def test_affy_to_pcl(self):
""" """
job = prepare_ba_job()
# Make sure that a previous test didn't leave a directory around.
shutil.rmtree("/home/user/data_store/processor_job_" + str(job.id), ignore_errors=True)
job_context = array_express.affy_to_pcl(job.pk)
self.assertEqual(job_context["platform_accession_code"], "hugene10st")
self.assertEqual(job_context["brainarray_package"], "hugene10sthsensgprobe")
updated_job = ProcessorJob.objects.get(pk=job.pk)
self.assertTrue(updated_job.success)
self.assertEqual(len(ComputationalResult.objects.all()), 1)
self.assertEqual(len(ComputedFile.objects.all()), 1)
self.assertEqual(ComputedFile.objects.all()[0].filename, "GSM1426071_CD_colon_active_1.PCL")
output_filename = ComputedFile.objects.all()[0].absolute_file_path
expected_data = pd.read_csv(
"/home/user/data_store/TEST/PCL/GSM1426071_CD_colon_active_1.PCL", sep="\t"
)["GSM1426071_CD_colon_active_1.CEL"]
actual_data = pd.read_csv(output_filename, sep="\t")["GSM1426071_CD_colon_active_1.CEL"]
assertMostlyAgrees(self, expected_data, actual_data)
os.remove(output_filename)
def test_convert_simple_pcl_with_header(self):
"""PCL with header
> ID_REF, VALUE
"""
job = prepare_job({
"accession_code": "GSM1234847",
"source_filename":
"https://www.ebi.ac.uk/arrayexpress/experiments/E-GEOD-51013/",
"filename": "GSM1234847_sample_table.txt",
"absolute_file_path":
"/home/user/data_store/raw/TEST/NO_OP/GSM1234847_sample_table.txt",
"platform_accession_code": "A-AFFY-38",
})
final_context = assertRunsSuccessfully(self, job)
expected_data = pd.read_csv(
"/home/user/data_store/TEST/NO_OP/EXPECTED/gene_converted_GSM1234847-tbl-1.txt",
sep="\t",
index_col=0,
)["VALUE"]
actual_data = pd.read_csv(final_context["output_file_path"],
sep="\t",
index_col=0)["VALUE"]
assertMostlyAgrees(self, expected_data, actual_data)
def test_affy_to_pcl_no_brainarray(self):
""" """
job = prepare_non_ba_job()
# Make sure that a previous test didn't leave a directory around.
shutil.rmtree("/home/user/data_store/processor_job_" + str(job.id), ignore_errors=True)
array_express.affy_to_pcl(job.pk)
updated_job = ProcessorJob.objects.get(pk=job.pk)
self.assertTrue(updated_job.success)
self.assertEqual(len(ComputationalResult.objects.all()), 1)
self.assertEqual(len(ComputedFile.objects.all()), 1)
self.assertEqual(ComputedFile.objects.all()[0].filename, "GSM45588.PCL")
output_filename = ComputedFile.objects.all()[0].absolute_file_path
expected_data = pd.read_csv("/home/user/data_store/TEST/PCL/GSM45588.PCL", sep="\t")[
"GSM45588.CEL"
]
actual_data = pd.read_csv(output_filename, sep="\t")["GSM45588.CEL"]
assertMostlyAgrees(self, expected_data, actual_data)
os.remove(output_filename)
def test_affy_to_pcl_huex_v1(self):
"""Special Case because there is no CDL for Huex V1"""
job = prepare_huex_v1_job()
shutil.rmtree("/home/user/data_store/processor_job_" + str(job.id), ignore_errors=True)
array_express.affy_to_pcl(job.pk)
updated_job = ProcessorJob.objects.get(pk=job.pk)
self.assertTrue(updated_job.success)
self.assertEqual(len(ComputationalResult.objects.all()), 1)
self.assertEqual(len(ComputedFile.objects.all()), 1)
self.assertEqual(
ComputedFile.objects.all()[0].filename, "GSM1364667_U_110208_7-02-10_S2.PCL"
)
output_filename = ComputedFile.objects.all()[0].absolute_file_path
expected_data = pd.read_csv(
"/home/user/data_store/TEST/PCL/GSM1364667_U_110208_7-02-10_S2.PCL", sep="\t"
)["GSM1364667_U_110208_7-02-10_S2.CEL"]
actual_data = pd.read_csv(output_filename, sep="\t")["GSM1364667_U_110208_7-02-10_S2.CEL"]
assertMostlyAgrees(self, expected_data, actual_data)
os.remove(ComputedFile.objects.all()[0].absolute_file_path)
def test_convert_illumina_no_header(self):
"""Illumina file without header, ex:
> ILMN_1885639 10.0000 0.7931
> ILMN_2209417 10.0000 0.2029
> ILMN_1765401 152.0873 0.0000
"""
job = prepare_job({
"accession_code": "GSM1089291",
"source_filename":
"https://github.com/AlexsLemonade/refinebio/files/2255178/GSM1089291-tbl-1.txt",
"filename": "GSM1089291-tbl-1.txt",
"absolute_file_path":
"/home/user/data_store/raw/TEST/NO_OP/GSM1089291-tbl-1.txt",
"platform_accession_code": "A-MEXP-1171",
"manufacturer": "ILLUMINA",
})
final_context = assertRunsSuccessfully(self, job)
self.assertTrue(
no_op.check_output_quality(final_context["output_file_path"]))
# To:
# ENSG00000105675 10
# ENSG00000085721 152.0873
# ENSG00000278494 152.0873
expected_data = pd.read_csv(
"/home/user/data_store/TEST/NO_OP/EXPECTED/gene_converted_GSM1089291-tbl-1.txt",
sep="\t",
names=["", "VALUE"],
index_col=0,
)["VALUE"]
actual_data = pd.read_csv(final_context["output_file_path"],
sep="\t",
names=["", "VALUE"],
index_col=0)["VALUE"]
assertMostlyAgrees(self, expected_data, actual_data)
def test_convert_processed_illumina(self):
"""Illumina file with header, ex:
> Reporter Identifier VALUE Detection Pval
> ILMN_1343291 14.943602 0
> ILMN_1343295 13.528082 0
"""
job = prepare_job({
"accession_code": "GSM557500",
"source_filename":
"https://www.ebi.ac.uk/arrayexpress/experiments/E-GEOD-22433/",
"filename": "GSM557500-tbl-1.txt",
"absolute_file_path":
"/home/user/data_store/raw/TEST/NO_OP/GSM557500-tbl-1.txt",
"platform_accession_code": "A-MEXP-1171",
"manufacturer": "ILLUMINA",
})
final_context = assertRunsSuccessfully(self, job)
self.assertTrue(
no_op.check_output_quality(final_context["output_file_path"]))
# To:
# ENSG00000156508 14.943602
# ENSG00000111640 13.528082
expected_data = pd.read_csv(
"/home/user/data_store/TEST/NO_OP/EXPECTED/gene_converted_GSM557500-tbl-1.txt",
sep="\t",
names=["", "VALUE"],
index_col=0,
)["VALUE"]
actual_data = pd.read_csv(final_context["output_file_path"],
sep="\t",
names=["", "VALUE"],
index_col=0)["VALUE"]
assertMostlyAgrees(self, expected_data, actual_data)