def test_correct_index_location_metazoa(self):
""" Tests that the files returned actually exist.
Tests the Metazoa division instead of the main division.
"""
survey_job = SurveyJob(source_type="TRANSCRIPTOME_INDEX")
survey_job.save()
key_value_pair = SurveyJobKeyValue(survey_job=survey_job,
key="ensembl_division",
value="EnsemblMetazoa")
key_value_pair.save()
key_value_pair = SurveyJobKeyValue(survey_job=survey_job,
key="organism_name",
value="Octopus bimaculoides")
key_value_pair.save()
surveyor = TranscriptomeIndexSurveyor(survey_job)
files = surveyor.discover_species()[0]
for file in files:
urllib.request.urlopen(file.source_url)
# Make sure the organism object got created by making sure
# this doesn't raise an exception.
Organism.objects.get(name="OCTOPUS_BIMACULOIDES")
def test_single_plant(self):
""" Tests that the files returned actually exist.
Tests the Metazoa division instead of the main division.
"""
survey_job = SurveyJob(source_type="TRANSCRIPTOME_INDEX")
survey_job.save()
key_value_pair = SurveyJobKeyValue(survey_job=survey_job,
key="ensembl_division",
value="EnsemblPlants")
key_value_pair.save()
key_value_pair = SurveyJobKeyValue(survey_job=survey_job,
key="organism_name",
value="Arabidopsis thaliana")
key_value_pair.save()
surveyor = TranscriptomeIndexSurveyor(survey_job)
files = surveyor.discover_species()[0]
for file in files:
urllib.request.urlopen(file.source_url)
# Make sure the organism object got created by making sure
# this doesn't raise an exception.
Organism.objects.get(name="ARABIDOPSIS_THALIANA")
def test_correct_index_location(self):
""" Tests that the files returned actually exist.
Uses an organism in the main division.
"""
survey_job = SurveyJob(source_type="TRANSCRIPTOME_INDEX")
survey_job.save()
key_value_pair = SurveyJobKeyValue(survey_job=survey_job,
key="ensembl_division",
value="Ensembl")
key_value_pair.save()
key_value_pair = SurveyJobKeyValue(survey_job=survey_job,
key="organism_name",
value="Danio rerio")
key_value_pair.save()
surveyor = TranscriptomeIndexSurveyor(survey_job)
files = surveyor.discover_species()[0]
# Make sure the organism object got created by making sure
# this doesn't raise an exception.
Organism.objects.get(name="DANIO_RERIO")
for file in files:
urllib.request.urlopen(file.source_url)
def test_survey_bacteria(self, mock_send_job):
survey_job = SurveyJob(source_type="TRANSCRIPTOME_INDEX")
survey_job.save()
key_value_pair = SurveyJobKeyValue(survey_job=survey_job,
key="ensembl_division",
value="EnsemblBacteria")
key_value_pair.save()
key_value_pair = SurveyJobKeyValue(survey_job=survey_job,
key="organism_name",
value="PSEUDOMONAS_AERUGINOSA")
key_value_pair.save()
surveyor = TranscriptomeIndexSurveyor(survey_job)
surveyor.survey(source_type="TRANSCRIPTOME_INDEX")
downloader_jobs = DownloaderJob.objects.order_by("id").all()
self.assertEqual(downloader_jobs.count(), 1)
send_job_calls = []
for downloader_job in downloader_jobs:
send_job_calls.append(
call(Downloaders.TRANSCRIPTOME_INDEX, downloader_job))
mock_send_job.assert_has_calls(send_job_calls)
# Make sure the organism object got created with the correct
# taxonomy id by making sure this doesn't raise an exception.
Organism.objects.get(name="PSEUDOMONAS_AERUGINOSA", taxonomy_id=287)
def test_survey(self, mock_send_job):
surveyor = TranscriptomeIndexSurveyor(self.survey_job)
surveyor.survey(source_type="TRANSCRIPTOME_INDEX")
downloader_jobs = DownloaderJob.objects.order_by("id").all()
self.assertGreater(downloader_jobs.count(), 50)
send_job_calls = []
for downloader_job in downloader_jobs:
send_job_calls.append(
call(Downloaders.TRANSCRIPTOME_INDEX, downloader_job))
mock_send_job.assert_has_calls(send_job_calls)
def test_survey(self, mock_get, mock_urlopen, mock_send_job):
json_file_path = os.path.join(os.path.dirname(__file__),
"test_transcriptome_species.json")
with open(json_file_path, "r") as json_file:
species_json = json.load(json_file)
# Insert the organisms into the database so the model doesn't call the
# taxonomy API to populate them.
for species in species_json:
# Account for the subtle difference between the API for
# the main Ensembl division and the API for the rest of
# them.
name_key = "common_name" if "common_name" in species else "name"
taxonomy_key = "taxonomy_id" if "taxonomy_id" in species else "taxon_id"
organism = Organism(name=species[name_key].upper(),
taxonomy_id=species[taxonomy_key],
is_scientific_name=True)
organism.save()
mock_get.return_value = Mock(ok=True)
mock_get.return_value.json.return_value = species_json
# There are two possible file locations. The correct one is
# determined by making a request to one to see if it
# exists. This URLError simulates it not existing.
mock_urlopen.side_effect = URLError("404 or something")
surveyor = TranscriptomeIndexSurveyor(self.survey_job)
surveyor.survey()
downloader_jobs = DownloaderJob.objects.order_by("id").all()
self.assertEqual(downloader_jobs.count(), len(species_json))
send_job_calls = []
for downloader_job in downloader_jobs:
send_job_calls.append(
call(Downloaders.TRANSCRIPTOME_INDEX, downloader_job.id))
mock_send_job.assert_has_calls(send_job_calls)
# There should be 2 Batches for each species (long and short
# transcriptome lengths).
batches = Batch.objects.all()
self.assertEqual(batches.count(), len(species_json) * 2)
# And each batch has two files: fasta and gtf
for batch in batches:
self.assertEqual(len(batch.files), 2)
def test_survey_fungi_none(self, mock_send_job):
"""When surveying fungi an organism_name must be supplied."""
survey_job = SurveyJob(source_type="TRANSCRIPTOME_INDEX")
survey_job.save()
key_value_pair = SurveyJobKeyValue(survey_job=survey_job,
key="ensembl_division",
value="EnsemblFungi")
key_value_pair.save()
surveyor = TranscriptomeIndexSurveyor(survey_job)
surveyor.survey(source_type="TRANSCRIPTOME_INDEX")
downloader_jobs = DownloaderJob.objects.order_by("id").all()
self.assertEqual(downloader_jobs.count(), 0)
mock_send_job.assert_not_called()
def test_survey(self, mock_send_job):
survey_job = SurveyJob(source_type="TRANSCRIPTOME_INDEX")
survey_job.save()
key_value_pair = SurveyJobKeyValue(
survey_job=survey_job, key="ensembl_division", value="EnsemblPlants"
)
key_value_pair.save()
surveyor = TranscriptomeIndexSurveyor(survey_job)
surveyor.survey(source_type="TRANSCRIPTOME_INDEX")
downloader_jobs = DownloaderJob.objects.order_by("id").all()
self.assertGreater(downloader_jobs.count(), 50)
send_job_calls = []
for downloader_job in downloader_jobs:
send_job_calls.append(call(Downloaders.TRANSCRIPTOME_INDEX, downloader_job))
mock_send_job.assert_has_calls(send_job_calls)
def _get_surveyor_for_source(survey_job: SurveyJob):
"""Factory method for ExternalSourceSurveyors."""
if survey_job.source_type == "ARRAY_EXPRESS":
return ArrayExpressSurveyor(survey_job)
if survey_job.source_type == "SRA":
return SraSurveyor(survey_job)
if survey_job.source_type == "TRANSCRIPTOME_INDEX":
return TranscriptomeIndexSurveyor(survey_job)
else:
raise SourceNotSupportedError("Source " + survey_job.source_type +
" is not supported.")
def test_correct_index_location_protist(self):
""" Tests that the files returned actually exist.
Tests the Metazoa division instead of the main division.
"""
survey_job = SurveyJob(source_type="TRANSCRIPTOME_INDEX")
survey_job.save()
key_value_pair = SurveyJobKeyValue(survey_job=survey_job,
key="ensembl_division",
value="EnsemblProtists")
key_value_pair.save()
key_value_pair = SurveyJobKeyValue(survey_job=survey_job,
key="organism_name",
value="Leishmania major")
key_value_pair.save()
surveyor = TranscriptomeIndexSurveyor(survey_job)
files = surveyor.discover_species()[0]
for file in files:
urllib.request.urlopen(file.source_url)
def test_correct_index_location(self):
""" Tests that the files returned actually exist.
Uses an organism in the main division.
"""
survey_job = SurveyJob(source_type="TRANSCRIPTOME_INDEX")
survey_job.save()
self.survey_job = survey_job
key_value_pair = SurveyJobKeyValue(survey_job=survey_job,
key="ensembl_division",
value="Ensembl")
key_value_pair.save()
key_value_pair = SurveyJobKeyValue(survey_job=survey_job,
key="organism_name",
value="Danio rerio")
key_value_pair.save()
surveyor = TranscriptomeIndexSurveyor(self.survey_job)
files = surveyor.discover_species()[0]
for file in files:
urllib.request.urlopen(file.source_url)