def test_maxmatch_cmd_generation(self):
"""Generate NUCmer command line with maxmatch."""
ncmd, _ = anim.construct_nucmer_cmdline(Path("file1.fna"),
Path("file2.fna"),
outdir=self.outdir,
maxmatch=True)
self.assertEqual(ncmd, self.ntgtmax)
def test_maxmatch_cmd_generation(self):
"""generate NUCmer command line with maxmatch."""
ncmd, fcmd = anim.construct_nucmer_cmdline("file1.fna",
"file2.fna",
outdir=self.outdir,
maxmatch=True)
assert_equal(ncmd, self.ntgtmax)
def test_anim_pairwise_basic(self):
"""Test generation of basic NUCmer pairwise comparison command."""
cmd_nucmer, cmd_filter = anim.construct_nucmer_cmdline(
Path("file1.fna"), Path("file2.fna"))
tgt_nucmer = "nucmer --mum -p nucmer_output/file1_vs_file2 file1.fna file2.fna"
tgt_filter = "delta_filter_wrapper.py delta-filter -1 nucmer_output/file1_vs_file2.delta nucmer_output/file1_vs_file2.filter"
self.assertEqual(cmd_nucmer, tgt_nucmer)
self.assertEqual(cmd_filter, tgt_filter)
def test_anim_pairwise_basic():
"""Test generation of basic NUCmer pairwise comparison command.
"""
cmd = anim.construct_nucmer_cmdline("file1.fna", "file2.fna")
assert_equal(
cmd, "nucmer -mum -p ./nucmer_output/file1_vs_file2 " +
"file1.fna file2.fna")
print(cmd)
def test_single_cmd_generation(self):
"""generate single abstract NUCmer/delta-filter command-line.
Tests that a single NUCmer/delta-filter command-line pair is
produced correctly
"""
cmds = anim.construct_nucmer_cmdline("file1.fna", "file2.fna",
outdir=self.outdir)
assert_equal(cmds, (self.ntgt, self.ftgt))
def test_anim_pairwise_maxmatch(self):
"""Test generation of NUCmer pairwise comparison command with maxmatch."""
cmd_nucmer, cmd_filter = anim.construct_nucmer_cmdline(
Path("file1.fna"), Path("file2.fna"), maxmatch=True)
tgt_nucmer = (
"nucmer --maxmatch -p nucmer_output/file1_vs_file2 file1.fna file2.fna"
)
tgt_filter = "delta_filter_wrapper.py delta-filter -1 nucmer_output/file1_vs_file2.delta nucmer_output/file1_vs_file2.filter"
self.assertEqual(cmd_nucmer, tgt_nucmer)
self.assertEqual(cmd_filter, tgt_filter)
def test_single_cmd_generation(self):
"""generate single abstract NUCmer/delta-filter command-line.
Tests that a single NUCmer/delta-filter command-line pair is
produced correctly
"""
cmds = anim.construct_nucmer_cmdline("file1.fna",
"file2.fna",
outdir=self.outdir)
assert_equal(cmds, (self.ntgt, self.ftgt))
def test_anim_pairwise_maxmatch():
"""Test generation of NUCmer pairwise comparison command with maxmatch.
"""
cmd = anim.construct_nucmer_cmdline("file1.fna",
"file2.fna",
maxmatch=True)
assert_equal(
cmd, "nucmer -maxmatch -p ./nucmer_output/file1_vs_file2 " +
"file1.fna file2.fna")
print(cmd)
def test_maxmatch_single(tmp_path, path_file_two):
"""Generate NUCmer command line with maxmatch."""
ncmd, _ = anim.construct_nucmer_cmdline(path_file_two[0],
path_file_two[1],
outdir=tmp_path,
maxmatch=True)
dir_nucmer = tmp_path / "nucmer_output"
expected = (
"nucmer --maxmatch -p "
f"{dir_nucmer / str(path_file_two[0].stem + '_vs_' + path_file_two[1].stem)} "
f"{path_file_two[0]} {path_file_two[1]}")
assert ncmd == expected
def generate_joblist(
comparisons: List[Tuple],
existingfiles: List[Path],
args: Namespace,
) -> List[ComparisonJob]:
"""Return list of ComparisonJobs.
:param comparisons: list of (Genome, Genome) tuples
:param existingfiles: list of pre-existing nucmer output files
:param args: Namespace of command-line arguments for the run
"""
logger = logging.getLogger(__name__)
joblist = [] # will hold ComparisonJob structs
for idx, (query, subject) in enumerate(
tqdm(comparisons, disable=args.disable_tqdm)):
ncmd, dcmd = anim.construct_nucmer_cmdline(
query.path,
subject.path,
args.outdir,
args.nucmer_exe,
args.filter_exe,
args.maxmatch,
)
logger.debug("Commands to run:\n\t%s\n\t%s", ncmd, dcmd)
outprefix = ncmd.split()[3] # prefix for NUCmer output
if args.nofilter:
outfname = Path(outprefix + ".delta")
else:
outfname = Path(outprefix + ".filter")
logger.debug("Expected output file for db: %s", outfname)
# If we're in recovery mode, we don't want to repeat a computational
# comparison that already exists, so we check whether the ultimate
# output is in the set of existing files and, if not, we add the jobs
# TODO: something faster than a list search (dict or set?)
# The comparisons collections always gets updated, so that results are
# added to the database whether they come from recovery mode or are run
# in this call of the script.
if args.recovery and outfname.name in existingfiles:
logger.debug("Recovering output from %s, not building job",
outfname)
else:
logger.debug("Building job")
# Build jobs
njob = pyani_jobs.Job("%s_%06d-n" % (args.jobprefix, idx), ncmd)
fjob = pyani_jobs.Job("%s_%06d-f" % (args.jobprefix, idx), dcmd)
fjob.add_dependency(njob)
joblist.append(
ComparisonJob(query, subject, dcmd, ncmd, outfname, fjob))
return joblist
def test_mummer_single(tmp_path, path_file_two):
"""Generate single NUCmer/delta-filter command-line."""
cmds = anim.construct_nucmer_cmdline(path_file_two[0],
path_file_two[1],
outdir=tmp_path)
dir_nucmer = tmp_path / "nucmer_output"
expected = (
("nucmer --mum -p "
f"{dir_nucmer / str(path_file_two[0].stem + '_vs_' + path_file_two[1].stem)} "
f"{path_file_two[0]} {path_file_two[1]}"),
("delta_filter_wrapper.py delta-filter -1 "
f"{dir_nucmer / str(path_file_two[0].stem + '_vs_' + path_file_two[1].stem + '.delta')} "
f"{dir_nucmer / str(path_file_two[0].stem + '_vs_' + path_file_two[1].stem + '.filter')}"
),
)
assert cmds == expected
def test_maxmatch_cmd_generation(self):
"""generate NUCmer command line with maxmatch."""
ncmd, fcmd = anim.construct_nucmer_cmdline("file1.fna", "file2.fna",
outdir=self.outdir,
maxmatch=True)
assert_equal(ncmd, self.ntgtmax)
def test_anim_pairwise():
"""Test generation of NUCmer pairwise comparison command.
"""
cmd = anim.construct_nucmer_cmdline("file1.fna", "file2.fna")
assert_equal(cmd, "nucmer -mum -p ./file1_vs_file2 file1.fna file2.fna")
print(cmd)