def test_trial_summary(self):
on_trial['_genomic'] = {'hugo_symbol': [{'value': 'TEST'}]}
on_trial['_clinical'] = {'disease_status': [{'value': ['TEST']}]}
other = {'management_group': [{'value': 'TEST'}]}
# create trial tree
db = get_db()
me = MatchEngine(db)
status, trial_tree = me.create_trial_tree(on_trial, no_validate=True)
# validate summary
summary = Summary(on_trial['_clinical'],
on_trial['_genomic'],
other,
trial_tree)
item = summary.create_summary(on_trial)
status_fields = ['drugs', 'genes', 'tumor_types', 'sponsor',
'phase_summary', 'accrual_goal', 'investigator', 'age_summary', 'protocol_number',
'disease_status', 'nct_number', 'disease_center', 'short_title',
'hormone_receptor_status']
for field in status_fields:
assert field in item, self._debug(item, field)
if field not in ['dfci_investigator', 'hormone_receptor_status']:
assert item[field], '%s| %s' % (field, item)
# remove all fields and validate that the summary will not error
del on_trial['age']
del on_trial['phase']
del on_trial['nct_id']
del on_trial['protocol_no']
del on_trial['principal_investigator']
del on_trial['cancer_center_accrual_goal_upper']
del on_trial['site_list']
del on_trial['sponsor_list']
del on_trial['drug_list']
del on_trial['staff_list']
status, trial_tree = me.create_trial_tree(on_trial, no_validate=True)
summary = Summary(on_trial['_clinical'],
on_trial['_genomic'],
other,
trial_tree)
item = summary.create_summary(on_trial)
for field in status_fields:
assert field in item, self._debug(item, field)
def build_trial_elasticsearch_fields(items):
"""
Create '_elasticsearch,' '_suggest' and '_summary' fields on trial documents.
Normalize oncotree diagnoses fields using 'normalized' collection in db
:param items:
:return:
"""
# get database connection.
db = database.get_db()
# loop over each item.
for item in items:
# build tree.
me = MatchEngine(db)
status, trial_tree = me.create_trial_tree(item, no_validate=True)
# look at every node.
genomic = {}
clinical = {}
other = {}
for n in trial_tree.nodes():
# get parent.
if 'node_id' not in trial_tree.nodes[n]:
continue
node_id = trial_tree.nodes[n]['node_id']
# look for multi-level nodes (right now its only match).
if 'match_tree' in trial_tree.nodes[n]:
# compress categories.
mt = trial_tree.nodes[n]['match_tree']
for x in mt:
if mt.nodes[x]['type'] == 'genomic':
insert_data_genomic(genomic, mt.nodes[x]['value'],
node_id)
if mt.nodes[x]['type'] == 'clinical':
insert_data_clinical(clinical, mt.nodes[x]['value'],
node_id)
# add the other nodes.
insert_data_other(trial_tree, node_id, n, other)
# create _summary, _suggest, and _elasticsearch fields
summary = Summary(clinical, genomic, other, trial_tree)
item['_summary'] = summary.create_summary(item)
autocomplete = Autocomplete(item)
item['_suggest'], item['_elasticsearch'], item['_summary']['primary_tumor_types'] = \
autocomplete.add_autocomplete()
logging.info("trial inserted " + item['protocol_no'])
logging.info("inserting trials to elasticsearch " +
str([item.setdefault("protocol_no") for item in items]))
def test_ms_status(self):
on_trial['_clinical'] = {}
on_trial['_genomic'] = {'mmr_status': [{'value': 'MMR-Proficient'}]}
db = get_db()
me = MatchEngine(db)
status, trial_tree = me.create_trial_tree(on_trial, no_validate=True)
summary = Summary(on_trial['_clinical'],
on_trial['_genomic'],
{},
trial_tree)
item = summary.create_summary(on_trial)
assert 'mmr_status' in item, self._debug(item, 'mmr_status')
on_trial['_genomic'] = {'ms_status': [{'value': 'MSI-H'}]}
status, trial_tree = me.create_trial_tree(on_trial, no_validate=True)
summary = Summary(on_trial['_clinical'],
on_trial['_genomic'],
{},
trial_tree)
item = summary.create_summary(on_trial)
assert 'ms_status' in item, self._debug(item, 'ms_status')