def _create_entities(self):
"""
Create participant with required entities
"""
# Sequencing center
sc = SequencingCenter.query.filter_by(name="Baylor").one_or_none()
if sc is None:
sc = SequencingCenter(name="Baylor")
db.session.add(sc)
db.session.commit()
# Create study
study = Study(external_id='phs001')
# Participants
p = Participant(external_id='p0', is_proband=True, study=study)
# Biospecimen
bs = Biospecimen(analyte_type='dna',
sequencing_center=sc,
participant=p)
# SequencingExperiment
data = {
'external_id': 'se',
'experiment_strategy': 'wgs',
'is_paired_end': True,
'platform': 'platform',
'sequencing_center': sc
}
se = SequencingExperiment(**data)
# Genomic Files
genomic_files = []
for i in range(4):
data = {
'file_name': 'gf_{}'.format(i),
'data_type': 'submitted aligned read',
'file_format': '.cram',
'urls': ['s3://file_{}'.format(i)],
'hashes': {
'md5': str(uuid.uuid4())
},
'is_harmonized': True if i % 2 else False
}
gf = GenomicFile(**data)
se.genomic_files.append(gf)
genomic_files.append(gf)
bs2 = Biospecimen(analyte_type='rna',
sequencing_center=sc,
participant=p)
db.session.add(bs, bs2)
db.session.add(study)
db.session.commit()
def _create_entities(self):
# Create study
study = Study(external_id='phs001')
# Create participant
p = Participant(external_id='p1',
is_proband=True, study=study)
# Create sequencing_center
sc = SequencingCenter.query.filter_by(name="Baylor").one_or_none()
if sc is None:
sc = SequencingCenter(name="Baylor")
db.session.add(sc)
db.session.commit()
# Create sequencing experiments
se1 = SequencingExperiment(**self._make_seq_exp('se1'),
sequencing_center_id=sc.kf_id)
se2 = SequencingExperiment(**self._make_seq_exp('se2'),
sequencing_center_id=sc.kf_id)
# Create biospecimen
bs = Biospecimen(external_sample_id='bio1', analyte_type='dna',
participant_id=p.kf_id,
sequencing_center_id=sc.kf_id)
# Create genomic files
gfs = []
for i in range(4):
kwargs = {
'file_name': 'file_{}'.format(i),
'data_type': 'submitted aligned read',
'file_format': '.cram',
'urls': ['s3://file_{}'.format(i)],
'hashes': {'md5': str(uuid.uuid4())},
'controlled_access': True,
'is_harmonized': True,
'reference_genome': 'Test01'
}
gf = GenomicFile(**kwargs,
sequencing_experiment_id=se1.kf_id)
if i % 2:
se1.genomic_files.append(gf)
else:
se2.genomic_files.append(gf)
gfs.append(gf)
bs.genomic_files = gfs
p.biospecimens = [bs]
db.session.add(p)
db.session.commit()
def test_create_and_find_biospecimen(self):
"""
Test creation of biospecimen
"""
study = Study(external_id='phs001')
db.session.add(study)
db.session.commit()
dt = datetime.now()
participant_id = "Test_Subject_0"
# creating participant
p = Participant(external_id=participant_id, is_proband=True,
study_id=study.kf_id)
db.session.add(p)
db.session.commit()
# Creating Biospecimen
sample_id = "Test_Sample_0"
aliquot_id = "Test_Aliquot_0"
data = self._make_biospecimen(external_sample_id=sample_id,
external_aliquot_id=aliquot_id)
ids = self.create_seqexp()
s = Biospecimen(**data, participant_id=p.kf_id,
sequencing_center_id=ids['sequencing_center_id'])
db.session.add(s)
db.session.commit()
self.assertEqual(Biospecimen.query.count(), 1)
bs = Biospecimen.query.first()
for key, value in data.items():
self.assertEqual(value, getattr(bs, key))
self.assertGreater(bs.created_at, dt)
self.assertGreater(bs.modified_at, dt)
self.assertIs(type(uuid.UUID(bs.uuid)), uuid.UUID)
def test_one_to_many_relationship_create(self):
"""
Test creating multiple biospecimens to the the Participant
"""
# create a participant with a biospecimen
(participant_id,
sample_id,
aliquot_id) = self.create_participant_biospecimen()
p = Participant.query.filter_by(
external_id=participant_id).one_or_none()
# adding another biospecimen to participant
data = self._make_biospecimen(external_sample_id='Test_Sample_1',
external_aliquot_id='Test_Aliquot_id')
ids = self.create_seqexp()
s = Biospecimen(**data, participant_id=p.kf_id,
sequencing_center_id=ids['sequencing_center_id'])
db.session.add(s)
db.session.commit()
p = Participant.query.filter_by(external_id=participant_id).all()
self.assertEqual(Participant.query.count(), 1)
self.assertEqual(p[0].biospecimens[0].external_sample_id,
'Test_Sample_0')
self.assertEqual(p[0].biospecimens[1].external_sample_id,
'Test_Sample_1')
self.assertEqual(p[0].kf_id, s.participant_id)
self.assertEqual(Biospecimen.query.count(), 2)
def create_participant_biospecimen(self):
"""
create a participant and biospecimen and save to db
returns participant_id and biospecimen_id
"""
participant_id = "Test_Subject_0"
sample_id = "Test_Sample_0"
aliquot_id = "Test_aliquot_0"
data = self._make_biospecimen(external_sample_id=sample_id,
external_aliquot_id=aliquot_id)
ids = self.create_seqexp()
biospecimen_0 = Biospecimen(**data,
sequencing_center_id=ids
['sequencing_center_id'])
participant_0 = Participant(
external_id=participant_id,
is_proband=True,
biospecimens=[biospecimen_0])
study = Study(external_id='phs001')
study.participants.append(participant_0)
db.session.add(study)
db.session.commit()
return participant_id, sample_id, aliquot_id
def _create_biospecimens(self, total):
"""
Create biospecimens with genomic_files
"""
s_list = []
dt = datetime.now()
for i in range(total):
biospecimen_data = {
'external_sample_id': 'sample_{}'.format(i),
'tissue_type': random.choice(self.tissue_type_list),
'composition': random.choice(self.composition_list),
'anatomical_site': random.choice(self.anatomical_site_list),
'age_at_event_days': random.randint(0, 32872),
'tumor_descriptor': random.choice(self.tumor_descriptor_list),
'external_aliquot_id': 'aliquot_{}'.format(i),
'shipment_origin': random.choice(self.shipment_origin_list),
'analyte_type': random.choice(self.analyte_type_list),
'concentration_mg_per_ml': (random.randint(700, 4000)) / 10,
'volume_ml': (random.randint(200, 400)) / 10,
'shipment_date': dt - relativedelta.relativedelta(
years=random.randint(1, 2)) - relativedelta.relativedelta(
months=random.randint(1, 12)) +
relativedelta.relativedelta(days=random.randint(1, 30))
}
genomic_files = self._create_genomic_files(
random.randint(self.min_gen_files,
self.max_gen_files))
sc = random.choice(SequencingCenter.query.all())
b = Biospecimen(
**biospecimen_data, genomic_files=genomic_files,
sequencing_center_id=sc.kf_id)
s_list.append(b)
return s_list
def _create_all_entities(self):
"""
Create 2 studies with genomic files and read groups
"""
sc = SequencingCenter(name='sc')
studies = []
ses = {}
gfs = {}
for j in range(2):
s = Study(external_id='s{}'.format(j))
p = Participant(external_id='p{}'.format(j))
s.participants.append(p)
study_gfs = gfs.setdefault('study{}'.format(j), [])
for i in range(3):
b = Biospecimen(external_sample_id='b{}'.format(i),
analyte_type='DNA',
sequencing_center=sc,
participant=p)
gf = GenomicFile(
external_id='study{}-gf{}'.format(j, i),
urls=['s3://mybucket/key'],
hashes={'md5': 'd418219b883fce3a085b1b7f38b01e37'})
study_gfs.append(gf)
b.genomic_files.append(gf)
study_ses = ses.setdefault('study{}'.format(j), [])
dt = datetime.now()
kwargs = {
'experiment_date': str(dt.replace(tzinfo=tz.tzutc())),
'experiment_strategy': 'WXS',
'library_name': 'Test_library_name_1',
'library_strand': 'Unstranded',
'is_paired_end': False,
'platform': 'Illumina',
'instrument_model': '454 GS FLX Titanium',
'max_insert_size': 600,
'mean_insert_size': 500,
'mean_depth': 40,
'total_reads': 800,
'mean_read_length': 200
}
se0 = SequencingExperiment(**kwargs,
sequencing_center=sc,
external_id='study{}-se0'.format(j))
se0.genomic_files.extend(study_gfs[0:2])
se1 = SequencingExperiment(**kwargs,
sequencing_center=sc,
external_id='study{}-se1'.format(j))
se1.genomic_files.extend([study_gfs[0], study_gfs[-1]])
study_ses.extend([se0, se1])
studies.append(s)
db.session.add_all(studies)
db.session.commit()
return ses, gfs, studies
def _create_all_entities():
"""
Create 2 studies with genomic files and read groups
"""
sc = SequencingCenter(name='sc')
studies = []
ses = {}
rgs = {}
gfs = {}
for j in range(2):
s = Study(external_id='s{}'.format(j))
p = Participant(external_id='p{}'.format(j))
s.participants.append(p)
study_gfs = gfs.setdefault('study{}'.format(j), [])
for i in range(3):
b = Biospecimen(external_sample_id='b{}'.format(i),
analyte_type='DNA',
sequencing_center=sc,
participant=p)
gf = GenomicFile(
external_id='study{}-gf{}'.format(j, i),
urls=['s3://mybucket/key', 'https://gen3.something.com/did'],
hashes={'md5': 'd418219b883fce3a085b1b7f38b01e37'})
study_gfs.append(gf)
b.genomic_files.append(gf)
study_rgs = rgs.setdefault('study{}'.format(j), [])
rg0 = ReadGroup(external_id='study{}-rg0'.format(j))
rg0.genomic_files.extend(study_gfs[0:2])
rg1 = ReadGroup(external_id='study{}-rg1'.format(j))
rg1.genomic_files.extend([study_gfs[0], study_gfs[-1]])
study_ses = ses.setdefault('study{}'.format(j), [])
se0 = SequencingExperiment(external_id='study{}-se0'.format(j),
experiment_strategy='WGS',
is_paired_end=True,
platform='platform',
sequencing_center=sc)
se0.genomic_files.extend(study_gfs[0:2])
se1 = SequencingExperiment(external_id='study{}-se1'.format(j),
experiment_strategy='WGS',
is_paired_end=True,
platform='platform',
sequencing_center=sc)
se1.genomic_files.extend([study_gfs[0], study_gfs[-1]])
study_rgs.extend([rg0, rg1])
study_ses.extend([se0, se1])
studies.append(s)
db.session.add_all(studies)
db.session.commit()
return ses, rgs, gfs, studies
def _create_biospecimens(self, total=2):
"""
Create biospecimens
"""
# Create Sequencing_center
sc = SequencingCenter(name='Baylor')
db.session.add(sc)
db.session.commit()
return [Biospecimen(external_sample_id='s{}'.format(i),
analyte_type='dna',
sequencing_center_id=sc.kf_id)
for i in range(total)]
def _create_biospecimen(self, _id, genomic_files=None,
sequencing_center_id=None,
participant_id=None):
"""
Create biospecimen with genomic_files
"""
bs = Biospecimen(external_sample_id=_id, analyte_type='dna',
genomic_files=genomic_files or [],
sequencing_center_id=sequencing_center_id,
participant_id=participant_id)
db.session.add(bs)
db.session.commit()
return bs
def test_one_to_many_realtionship_update(self):
"""
Test Updating one of the biospecimens in the participant
"""
# create a participant with a biospecimen
(participant_id,
sample_id,
aliquot_id) = self.create_participant_biospecimen()
# Get Participant
p = Participant.query.filter_by(
external_id=participant_id).one_or_none()
# adding another biospecimen to participant
data = self._make_biospecimen(external_sample_id='Test_Sample_1',
external_aliquot_id='Test_Aliquot_1')
ids = self.create_seqexp()
s = Biospecimen(**data, participant_id=p.kf_id,
sequencing_center_id=ids['sequencing_center_id'])
db.session.add(s)
db.session.commit()
# Get Biospecimen and Person with multiple Entries
p = Participant.query.filter_by(external_id=participant_id).all()
s = Biospecimen.query.filter_by(external_sample_id='Test_Sample_1').\
one_or_none()
# update one of the biospecimen attribute
s.source_text_tissue_type = 'Tumor'
s = Biospecimen.query.filter_by(external_sample_id='Test_Sample_1').\
one_or_none()
self.assertEqual(s.source_text_tissue_type, 'Tumor')
self.assertEqual(Participant.query.count(), 1)
self.assertEqual(p[0].biospecimens[1].external_sample_id,
'Test_Sample_1')
self.assertEqual(Biospecimen.query.count(), 2)
def _create_save_to_db(self):
"""
Create and save diagnosis
Requires creating a participant
Create a diagnosis and add it to participant as kwarg
Save participant
"""
# Create study
study = Study(external_id='phs001')
# Create diagnosis
kwargs = {
'external_id': 'd1',
'source_text_diagnosis': 'flu',
'diagnosis_category': 'Cancer',
'source_text_tumor_location': 'Brain',
'age_at_event_days': 365,
'mondo_id_diagnosis': 'DOID:8469',
'icd_id_diagnosis': 'J10.01',
'uberon_id_tumor_location': 'UBERON:0000955',
'spatial_descriptor': 'left side'
}
d = Diagnosis(**kwargs)
# Create and save participant with diagnosis
participant_id = 'Test subject 0'
p = Participant(external_id=participant_id,
diagnoses=[d],
is_proband=True,
study=study)
db.session.add(p)
db.session.commit()
# Create sequencing center
s = SequencingCenter(name='washu')
db.session.add(s)
db.session.commit()
# Create biospecimen
b = Biospecimen(analyte_type='DNA',
sequencing_center_id=s.kf_id,
participant=p)
db.session.add(s)
db.session.add(b)
db.session.commit()
kwargs['participant_id'] = p.kf_id
kwargs['kf_id'] = d.kf_id
return kwargs
def test_not_null_constraint(self):
"""
Test biospecimen cannot be created with out required parameters
such as participant_id
"""
# Create Biospecimen
sample_id = "Test_Sample_0"
# With Missing Kf_id
data = self._make_biospecimen(external_sample_id=sample_id)
s = Biospecimen(**data)
db.session.add(s)
# Add Biospecimen to db
with self.assertRaises(IntegrityError):
db.session.commit()
def test_foreign_key_constraint(self):
"""
Test biospecimen cannot be created with empty participant_id
"""
# Create Biospecimen
biospecimen_id = "Test_Sample_0"
# With Empty Kf_id
data = self._make_biospecimen(external_sample_id=biospecimen_id)
s = Biospecimen(**data, participant_id='')
db.session.add(s)
# Add Biospecimen to db
with self.assertRaises(IntegrityError):
db.session.commit()
def test_link_biospecimen_diagnosis(self):
"""
Test Deleting one of the biospecimens
"""
# create a participant with a biospecimen
(participant_id,
sample_id,
aliquot_id) = self.create_participant_biospecimen()
p = Participant.query.first()
# Create diagnosis
kwargs = {
'external_id': 'id_1',
'source_text_diagnosis': 'diagnosis_1',
'age_at_event_days': 365,
'diagnosis_category': 'cancer',
'source_text_tumor_location': 'Brain',
'mondo_id_diagnosis': 'DOID:8469',
'uberon_id_tumor_location': 'UBERON:0000955',
'icd_id_diagnosis': 'J10.01',
'spatial_descriptor': 'left side',
'participant_id': p.kf_id
}
dg = Diagnosis(**kwargs)
db.session.add(dg)
biospecimen = Biospecimen.query.first()
# create link btn bs and ds
bs_ds = BiospecimenDiagnosis(biospecimen_id=biospecimen.kf_id,
diagnosis_id=dg.kf_id)
db.session.add(bs_ds)
db.session.commit()
self.assertEqual(BiospecimenDiagnosis.query.count(), 1)
self.assertEqual(bs_ds.biospecimen_id, biospecimen.kf_id)
self.assertEqual(bs_ds.diagnosis_id, dg.kf_id)
s = Study(external_id="study")
sc = SequencingCenter.query.first()
p1 = Participant(external_id='p1', study=s)
b1 = Biospecimen(analyte_type='RNA', participant=p1,
sequencing_center_id=sc.kf_id)
db.session.add(s)
db.session.commit()
# Participant 1 - Link their biop b1 to Participant 0 diagnosis d0
bd1 = BiospecimenDiagnosis(biospecimen_id=b1.kf_id,
diagnosis_id=dg.kf_id)
db.session.add(bd1)
with self.assertRaises(DatabaseValidationError):
db.session.commit()
db.session.rollback()
def _create_all_entities(self):
"""
Create 2 studies with genomic files and read groups
"""
sc = SequencingCenter(name='sc')
studies = []
rgs = {}
gfs = {}
for j in range(2):
s = Study(external_id='s{}'.format(j))
p = Participant(external_id='p{}'.format(j))
s.participants.append(p)
study_gfs = gfs.setdefault('study{}'.format(j), [])
for i in range(3):
b = Biospecimen(external_sample_id='b{}'.format(i),
analyte_type='DNA',
sequencing_center=sc,
participant=p)
gf = GenomicFile(
external_id='study{}-gf{}'.format(j, i),
urls=['s3://mybucket/key'],
hashes={'md5': 'd418219b883fce3a085b1b7f38b01e37'})
study_gfs.append(gf)
b.genomic_files.append(gf)
study_rgs = rgs.setdefault('study{}'.format(j), [])
rg0 = ReadGroup(external_id='study{}-rg0'.format(j))
rg0.genomic_files.extend(study_gfs[0:2])
rg1 = ReadGroup(external_id='study{}-rg1'.format(j))
rg1.genomic_files.extend([study_gfs[0], study_gfs[-1]])
study_rgs.extend([rg0, rg1])
studies.append(s)
db.session.add_all(studies)
db.session.commit()
return rgs, gfs, studies
def test_cascade_delete_via_biospecimen(self):
"""
Test delete existing diagnosis
Delete biospecimen to which diagnosis belongs
"""
# Create and save genomic files and dependent entities
kwargs_dict, diagnoses = self._create_diagnoses(total=1)
# Add another biospecimen
p = Participant.query.first()
sc = SequencingCenter.query.first()
b = Biospecimen(analyte_type='DNA',
sequencing_center=sc,
participant=p)
db.session.add(b)
db.session.commit()
# Link bio and diags
biospecimens = Biospecimen.query.all()
diagnosis = Diagnosis.query.first()
for biospecimen in biospecimens:
bsds = BiospecimenDiagnosis(biospecimen=biospecimen,
diagnosis=diagnosis)
db.session.add(bsds)
db.session.commit()
# Get initial counts
b_count = Biospecimen.query.count()
d_count = Diagnosis.query.count()
bd_count = BiospecimenDiagnosis.query.count()
# Delete biospecimen
db.session.delete(b)
db.session.commit()
# Check database
assert BiospecimenDiagnosis.query.count() == bd_count - 1
assert Diagnosis.query.count() == d_count
assert Biospecimen.query.count() == b_count - 1
def test_add_invalid_biospecimen(self):
"""
Test that a diagnosis cannot be linked with a biospecimen if
they refer to different participants
"""
diagnoses, kwarg_dict = self._create_diagnoses()
# Get first participant
st = Study.query.first()
s = SequencingCenter.query.first()
# Create new participant with biospecimen
p1 = Participant(external_id='p1', is_proband=True, study_id=st.kf_id)
b = Biospecimen(analyte_type='DNA',
sequencing_center_id=s.kf_id,
participant=p1)
db.session.add(b)
db.session.commit()
# Try linking
d = Diagnosis.query.first()
b.diagnoses.append(d)
with self.assertRaises(DatabaseValidationError):
db.session.commit()
db.session.rollback()
def test_one_to_many_relationship_delete(self):
"""
Test Deleting one of the biospecimens
"""
# create a participant with a biospecimen
(participant_id,
sample_id,
aliquot_id) = self.create_participant_biospecimen()
p = Participant.query.filter_by(
external_id=participant_id).one_or_none()
# adding another biospecimen to participant
data = self._make_biospecimen(external_sample_id='Test_Sample_1',
external_aliquot_id='Test_Aliquot_1')
ids = self.create_seqexp()
s = Biospecimen(**data, participant_id=p.kf_id,
sequencing_center_id=ids['sequencing_center_id'])
db.session.add(s)
db.session.commit()
# Delete Biospecimen
db.session.delete(s)
db.session.commit()
self.assertEqual(Biospecimen.query.count(), 1)
def _create_diagnoses(self, total=2):
"""
Create diagnoses and other requred entities
"""
# Create study
study = Study(external_id='phs001')
# Create participant
participant_id = 'Test subject 0'
p = Participant(external_id=participant_id,
is_proband=True,
study=study)
# Create sequencing center
s = SequencingCenter(name='washu')
db.session.add(s)
db.session.commit()
# Create biospecimen
b = Biospecimen(analyte_type='DNA',
sequencing_center_id=s.kf_id,
participant=p)
db.session.add(p)
db.session.add(b)
db.session.commit()
# Create diagnoses
diagnoses = []
kwarg_dict = {}
for i in range(total):
d, kwargs = self._create_diagnosis(i, participant_id=p.kf_id)
kwarg_dict[d.external_id] = kwargs
diagnoses.append(d)
db.session.add_all(diagnoses)
db.session.commit()
return diagnoses, kwarg_dict
def _create_save_to_db(self):
"""
Create and save biospecimen
Requires creating a participant
Create a biospecimen and add it to participant as kwarg
Save participant
"""
dt = datetime.now()
study = Study(external_id='phs001')
db.session.add(study)
db.session.commit()
sc = SequencingCenter.query.filter_by(name="Baylor").one_or_none()
if sc is None:
sc = SequencingCenter(name="Baylor")
db.session.add(sc)
db.session.commit()
se = SequencingExperiment(external_id="Test_seq_ex_o",
experiment_strategy="WGS",
is_paired_end="True",
platform="Test_platform",
sequencing_center_id=sc.kf_id)
db.session.add(se)
db.session.commit()
# Create biospecimen
kwargs = {
'external_sample_id': 's1',
'external_aliquot_id': 'a1',
'source_text_tissue_type': 'Normal',
'composition': 'composition1',
'source_text_anatomical_site': 'Brain',
'age_at_event_days': 365,
'source_text_tumor_descriptor': 'Metastatic',
'shipment_origin': 'CORIELL',
'analyte_type': 'DNA',
'concentration_mg_per_ml': 100,
'volume_ul': 12.67,
'shipment_date': dt,
'spatial_descriptor': 'left side',
'ncit_id_tissue_type': 'Test',
'ncit_id_anatomical_site': 'C12439',
'uberon_id_anatomical_site': 'UBERON:0000955',
'consent_type': 'GRU-IRB',
'dbgap_consent_code': 'phs00000.c1',
'sequencing_center_id': sc.kf_id
}
d = Biospecimen(**kwargs)
# Create and save participant with biospecimen
p = Participant(external_id='Test subject 0',
biospecimens=[d],
is_proband=True,
study_id=study.kf_id)
db.session.add(p)
db.session.commit()
kwargs['participant_id'] = p.kf_id
kwargs['kf_id'] = d.kf_id
return kwargs
def _create_all_entities(self):
"""
Create 2 studies with same content
Content: 3 participants, 4 biospecimens, 4 diagnoses
"""
# Create entities
sc = SequencingCenter.query.filter_by(name='sc').first()
if not sc:
sc = SequencingCenter(name='sc')
studies = []
# Two studies
for j in range(2):
s = Study(external_id='s{}'.format(j))
p0 = Participant(external_id='study{}-p0'.format(j))
p1 = Participant(external_id='study{}-p1'.format(j))
p2 = Participant(external_id='study{}-p2'.format(j))
# Participant 0
# Has 2 Biospecimens
for i in range(2):
b = Biospecimen(external_sample_id='study{}-p0-b{}'.format(
j, i),
analyte_type='DNA',
sequencing_center=sc)
# Biospecimen b0 has 2 diagnoses
if i == 0:
for k in range(2):
d = Diagnosis(
external_id='study{}-p0-d{}'.format(j, k))
p0.diagnoses.append(d)
# Biospecimen b1 has 1 diagnosis
else:
d = Diagnosis(
external_id='study{}-p0-d{}'.format(j, k + 1))
p0.diagnoses.append(d)
p0.biospecimens.append(b)
# Participant 1
# Has 1 biospecimen, 1 diagnosis
b = Biospecimen(external_sample_id='study{}-p1-b0'.format(j),
analyte_type='DNA',
sequencing_center=sc)
d = Diagnosis(external_id='study{}-p1-d0'.format(j))
p1.biospecimens.append(b)
p1.diagnoses.append(d)
# Participant 2
# Has 1 biospecimen
b = Biospecimen(external_sample_id='study{}-p2-b0'.format(j),
analyte_type='DNA',
sequencing_center=sc)
p2.biospecimens.append(b)
s.participants.extend([p0, p1, p2])
studies.append(s)
db.session.add_all(studies)
db.session.commit()
# Create links between bios and diags
bs_dgs = []
# Participant 0
p0 = studies[0].participants[0]
# b0-d0
bs_dgs.append(
BiospecimenDiagnosis(biospecimen_id=p0.biospecimens[0].kf_id,
diagnosis_id=p0.diagnoses[0].kf_id))
# b0-d1
bs_dgs.append(
BiospecimenDiagnosis(biospecimen_id=p0.biospecimens[0].kf_id,
diagnosis_id=p0.diagnoses[1].kf_id))
# b1-d2
bs_dgs.append(
BiospecimenDiagnosis(biospecimen_id=p0.biospecimens[1].kf_id,
diagnosis_id=p0.diagnoses[2].kf_id))
# b0-d2
bs_dgs.append(
BiospecimenDiagnosis(biospecimen_id=p0.biospecimens[0].kf_id,
diagnosis_id=p0.diagnoses[2].kf_id))
# Participant 1
p1 = studies[0].participants[1]
# b0-d0
bs_dgs.append(
BiospecimenDiagnosis(biospecimen_id=p1.biospecimens[0].kf_id,
diagnosis_id=p1.diagnoses[0].kf_id))
db.session.add_all(bs_dgs)
db.session.commit()
def participants(client):
# Add a bunch of studies for pagination
for i in range(101):
s = Study(external_id='Study_{}'.format(i))
db.session.add(s)
for i in range(101):
ca = CavaticaApp(name='app', revision=0)
db.session.add(ca)
# Add a bunch of study files
s0 = Study.query.filter_by(external_id='Study_0').one()
s1 = Study.query.filter_by(external_id='Study_1').one()
for i in range(101):
sf = StudyFile(file_name='blah', study_id=s0.kf_id)
db.session.add(sf)
# Add a bunch of investigators
for _ in range(102):
inv = Investigator(name='test')
inv.studies.extend([s0, s1])
db.session.add(inv)
# Add a bunch of families
families = []
for i in range(101):
families.append(Family(external_id='Family_{}'.format(i)))
db.session.add_all(families)
db.session.flush()
participants = []
f0 = Family.query.filter_by(external_id='Family_0').one()
f1 = Family.query.filter_by(external_id='Family_1').one()
seq_cen = None
for i in range(102):
f = f0 if i < 50 else f1
s = s0 if i < 50 else s1
data = {
'external_id': "test",
'is_proband': True,
'race': 'Asian',
'ethnicity': 'Hispanic or Latino',
'diagnosis_category': 'Cancer',
'gender': 'Male'
}
p = Participant(**data, study_id=s.kf_id, family_id=f.kf_id)
diag = Diagnosis()
p.diagnoses = [diag]
outcome = Outcome()
p.outcomes = [outcome]
phen = Phenotype()
p.phenotypes = [phen]
participants.append(p)
db.session.add(p)
db.session.flush()
seq_data = {
'external_id': 'Seq_0',
'experiment_strategy': 'WXS',
'library_name': 'Test_library_name_1',
'library_strand': 'Unstranded',
'is_paired_end': False,
'platform': 'Test_platform_name_1'
}
gf_kwargs = {
'external_id': 'gf_0',
'file_name': 'hg38.fq',
'data_type': 'Aligned Reads',
'file_format': 'fastq',
'size': 1000,
'urls': ['s3://bucket/key'],
'hashes': {
'md5': str(uuid.uuid4())
},
'controlled_access': False
}
seq_cen = SequencingCenter.query.filter_by(name="Baylor")\
.one_or_none()
if seq_cen is None:
seq_cen = SequencingCenter(external_id='SC_0', name="Baylor")
db.session.add(seq_cen)
db.session.flush()
seq_exp = SequencingExperiment(**seq_data,
sequencing_center_id=seq_cen.kf_id)
db.session.add(seq_exp)
samp = Biospecimen(analyte_type='an analyte',
sequencing_center_id=seq_cen.kf_id,
participant=p)
db.session.add(samp)
p.biospecimens = [samp]
gf = GenomicFile(**gf_kwargs,
sequencing_experiment_id=seq_exp.kf_id)
db.session.add(gf)
samp.genomic_files.append(gf)
samp.diagnoses.append(diag)
db.session.flush()
rg = ReadGroup(lane_number=4, flow_cell='FL0123')
rg.genomic_files.append(gf)
ct = CavaticaTask(name='task_{}'.format(i))
ct.genomic_files.append(gf)
ca.cavatica_tasks.append(ct)
# Family relationships
for participant1, participant2 in iterate_pairwise(participants):
gender = participant1.gender
rel = 'mother'
if gender == 'male':
rel = 'father'
r = FamilyRelationship(participant1=participant1,
participant2=participant2,
participant1_to_participant2_relation=rel)
db.session.add(r)
db.session.commit()
