def setUp(self):
self.ref_length_file = StringIO(TRANSCRIPT_LENGTHS)
self.annotation_file = StringIO(TRANSCRIPT_ANNOTATION)
self.annotation_lines = TRANSCRIPT_ANNOTATION.split("\n")
self.alignment_file = StringIO(READ_SET_1)
self.metadata_file = StringIO(METADATA_EXPERIMENT_STR_1)
self.handle = h5py.File(BytesIO(), "w")
create.initialize(self.handle, "merzifon", "hg38")
create.set_reference_names_and_lengths(self.handle,
self.ref_length_file)
create.set_annotation(self.handle, self.annotation_lines)
ref_names = get_reference_names(self.handle)
ref_lengths = get_reference_lengths(self.handle)
region_coordinates = get_region_boundaries(self.handle)
exp_handle = self.handle[EXPERIMENTS_name]["merzifon"]
create_experiment.create_experiment(
ribo_exp_handle=exp_handle,
experiment_name="merzifon",
alignment_file_handle=self.alignment_file,
ref_names=ref_names,
ref_lengths=ref_lengths,
region_coordinates=region_coordinates,
metagene_radius=METAGENE_RADIUS,
left_span=LEFT_SPAN,
right_span=RIGHT_SPAN,
length_min=2,
length_max=5,
metadata=self.metadata_file,
store_coverage=True,
nprocess=4)
def test_get_reference_names(self):
create.initialize(self.handle,
"merzifon",
reference_name="appris_human_v2")
create.set_reference_names_and_lengths(self.handle, self.ref_len_file)
create.set_annotation(h5_handle=self.handle,
annotation_lines=self.annotation_lines)
ref_array = self.handle[REFERENCE_name][REF_ANNOTATION_NAME][...]
self.assertEqual(ref_array[0, 0], 50)
self.assertEqual(ref_array[1, 0], 0)
self.assertEqual(ref_array[1, 2], 875)
self.assertEqual(ref_array[2, 1], 1251)
self.assertEqual(ref_array[3, 2], 565)
def test_set_reference_names_and_lengths(self):
create.initialize(self.handle,
"merzifon",
reference_name="appris_human_v2")
create.set_reference_names_and_lengths(self.handle, self.ref_len_file)
ref_h = self.handle[REFERENCE_name]
ref_names = ref_h[REF_DG_REFERENCE_NAMES][...].astype(str)
self.assertIn("GAPDH", ref_names[0])
self.assertIn("BRCA", ref_names[3])
self.assertEqual(4, len(ref_names))
ref_lengths = ref_h[REF_DG_REFERENCE_LENGTHS][...]
self.assertEqual(875, ref_lengths[1])
self.assertEqual(1462, ref_lengths[2])
self.assertNotEqual(1462, ref_lengths[0])
def test_set_coverage_vectors(self):
create.initialize(self.handle,
"merzifon",
reference_name="appris_human_v2")
create.set_reference_names_and_lengths(self.handle, self.ref_len_file)
create.set_annotation(h5_handle=self.handle,
annotation_lines=self.annotation_lines)
create.set_coverage_vectors(self.handle, 5)
start_site_cov = self.handle[REFERENCE_name][REF_DG_START_SITE_COV][
...]
stop_site_cov = self.handle[REFERENCE_name][REF_DG_STOP_SITE_COV][...]
self.assertListEqual(list(start_site_cov),
[2, 2, 2, 3, 3, 4, 4, 4, 4, 4, 4])
self.assertListEqual(list(stop_site_cov),
[4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3])
self.assertTrue(
list(stop_site_cov) != [6, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3])
def test_start_site_coverage_from_ribo(self):
create.initialize(self.handle, "merzifon",
reference_name = "appris_human_v2")
create.set_reference_names_and_lengths(
self.handle,
self.ref_len_file)
create.set_annotation(
h5_handle = self.handle,
annotation_lines = TRANSCRIPT_ANNOTATION.split("\n") )
ribo_annotation = get_region_boundaries(self.handle)
ref_names = get_reference_names(self.handle)
ref_lengths = get_reference_lengths(self.handle)
input_stream = StringIO(READ_SET_1)
coverage = find_coverage(input_stream,
ref_names , ref_lengths )
site_coverage = find_site_coverage(coverage = coverage,
radius = 2,
annotation = ribo_annotation,
site_type = "start")
comparison = (ACTUAL_START_SITE_COVERAGE == site_coverage)
self.assertTrue( np.all( comparison ) )
def test_init(self):
create.initialize(self.handle,
"merzifon",
reference_name="appris_human_v2")
self.assertIn("merzifon", self.handle[EXPERIMENTS_name].keys())
self.assertIn(REFERENCE_name, self.handle.keys())
def setUp(self):
self.tmp_files = list()
self.ref_len_file = StringIO(GENERIC_TRANSCRIPT_LENGTHS)
self.annotation_file = StringIO(GENERIC_TRANSCRIPT_ANNOTATION)
self.alignment_file_1 = StringIO(READ_SET_1)
self.alignment_file_2 = StringIO(READ_SET_2)
self.handle_io = BytesIO()
self.handle = h5py.File(self.handle_io, "w")
self.handle_2 = h5py.File(BytesIO(), "w")
self.h5_handle = h5py.File(BytesIO(), "w")
initialize(self.h5_handle,
experiment_name="dummy",
reference_name="test_ref")
(ref_names, ref_lengths) = \
set_reference_names_and_lengths(self.h5_handle , self.ref_len_file)
self.ref_len_file.seek(0)
self.annotation_lines = GENERIC_TRANSCRIPT_ANNOTATION.split("\n")
create.create_ribo(ribo=self.handle,
experiment_name="experiment-1",
alignment_file=self.alignment_file_1,
reference_name="hg38",
lengths_file=self.ref_len_file,
annotation_file=self.annotation_file,
metagene_radius=METAGENE_RADIUS,
left_span=LEFT_SPAN,
right_span=RIGHT_SPAN,
length_min=LENGTH_MIN,
length_max=LENGTH_MAX,
store_coverage=True,
nprocess=NPROCESS,
tmp_file_prefix="")
self.handle.close()
self.sample_ribo = Ribo(self.handle_io)
# Get the region counts
self.cds_counts = \
self.sample_ribo.get_region_counts( region_name = CDS_name,
sum_references = False)
self.utr5_counts = \
self.sample_ribo.get_region_counts( region_name = UTR5_name,
sum_references = False)
self.utr3_counts = \
self.sample_ribo.get_region_counts( region_name = UTR3_name,
sum_references = False)
self.utr5j_counts = \
self.sample_ribo.get_region_counts( region_name = UTR5_JUNCTION_name,
sum_references = False)
self.utr3j_counts = \
self.sample_ribo.get_region_counts( region_name = UTR3_JUNCTION_name,
sum_references = False)