def test_salmon_quant_one_sample_double_reads(self):
"""Test `salmon quant` on a sample that has double reads."""
# Set up organism index database objects.
prepare_organism_indices()
# Create an Experiment that includes two samples.
# (The first sample has test data available, but the second does not.)
experiment_accession = 'test_experiment'
experiment = Experiment.objects.create(accession_code=experiment_accession)
c_elegans = Organism.get_object_for_name("CAENORHABDITIS_ELEGANS")
# test_sample record
sample_accession = 'test_sample'
test_sample = Sample.objects.create(accession_code=sample_accession,
organism=c_elegans,
source_database='SRA',
technology='RNA-SEQ')
ExperimentSampleAssociation.objects.create(experiment=experiment, sample=test_sample)
# fake_sample record (created to prevent tximport step in this experiment)
fake_sample = Sample.objects.create(accession_code='fake_sample',
source_database='SRA',
technology='RNA-SEQ')
ExperimentSampleAssociation.objects.create(experiment=experiment, sample=fake_sample)
experiment_dir = '/home/user/data_store/salmon_tests/test_experiment'
og_read_1 = OriginalFile()
og_read_1.absolute_file_path = os.path.join(experiment_dir, 'raw/reads_1.fastq')
og_read_1.filename = "reads_1.fastq"
og_read_1.save()
OriginalFileSampleAssociation.objects.create(original_file=og_read_1, sample=test_sample).save()
og_read_2 = OriginalFile()
og_read_2.absolute_file_path = os.path.join(experiment_dir, "raw/reads_2.fastq")
og_read_2.filename = "reads_1.fastq"
og_read_2.save()
OriginalFileSampleAssociation.objects.create(original_file=og_read_2, sample=test_sample).save()
sample_dir = os.path.join(experiment_dir, 'test_sample')
job_context = salmon._prepare_files({"job_dir_prefix": "TEST",
"job_id": "TEST",
"job": ProcessorJob(),
'pipeline': Pipeline(name="Salmon"),
'computed_files': [],
"original_files": [og_read_1, og_read_2]})
# Run salmon.
self.check_salmon_quant(job_context, sample_dir)
# Confirm that this experiment is not ready for tximport yet,
# because `salmon quant` is not run on 'fake_sample'.
experiments_ready = salmon.get_tximport_inputs(job_context)['tximport_inputs']
self.assertEqual(len(experiments_ready), 0)
def test_salmon_determine_index_length_double_read(self):
"""Test that the right length is calculated when the sample has two reads."""
job, files = prepare_job()
job_context = salmon._set_job_prefix({'original_files': files,
'job_id': job})
job_context = salmon._prepare_files(job_context)
results = salmon._determine_index_length(job_context)
self.assertEqual(results['index_length_raw'], 41)
self.assertEqual(results['index_length'], 'short')
def test_prepare_files_failure(self):
batch, _, _ = init_objects()
processor_job = ProcessorJob.create_job_and_relationships(
batches=[batch])
job_context = utils.start_job({
"job": processor_job,
"job_id": processor_job.id
})
job_context = salmon._prepare_files(job_context)
self.assertFalse(job_context["success"])
self.assertEqual(
processor_job.failure_reason,
"Exception caught while retrieving raw file ERR003000_2.fastq.gz")
self.assertFalse(os.path.isfile(batch.files[0].get_temp_pre_path()))
def test_download_index_not_found(self):
batch, _, _ = init_objects()
processor_job = ProcessorJob.create_job_and_relationships(
batches=[batch])
job_context = utils.start_job({
"job": processor_job,
"job_id": processor_job.id,
"kmer_size": "23"
})
job_context = salmon._prepare_files(job_context)
# Function we're testing.
salmon._download_index(job_context)
self.assertFalse(job_context["success"])
self.assertEqual(
processor_job.failure_reason,
"Failed to find an index for organism H**O SAPIENS with kmer_size of 23."
)
def test_fastqc(self):
job, og_files = prepare_job()
win_context = {
'job': job,
'job_id': 789,
'job_dir_prefix': "processor_job_789",
'pipeline': Pipeline(name="Salmon"),
'qc_directory': "/home/user/data_store/raw/TEST/SALMON/qc",
'original_files': og_files,
'input_file_path': og_files[0],
'input_file_path_2': og_files[1],
"computed_files": [],
'success': True
}
# Ensure clean testdir
shutil.rmtree(win_context['qc_directory'], ignore_errors=True)
os.makedirs(win_context['qc_directory'], exist_ok=True)
win_context = salmon._prepare_files(win_context)
win = salmon._run_fastqc(win_context)
self.assertTrue(win['success'])
win = salmon._run_multiqc(win_context)
self.assertTrue(win['success'])
for file in win['qc_files']:
self.assertTrue(os.path.isfile(file.absolute_file_path))
fail_context = {
'job': job,
'job_id': 'hippityhoppity',
'pipeline': Pipeline(name="Salmon"),
'qc_directory': "/home/user/data_store/raw/TEST/SALMON/derp",
'original_files': [],
'success': True,
'computed_files': []
}
fail = salmon._run_fastqc(fail_context)
self.assertFalse(fail['success'])
def test_download_index_missing(self, mock_download_processed_file):
batch, _, _ = init_objects()
_insert_salmon_index()
processor_job = ProcessorJob.create_job_and_relationships(
batches=[batch])
job_context = utils.start_job({
"job": processor_job,
"job_id": processor_job.id,
"job_dir_prefix": "dummy",
"kmer_size": "23"
})
job_context = salmon._prepare_files(job_context)
mock_download_processed_file.side_effect = FileNotFoundError()
# The function being testing.
salmon._download_index(job_context)
self.assertFalse(job_context["success"])
self.assertEqual(
processor_job.failure_reason,
"Failed to download and extract index tarball Homo_sapiens_short.gtf.gz"
)
def test_salmon_quant_two_samples_single_read(self):
"""Test `salmon quant` outputs on two samples that have single
read and that belong to same experiment.
"""
prepare_organism_indices()
# Create one experiment and two related samples, based on:
# https://www.ncbi.nlm.nih.gov/sra/?term=SRP040623
# (For testing purpose, only two of the four samples' data are included.)
experiment_accession = 'PRJNA242809'
experiment = Experiment.objects.create(accession_code=experiment_accession)
c_elegans = Organism.get_object_for_name("CAENORHABDITIS_ELEGANS")
## Sample 1
sample1_accession = 'SRR1206053'
sample1 = Sample.objects.create(accession_code=sample1_accession,
organism=c_elegans)
ExperimentSampleAssociation.objects.create(experiment=experiment, sample=sample1)
experiment_dir = "/home/user/data_store/salmon_tests/PRJNA242809"
og_file_1 = OriginalFile()
og_file_1.absolute_file_path = os.path.join(experiment_dir, "raw/SRR1206053.fastq.gz")
og_file_1.filename = "SRR1206053.fastq.gz"
og_file_1.save()
OriginalFileSampleAssociation.objects.create(original_file=og_file_1, sample=sample1).save()
## Sample 2
sample2_accession = 'SRR1206054'
sample2 = Sample.objects.create(accession_code=sample2_accession,
organism=c_elegans)
ExperimentSampleAssociation.objects.create(experiment=experiment, sample=sample2)
og_file_2 = OriginalFile()
og_file_2.absolute_file_path = os.path.join(experiment_dir, "raw/SRR1206054.fastq.gz")
og_file_2.filename = "SRR1206054.fastq.gz"
og_file_2.save()
OriginalFileSampleAssociation.objects.create(original_file=og_file_2, sample=sample2).save()
# Test `salmon quant` on sample1 (SRR1206053)
sample1_dir = os.path.join(experiment_dir, sample1_accession)
job1_context = salmon._prepare_files({"job_dir_prefix": "TEST",
"job_id": "TEST",
'pipeline': Pipeline(name="Salmon"),
'computed_files': [],
"original_files": [og_file_1]})
# Check quant.sf in `salmon quant` output dir of sample1
self.check_salmon_quant(job1_context, sample1_dir)
# Confirm that this experiment is not ready for tximport yet.
experiments_ready = salmon._get_tximport_inputs(job1_context)
self.assertEqual(len(experiments_ready), 0)
# This job should not have produced any tximport output
# because the other sample isn't ready yet.
self.assertFalse(os.path.exists(os.path.join(job1_context["work_dir"], 'txi_out.RDS')))
# Now run `salmon quant` on sample2 (SRR1206054) too
sample2_dir = os.path.join(experiment_dir, sample2_accession)
job2_context = salmon._prepare_files({"job_dir_prefix": "TEST2",
"job_id": "TEST2",
'pipeline': Pipeline(name="Salmon"),
'computed_files': [],
"original_files": [og_file_2]})
# Clean up tximport output:
rds_filename = os.path.join(job2_context["work_dir"], 'txi_out.RDS')
if (os.path.isfile(rds_filename)):
os.remove(rds_filename)
# Check quant.sf in `salmon quant` output dir of sample2
self.check_salmon_quant(job2_context, sample2_dir)
# rds_filename should have been generated by tximport at this point.
# Note: `tximport` step is launched by subprocess module in Python.
# If input "quant.sf" files are too large, we may have to wait for
# a few seconds before testing the existence of rds_filename.
self.assertTrue(os.path.exists(rds_filename))
for computed_file in job2_context['computed_files']:
if computed_file.filename[-4:] == '.RDS':
rds_file_path = computed_file.absolute_file_path
cmd_tokens = [
"/usr/bin/Rscript", "--vanilla",
"/home/user/data_refinery_workers/processors/test_tximport.R",
"--txi_out", rds_file_path,
"--gene2txmap", job2_context["genes_to_transcripts_path"]
]
tximport_test_result = subprocess.run(cmd_tokens, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
if tximport_test_result.returncode != 0:
# If the exit code is not 0 then tximport failed so fail the tests.
self.assertTrue(False)
# Check the individual files
self.assertTrue(len(job2_context['individual_files']), 2)
for file in job2_context['individual_files']:
self.assertTrue(os.path.isfile(file.absolute_file_path))
def test_success(self):
"""Tests the successful path of the module under test."""
logger.info("STARTING SALMON SUCCESS TEST!!!!!!!!")
# Set up test environment.
batch, first_file, second_file = init_objects()
_insert_salmon_index()
# Change the batch/files to point to test-specific locations
batch.platform_accession_code = "TEST"
batch.save()
first_file.internal_location = "TEST/SALMON"
first_file.save()
second_file.internal_location = "TEST/SALMON"
second_file.save()
processor_job = ProcessorJob.create_job_and_relationships(
batches=[batch])
processor_job.save()
job_context = utils.start_job({
"job": processor_job,
"job_id": processor_job.id
})
job_context = salmon._set_job_prefix(job_context)
# Ensure temp dir isn't leftover from a previous test.
temp_dir = first_file.get_temp_dir(job_context["job_dir_prefix"])
shutil.rmtree(temp_dir, ignore_errors=True)
# One of the functions being tested:
job_context = salmon._prepare_files(job_context)
input_file_path = job_context["input_file_path"]
self.assertIsInstance(input_file_path, str)
self.assertTrue(os.path.isfile(input_file_path))
input_file_path_2 = job_context["input_file_path_2"]
self.assertIsInstance(input_file_path_2, str)
self.assertTrue(os.path.isfile(input_file_path_2))
output_directory_path = job_context["output_directory"]
self.assertIsInstance(output_directory_path, str)
self.assertTrue(os.path.isdir(output_directory_path))
job_context = salmon._determine_index_length(job_context)
# The 'kmer_size' key has been added to job_context with the
# correct value.
self.assertEqual(job_context["kmer_size"], "23")
# Another function being tested
job_context = salmon._download_index(job_context)
self.assertTrue(job_context["success"])
self.assertTrue("index_directory" in job_context)
self.assertTrue(os.path.isdir(job_context["index_directory"]))
self.assertEqual(9, len(os.listdir(job_context["index_directory"])))
# Another function being tested
job_context = salmon._run_salmon(job_context)
self.assertTrue(job_context["success"])
self.assertGreater(len(os.listdir(output_directory_path)), 1)
# The last function to test
job_context = salmon._zip_and_upload(job_context)
self.assertTrue(job_context["success"])
self.assertTrue(os.path.exists(first_file.get_processed_path()))
# Clean up both input and output files
first_file.remove_temp_directory()
shutil.rmtree(first_file.get_processed_dir())
logger.info("ENDING SALMON SUCCESS TEST!!!!!!!!")
