def check_distances(ref_fasta, fastq_folder, work_dir):
bad_fastqs = list()
# fastqs = glob.glob(os.path.join(fastq_folder, '*R1*'))
mash.sketch(os.path.join(fastq_folder, '*R1*'), output_sketch=os.path.join(work_dir, 'sketch.msh'), threads=5)
mash.dist(os.path.join(work_dir, 'sketch.msh'), ref_fasta, threads=48,
output_file=os.path.join(work_dir, 'distances.tab'))
mash_output = mash.read_mash_output(os.path.join(work_dir, 'distances.tab'))
for item in mash_output:
print(item.reference, item.query, str(item.distance))
if item.distance > 0.15: # Moved value from 0.06 to 0.15 - was definitely too conservative before.
bad_fastqs.append(item.reference)
return bad_fastqs
def test_mash_sketch_call_multithreaded():
out, err, cmd = mash.sketch('tests/dummy_fastq/*fastq',
output_sketch='tests/sketch.msh',
returncmd=True,
threads=4)
assert cmd == 'mash sketch tests/dummy_fastq/*fastq -o tests/sketch.msh -p 4 '
os.remove('tests/sketch.msh')
def check_distances(ref_fasta, fasta_folder):
bad_fastqs = list()
# fastqs = glob.glob(os.path.join(fastq_folder, '*R1*'))
mash.sketch(os.path.join(fasta_folder, '*.fasta'),
output_sketch=os.path.join(fasta_folder, 'sketch.msh'),
threads=56)
mash.dist(os.path.join(fasta_folder, 'sketch.msh'),
ref_fasta,
threads=56,
output_file=os.path.join(fasta_folder, 'distances.tab'))
mash_output = mash.read_mash_output(
os.path.join(fasta_folder, 'distances.tab'))
for item in mash_output:
print(item.reference, item.query, str(item.distance))
if item.distance > 0.06: # May need to adjust this value.
bad_fastqs.append(item.reference)
return bad_fastqs
def test_sketch_no_input_files():
with pytest.raises(ValueError):
mash.sketch()
def test_mash_sketch_call():
out, err, cmd = mash.sketch('tests/dummy_fastq/*fastq',
output_sketch='tests/sketch.msh',
returncmd=True)
assert cmd == 'mash sketch tests/dummy_fastq/*fastq -o tests/sketch.msh -p 1 '
os.remove('tests/sketch.msh')
def mash_for_potential_plasmids(plasmid_db,
forward_reads,
output_dir,
reverse_reads=None,
threads=1,
logfile=None,
identity_cutoff=0.95):
"""
Uses mash to find a list of potential plasmids in a set of forward (and optionally reverse) reads.
:param plasmid_db: Path to a multi-Fasta-formatted file that has plasmid sequences of interest.
:param forward_reads: Path to forward reads.
:param output_dir: Path to output directory where mash sketch/screen result file will be stored.
:param reverse_reads: Path to reverse reads. If not specified, things will work in unpaired mode.
:param threads: Number of threads to run mash analyses on.
:param logfile: Path to logfile you want to use.
:param identity_cutoff: Mash screen identity cutoff. Values lower than this won't be reported.
:return: potential_plasmids: A list where each entry is a putatively present plasmid, identified by
the fasta header.
"""
potential_plasmids = list()
# Make sure the output dir specified gets created if it doesn't exist.
if not os.path.isdir(output_dir):
os.makedirs(output_dir)
# Make a sketch of the plasmid db.
out, err = mash.sketch(plasmid_db,
output_sketch=os.path.join(output_dir,
'plasmid_sketch.msh'),
threads=threads,
i='')
if logfile:
accessoryFunctions.write_to_logfile(out, err, logfile)
# Now it's time to use mash screen to try to figure out what plasmids might be present in our sample.
if reverse_reads: # As usual, do things slightly differently for paired vs unpaired reads.
out, err = mash.screen(os.path.join(output_dir, 'plasmid_sketch.msh'),
forward_reads,
reverse_reads,
output_file=os.path.join(
output_dir, 'screen_results.tsv'),
threads=threads,
i=identity_cutoff)
if logfile:
accessoryFunctions.write_to_logfile(out, err, logfile)
else: # Unpaired read mode.
out, err = mash.screen(os.path.join(output_dir, 'plasmid_sketch.msh'),
forward_reads,
output_file=os.path.join(
output_dir, 'screen_results.tsv'),
threads=threads,
i=identity_cutoff)
if logfile:
accessoryFunctions.write_to_logfile(out, err, logfile)
# Now need to read through the list of potential plasmids generated by the mash screen.
results = mash.read_mash_screen(
screen_result=os.path.join(output_dir, 'screen_results.tsv'))
for item in results:
potential_plasmids.append(item.query_id)
return potential_plasmids