def test_index(self):
# Create the list of files
files = ["trinity.gtf",
"trinity.gff3",
"trinity.cDNA_match.gff3",
"trinity.match_matchpart.gff3"]
# files = [pkg_resources.resource_filename("Mikado.tests", filename) for filename in files]
namespace = Namespace(default=False)
namespace.distance = 2000
namespace.index = True
namespace.prediction = None
namespace.log = os.path.join(tempfile.gettempdir(), "index.log")
logger = create_null_logger("null")
for ref in files:
with self.subTest(ref=ref):
temp_ref = os.path.join(tempfile.gettempdir(), ref)
with pkg_resources.resource_stream("Mikado.tests", ref) as ref_handle,\
open(temp_ref, "wb") as out_handle:
out_handle.write(ref_handle.read())
namespace.reference = to_gff(temp_ref)
compare(namespace)
self.assertTrue(os.path.exists(namespace.log))
self.assertTrue(os.path.exists("{}.midx".format(namespace.reference.name)))
self.assertGreater(os.stat("{}.midx".format(namespace.reference.name)).st_size, 0)
genes, positions = load_index(namespace, logger)
self.assertIsInstance(genes, dict)
self.assertIsInstance(positions, dict)
self.assertEqual(len(genes), 38)
os.remove(namespace.reference.name)
os.remove(namespace.log)
os.remove("{}.midx".format(namespace.reference.name))
def test_compare_trinity(self):
# Create the list of files
files = [
"trinity.gtf", "trinity.gff3", "trinity.cDNA_match.gff3",
"trinity.match_matchpart.gff3"
]
files = [
pkg_resources.resource_filename("Mikado.tests", filename)
for filename in files
]
namespace = Namespace(default=False)
namespace.distance = 2000
namespace.no_save_index = True
for ref, pred in itertools.permutations(files, 2):
with self.subTest(ref=ref, pred=pred):
namespace.reference = to_gff(ref)
namespace.prediction = to_gff(pred)
namespace.log = os.path.join(
tempfile.gettempdir(),
"compare_{}_{}.log".format(files.index(ref),
files.index(pred)))
namespace.out = os.path.join(
tempfile.gettempdir(),
"compare_{}_{}".format(files.index(ref),
files.index(pred)))
compare(namespace)
refmap = "{}.refmap".format(namespace.out)
tmap = "{}.tmap".format(namespace.out)
stats = "{}.stats".format(namespace.out)
self.assertTrue(os.path.exists(namespace.log))
# with open(log) as log_handle:
# log = [_.rstrip() for _ in log_handle]
for fname in [refmap, stats, tmap]:
self.assertTrue(os.path.exists(fname))
self.assertGreater(os.stat(fname).st_size, 0)
with open(refmap) as _:
reader = csv.DictReader(_, delimiter="\t")
counter = 0
for counter, line in enumerate(reader, start=1):
ccode = line["ccode"]
self.assertIn(ccode, ("_", "=", "f,_", "f,="),
(ref, pred, line))
self.assertEqual(counter, 38)
for suff in ["log", "refmap", "tmap", "stats"]:
[
os.remove(_) for _ in glob.glob(
os.path.join(tempfile.gettempdir(), "compare_*.{}".format(
suff)))
]
def test_compare_trinity(self):
# Create the list of files
files = ["trinity.gtf",
"trinity.gff3",
"trinity.cDNA_match.gff3",
"trinity.match_matchpart.gff3"]
files = [pkg_resources.resource_filename("Mikado.tests", filename) for filename in files]
namespace = Namespace(default=False)
namespace.distance = 2000
namespace.no_save_index = True
for ref, pred in itertools.permutations(files, 2):
with self.subTest(ref=ref, pred=pred):
namespace.reference = to_gff(ref)
namespace.prediction = to_gff(pred)
namespace.log = os.path.join(tempfile.gettempdir(), "compare_{}_{}.log".format(
files.index(ref), files.index(pred)))
namespace.out = os.path.join(tempfile.gettempdir(), "compare_{}_{}".format(
files.index(ref), files.index(pred)))
compare(namespace)
refmap = "{}.refmap".format(namespace.out)
tmap = "{}.tmap".format(namespace.out)
stats = "{}.stats".format(namespace.out)
self.assertTrue(os.path.exists(namespace.log))
# with open(log) as log_handle:
# log = [_.rstrip() for _ in log_handle]
for fname in [refmap, stats, tmap]:
self.assertTrue(os.path.exists(fname))
self.assertGreater(os.stat(fname).st_size, 0)
with open(refmap) as _:
reader = csv.DictReader(_, delimiter="\t")
counter = 0
for counter, line in enumerate(reader, start=1):
ccode = line["ccode"]
self.assertIn(ccode,
("_", "=", "f,_", "f,="),
(ref, pred, line))
self.assertEqual(counter, 38)
for suff in ["log", "refmap", "tmap", "stats"]:
[os.remove(_) for _ in glob.glob(os.path.join(tempfile.gettempdir(),
"compare_*.{}".format(suff)))]
def test_index(self):
# Create the list of files
files = [
"trinity.gtf", "trinity.gff3", "trinity.cDNA_match.gff3",
"trinity.match_matchpart.gff3"
]
# files = [pkg_resources.resource_filename("Mikado.tests", filename) for filename in files]
namespace = Namespace(default=False)
namespace.distance = 2000
namespace.index = True
namespace.prediction = None
namespace.log = os.path.join(tempfile.gettempdir(), "index.log")
logger = create_null_logger("null")
for ref in files:
with self.subTest(ref=ref):
temp_ref = os.path.join(tempfile.gettempdir(), ref)
with pkg_resources.resource_stream("Mikado.tests", ref) as ref_handle,\
open(temp_ref, "wb") as out_handle:
out_handle.write(ref_handle.read())
namespace.reference = to_gff(temp_ref)
compare(namespace)
self.assertTrue(os.path.exists(namespace.log))
self.assertTrue(
os.path.exists("{}.midx".format(namespace.reference.name)))
self.assertGreater(
os.stat("{}.midx".format(
namespace.reference.name)).st_size, 0)
genes, positions = load_index(namespace, logger)
self.assertIsInstance(genes, dict)
self.assertIsInstance(positions, dict)
self.assertEqual(len(genes), 38)
os.remove(namespace.reference.name)
os.remove(namespace.log)
os.remove("{}.midx".format(namespace.reference.name))