def setUp(self):
super().setUp()
# We need to init the ribo object in write mode
# Because we are going to add tnaseq data to it.
self.sample_ribo = Ribo(self.merged_io, file_mode="r+")
self.rnaseq_file_1 = StringIO(RNASEQ_READS)
self.rnaseq_file_2 = StringIO(RNASEQ_READS_2)
set_rnaseq(ribo_handle=self.sample_ribo._handle,
name="merzifon",
rnaseq_reads=self.rnaseq_file_1,
format="bed",
rnaseq_counts=None)
set_rnaseq(ribo_handle=self.sample_ribo._handle,
name="ankara",
rnaseq_reads=self.rnaseq_file_2,
format="bed",
rnaseq_counts=None)
# We need to re-initialize the ribo object
# so that the changes take effect.
self.sample_ribo._handle.close()
self.sample_ribo = Ribo(self.merged_io, file_mode="r+")
class TestRNASEQ_2(ApiTestBase):
def setUp(self):
super().setUp()
# We need to init the ribo object in write mode
# Because we are going to add tnaseq data to it.
self.sample_ribo = Ribo(self.merged_io, file_mode="r+")
self.rnaseq_file_1 = StringIO(RNASEQ_READS)
self.rnaseq_file_2 = StringIO(RNASEQ_READS_2)
set_rnaseq(ribo_handle=self.sample_ribo._handle,
name="merzifon",
rnaseq_reads=self.rnaseq_file_1,
format="bed",
rnaseq_counts=None)
set_rnaseq(ribo_handle=self.sample_ribo._handle,
name="ankara",
rnaseq_reads=self.rnaseq_file_2,
format="bed",
rnaseq_counts=None)
# We need to re-initialize the ribo object
# so that the changes take effect.
self.sample_ribo._handle.close()
self.sample_ribo = Ribo(self.merged_io, file_mode="r+")
def test_has_rnaseq(self):
self.assertTrue(self.sample_ribo.has_rnaseq("merzifon"))
self.assertTrue(self.sample_ribo.has_rnaseq("ankara"))
def test_get_rnaseq_multiple(self):
rnaseq_df = self.sample_ribo.get_rnaseq()
self.assertTrue(
np.allclose([1, 0, 2, 1, 3], rnaseq_df.loc["merzifon", "GAPDH"]))
self.assertTrue(
np.allclose([0, 1, 3, 0, 1], rnaseq_df.loc["merzifon", "VEGFA"]))
self.assertTrue(
np.allclose([0, 1, 0, 0, 2], rnaseq_df.loc["merzifon", "MYC"]))
self.assertTrue(
np.isclose(rnaseq_df.loc["merzifon", "GAPDH"][CDS_name], 2))
self.assertTrue(
np.allclose([0, 0, 0, 0, 0], rnaseq_df.loc["ankara", "GAPDH"]))
self.assertTrue(
np.allclose([0, 0, 0, 2, 0], rnaseq_df.loc["ankara", "VEGFA"]))
self.assertTrue(
np.allclose([0, 0, 0, 0, 0], rnaseq_df.loc["ankara", "MYC"]))
self.assertTrue(
np.isclose(rnaseq_df.loc["ankara", "VEGFA"][UTR3_JUNCTION_name],
2))
class TestRNASEQ(ApiTestBase):
def setUp(self):
super().setUp()
# We need to init the ribo object in write mode
# Because we are going to add tnaseq data to it.
self.sample_ribo = Ribo(self.merged_io, file_mode="r+")
self.rnaseq_file_1 = StringIO(RNASEQ_READS)
self.rnaseq_file_2 = StringIO(RNASEQ_READS_2)
set_rnaseq(ribo_handle=self.sample_ribo._handle,
name="merzifon",
rnaseq_reads=self.rnaseq_file_1,
format="bed",
rnaseq_counts=None)
# We need to re-initialize the ribo object
# so that the changes take effect.
self.sample_ribo._handle.close()
self.sample_ribo = Ribo(self.merged_io, file_mode="r+")
def test_has_rnaseq(self):
self.assertTrue(self.sample_ribo.has_rnaseq("merzifon"))
self.assertTrue(not self.sample_ribo.has_rnaseq("ankara"))
def test_rnaseq_info(self):
self.assertTrue(self.sample_ribo.\
info["experiments"]["merzifon"]["RNA-Seq"])
self.assertTrue(not self.sample_ribo.\
info["experiments"]["ankara"]["RNA-Seq"])
def test_get_rnaseq_single(self):
rnaseq_df = self.sample_ribo.get_rnaseq("merzifon")
self.assertTrue(
np.allclose([1, 0, 2, 1, 3], rnaseq_df.loc["merzifon", "GAPDH"]))
self.assertTrue(
np.allclose([0, 1, 3, 0, 1], rnaseq_df.loc["merzifon", "VEGFA"]))
self.assertTrue(
np.allclose([0, 1, 0, 0, 2], rnaseq_df.loc["merzifon", "MYC"]))
self.assertTrue(
np.isclose(rnaseq_df.loc["merzifon", "GAPDH"][CDS_name], 2))
def test_get_rnaseq_from_nornaseq_exp(self):
with self.assertRaises(NORNASEQ) as exception_context:
rnaseq_df = self.sample_ribo.get_rnaseq("ankara")
class TestGetCoverage(ApiTestBase):
def setUp(self):
super().setUp()
self.file_handle_3 = BytesIO()
self.ribo_handle_3 = h5py.File(self.file_handle_3, "w")
create.create_ribo(ribo=self.ribo_handle_3,
experiment_name="adana",
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=2,
length_max=5,
store_coverage=True,
nprocess=1,
tmp_file_prefix="")
self.ribo_handle_3.close()
self.adana_ribo = Ribo(self.file_handle_3)
def test_get_coverage(self):
coverage = self.adana_ribo.get_coverage("adana")
self.assertEqual(coverage["GAPDH"][4], 7)
self.assertEqual(coverage["VEGFA"][15], 0)
self.assertEqual(coverage["MYC"][10], 13)
self.assertEqual(coverage["MYC"][0], 2)
def test_get_coverage_nonexising_exp(self):
with self.assertRaises(ExperimentDoesntExist) as exception_context:
has_coverage = self.sample_ribo.get_coverage("nonexisting")
def setUp(self, rename_func=None):
self.tmp_files = list()
self.ref_len_file = StringIO(TRANSCRIPT_LENGTHS)
self.annotation_file = StringIO(TRANSCRIPT_ANNOTATION)
self.alignment_file_1 = StringIO(READ_SET_1)
self.alignment_file_2 = StringIO(READ_SET_2)
self.handle = h5py.File(BytesIO(), "w")
self.handle_2 = h5py.File(BytesIO(), "w")
create.create_ribo(ribo=self.handle,
experiment_name="merzifon",
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=2,
length_max=5,
store_coverage=False,
nprocess=NPROCESS,
tmp_file_prefix="")
self.ref_len_file.seek(0)
self.annotation_file.seek(0)
self.alignment_file_1 = StringIO(READ_SET_1)
set_metadata(self.handle, "merzifon", METADATA_EXPERIMENT_DICT)
create.create_ribo(ribo=self.handle_2,
experiment_name="ankara",
alignment_file=self.alignment_file_2,
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=2,
length_max=5,
store_coverage=True,
nprocess=NPROCESS,
tmp_file_prefix="")
self.ref_len_file.seek(0)
self.annotation_file.seek(0)
self.alignment_file_2 = StringIO(READ_SET_2)
self.merged_io = BytesIO()
self.merged_ribo = h5py.File(self.merged_io, "w")
merge_ribos(self.merged_ribo, [self.handle, self.handle_2])
set_metadata(self.merged_ribo, name=None, metadata=RIBO_METADATA_STR_1)
self.merged_ribo.close()
self.sample_ribo = Ribo(self.merged_io, alias=rename_func)
def setUp(self):
super().setUp()
self.file_handle_3 = BytesIO()
self.ribo_handle_3 = h5py.File(self.file_handle_3, "w")
create.create_ribo(ribo=self.ribo_handle_3,
experiment_name="adana",
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=2,
length_max=5,
store_coverage=True,
nprocess=1,
tmp_file_prefix="")
self.ribo_handle_3.close()
self.adana_ribo = Ribo(self.file_handle_3)
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)