def handle(self, *args, **options):
""" For every (or a supplied) organism, fetch all of the experiments and compile large but normally formated Dataset.
Send all of them to the Smasher. Smash them. Retrieve manually as desired.
"""
dataset_ids = []
if options["organism"] is None:
all_organisms = Organism.objects.all()
else:
all_organisms = [
Organism.get_object_for_name(options["organism"].upper())
]
for organism in all_organisms:
data = {}
experiments = Experiment.objects.filter(
id__in=(ExperimentOrganismAssociation.objects.filter(
organism=organism)).values('experiment'))
for experiment in experiments:
data[experiment.accession_code] = list(
experiment.samples.filter(organism=organism).values_list(
'accession_code', flat=True))
job = ProcessorJob()
job.pipeline_applied = "COMPENDIA"
job.save()
dset = Dataset()
dset.data = data
dset.scale_by = 'NONE'
dset.aggregate_by = 'SPECIES'
dset.quantile_normalize = False
dset.save()
pjda = ProcessorJobDatasetAssociation()
pjda.processor_job = job
pjda.dataset = dset
pjda.save()
final_context = create_compendia.create_compendia(job.id)
sys.exit(0)
def handle(self, *args, **options):
if options["job_id"] is None:
logger.error("You must specify a job ID.", job_id=options["job_id"])
sys.exit(1)
try:
job_type = ProcessorPipeline[options["job_name"]]
except KeyError:
logger.error(
"You must specify a valid job name.",
job_name=options["job_name"],
job_id=options["job_id"],
)
sys.exit(1)
if job_type is ProcessorPipeline.AFFY_TO_PCL:
from data_refinery_workers.processors.array_express import affy_to_pcl
affy_to_pcl(options["job_id"])
elif job_type is ProcessorPipeline.TRANSCRIPTOME_INDEX_SHORT:
from data_refinery_workers.processors.transcriptome_index import (
build_transcriptome_index,
)
build_transcriptome_index(options["job_id"], length="short")
elif job_type is ProcessorPipeline.TRANSCRIPTOME_INDEX_LONG:
from data_refinery_workers.processors.transcriptome_index import (
build_transcriptome_index,
)
build_transcriptome_index(options["job_id"], length="long")
elif job_type is ProcessorPipeline.AGILENT_TWOCOLOR_TO_PCL:
from data_refinery_workers.processors.agilent_twocolor import agilent_twocolor_to_pcl
agilent_twocolor_to_pcl(options["job_id"])
elif job_type is ProcessorPipeline.ILLUMINA_TO_PCL:
from data_refinery_workers.processors.illumina import illumina_to_pcl
illumina_to_pcl(options["job_id"])
elif job_type is ProcessorPipeline.SALMON:
from data_refinery_workers.processors.salmon import salmon
salmon(options["job_id"])
elif job_type is ProcessorPipeline.TXIMPORT:
from data_refinery_workers.processors.tximport import tximport
tximport(options["job_id"])
elif job_type is ProcessorPipeline.SMASHER:
from data_refinery_workers.processors.smasher import smash
smash(options["job_id"])
elif job_type is ProcessorPipeline.CREATE_COMPENDIA:
from data_refinery_workers.processors.create_compendia import create_compendia
create_compendia(options["job_id"])
elif job_type is ProcessorPipeline.CREATE_QUANTPENDIA:
from data_refinery_workers.processors.create_quantpendia import create_quantpendia
create_quantpendia(options["job_id"])
elif job_type is ProcessorPipeline.NO_OP:
from data_refinery_workers.processors.no_op import no_op_processor
no_op_processor(options["job_id"])
elif job_type is ProcessorPipeline.JANITOR:
from data_refinery_workers.processors.janitor import run_janitor
run_janitor(options["job_id"])
elif job_type is ProcessorPipeline.QN_REFERENCE:
from data_refinery_workers.processors import qn_reference
qn_reference.create_qn_reference(options["job_id"])
else:
logger.error(
(
"A valid job name was specified for job %s with id %d but "
"no processor function is known to run it."
),
options["job_name"],
options["job_id"],
)
sys.exit(1)
sys.exit(0)
def test_create_compendia(self):
job = ProcessorJob()
job.pipeline_applied = ProcessorPipeline.CREATE_COMPENDIA.value
job.save()
# MICROARRAY TECH
experiment = Experiment()
experiment.accession_code = "GSE1487313"
experiment.save()
result = ComputationalResult()
result.save()
gallus_gallus = Organism.get_object_for_name("GALLUS_GALLUS",
taxonomy_id=1001)
sample = Sample()
sample.accession_code = "GSM1487313"
sample.title = "GSM1487313"
sample.organism = gallus_gallus
sample.technology = "MICROARRAY"
sample.save()
sra = SampleResultAssociation()
sra.sample = sample
sra.result = result
sra.save()
esa = ExperimentSampleAssociation()
esa.experiment = experiment
esa.sample = sample
esa.save()
computed_file = ComputedFile()
computed_file.filename = "GSM1487313_liver.PCL"
computed_file.absolute_file_path = "/home/user/data_store/PCL/" + computed_file.filename
computed_file.result = result
computed_file.size_in_bytes = 123
computed_file.is_smashable = True
computed_file.save()
assoc = SampleComputedFileAssociation()
assoc.sample = sample
assoc.computed_file = computed_file
assoc.save()
# Missing sample that will be filtered
sample = Sample()
sample.accession_code = "GSM1487222"
sample.title = "this sample will be filtered"
sample.organism = gallus_gallus
sample.technology = "MICROARRAY"
sample.save()
sra = SampleResultAssociation()
sra.sample = sample
sra.result = result
sra.save()
esa = ExperimentSampleAssociation()
esa.experiment = experiment
esa.sample = sample
esa.save()
computed_file = ComputedFile()
computed_file.filename = "GSM1487222_empty.PCL"
computed_file.absolute_file_path = "/home/user/data_store/PCL/doesnt_exists.PCL"
computed_file.result = result
computed_file.size_in_bytes = 123
computed_file.is_smashable = True
computed_file.save()
assoc = SampleComputedFileAssociation()
assoc.sample = sample
assoc.computed_file = computed_file
assoc.save()
# RNASEQ TECH
experiment2 = Experiment()
experiment2.accession_code = "SRS332914"
experiment2.save()
result2 = ComputationalResult()
result2.save()
sample2 = Sample()
sample2.accession_code = "SRS332914"
sample2.title = "SRS332914"
sample2.organism = gallus_gallus
sample2.technology = "RNA-SEQ"
sample2.save()
sra2 = SampleResultAssociation()
sra2.sample = sample2
sra2.result = result2
sra2.save()
esa2 = ExperimentSampleAssociation()
esa2.experiment = experiment2
esa2.sample = sample2
esa2.save()
computed_file2 = ComputedFile()
computed_file2.filename = "SRP149598_gene_lengthScaledTPM.tsv"
computed_file2.absolute_file_path = "/home/user/data_store/PCL/" + computed_file2.filename
computed_file2.result = result2
computed_file2.size_in_bytes = 234
computed_file2.is_smashable = True
computed_file2.save()
assoc2 = SampleComputedFileAssociation()
assoc2.sample = sample2
assoc2.computed_file = computed_file2
assoc2.save()
dset = Dataset()
dset.data = {
"GSE1487313": ["GSM1487313", "GSM1487222"],
"SRX332914": ["SRS332914"]
}
dset.scale_by = "NONE"
dset.aggregate_by = "SPECIES"
dset.svd_algorithm = "ARPACK"
dset.quantile_normalize = False
dset.save()
pjda = ProcessorJobDatasetAssociation()
pjda.processor_job = job
pjda.dataset = dset
pjda.save()
final_context = create_compendia.create_compendia(job.id)
self.assertFalse(job.success)
# check that sample with no computed file was skipped
self.assertTrue("GSM1487222" in final_context["filtered_samples"])
self.assertEqual(
final_context["filtered_samples"]["GSM1487222"]
["experiment_accession_code"],
"GSE1487313",
)
def test_create_compendia_danio(self):
job = ProcessorJob()
job.pipeline_applied = ProcessorPipeline.CREATE_COMPENDIA.value
job.save()
# MICROARRAY TECH
experiment = Experiment()
experiment.accession_code = "GSE1234"
experiment.save()
result = ComputationalResult()
result.save()
qn_target = ComputedFile()
qn_target.filename = "danio_target.tsv"
qn_target.absolute_file_path = "/home/user/data_store/QN/danio_target.tsv"
qn_target.is_qn_target = True
qn_target.size_in_bytes = "12345"
qn_target.sha1 = "aabbccddeeff"
qn_target.result = result
qn_target.save()
danio_rerio = Organism(name="DANIO_RERIO",
taxonomy_id=1,
qn_target=result)
danio_rerio.save()
cra = ComputationalResultAnnotation()
cra.data = {}
cra.data["organism_id"] = danio_rerio.id
cra.data["is_qn"] = True
cra.result = result
cra.save()
result = ComputationalResult()
result.save()
micros = []
for file in os.listdir("/home/user/data_store/raw/TEST/MICROARRAY/"):
if "microarray.txt" in file:
continue
sample = Sample()
sample.accession_code = file
sample.title = file
sample.organism = danio_rerio
sample.technology = "MICROARRAY"
sample.save()
sra = SampleResultAssociation()
sra.sample = sample
sra.result = result
sra.save()
esa = ExperimentSampleAssociation()
esa.experiment = experiment
esa.sample = sample
esa.save()
computed_file = ComputedFile()
computed_file.filename = file
computed_file.absolute_file_path = "/home/user/data_store/raw/TEST/MICROARRAY/" + file
computed_file.result = result
computed_file.size_in_bytes = 123
computed_file.is_smashable = True
computed_file.save()
assoc = SampleComputedFileAssociation()
assoc.sample = sample
assoc.computed_file = computed_file
assoc.save()
micros.append(file)
experiment = Experiment()
experiment.accession_code = "GSE5678"
experiment.save()
result = ComputationalResult()
result.save()
rnas = []
for file in os.listdir("/home/user/data_store/raw/TEST/RNASEQ/"):
if "rnaseq.txt" in file:
continue
sample = Sample()
sample.accession_code = file
sample.title = file
sample.organism = danio_rerio
sample.technology = "RNASEQ"
sample.save()
sra = SampleResultAssociation()
sra.sample = sample
sra.result = result
sra.save()
esa = ExperimentSampleAssociation()
esa.experiment = experiment
esa.sample = sample
esa.save()
computed_file = ComputedFile()
computed_file.filename = file
computed_file.absolute_file_path = "/home/user/data_store/raw/TEST/RNASEQ/" + file
computed_file.result = result
computed_file.size_in_bytes = 123
computed_file.is_smashable = True
computed_file.save()
assoc = SampleComputedFileAssociation()
assoc.sample = sample
assoc.computed_file = computed_file
assoc.save()
rnas.append(file)
# Missing sample that will be filtered
sample = Sample()
sample.accession_code = "GSM1487222"
sample.title = "this sample will be filtered"
sample.organism = danio_rerio
sample.technology = "RNASEQ"
sample.save()
sra = SampleResultAssociation()
sra.sample = sample
sra.result = result
sra.save()
esa = ExperimentSampleAssociation()
esa.experiment = experiment
esa.sample = sample
esa.save()
rnas.append(sample.accession_code)
dset = Dataset()
dset.data = {"GSE1234": micros, "GSE5678": rnas}
dset.scale_by = "NONE"
dset.aggregate_by = "SPECIES"
dset.svd_algorithm = "ARPACK"
dset.quantile_normalize = False
dset.save()
pjda = ProcessorJobDatasetAssociation()
pjda.processor_job = job
pjda.dataset = dset
pjda.save()
final_context = create_compendia.create_compendia(job.id)
# Verify result
self.assertEqual(
final_context["compendium_result"].result.computedfile_set.count(),
1)
for file in final_context[
"compendium_result"].result.computedfile_set.all():
self.assertTrue(os.path.exists(file.absolute_file_path))
# test compendium_result
self.assertEqual(final_context["compendium_result"].svd_algorithm,
"ARPACK")
self.assertEqual(
final_context["compendium_result"].primary_organism.name,
final_context["organism_name"])
self.assertEqual(
final_context["compendium_result"].primary_organism.name,
"DANIO_RERIO")
self.assertEqual(final_context["compendium_result"].organisms.count(),
1)
# check that sample with no computed file was skipped
self.assertTrue("GSM1487222" in final_context["filtered_samples"])
self.assertEqual(
final_context["filtered_samples"]["GSM1487222"]
["experiment_accession_code"], "GSE5678")
def test_create_compendia(self):
job = ProcessorJob()
job.pipeline_applied = "COMPENDIA"
job.save()
# MICROARRAY TECH
experiment = Experiment()
experiment.accession_code = "GSE1487313"
experiment.save()
result = ComputationalResult()
result.save()
gallus_gallus = Organism.get_object_for_name("GALLUS_GALLUS")
sample = Sample()
sample.accession_code = 'GSM1487313'
sample.title = 'GSM1487313'
sample.organism = gallus_gallus
sample.technology = "MICROARRAY"
sample.save()
sra = SampleResultAssociation()
sra.sample = sample
sra.result = result
sra.save()
esa = ExperimentSampleAssociation()
esa.experiment = experiment
esa.sample = sample
esa.save()
computed_file = ComputedFile()
computed_file.filename = "GSM1487313_liver.PCL"
computed_file.absolute_file_path = "/home/user/data_store/PCL/" + computed_file.filename
computed_file.result = result
computed_file.size_in_bytes = 123
computed_file.is_smashable = True
computed_file.save()
assoc = SampleComputedFileAssociation()
assoc.sample = sample
assoc.computed_file = computed_file
assoc.save()
# RNASEQ TECH
experiment2 = Experiment()
experiment2.accession_code = "SRS332914"
experiment2.save()
result2 = ComputationalResult()
result2.save()
sample2 = Sample()
sample2.accession_code = 'SRS332914'
sample2.title = 'SRS332914'
sample2.organism = gallus_gallus
sample2.technology = "RNA-SEQ"
sample2.save()
sra2 = SampleResultAssociation()
sra2.sample = sample2
sra2.result = result2
sra2.save()
esa2 = ExperimentSampleAssociation()
esa2.experiment = experiment2
esa2.sample = sample2
esa2.save()
computed_file2 = ComputedFile()
computed_file2.filename = "SRP149598_gene_lengthScaledTPM.tsv"
computed_file2.absolute_file_path = "/home/user/data_store/PCL/" + computed_file2.filename
computed_file2.result = result2
computed_file2.size_in_bytes = 234
computed_file2.is_smashable = True
computed_file2.save()
assoc2 = SampleComputedFileAssociation()
assoc2.sample = sample2
assoc2.computed_file = computed_file2
assoc2.save()
dset = Dataset()
dset.data = {'GSE1487313': ['GSM1487313'], 'SRX332914': ['SRS332914']}
dset.scale_by = 'NONE'
dset.aggregate_by = 'SPECIES'
dset.quantile_normalize = False
dset.save()
pjda = ProcessorJobDatasetAssociation()
pjda.processor_job = job
pjda.dataset = dset
pjda.save()
final_context = create_compendia.create_compendia(job.id)
def test_create_compendia_danio(self):
job = ProcessorJob()
job.pipeline_applied = "COMPENDIA"
job.save()
# MICROARRAY TECH
experiment = Experiment()
experiment.accession_code = "GSE1234"
experiment.save()
result = ComputationalResult()
result.save()
danio_rerio = Organism.get_object_for_name("DANIO_RERIO")
micros = []
for file in os.listdir('/home/user/data_store/raw/TEST/MICROARRAY/'):
if 'microarray.txt' in file:
continue
sample = Sample()
sample.accession_code = file
sample.title = file
sample.organism = danio_rerio
sample.technology = "MICROARRAY"
sample.save()
sra = SampleResultAssociation()
sra.sample = sample
sra.result = result
sra.save()
esa = ExperimentSampleAssociation()
esa.experiment = experiment
esa.sample = sample
esa.save()
computed_file = ComputedFile()
computed_file.filename = file
computed_file.absolute_file_path = "/home/user/data_store/raw/TEST/MICROARRAY/" + file
computed_file.result = result
computed_file.size_in_bytes = 123
computed_file.is_smashable = True
computed_file.save()
assoc = SampleComputedFileAssociation()
assoc.sample = sample
assoc.computed_file = computed_file
assoc.save()
micros.append(file)
experiment = Experiment()
experiment.accession_code = "GSE5678"
experiment.save()
result = ComputationalResult()
result.save()
rnas = []
for file in os.listdir('/home/user/data_store/raw/TEST/RNASEQ/'):
if 'rnaseq.txt' in file:
continue
sample = Sample()
sample.accession_code = file
sample.title = file
sample.organism = danio_rerio
sample.technology = "RNASEQ"
sample.save()
sra = SampleResultAssociation()
sra.sample = sample
sra.result = result
sra.save()
esa = ExperimentSampleAssociation()
esa.experiment = experiment
esa.sample = sample
esa.save()
computed_file = ComputedFile()
computed_file.filename = file
computed_file.absolute_file_path = "/home/user/data_store/raw/TEST/RNASEQ/" + file
computed_file.result = result
computed_file.size_in_bytes = 123
computed_file.is_smashable = True
computed_file.save()
assoc = SampleComputedFileAssociation()
assoc.sample = sample
assoc.computed_file = computed_file
assoc.save()
rnas.append(file)
result = ComputationalResult()
result.save()
qn_target = ComputedFile()
qn_target.filename = "danio_target.tsv"
qn_target.absolute_file_path = '/home/user/data_store/QN/danio_target.tsv'
qn_target.is_qn_target = True
qn_target.size_in_bytes = "12345"
qn_target.sha1 = "aabbccddeeff"
qn_target.result = result
qn_target.save()
cra = ComputationalResultAnnotation()
cra.data = {}
cra.data['organism_id'] = danio_rerio.id
cra.data['is_qn'] = True
cra.result = result
cra.save()
dset = Dataset()
dset.data = {'GSE1234': micros, 'GSE5678': rnas}
dset.scale_by = 'NONE'
dset.aggregate_by = 'SPECIES'
dset.quantile_normalize = False
dset.save()
pjda = ProcessorJobDatasetAssociation()
pjda.processor_job = job
pjda.dataset = dset
pjda.save()
final_context = create_compendia.create_compendia(job.id)
# Verify result
self.assertEqual(len(final_context['computed_files']), 3)
for file in final_context['computed_files']:
self.assertTrue(os.path.exists(file.absolute_file_path))
def test_create_compendia(self):
DATA_DIR = "/home/user/data_store/PCL/"
job = ProcessorJob()
job.pipeline_applied = ProcessorPipeline.CREATE_COMPENDIA.value
job.save()
gallus_gallus = Organism.get_object_for_name("GALLUS_GALLUS",
taxonomy_id=1001)
# MICROARRAY TECH
(experiment,
_) = Experiment.objects.get_or_create(accession_code="GSE1487313")
experiment.accession_code = "GSE1487313"
experiment.save()
create_sample_for_experiment(
{
"organism": gallus_gallus,
"accession_code": "GSM1487313",
"technology": "MICROARRAY",
"filename": "GSM1487313_liver.PCL",
"data_dir": DATA_DIR,
},
experiment,
)
# Missing sample that will be filtered
create_sample_for_experiment(
{
"organism": gallus_gallus,
"accession_code": "GSM1487222",
"title": "this sample will be filtered",
"technology": "MICROARRAY",
"filename": "GSM1487222_empty.PCL",
"data_dir": DATA_DIR,
},
experiment,
)
# RNASEQ TECH
experiment2 = Experiment()
experiment2.accession_code = "SRP149598"
experiment2.save()
create_sample_for_experiment(
{
"organism": gallus_gallus,
"accession_code": "SRR7250867",
"technology": "RNA-SEQ",
"filename": "SRP149598_gene_lengthScaledTPM.tsv",
"data_dir": DATA_DIR,
},
experiment,
)
dset = Dataset()
dset.data = {
"GSE1487313": ["GSM1487313", "GSM1487222"],
"SRP149598": ["SRR7250867"],
}
dset.scale_by = "NONE"
dset.aggregate_by = "SPECIES"
dset.svd_algorithm = "ARPACK"
dset.quantile_normalize = True
dset.save()
pjda = ProcessorJobDatasetAssociation()
pjda.processor_job = job
pjda.dataset = dset
pjda.save()
final_context = create_compendia.create_compendia(job.id)
# Because one of the samples is filtered out, there will be too few
# remaining samples to smash together, so we expect this job to fail.
self.assertFailed(job, "k must be between 1 and min(A.shape)")
# check that sample with no computed file was skipped
self.assertTrue("GSM1487222" in final_context["filtered_samples"])
self.assertEqual(
final_context["filtered_samples"]["GSM1487222"]
["experiment_accession_code"],
"GSE1487313",
)
def test_create_compendia_microarray_only(self):
"""
Make sure that we can actually create a compendium with just microarray samples.
"""
job = ProcessorJob()
job.pipeline_applied = ProcessorPipeline.CREATE_COMPENDIA.value
job.save()
# MICROARRAY TECH
experiment = Experiment()
experiment.accession_code = "GSE1234"
experiment.save()
result = ComputationalResult()
result.save()
qn_target = ComputedFile()
qn_target.filename = "danio_target.tsv"
qn_target.absolute_file_path = "/home/user/data_store/QN/danio_target.tsv"
qn_target.is_qn_target = True
qn_target.size_in_bytes = "12345"
qn_target.sha1 = "aabbccddeeff"
qn_target.result = result
qn_target.save()
danio_rerio = Organism(name="DANIO_RERIO",
taxonomy_id=1,
qn_target=result)
danio_rerio.save()
cra = ComputationalResultAnnotation()
cra.data = {}
cra.data["organism_id"] = danio_rerio.id
cra.data["is_qn"] = True
cra.result = result
cra.save()
result = ComputationalResult()
result.save()
micros = []
for file in os.listdir("/home/user/data_store/raw/TEST/MICROARRAY/"):
if "microarray.txt" in file:
continue
create_sample_for_experiment(
{
"organism": danio_rerio,
"accession_code": file,
"technology": "MICROARRAY",
"filename": file,
"data_dir": "/home/user/data_store/raw/TEST/MICROARRAY/",
},
experiment,
)
micros.append(file)
dset = Dataset()
dset.data = {"GSE1234": micros}
dset.scale_by = "NONE"
dset.aggregate_by = "SPECIES"
dset.svd_algorithm = "ARPACK"
dset.quantile_normalize = True
dset.save()
pjda = ProcessorJobDatasetAssociation()
pjda.processor_job = job
pjda.dataset = dset
pjda.save()
final_context = create_compendia.create_compendia(job.id)
self.assertSucceeded(job)
# Verify result
self.assertEqual(
final_context["compendium_result"].result.computedfile_set.count(),
1)
for file in final_context[
"compendium_result"].result.computedfile_set.all():
self.assertTrue(os.path.exists(file.absolute_file_path))
# test compendium_result
self.assertEqual(final_context["compendium_result"].svd_algorithm,
"ARPACK")
self.assertEqual(
final_context["compendium_result"].primary_organism.name,
final_context["organism_name"],
)
self.assertEqual(
final_context["compendium_result"].primary_organism.name,
"DANIO_RERIO")
self.assertEqual(final_context["compendium_result"].organisms.count(),
1)
zf = zipfile.ZipFile(final_context["compendium_result"].result.
computedfile_set.first().absolute_file_path)
with zf.open("aggregated_metadata.json") as f:
metadata = json.load(f)
self.assertFalse(metadata.get("quant_sf_only"))
# 420 microarray
self.assertEqual(metadata.get("num_samples"), 420)
self.assertEqual(metadata.get("num_experiments"), 1)
# Make sure the data were quantile normalized
self.assertTrue(metadata.get("quantile_normalized"))
self.assertIn("ks_statistic", final_context)
self.assertIn("ks_pvalue", final_context)
self.assertEqual(final_context["ks_pvalue"], 1.0)
def test_create_compendia_danio(self):
job = ProcessorJob()
job.pipeline_applied = ProcessorPipeline.CREATE_COMPENDIA.value
job.save()
# MICROARRAY TECH
experiment = Experiment()
experiment.accession_code = "GSE1234"
experiment.save()
result = ComputationalResult()
result.save()
qn_target = ComputedFile()
qn_target.filename = "danio_target.tsv"
qn_target.absolute_file_path = "/home/user/data_store/QN/danio_target.tsv"
qn_target.is_qn_target = True
qn_target.size_in_bytes = "12345"
qn_target.sha1 = "aabbccddeeff"
qn_target.result = result
qn_target.save()
danio_rerio = Organism(name="DANIO_RERIO",
taxonomy_id=1,
qn_target=result)
danio_rerio.save()
cra = ComputationalResultAnnotation()
cra.data = {}
cra.data["organism_id"] = danio_rerio.id
cra.data["is_qn"] = True
cra.result = result
cra.save()
result = ComputationalResult()
result.save()
micros = []
for file in os.listdir("/home/user/data_store/raw/TEST/MICROARRAY/"):
if "microarray.txt" in file:
continue
create_sample_for_experiment(
{
"organism": danio_rerio,
"accession_code": file,
"technology": "MICROARRAY",
"filename": file,
"data_dir": "/home/user/data_store/raw/TEST/MICROARRAY/",
},
experiment,
)
micros.append(file)
experiment = Experiment()
experiment.accession_code = "GSE5678"
experiment.save()
result = ComputationalResult()
result.save()
rnas = []
for file in os.listdir("/home/user/data_store/raw/TEST/RNASEQ/"):
if "rnaseq.txt" in file:
continue
create_sample_for_experiment(
{
"organism": danio_rerio,
"accession_code": file,
"technology": "RNA-SEQ",
"filename": file,
"data_dir": "/home/user/data_store/raw/TEST/RNASEQ/",
},
experiment,
)
rnas.append(file)
# Missing sample that will be filtered
sample = create_sample_for_experiment(
{
"organism": danio_rerio,
"accession_code": "GSM1487222",
"title": "this sample will be filtered",
"technology": "RNA-SEQ",
"filename": None,
},
experiment,
)
rnas.append(sample.accession_code)
dset = Dataset()
dset.data = {"GSE1234": micros, "GSE5678": rnas}
dset.scale_by = "NONE"
dset.aggregate_by = "SPECIES"
dset.svd_algorithm = "ARPACK"
dset.quantile_normalize = True
dset.save()
pjda = ProcessorJobDatasetAssociation()
pjda.processor_job = job
pjda.dataset = dset
pjda.save()
final_context = create_compendia.create_compendia(job.id)
self.assertSucceeded(job)
# Verify result
self.assertEqual(
final_context["compendium_result"].result.computedfile_set.count(),
1)
for file in final_context[
"compendium_result"].result.computedfile_set.all():
self.assertTrue(os.path.exists(file.absolute_file_path))
# test compendium_result
self.assertEqual(final_context["compendium_result"].svd_algorithm,
"ARPACK")
self.assertEqual(
final_context["compendium_result"].primary_organism.name,
final_context["organism_name"],
)
self.assertEqual(
final_context["compendium_result"].primary_organism.name,
"DANIO_RERIO")
self.assertEqual(final_context["compendium_result"].organisms.count(),
1)
self.assertEqual(len(final_context["filtered_samples"]), 10)
# check that sample with no computed file was skipped
self.assertTrue("GSM1487222" in final_context["filtered_samples"])
self.assertEqual(
final_context["filtered_samples"]["GSM1487222"]
["experiment_accession_code"], "GSE5678")
self.assertIn(
"This sample did not have a processed file",
final_context["filtered_samples"]["GSM1487222"]["reason"],
)
# check that the 9 files with lots of missing measurements were filtered
self.assertEqual(
len(
list(
filter(
lambda x: "less than 50% present values" in x["reason"
],
final_context["filtered_samples"].values(),
))),
9,
)
zf = zipfile.ZipFile(final_context["compendium_result"].result.
computedfile_set.first().absolute_file_path)
with zf.open("aggregated_metadata.json") as f:
metadata = json.load(f)
self.assertFalse(metadata.get("quant_sf_only"))
self.assertEqual(metadata.get("compendium_version"), 1)
# 420 microarray + 420 RNA seq
# -1 that is filtered for a missing file
# -9 that are filtered for having less than 50% present values
self.assertEqual(metadata.get("num_samples"), 830)
self.assertEqual(metadata.get("num_experiments"), 2)
# Make sure the data were quantile normalized
self.assertTrue(metadata.get("quantile_normalized"))
self.assertIn("ks_statistic", final_context)
self.assertIn("ks_pvalue", final_context)
self.assertEqual(final_context["ks_pvalue"], 1.0)