using
multiprocessing. Uses fasta_names to organize output folders for dnadiff as
fastaname1_vs_fastaname2."""
assert len(fasta_files) == len(fasta_names)
pool = Pool()
args = []
for i in range(len(fasta_files)):
for j in range(i + 1, len(fasta_files)):
out_dir = ospj(
output_folder, "{fn1}_vs_{fn2}".format(fn1=fasta_names[i],
fn2=fasta_names[j]))
dir_utils.mkdir_p(out_dir)
args.append((fasta_files[i], fasta_files[j], ospj(out_dir, "out")))
pool.map(run_dnadiff_star, args)
pool.close()
pool.join()
def setUp(self):
"""Delete temporary dir if it exists then create it"""
self.tearDown()
dir_utils.mkdir_p(TMP_BASENAME_DIR)
def setUp(self):
"""Delete temporary dir if it exists then create it"""
self.tearDown()
dir_utils.mkdir_p(TMP_BASENAME_DIR)
