def test_get_results(self):
""" Test our ability to collect the appropriate samples. """
sample = Sample()
sample.accession_code = 'GSM45588'
sample.save()
result = ComputationalResult()
result.save()
computed_file1 = ComputedFile()
computed_file1.filename = "oh_boy.txt"
computed_file1.result = result
computed_file1.size_in_bytes = 123
computed_file1.is_smashable = True
computed_file1.save()
computed_file2 = ComputedFile()
computed_file2.filename = "gee_whiz.bmp"
computed_file2.result = result
computed_file2.size_in_bytes = 123
computed_file2.is_smashable = False
computed_file2.save()
assoc = SampleResultAssociation()
assoc.sample = sample
assoc.result = result
assoc.save()
assoc = SampleComputedFileAssociation()
assoc.sample = sample
assoc.computed_file = computed_file1
assoc.save()
assoc = SampleComputedFileAssociation()
assoc.sample = sample
assoc.computed_file = computed_file2
assoc.save()
computed_files = sample.get_result_files()
self.assertEqual(computed_files.count(), 2)
def _run_salmontools(job_context: Dict) -> Dict:
""" Run Salmontools to extract unmapped genes. """
logger.debug("Running SalmonTools ...")
unmapped_filename = job_context[
"output_directory"] + "aux_info/unmapped_names.txt"
command_str = "salmontools extract-unmapped -u {unmapped_file} -o {output} "
output_prefix = job_context["salmontools_directory"] + "unmapped_by_salmon"
command_str = command_str.format(unmapped_file=unmapped_filename,
output=output_prefix)
if "input_file_path_2" in job_context:
command_str += "-1 {input_1} -2 {input_2}"
command_str = command_str.format(
input_1=job_context["input_file_path"],
input_2=job_context["input_file_path_2"])
else:
command_str += "-r {input_1}"
command_str = command_str.format(
input_1=job_context["input_file_path"])
start_time = timezone.now()
logger.debug(
"Running the following SalmonTools command: %s",
command_str,
processor_job=job_context["job_id"],
)
completed_command = subprocess.run(command_str.split(),
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
end_time = timezone.now()
# As of SalmonTools 0.1.0, completed_command.returncode is always 0,
# (even if error happens). completed_command.stderr is not totally
# reliable either, because it will output the following line even
# when the execution succeeds:
# "There were <N> unmapped reads\n"
# in which "<N>" is the number of lines in input unmapped_names.txt.
#
# As a workaround, we are using a regular expression here to test
# the status of SalmonTools execution. Any text in stderr that is
# not in the above format is treated as error message.
status_str = completed_command.stderr.decode().strip()
success_pattern = r"^There were \d+ unmapped reads$"
if re.match(success_pattern, status_str):
# Zip up the output of salmontools
try:
with tarfile.open(job_context["salmontools_archive"],
"w:gz") as tar:
tar.add(job_context["salmontools_directory"], arcname=os.sep)
except Exception:
logger.exception(
"Exception caught while zipping processed directory %s",
job_context["salmontools_directory"],
processor_job=job_context["job_id"],
)
failure_template = "Exception caught while zipping salmontools directory {}"
job_context["job"].failure_reason = failure_template.format(
job_context["salmontools_archive"])
job_context["success"] = False
return job_context
result = ComputationalResult()
result.commands.append(command_str)
result.time_start = start_time
result.time_end = end_time
result.is_ccdl = True
try:
processor_key = "SALMONTOOLS"
result.processor = utils.find_processor(processor_key)
except Exception as e:
return utils.handle_processor_exception(job_context, processor_key,
e)
result.save()
job_context["pipeline"].steps.append(result.id)
assoc = SampleResultAssociation()
assoc.sample = job_context["sample"]
assoc.result = result
assoc.save()
computed_file = ComputedFile()
computed_file.filename = job_context["salmontools_archive"].split(
"/")[-1]
computed_file.absolute_file_path = job_context["salmontools_archive"]
computed_file.calculate_sha1()
computed_file.calculate_size()
computed_file.is_public = True
computed_file.is_smashable = False
computed_file.is_qc = True
computed_file.result = result
computed_file.save()
job_context["computed_files"].append(computed_file)
assoc = SampleComputedFileAssociation()
assoc.sample = job_context["sample"]
assoc.computed_file = computed_file
assoc.save()
job_context["result"] = result
job_context["success"] = True
else: # error in salmontools
logger.error(
"Shell call to salmontools failed with error message: %s",
status_str,
processor_job=job_context["job_id"],
)
job_context["job"].failure_reason = (
"Shell call to salmontools failed because: " + status_str)
job_context["success"] = False
return job_context