def test_run_query(self):
# reinstantiate MatchEngine so that the set of all sample ids in the database includes the documents that were
# posted by the unit test setUp
self.me = MatchEngine(self.db)
# define a clinical node
node = {'type': 'clinical', 'value': {'ONCOTREE_PRIMARY_DIAGNOSIS': 'Adrenal Gland', 'AGE_NUMERICAL': '>=18'}}
# run query
result, matches = self.me.run_query(node)
# assert number of samples are 89
assert len(result) == 1, len(result)
assert self.sample_id in result
# define a genomic criteria
node = {'type': 'genomic', 'value': {'HUGO_SYMBOL': '!BRAF'}}
# run query
result, matches = self.me.run_query(node)
# assert number of samples is 1
assert len(result) == 9, len(result)
assert self.sample_id not in result
self.add_genomic_v2()
node = {'type': 'genomic', 'value': {'HUGO_SYMBOL': 'WHSC1'}}
result, matches = self.me.run_query(node)
assert 'actionability' in matches[0]
assert matches[0]['mmr_status'] == 'Proficient (MMR-P / MSS)'
def test_extract_hr_status(self):
m = MatchEngine(get_db())
match_tree = trial['treatment_list']['step'][0]['match'][5]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
hr = pmt.extract_hr_status()
assert sorted(hr) == sorted(['HER2 Negative', 'ER Negative', 'PR Positive'])
def test_extract_signatures(self):
m = MatchEngine(get_db())
match_tree = trial['treatment_list']['step'][0]['match'][3]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
s = pmt.extract_signatures()
assert 'MMR-D' in s[0]
assert 'MSI-H' in s[1]
def test_extract_hr_status(self):
m = MatchEngine(get_db())
match_tree = trial['treatment_list']['step'][0]['match'][5]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
hr = pmt.extract_hr_status()
assert sorted(hr) == sorted(
['HER2 Negative', 'ER Negative', 'PR Positive'])
def test_extract_signatures(self):
m = MatchEngine(get_db())
match_tree = trial['treatment_list']['step'][0]['match'][3]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
s = pmt.extract_signatures()
assert 'MMR-D' in s[0]
assert 'MSI-H' in s[1]
def run_matchengine():
"""
Computes matches between all trials in the database and the given subset list of patient MRNs
:param mrns: List of patient MRNs
:return: database collection of trial matches
"""
db = database.get_db()
me = MatchEngine(db)
me.find_trial_matches()
def run_matchengine():
"""
Computes matches between all trials in the database and the given subset list of patient MRNs
:param mrns: List of patient MRNs
:return: database collection of trial matches
"""
db = database.get_db()
me = MatchEngine(db)
me.find_trial_matches()
def trial_insert(items):
# get database connection.
db = database.get_db()
# loop over each item.
for item in items:
# log this.
logging.info("trial inserted")
# 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.node[n]:
continue
node_id = trial_tree.node[n]['node_id']
# look for multi-level nodes (right now its only match).
if 'match_tree' in trial_tree.node[n]:
# compress categories.
mt = trial_tree.node[n]['match_tree']
for x in mt:
if mt.node[x]['type'] == 'genomic':
insert_data_genomic(genomic, mt.node[x]['value'],
node_id)
if mt.node[x]['type'] == 'clinical':
insert_data_clinical(clinical, mt.node[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()
return items
def test_extract_variants(self):
m = MatchEngine(get_db())
match_tree = trial['treatment_list']['step'][0]['match'][0]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
v = pmt.extract_variants()
assert 'BRAF V600E' in v['variants']
assert 'BRAF V600K' in v['variants']
assert 'KRAS any' in v['variants']
assert 'EGFR wt' in v['wts']
assert len(v['variants']) == 3
assert len(v['wts']) == 1
match_tree = trial['treatment_list']['step'][0]['match'][1]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
v = pmt.extract_variants()
assert 'PTEN CNV' in v['cnvs']
assert 'BRCA1 SV' in v['svs']
assert 'BRAF V600' in v['exclusions']
assert len(v['variants']) == 0
assert len(v['cnvs']) == 1
assert len(v['svs']) == 1
assert len(v['wts']) == 0
assert len(v['exclusions']) == 1
match_tree = trial['treatment_list']['step'][0]['match'][2]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
v = pmt.extract_variants()
assert 'BRAF V600E' not in v['variants']
assert len(v['variants']) == 0
assert len(v['wts']) == 0
assert 'BRAF V600E' in v['exclusions']
match_tree = trial['treatment_list']['step'][0]['match'][4]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
v = pmt.extract_variants()
assert 'BRAF V600K' in v['variants']
assert 'EGFR any' in v['variants']
assert len(v['variants']) == 2
assert 'PTEN CNV' in v['cnvs']
assert len(v['cnvs']) == 1
assert 'KRAS' in v['exclusions']
assert 'NRAS' in v['exclusions']
assert len(v['exclusions']) == 2
assert 'NTRK1 wt' in v['wts']
assert len(v['wts']) == 1
def trial_insert(items):
# get database connection.
db = database.get_db()
# loop over each item.
for item in items:
# log this.
logging.info("trial inserted")
# 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.node[n]:
continue
node_id = trial_tree.node[n]['node_id']
# look for multi-level nodes (right now its only match).
if 'match_tree' in trial_tree.node[n]:
# compress categories.
mt = trial_tree.node[n]['match_tree']
for x in mt:
if mt.node[x]['type'] == 'genomic':
insert_data_genomic(genomic, mt.node[x]['value'], node_id)
if mt.node[x]['type'] == 'clinical':
insert_data_clinical(clinical, mt.node[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()
return items
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 test_extract_cancer_types(self):
m = MatchEngine(get_db())
match_tree = match_tree_example
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
cancer_type_dict = pmt.extract_cancer_types()
assert sorted(cancer_type_dict['diagnoses']) == sorted(
['Ocular Melanoma']), cancer_type_dict['diagnoses']
assert sorted(cancer_type_dict['cancer_types_expanded']) == sorted([
'Ocular Melanoma', 'Uveal Melanoma', 'Conjunctival Melanoma'
]), cancer_type_dict['cancer_types_expanded']
assert sorted(cancer_type_dict['excluded_cancer_types']
) == [], cancer_type_dict['excluded_cancer_types']
assert cancer_type_dict['primary_cancer_types'] == [
'Eye'
], cancer_type_dict['primary_cancer_types']
m = MatchEngine(get_db())
match_tree = match_tree_example2
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
cancer_type_dict = pmt.extract_cancer_types()
assert sorted(cancer_type_dict['diagnoses']) == sorted(
['_SOLID_']), cancer_type_dict['diagnoses']
assert 'Acute Lymphoid Leukemia' not in cancer_type_dict[
'cancer_types_expanded'], cancer_type_dict['cancer_types_expanded']
assert sorted(cancer_type_dict['excluded_cancer_types']
) == [], cancer_type_dict['excluded_cancer_types']
assert cancer_type_dict['primary_cancer_types'] == [
'All Solid Tumors'
], cancer_type_dict['primary_cancer_types']
m = MatchEngine(get_db())
match_tree = match_tree_example3
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
cancer_type_dict = pmt.extract_cancer_types()
assert sorted(cancer_type_dict['diagnoses']) == sorted(
['_LIQUID_']), cancer_type_dict['diagnoses']
assert 'Acute Lymphoid Leukemia' in cancer_type_dict[
'cancer_types_expanded'], cancer_type_dict['cancer_types_expanded']
assert sorted(cancer_type_dict['excluded_cancer_types']
) == [], cancer_type_dict['excluded_cancer_types']
assert cancer_type_dict['primary_cancer_types'] == [
'All Liquid Tumors'
], cancer_type_dict['primary_cancer_types']
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 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')
def test_extract_genes(self):
m = MatchEngine(get_db())
match_tree = trial['treatment_list']['step'][0]['match'][0]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
genes = pmt.extract_genes()
assert 'BRAF' in genes, genes
assert 'KRAS' in genes, genes
assert 'EGFR' not in genes
assert 'test' not in genes, genes
assert len(genes) == 2, genes
match_tree = trial['treatment_list']['step'][0]['match'][2]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
genes = pmt.extract_genes()
assert 'BRAF' not in genes, genes
def test_extract_genes(self):
m = MatchEngine(get_db())
match_tree = trial['treatment_list']['step'][0]['match'][0]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
genes = pmt.extract_genes()
assert 'BRAF' in genes, genes
assert 'KRAS' in genes, genes
assert 'EGFR' not in genes
assert 'test' not in genes, genes
assert len(genes) == 2, genes
match_tree = trial['treatment_list']['step'][0]['match'][2]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
genes = pmt.extract_genes()
assert 'BRAF' not in genes, genes
def __init__(self, item):
"""
Creates data for ElasticSearch's autocomplete index
:param item: Trial info:
- treatment_list: Nested dictionary containing all match criteria
- summary: Summary object created by the API
"""
self.summary = item['_summary']
self.treatment_list = item['treatment_list']
self.vdict = {
'variants': [],
'wts': [],
'svs': [],
'cnvs': [],
'exclusions': []
}
self.genes = []
self.cancer_type_dict = None
self.m = MatchEngine(get_db())
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')
def _get_signatures(self, item):
"""
Creates hormone receptor status and mutational signature summary lists
:param item: Trial document
"""
m = MatchEngine(get_db())
for step in item['treatment_list']['step']:
if 'match' in step:
g = m.create_match_tree(step['match'][0])
pmt = ParseMatchTree(g)
signatures = pmt.extract_signatures()
self.mmr.extend(signatures[0])
self.ms.extend(signatures[1])
self.sigs.extend(signatures[2])
self.hr.extend(pmt.extract_hr_status())
if 'arm' in step:
for arm in step['arm']:
if 'match' in arm:
g = m.create_match_tree(arm['match'][0])
pmt = ParseMatchTree(g)
signatures = pmt.extract_signatures()
self.mmr.extend(signatures[0])
self.ms.extend(signatures[1])
self.sigs.extend(signatures[2])
self.hr.extend(pmt.extract_hr_status())
if 'dose_level' in arm:
for dose in arm['dose_level']:
if 'match' in dose:
g = m.create_match_tree(dose['match'][0])
pmt = ParseMatchTree(g)
signatures = pmt.extract_signatures()
self.mmr.extend(signatures[0])
self.ms.extend(signatures[1])
self.sigs.extend(signatures[2])
self.hr.extend(pmt.extract_hr_status())
def match(args):
"""
Matches all trials in database to patients
:param daemon: Boolean flag; when true, runs the matchengine once per 24 hours.
"""
db = get_db(args.mongo_uri)
while True:
me = MatchEngine(db)
me.find_trial_matches()
# exit if it is not set to run as a nightly automated daemon, otherwise sleep for a day
if not args.daemon:
# choose output file format
if args.json_format:
file_format = 'json'
elif args.outpath and len(args.outpath.split('.')) > 1:
file_format = args.outpath.split('.')[-1]
if file_format not in ['json', 'csv']:
file_format = 'csv'
else:
file_format = 'csv'
# choose output path
if args.outpath:
outpath = args.outpath.split('.')[0]
else:
outpath = './results'
# export results
export_results(args.mongo_uri, file_format, outpath)
break
else:
time.sleep(86400) # sleep for 24 hours
def _get_signatures(self, item):
"""
Creates hormone receptor status and mutational signature summary lists
:param item: Trial document
"""
m = MatchEngine(get_db())
for step in item['treatment_list']['step']:
if 'match' in step:
g = m.create_match_tree(step['match'][0])
pmt = ParseMatchTree(g)
signatures = pmt.extract_signatures()
self.mmr.extend(signatures[0])
self.ms.extend(signatures[1])
self.hr.extend(pmt.extract_hr_status())
if 'arm' in step:
for arm in step['arm']:
if 'match' in arm:
g = m.create_match_tree(arm['match'][0])
pmt = ParseMatchTree(g)
signatures = pmt.extract_signatures()
self.mmr.extend(signatures[0])
self.ms.extend(signatures[1])
self.hr.extend(pmt.extract_hr_status())
if 'dose_level' in arm:
for dose in arm['dose_level']:
if 'match' in dose:
g = m.create_match_tree(dose['match'][0])
pmt = ParseMatchTree(g)
signatures = pmt.extract_signatures()
self.mmr.extend(signatures[0])
self.ms.extend(signatures[1])
self.hr.extend(pmt.extract_hr_status())
def test_extract_variants(self):
m = MatchEngine(get_db())
match_tree = trial['treatment_list']['step'][0]['match'][0]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
v = pmt.extract_variants()
assert 'BRAF V600E' in v['variants']
assert 'BRAF V600K' in v['variants']
assert 'KRAS any' in v['variants']
assert 'EGFR wt' in v['wts']
assert len(v['variants']) == 3
assert len(v['wts']) == 1
match_tree = trial['treatment_list']['step'][0]['match'][1]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
v = pmt.extract_variants()
assert 'PTEN CNV' in v['cnvs']
assert 'BRCA1 SV' in v['svs']
assert 'BRAF V600' in v['exclusions']
assert len(v['variants']) == 0
assert len(v['cnvs']) == 1
assert len(v['svs']) == 1
assert len(v['wts']) == 0
assert len(v['exclusions']) == 1
match_tree = trial['treatment_list']['step'][0]['match'][2]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
v = pmt.extract_variants()
assert 'BRAF V600E' not in v['variants']
assert len(v['variants']) == 0
assert len(v['wts']) == 0
assert 'BRAF V600E' in v['exclusions']
match_tree = trial['treatment_list']['step'][0]['match'][4]
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
v = pmt.extract_variants()
assert 'BRAF V600K' in v['variants']
assert 'EGFR any' in v['variants']
assert len(v['variants']) == 2
assert 'PTEN CNV' in v['cnvs']
assert len(v['cnvs']) == 1
assert 'KRAS' in v['exclusions']
assert 'NRAS' in v['exclusions']
assert len(v['exclusions']) == 2
assert 'NTRK1 wt' in v['wts']
assert len(v['wts']) == 1
def __init__(self, item):
"""
Creates data for ElasticSearch's autocomplete index
:param item: Trial info:
- treatment_list: Nested dictionary containing all match criteria
- summary: Summary object created by the API
"""
self.summary = item['_summary']
self.treatment_list = item['treatment_list']
self.vdict = {
'variants': [],
'wts': [],
'svs': [],
'cnvs': [],
'exclusions': []
}
self.genes = []
self.cancer_type_dict = None
self.m = MatchEngine(get_db())
def test_extract_cancer_types(self):
m = MatchEngine(get_db())
match_tree = match_tree_example
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
cancer_type_dict = pmt.extract_cancer_types()
assert sorted(cancer_type_dict['diagnoses']) == sorted([
'Ocular Melanoma'
]), cancer_type_dict['diagnoses']
assert sorted(cancer_type_dict['cancer_types_expanded']) == sorted([
'Ocular Melanoma',
'Uveal Melanoma',
'Conjunctival Melanoma'
]), cancer_type_dict['cancer_types_expanded']
assert sorted(cancer_type_dict['excluded_cancer_types']) == [], cancer_type_dict['excluded_cancer_types']
assert cancer_type_dict['primary_cancer_types'] == ['Eye'], cancer_type_dict['primary_cancer_types']
m = MatchEngine(get_db())
match_tree = match_tree_example2
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
cancer_type_dict = pmt.extract_cancer_types()
assert sorted(cancer_type_dict['diagnoses']) == sorted(['_SOLID_']), cancer_type_dict['diagnoses']
assert 'Acute Lymphoid Leukemia' not in cancer_type_dict['cancer_types_expanded'], cancer_type_dict['cancer_types_expanded']
assert sorted(cancer_type_dict['excluded_cancer_types']) == [], cancer_type_dict['excluded_cancer_types']
assert cancer_type_dict['primary_cancer_types'] == ['All Solid Tumors'], cancer_type_dict['primary_cancer_types']
m = MatchEngine(get_db())
match_tree = match_tree_example3
g = m.create_match_tree(match_tree)
pmt = ParseMatchTree(g)
cancer_type_dict = pmt.extract_cancer_types()
assert sorted(cancer_type_dict['diagnoses']) == sorted(['_LIQUID_']), cancer_type_dict['diagnoses']
assert 'Acute Lymphoid Leukemia' in cancer_type_dict['cancer_types_expanded'], cancer_type_dict[
'cancer_types_expanded']
assert sorted(cancer_type_dict['excluded_cancer_types']) == [], cancer_type_dict['excluded_cancer_types']
assert cancer_type_dict['primary_cancer_types'] == ['All Liquid Tumors'], cancer_type_dict['primary_cancer_types']
class TestMatchEngine(TestSetUp):
# global vars.
me = None
def setUp(self):
super(TestMatchEngine, self).setUp()
# add clinical collection
self.db.clinical.insert_many([{
'ONCOTREE_PRIMARY_DIAGNOSIS_NAME': onc,
'SAMPLE_ID': self.sample_id,
'VITAL_STATUS': 'alive',
'DFCI_MRN': self.mrn,
'REPORT_DATE': self.static_date,
'BIRTH_DATE': self.static_date,
'GENDER': 'Male'
} for onc in ['_LIQUID_', '_SOLID_']])
self.add_clinical()
self.add_genomic()
def tearDown(self):
self.db.clinical.drop()
self.db.genomic.drop()
def test_validate_yaml_format(self):
# Read yaml file
test_inp = read_file(os.path.join(YAML_DIR, '00-000.yml'))
# Parse yaml document, The status should be 1 as validation should fail
status, data = self.me.validate_yaml_format(test_inp)
assert status == 1
# Parse yaml document, The status should be 0 as validation should pass
test_inp = read_file(os.path.join(YAML_DIR, '00-001.yml'))
status, data = self.me.validate_yaml_format(test_inp)
assert status == 0
# Assert the protocol id is correctly annotated
assert data['protocol_no'] == '00-001'
assert data['protocol_id'] == 00001
def test_validate_yaml_data(self):
# Read yaml file
test_inp = read_file(os.path.join(YAML_DIR, '00-001.yml'))
status, data = self.me.validate_yaml_format(test_inp)
# Validate the schema for yaml document
errors = self.me.validate_yaml_data(data)
# Assert that there are no errors
assert len(errors) == 0
test_inp = read_file(os.path.join(YAML_DIR, '00-002.yml'))
status, data = self.me.validate_yaml_format(test_inp)
# Assert Schema check fails
errors = self.me.validate_yaml_data(data)
assert errors['protocol_id'][0] == 'required field'
# assert we don't need a match clause at root.
test_inp = read_file(os.path.join(YAML_DIR, '00-003.yml'))
status, data = self.me.validate_yaml_format(test_inp)
assert status == 0
def test_run_query(self):
# reinstantiate MatchEngine so that the set of all sample ids in the database includes the documents that were
# posted by the unit test setUp
self.me = MatchEngine(self.db)
# define a clinical node
node = {'type': 'clinical', 'value': {'ONCOTREE_PRIMARY_DIAGNOSIS': 'Adrenal Gland', 'AGE_NUMERICAL': '>=18'}}
# run query
result, matches = self.me.run_query(node)
# assert number of samples are 89
assert len(result) == 1, len(result)
assert self.sample_id in result
# define a genomic criteria
node = {'type': 'genomic', 'value': {'HUGO_SYMBOL': '!BRAF'}}
# run query
result, matches = self.me.run_query(node)
# assert number of samples is 1
assert len(result) == 9, len(result)
assert self.sample_id not in result
self.add_genomic_v2()
node = {'type': 'genomic', 'value': {'HUGO_SYMBOL': 'WHSC1'}}
result, matches = self.me.run_query(node)
assert 'actionability' in matches[0]
assert matches[0]['mmr_status'] == 'Proficient (MMR-P / MSS)'
def test_prepare_clinical_criteria(self):
onc = 'ONCOTREE_PRIMARY_DIAGNOSIS'
oncname = 'ONCOTREE_PRIMARY_DIAGNOSIS_NAME'
# create clinical criteria
item = {'AGE_NUMERICAL': '>=18', onc: 'Melanoma'}
# convert to mongo query
c = self.me.prepare_clinical_criteria(item)
# assert length of ONCOTREE_DIAGNOSIS for 'Melanoma' is 9
assert len(c[oncname]['$in']) == 8
# check 'BIRTH DATE mongo query does less than search'
assert c['BIRTH_DATE'].keys()[0] == '$lte'
# check "!"
item = {'AGE_NUMERICAL': '<=18', onc: '!Melanoma'}
c = self.me.prepare_clinical_criteria(item)
assert c['BIRTH_DATE'].keys()[0] == '$gte'
assert len(c[oncname]['$nin']) == 8
# check with a list of diagnoses
item = {'AGE_NUMERICAL': '>=18', onc: ['!Melanoma', '!Glioblastoma', 'Pheochromocytoma', 'Astrocytoma']}
c = self.me.prepare_clinical_criteria(item)
assert c['BIRTH_DATE'].keys()[0] == '$lte'
assert '$nin' in c[oncname]
assert '$in' in c[oncname]
assert len(c[oncname]['$in']) == 2
assert len(c[oncname]['$nin']) == 12
# check _SOLID_ && _LIQUID_
liquid_item = {'AGE_NUMERICAL': '>=18', onc: '_LIQUID_'}
solid_item = {'AGE_NUMERICAL': '>=18', onc: '_SOLID_'}
liqc = self.me.prepare_clinical_criteria(liquid_item)
solc = self.me.prepare_clinical_criteria(solid_item)
assert len(liqc[oncname]['$in']) == 51, len(liqc[oncname]['$in'])
assert len(solc[oncname]['$in']) == 561, len(solc[oncname]['$in'])
def test_prepare_genomic_criteria(self):
# create a genomic criteria
item = {'HUGO_SYMBOL': '!KRAS', 'PROTEIN_CHANGE': 'p.V600E'}
# convert to mongo query
c, neg, _ = self.me.prepare_genomic_criteria(item)
# check ! symbol
assert c['$and'][0]['TRUE_HUGO_SYMBOL']['$eq'] == 'KRAS'
assert neg is True
# check protein change
assert c['$and'][0]['TRUE_PROTEIN_CHANGE']['$eq'] == 'p.V600E'
# check wildtype
assert '$or' in c['$and'][1], c
assert c['$and'][1]['$or'] == [{'WILDTYPE': False}, {'WILDTYPE': {'$exists': False}}]
def test_sv(self):
# create a genomic criteria
item = {'HUGO_SYMBOL': 'KRAS', 'VARIANT_CATEGORY': 'SV'}
# convert to mongo query
c, neg, _ = self.me.prepare_genomic_criteria(item)
# check sv
assert c['$and'][0]['VARIANT_CATEGORY']['$eq'] == 'SV'
# check wildtype
assert '$or' in c['$and'][1], c
assert c['$and'][1]['$or'] == [{'WILDTYPE': False}, {'WILDTYPE': {'$exists': False}}]
def test_create_trial_tree(self):
# parse yaml file and create tree.
test_inp = read_file(os.path.join(YAML_DIR, '00-004.yml'))
status, trial_tree = self.me.create_trial_tree(test_inp)
# assert it was successful.
assert status == 0
# check that we have 2 match trees.
cnt = 0
for n in trial_tree.nodes():
if 'match_tree' in trial_tree.node[n]:
cnt += 1
assert cnt == 2
# parse yaml file and create tree.
test_inp = read_file(os.path.join(YAML_DIR, '00-004.yml'))
status, trial_tree = self.me.create_trial_tree(test_inp)
# check that we have 14 nodes.
assert len(list(trial_tree.nodes())) == 4
# assert we have 3 match trees.
cnt = 0
for n in trial_tree.nodes():
if 'match_tree' in trial_tree.node[n]:
cnt += 1
assert cnt == 2
def test_create_match_tree(self):
# parse yaml file and create trial tree.
test_inp = read_file(os.path.join(YAML_DIR, '00-004.yml'))
status, trial_tree = self.me.create_trial_tree(test_inp)
# get the graph for the only match.
g = None
i = -1
number_of_nodes = [2, 10]
edges = [[(1, 2)], [(1, 2), (2, 3), (2, 4), (4, 5), (4, 6), (4, 7), (4, 8), (4, 9), (4, 10)]]
for n in trial_tree.nodes():
if 'match_tree' in trial_tree.node[n]:
i += 1
g = trial_tree.node[n]['match_tree']
assert g is not None
# Check if tree contain correct number of nodes
assert g.number_of_nodes() == number_of_nodes[i]
# Check edges are correctly created
assert list(nx.dfs_edges(g)) == edges[i]
# First node should be and
if i == 0:
assert g.node[1]['type'] == 'match'
assert g.node[2]['type'] == 'clinical'
print g.node[2]['value']
assert g.node[2]['value'] == {'disease_status': ['Advanced']}
elif i == 1:
assert g.node[1]['type'] == 'match'
assert g.node[2]['type'] == 'and'
assert g.node[3]['type'] == 'genomic'
assert g.node[3]['value'] == {'hugo_symbol': 'IDH1', 'wildcard_protein_change': 'p.R132', 'variant_category': 'Mutation'}
assert g.node[4]['type'] == 'or'
assert g.node[5]['type'] == 'clinical'
assert g.node[5]['value'] == {'age_numerical': '>=18', 'oncotree_primary_diagnosis': '_SOLID_'}
assert g.node[6]['type'] == 'clinical'
assert g.node[6]['value'] == {'age_numerical': '>=18', 'oncotree_primary_diagnosis': 'Diffuse Glioma'}
assert g.node[7]['type'] == 'clinical'
assert g.node[7]['value'] == {'age_numerical': '>=18', 'oncotree_primary_diagnosis': 'Encapsulated Glioma'}
assert g.node[8]['type'] == 'clinical'
assert g.node[8]['value'] == {'age_numerical': '>=18', 'oncotree_primary_diagnosis': 'Cholangiocarcinoma'}
assert g.node[9]['type'] == 'clinical'
assert g.node[9]['value'] == {'age_numerical': '>=18', 'oncotree_primary_diagnosis': 'Acute Myeloid Leukemia'}
assert g.node[10]['type'] == 'clinical'
assert g.node[10]['value'] == {'age_numerical': '>=18', 'oncotree_primary_diagnosis': 'Myelodysplasia'}
def test_search_oncotree_diagnosis(self):
# Glioblastoma
c = {'ONCOTREE_PRIMARY_DIAGNOSIS_NAME': {'$eq': 'Glioblastoma'}}
oncotree = build_oncotree()
c['ONCOTREE_PRIMARY_DIAGNOSIS_NAME'] = self.me._search_oncotree_diagnosis(oncotree, c)
conc = c['ONCOTREE_PRIMARY_DIAGNOSIS_NAME']
assert '$in' in conc, conc
assert conc['$in'] == ['Small Cell Glioblastoma', 'Gliosarcoma', 'Glioblastoma Multiforme', 'Glioblastoma'], conc
# Melanoma
c = {'ONCOTREE_PRIMARY_DIAGNOSIS_NAME': {'$eq': 'Melanoma'}}
conc = self.me._search_oncotree_diagnosis(oncotree, c)
assert '$in' in conc, conc
assert conc['$in'] == [
'Melanoma', 'Congenital Nevus', 'Genitourinary Mucosal Melanoma', 'Cutaneous Melanoma',
'Melanoma of Unknown Primary', 'Desmoplastic Melanoma', 'Lentigo Maligna Melanoma', 'Acral Melanoma'
]
def setUp(self):
"""
Descriptions of test patients
1: >18, Adrenal Gland, Female, BRAF F346R Mutation
2: >18, Melanoma, Female, EGFR L858R Mutation
3: >18, Melanoma, Female, EGFR F346A Mutation
4: >18, Melanoma, Female, EGFR F346B Mutation
5: >18, Melanoma, Female, EGFR F000F Mutation
6: >0.5 && <18, Melanoma, Male, EGFR SV
7: >0.5 && <18, Glioblastoma, Male, EGFR CNV Hetero del
8: >0.5 && <18, Glioblastoma, Male, EGFR CNV Gain
9: >0.5 && <18, Glioblastoma, Male, EGFR CNV H**o del
10: <0.5, Glioblastoma, Male, EGFR CNV High amp
Descriptions of test trials
00-001.yml: dose: EGFR L858R && >=18/_SOLID_
00-002.yml: arm: EGFR L858R && >=18/_SOLID_
00-003.yml: step: EGFR L858R && >=18/_SOLID_
00-004.yml dose: EGFR L858R && >=18/_SOLID_
00-005.yml 2 doses: EGFR L858R && >=18/_SOLID_
00-006.yml exon: !13
"""
self.db = get_db(None)
for res in ["clinical", "dashboard", "filter", "genomic", "hipaa", "match", "normalize", "oplog"
"response", "statistics", "status", "team", "trial", "trial_match", "user"]:
self.db.drop_collection(res)
self.me = MatchEngine(self.db)
self.trials = {}
self.clinical_id = ObjectId()
self.mrn = 'TCGA-BH-A1FR'
self.sample_id = 'TCGA-OR-A5J1'
self.mrns = [self.mrn] + [self.__random_id() for _ in range(9)]
self.sample_ids = [self.sample_id] + [self.__random_id() for _ in range(9)]
self.clinical_ids = [self.clinical_id] + [ObjectId() for _ in range(9)]
self.static_date = dt.datetime.today()
# clinical collection
self.oncotree_diagnoses = ['Adrenal Gland'] + ['Melanoma'] * 5 + ['Glioblastoma'] * 4
self.genders = ['Female'] * 5 + ['Male'] * 5
# ages
adult = self.static_date - dt.timedelta(days=365*19)
child = self.static_date - dt.timedelta(days=365*10)
infant = self.static_date - dt.timedelta(days=30*4)
self.ages = [adult] * 5 + [child] * 4 + [infant]
self.clinical = [{
'_id': clinical_id,
'ONCOTREE_PRIMARY_DIAGNOSIS_NAME': diagnosis,
'SAMPLE_ID': sample_id,
'VITAL_STATUS': 'alive',
'MRN': mrn,
'REPORT_DATE': self.static_date,
'BIRTH_DATE': age,
'GENDER': gender
} for diagnosis, gender, age, clinical_id, sample_id, mrn in zip(
self.oncotree_diagnoses, self.genders, self.ages, self.clinical_ids, self.sample_ids, self.mrns)]
# genomic collection
self.genes = ['BRAF'] + ['EGFR'] * 9
self.protein_changes = ['p.F346R', 'p.L858R', 'p.F346A', 'p.F346B', 'p.F000F', None, None, None, None, None]
self.variant_categories = ['MUTATION'] * 5 + ['SV', 'CNV', 'CNV', 'CNV', 'CNV']
self.wildtypes = [False] * 10
self.cnv_calls = [None, None, None, None, None, None,
'Heterozygous deletion', 'Gain', 'Homozygous deletion', 'High level amplification']
self.genomic = [{
'TRUE_VARIANT_CLASSIFICATION': 'In_Frame_Del',
'TRUE_PROTEIN_CHANGE': protein_change,
'VARIANT_CATEGORY': variant_category,
'CHROMOSOME': 'chr3',
'POSITION': 178952085,
'TRUE_STRAND': '+',
'WILDTYPE': wildtype,
'CLINICAL_ID': _id,
'CNV_CALL': cnv_call,
'TRUE_HUGO_SYMBOL': gene,
'SAMPLE_ID': sample_id,
'TRUE_TRANSCRIPT_EXON': 19
} for protein_change, variant_category, wildtype, cnv_call, gene, _id, sample_id in zip(
self.protein_changes, self.variant_categories, self.wildtypes,
self.cnv_calls, self.genes, self.clinical_ids, self.sample_ids
)]
# test trials
self.test_trials = ['00-001', '00-002', '00-003']
# demo match results
pnos = ['00-001', '00-001', '00-001', '00-002', '00-002', '00-002']
mlevels = ['arm', 'arm', 'arm', 'dose', 'dose', 'dose']
iids = ['1', '2', '3', '4', '5', '6']
galts = ['Alt1', 'Alt2', 'Alt2', 'Alt3', 'Alt3', 'Alt3']
self.matches = [{
'mrn': 'SAMPLE1',
'sample_id': 'SAMPLE1-ID',
'protocol_no': protocol_no,
'match_level': match_level,
'internal_id': internal_id,
'genomic_alteration': genomic_alteration
} for protocol_no, match_level, internal_id, genomic_alteration in zip(
pnos, mlevels, iids, galts
)]
class Autocomplete:
def __init__(self, item):
"""
Creates data for ElasticSearch's autocomplete index
:param item: Trial info:
- treatment_list: Nested dictionary containing all match criteria
- summary: Summary object created by the API
"""
self.summary = item['_summary']
self.treatment_list = item['treatment_list']
self.vdict = {
'variants': [],
'wts': [],
'svs': [],
'cnvs': [],
'exclusions': []
}
self.genes = []
self.cancer_type_dict = None
self.m = MatchEngine(get_db())
@staticmethod
def _get_cancer_type_weight(cancer_type, hierarchy='default'):
"""
Sets the weights for ElasticSearch autocompletion on cancer types. Cancer type terms
are split so that autocomplete suggestions will populate regardless of which word in the
multi-word cancer type string is initially input. Higher weighted terms will populate the
top of the autocomplete dropdown list.
:param cancer_type: Text to display in the autocomplete dropdown list.
:param hierarchy: Weight to give the text.
:return: Dictionary specifying ElasticSearch rules.
"""
weight_dict = {'primary': 10, 'default': 5, 'bucket': 20}
if cancer_type == 'All Solid Tumors' or cancer_type == 'All Liquid Tumors':
hierarchy = 'bucket'
return {
'input':
list(
set([cancer_type] +
[i for i in cancer_type.split() if len(i) > 3])),
'output':
cancer_type,
'weight':
weight_dict[hierarchy]
}
@staticmethod
def _get_variants_weight(variant, esrule='variants'):
"""
Sets the weights for ElasticSearch autocompletion on gene variants. Higher weighted terms will populate the
top of the autocomplete dropdown list.
:param variant: Text to display in the autocomplete dropdown list.
:param esrule: Type of variant. This will determine the ElasticSearch parameters.
:return: Dictionary specifying ElasticSearch rules.
"""
weight_dict = {'variants': 1, 'wts': 5, 'svs': 3, 'cnvs': 3}
return {'input': variant, 'weight': weight_dict[esrule]}
@staticmethod
def _get_investigator_suggest(investigator, dfci_investigator):
"""
Creates a list of investigators from the _summary field of the trial collection
"""
iin = []
iout = ''
ispl = [i.strip() for i in investigator.split(',')]
if len(ispl) == 1:
iin = [ispl[0]]
iout = investigator
elif len(ispl) >= 2:
iin = [ispl[0], ispl[1]]
iout = '%s %s' % (ispl[1], ispl[0])
dfci_in = []
dfci_out = ''
if dfci_investigator is not None and 'first_name' in dfci_investigator:
dfci_in.append(dfci_investigator['first_name'].strip())
dfci_out += dfci_investigator['first_name'].strip()
if dfci_investigator is not None and 'last_name' in dfci_investigator:
dfci_in.append(dfci_investigator['last_name'].strip())
dfci_out += ' %s' % dfci_investigator['last_name'].strip()
inv_suggest = [{'input': [i for i in iin if i != ''], 'output': iout}]
if dfci_out != iout and dfci_out != '':
inv_suggest.append({'input': dfci_in, 'output': dfci_out.strip()})
return inv_suggest
@staticmethod
def _get_tumor_types_search(ct_suggest):
"""
Maps special cancer type text output to the values stored in the ElasticSearch index.
:param ct_suggest: Cancer type text to display.
:return: Cancer type text stored in th ElasticSearch index, which we will query.
"""
tts = []
for ct in ct_suggest:
if 'output' in ct and ct['output'] == 'All Solid Tumors':
tts.append('_SOLID_')
elif 'output' in ct and ct['output'] == 'All Liquid Tumors':
tts.append('_LIQUID_')
else:
tts.append(ct['output'])
return tts
def _extract_data_from_match(self, match):
"""
Extract Cancer Type, Gene, and Variant data from the given match tree
"""
g = self.m.create_match_tree(match)
pmt = ParseMatchTree(g)
self.cancer_type_dict = pmt.extract_cancer_types()
self.genes.extend(pmt.extract_genes())
vdict_tmp = pmt.extract_variants()
for k, v in self.vdict.iteritems():
v.extend(vdict_tmp[k])
def add_autocomplete(self):
"""
Recursively iterates through the treatment list and creates a list of genes contained within.
:return: Nested dictionary containing all genes referenced within this trial
"""
for step in self.treatment_list['step']:
if 'match' in step:
self._extract_data_from_match(step['match'][0])
if 'arm' in step:
for arm in step['arm']:
if 'match' in arm:
self._extract_data_from_match(arm['match'][0])
if 'dose_level' in arm:
for dose in arm['dose_level']:
if 'match' in dose:
self._extract_data_from_match(dose['match'][0])
if self.cancer_type_dict is None:
self.cancer_type_dict = {
'diagnoses': [],
'primary_cancer_types': [],
'cancer_types_expanded': [],
'excluded_cancer_types': []
}
weighted_cancer_types = []
for ct in self.cancer_type_dict['primary_cancer_types']:
suggestion = self._get_cancer_type_weight(ct, hierarchy='primary')
weighted_cancer_types.append(suggestion)
for ct in set(self.cancer_type_dict['cancer_types_expanded']) - set(
self.cancer_type_dict['primary_cancer_types']):
suggestion = self._get_cancer_type_weight(ct, hierarchy='default')
weighted_cancer_types.append(suggestion)
weighted_variants = {}
for key in ['variants', 'cnvs', 'svs', 'wts']:
weighted_variants[key] = []
for v in set(self.vdict[key]):
suggestion = self._get_variants_weight(v, esrule=key)
weighted_variants[key].append(suggestion)
suggestors = {
"cancer_type_suggest":
weighted_cancer_types,
"hugo_symbol_suggest": {
"input": list(set(self.genes))
},
"variant_suggest": [
i for i in weighted_variants['variants']
if not i['input'].endswith('any')
],
"wildtype_suggest":
weighted_variants['wts'],
"cnv_suggest":
weighted_variants['cnvs'],
"sv_suggest":
weighted_variants['svs'],
"protocol_no_suggest": {
'input': self.summary['protocol_number']
},
"disease_center_suggest": {
'input': [
i.replace('(', '').replace(')', '')
for i in self.summary['disease_center'].split()
],
'output':
self.summary['disease_center']
},
'disease_status_suggest': {
'input': self.summary['disease_status']
},
'drug_suggest': {
'input': [i.title() for i in self.summary['drugs']]
},
'investigator_suggest':
self._get_investigator_suggest(self.summary['investigator'],
self.summary['dfci_investigator']),
'mmr_status_suggest': {
'input': self.summary['mmr_status'] + self.summary['ms_status']
},
'nct_number_suggest': {
'input': self.summary['nct_number']
}
}
searchers = {
"tumor_types":
list(set(self._get_tumor_types_search(weighted_cancer_types))),
"genes":
list(set(self.genes)),
"variants":
list(set([i['input'] for i in weighted_variants['variants']])),
"wildtype_genes":
list(set([i['input'] for i in weighted_variants['wts']])),
"cnv_genes":
list(set([i['input'] for i in weighted_variants['cnvs']])),
"sv_genes":
list(set([i['input'] for i in weighted_variants['svs']])),
"exclusion_genes":
list(set(self.vdict['exclusions'])),
"protocol_no":
self.summary["protocol_number"],
"drugs":
self.summary["drugs"],
"age":
self.summary["age_summary"],
"phase":
self.summary["phase_summary"],
"disease_status":
self.summary["disease_status"],
"nct_number":
self.summary["nct_number"],
"disease_center":
self.summary["disease_center"],
"mmr_status":
self.summary["mmr_status"],
"ms_status":
self.summary["ms_status"],
"mutational_signatures":
self.summary["mutational_signatures"],
"investigator":
[i['output'] for i in suggestors['investigator_suggest']],
"short_title":
self.summary["short_title"]
}
return suggestors, searchers, parse_primary_cancer_types(
self.cancer_type_dict['primary_cancer_types'])
class Autocomplete:
def __init__(self, item):
"""
Creates data for ElasticSearch's autocomplete index
:param item: Trial info:
- treatment_list: Nested dictionary containing all match criteria
- summary: Summary object created by the API
"""
self.summary = item['_summary']
self.treatment_list = item['treatment_list']
self.vdict = {
'variants': [],
'wts': [],
'svs': [],
'cnvs': [],
'exclusions': []
}
self.genes = []
self.cancer_type_dict = None
self.m = MatchEngine(get_db())
@staticmethod
def _get_cancer_type_weight(cancer_type, hierarchy='default'):
"""
Sets the weights for ElasticSearch autocompletion on cancer types. Cancer type terms
are split so that autocomplete suggestions will populate regardless of which word in the
multi-word cancer type string is initially input. Higher weighted terms will populate the
top of the autocomplete dropdown list.
:param cancer_type: Text to display in the autocomplete dropdown list.
:param hierarchy: Weight to give the text.
:return: Dictionary specifying ElasticSearch rules.
"""
weight_dict = {'primary': 10, 'default': 5, 'bucket': 20}
if cancer_type == 'All Solid Tumors' or cancer_type == 'All Liquid Tumors':
hierarchy = 'bucket'
return {
'input': list(set([cancer_type] + [i for i in cancer_type.split() if len(i) > 3])),
'output': cancer_type,
'weight': weight_dict[hierarchy]
}
@staticmethod
def _get_variants_weight(variant, esrule='variants'):
"""
Sets the weights for ElasticSearch autocompletion on gene variants. Higher weighted terms will populate the
top of the autocomplete dropdown list.
:param variant: Text to display in the autocomplete dropdown list.
:param esrule: Type of variant. This will determine the ElasticSearch parameters.
:return: Dictionary specifying ElasticSearch rules.
"""
weight_dict = {
'variants': 1,
'wts': 5,
'svs': 3,
'cnvs': 3
}
return {'input': variant, 'weight': weight_dict[esrule]}
@staticmethod
def _get_investigator_suggest(investigator, dfci_investigator):
"""
Creates a list of investigators from the _summary field of the trial collection
"""
iin = []
iout = ''
ispl = [i.strip() for i in investigator.split(',')]
if len(ispl) == 1:
iin = [ispl[0]]
iout = investigator
elif len(ispl) >= 2:
iin = [ispl[0], ispl[1]]
iout = '%s %s' % (ispl[1], ispl[0])
dfci_in = []
dfci_out = ''
if dfci_investigator is not None and 'first_name' in dfci_investigator:
dfci_in.append(dfci_investigator['first_name'].strip())
dfci_out += dfci_investigator['first_name'].strip()
if dfci_investigator is not None and 'last_name' in dfci_investigator:
dfci_in.append(dfci_investigator['last_name'].strip())
dfci_out += ' %s' % dfci_investigator['last_name'].strip()
inv_suggest = [{
'input': [i for i in iin if i != ''],
'output': iout
}]
if dfci_out != iout and dfci_out != '':
inv_suggest.append({
'input': dfci_in,
'output': dfci_out.strip()
})
return inv_suggest
@staticmethod
def _get_tumor_types_search(ct_suggest):
"""
Maps special cancer type text output to the values stored in the ElasticSearch index.
:param ct_suggest: Cancer type text to display.
:return: Cancer type text stored in th ElasticSearch index, which we will query.
"""
tts = []
for ct in ct_suggest:
if 'output' in ct and ct['output'] == 'All Solid Tumors':
tts.append('_SOLID_')
elif 'output' in ct and ct['output'] == 'All Liquid Tumors':
tts.append('_LIQUID_')
else:
tts.append(ct['output'])
return tts
def _extract_data_from_match(self, match):
"""
Extract Cancer Type, Gene, and Variant data from the given match tree
"""
g = self.m.create_match_tree(match)
pmt = ParseMatchTree(g)
self.cancer_type_dict = pmt.extract_cancer_types()
self.genes.extend(pmt.extract_genes())
vdict_tmp = pmt.extract_variants()
for k, v in self.vdict.iteritems():
v.extend(vdict_tmp[k])
def add_autocomplete(self):
"""
Recursively iterates through the treatment list and creates a list of genes contained within.
:return: Nested dictionary containing all genes referenced within this trial
"""
for step in self.treatment_list['step']:
if 'match' in step:
self._extract_data_from_match(step['match'][0])
if 'arm' in step:
for arm in step['arm']:
if 'match' in arm:
self._extract_data_from_match(arm['match'][0])
if 'dose_level' in arm:
for dose in arm['dose_level']:
if 'match' in dose:
self._extract_data_from_match(dose['match'][0])
if self.cancer_type_dict is None:
self.cancer_type_dict = {
'diagnoses': [],
'primary_cancer_types': [],
'cancer_types_expanded': [],
'excluded_cancer_types': []
}
weighted_cancer_types = []
for ct in self.cancer_type_dict['primary_cancer_types']:
suggestion = self._get_cancer_type_weight(ct, hierarchy='primary')
weighted_cancer_types.append(suggestion)
for ct in set(self.cancer_type_dict['cancer_types_expanded']) - set(self.cancer_type_dict['primary_cancer_types']):
suggestion = self._get_cancer_type_weight(ct, hierarchy='default')
weighted_cancer_types.append(suggestion)
weighted_variants = {}
for key in ['variants', 'cnvs', 'svs', 'wts']:
weighted_variants[key] = []
for v in set(self.vdict[key]):
suggestion = self._get_variants_weight(v, esrule=key)
weighted_variants[key].append(suggestion)
suggestors = {
"cancer_type_suggest": weighted_cancer_types,
"hugo_symbol_suggest": {"input": list(set(self.genes))},
"variant_suggest": [i for i in weighted_variants['variants'] if not i['input'].endswith('any')],
"wildtype_suggest": weighted_variants['wts'],
"cnv_suggest": weighted_variants['cnvs'],
"sv_suggest": weighted_variants['svs'],
"protocol_no_suggest": {'input': self.summary['protocol_number']},
"disease_center_suggest": {
'input': [i.replace('(', '').replace(')', '') for i in self.summary['disease_center'].split()],
'output': self.summary['disease_center']
},
'disease_status_suggest': {'input': self.summary['disease_status']},
'drug_suggest': {'input': [i.title() for i in self.summary['drugs']]},
'investigator_suggest': self._get_investigator_suggest(self.summary['investigator'],
self.summary['dfci_investigator']),
'mmr_status_suggest': {'input': self.summary['mmr_status'] + self.summary['ms_status']},
'nct_number_suggest': {'input': self.summary['nct_number']}
}
searchers = {
"tumor_types": list(set(self._get_tumor_types_search(weighted_cancer_types))),
"genes": list(set(self.genes)),
"variants": list(set([i['input'] for i in weighted_variants['variants']])),
"wildtype_genes": list(set([i['input'] for i in weighted_variants['wts']])),
"cnv_genes": list(set([i['input'] for i in weighted_variants['cnvs']])),
"sv_genes": list(set([i['input'] for i in weighted_variants['svs']])),
"exclusion_genes": list(set(self.vdict['exclusions'])),
"protocol_no": self.summary["protocol_number"],
"drugs": self.summary["drugs"],
"age": self.summary["age_summary"],
"phase": self.summary["phase_summary"],
"disease_status": self.summary["disease_status"],
"nct_number": self.summary["nct_number"],
"disease_center": self.summary["disease_center"],
"mmr_status": self.summary["mmr_status"],
"ms_status": self.summary["ms_status"],
"mutational_signatures": self.summary["mutational_signatures"],
"investigator": [i['output'] for i in suggestors['investigator_suggest']],
"short_title": self.summary["short_title"]
}
return suggestors, searchers, parse_primary_cancer_types(self.cancer_type_dict['primary_cancer_types'])