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 test_post(self):
"""
Test create a new read_group_genomic_file
"""
# Create needed entities
gf = GenomicFile(external_id='gf0')
rg = ReadGroup(external_id='rg0')
db.session.add_all([gf, rg])
db.session.commit()
kwargs = {
'read_group_id': rg.kf_id,
'genomic_file_id': gf.kf_id,
'external_id': 'rg0-gf0'
}
# Send get request
response = self.client.post(url_for(RG_GF_LIST_URL),
data=json.dumps(kwargs),
headers=self._api_headers())
# Check response status status_code
self.assertEqual(response.status_code, 201)
# Check response content
response = json.loads(response.data.decode('utf-8'))
assert response['results']['kf_id']
self.assertEqual(1, ReadGroupGenomicFile.query.count())
def _create_save_to_db(self):
"""
Make all entities
"""
# Create many to many rg and gf
rgs = []
gfs = []
for i in range(2):
gfs.append(GenomicFile(external_id='gf{}'.format(i)))
rgs.append(ReadGroup(external_id='rg{}'.format(i)))
db.session.add(
ReadGroupGenomicFile(genomic_file=gfs[0],
read_group=rgs[0],
external_id='rg0-gf0'))
db.session.add(
ReadGroupGenomicFile(genomic_file=gfs[0],
read_group=rgs[1],
external_id='rg1-gf0'))
db.session.add(
ReadGroupGenomicFile(genomic_file=gfs[1],
read_group=rgs[0],
external_id='rg0-gf1'))
db.session.add(
ReadGroupGenomicFile(genomic_file=gfs[1],
read_group=rgs[1],
external_id='rg1-gf1'))
db.session.commit()
return rgs, gfs
def _create_save_to_db(self):
"""
Create and save read_group
"""
rg = ReadGroup(external_id='blah', lane_number=3, flow_cell='FL0101')
db.session.add(rg)
db.session.commit()
return rg
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 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()