def extract_cancer_types(self):
"""
Returns all cancer types located in the match tree
:param g: DiGraph match tree
:return: List of cancer types
"""
diagnoses = []
cancer_types_expanded = []
primary_cancer_types = []
excluded_cancer_types = []
onco_tree = oncotreenx.build_oncotree(file_path=TUMOR_TREE)
liquid_children_txt, solid_children_txt = expand_liquid_oncotree(onco_tree)
# iterate through the graph
for node_id in list(nx.dfs_postorder_nodes(self.g, source=1)):
node = self.g.node[node_id]
if node['type'] == 'clinical':
if 'oncotree_primary_diagnosis' in node['value']:
diagnosis = node['value']['oncotree_primary_diagnosis']
n = oncotreenx.lookup_text(onco_tree, diagnosis.replace('!', ''))
children = list(nx.dfs_tree(onco_tree, n))
if diagnosis == '_SOLID_':
children_txt = solid_children_txt
primary_parent = 'All Solid Tumors'
parents_txt = ['All Solid Tumors']
elif diagnosis == '_LIQUID_':
children_txt = liquid_children_txt
primary_parent = 'All Liquid Tumors'
parents_txt = ['All Liquid Tumors']
else:
children_txt = [onco_tree.node[nn]['text'] for nn in children]
if n is not None:
parents, parents_txt, primary_parent = get_parents(onco_tree, n)
else:
parents_txt = []
primary_parent = ''
diagnoses.append(diagnosis)
if diagnosis.startswith('!'):
excluded_cancer_types.append(diagnosis.replace('!', ''))
excluded_cancer_types.extend(children_txt)
else:
primary_tumors = get_primary_tumors()
cancer_types_expanded.append(parse_diagnosis(diagnosis))
cancer_types_expanded.extend(children_txt)
cancer_types_expanded.extend([i for i in parents_txt if i.split()[0] not in primary_tumors])
primary_cancer_types.append(primary_parent)
return {
'diagnoses': list(set(i for i in diagnoses if i.strip() != 'root')),
'cancer_types_expanded': list(set(i for i in cancer_types_expanded if i.strip() != 'root')),
'primary_cancer_types': list(set(i for i in primary_cancer_types if i.strip() != 'root')),
'excluded_cancer_types': list(set(i for i in excluded_cancer_types if i.strip() != 'root'))
}
def extract_cancer_types(self):
"""
Returns all cancer types located in the match tree
:param g: DiGraph match tree
:return: List of cancer types
"""
diagnoses = []
cancer_types_expanded = []
primary_cancer_types = []
excluded_cancer_types = []
onco_tree = oncotreenx.build_oncotree(file_path=TUMOR_TREE)
liquid_children_txt, solid_children_txt = expand_liquid_oncotree(onco_tree)
# iterate through the graph
for node_id in list(nx.dfs_postorder_nodes(self.g, source=1)):
node = self.g.nodes[node_id]
if node['type'] == 'clinical':
if 'oncotree_primary_diagnosis' in node['value']:
diagnosis = node['value']['oncotree_primary_diagnosis']
n = oncotreenx.lookup_text(onco_tree, diagnosis.replace('!', ''))
children = list(nx.dfs_tree(onco_tree, n))
if diagnosis == '_SOLID_':
children_txt = solid_children_txt
primary_parent = 'All Solid Tumors'
parents_txt = ['All Solid Tumors']
elif diagnosis == '_LIQUID_':
children_txt = liquid_children_txt
primary_parent = 'All Liquid Tumors'
parents_txt = ['All Liquid Tumors']
else:
children_txt = [onco_tree.nodes[nn]['text'] for nn in children]
if n is not None:
parents, parents_txt, primary_parent = get_parents(onco_tree, n)
else:
parents_txt = []
primary_parent = ''
diagnoses.append(diagnosis)
if diagnosis.startswith('!'):
excluded_cancer_types.append(diagnosis.replace('!', ''))
excluded_cancer_types.extend(children_txt)
else:
primary_tumors = get_primary_tumors()
cancer_types_expanded.append(parse_diagnosis(diagnosis))
cancer_types_expanded.extend(children_txt)
cancer_types_expanded.extend([i for i in parents_txt if i.split()[0] not in primary_tumors])
primary_cancer_types.append(primary_parent)
return {
'diagnoses': list(set(i for i in diagnoses if i.strip() != 'root')),
'cancer_types_expanded': list(set(i for i in cancer_types_expanded if i.strip() != 'root')),
'primary_cancer_types': list(set(i for i in primary_cancer_types if i.strip() != 'root')),
'excluded_cancer_types': list(set(i for i in excluded_cancer_types if i.strip() != 'root'))
}
def reset_elasticsearch_mapping():
logging.info("reset_elasticsearch_mapping")
with open(ES_MAPPING) as es_mapping_file_handle:
json_payload = json.load(es_mapping_file_handle)['trial']
ot = build_oncotree(TUMOR_TREE)
order = ["All Solid Tumors", "All Liquid Tumors"]
top_level_ot = sorted([
node for node, path in nx.shortest_path(ot, 'root').items()
if len(path) == 2
],
key=lambda x: ot.node[x]['text'])
for top_level in top_level_ot:
order.append(ot.node[top_level]['text'])
if '/' in ot.node[top_level]['text']:
order = order + ot.node[top_level]['text'].split('/')
second_level_ot = sorted(
[item for item in nx.descendants(ot, top_level)],
key=lambda x: ot.node[x]['text'])
for second_level in second_level_ot:
order.append(ot.node[second_level]['text'])
third_level_ot = sorted(
[item for item in nx.descendants(ot, second_level)],
key=lambda x: ot.node[x]['text'])
for third_level in third_level_ot:
order.append(third_level)
json_payload["_meta"] = dict(json_payload.setdefault('_meta', dict()),
**{"tumor_type_sort_order": order})
r = requests.put(ES_URI + "/_mapping/trial",
json=json_payload,
auth=HTTPBasicAuth(ES_USER, ES_PASSWORD))
msg = {"status_code": r.status_code, "text": r.text}
logging.info(msg)
return msg
def test_build_oncotree(self):
# build the tree.
g = build_oncotree(file_path='data/tumor_types.txt')
# assert we have some nodes.
assert len(g.nodes()) > 10
def __init__(self, args):
self.args = args
self.mda_df = None
self.vicc_df = None
self.uhn_df = None
self.grcc_df = None
self.oncotree = oncotreenx.build_oncotree()
def test_ncit(self):
# loop over tree type.
for x in ['data/tumor_types.old.txt', 'data/tumor_types.txt']:
# build the tree.
g = build_oncotree(file_path=x)
# spot check several values.
g.node['BLOOD']['metanci'] == 'C12434'
g.node['PT']['metanci'] == 'C7575'
def unique_query():
# parse parameters
status, val = parse_resource_field()
# bad args.
if status == 1:
return val
# good args.
resource, field = val
# special case for oncotree.
if resource == 'clinical' and field == 'ONCOTREE_PRIMARY_DIAGNOSIS_NAME':
# make oncotree.
onco_tree = oncotreenx.build_oncotree(settings.DATA_ONCOTREE_FILE)
# loop over every-node and do text match.
#results = set([onco_tree.node[n]['text'] for n in onco_tree.nodes()])
#results.remove("root")
#results = list(results)
# turn into
results = list()
for n in onco_tree.nodes():
tmp = {
'text': onco_tree.node[n]['text'],
'code': n
}
results.append(tmp)
else:
# search for this field.
db = app.data.driver.db
results = db[resource].distinct(field)
# remove non.
tmp = set(results)
if None in tmp:
tmp.remove(None)
results = list(tmp)
# encode response.
data = json.dumps({'resource': resource, 'field': field, 'values': results})
resp = Response(response=data,
status=200,
mimetype="application/json")
return resp
def __init__(self, args):
self.args = args
self.sample_df = None
self.patient_df = None
self.impact341_df = pd.DataFrame(columns=OUT_COLS)
self.impact410_df = pd.DataFrame(columns=OUT_COLS)
self.panel_dict = {
'MSK-IMPACT341': self.impact341_df,
'MSK-IMPACT410': self.impact410_df
}
self.oncotree = oncotreenx.build_oncotree()
self.i = 0
def build_oncotree():
"""Builds oncotree"""
return oncotreenx.build_oncotree(file_path=TUMOR_TREE)
def prepare_criteria(item):
onco_tree = oncotreenx.build_oncotree(settings.DATA_ONCOTREE_FILE)
c = {}
clin_txt_1 = ""
clin_txt_2_gender = ""
clin_txt_2_age = ""
if 'clinical_filter' in item:
clin_tmp = json.dumps(item['clinical_filter'])
for key, val in REREPLACEMENTS.items():
clin_tmp = clin_tmp.replace(key, val)
c = json.loads(clin_tmp)
if 'GENDER' in item['clinical_filter']:
clin_txt_2_gender = item['clinical_filter']['GENDER']
if 'BIRTH_DATE' in item['clinical_filter']:
op = next(iter(item['clinical_filter']['BIRTH_DATE'].keys()))
val = next(iter(item['clinical_filter']['BIRTH_DATE'].values()))
try:
val = datetime.datetime.strptime(val.replace(" GMT", ""),
'%a, %d %b %Y %H:%M:%S')
except ValueError:
val = dateutil.parser.parse(val)
# compute the age.
today = datetime.date.today()
tmp = today.year - val.year - ((today.month, today.day) <
(val.month, val.day - 1))
val = tmp
if op.count("gte") > 0:
clin_txt_2_age = "< %s" % val
else:
clin_txt_2_age = "> %s" % val
# parse date-times.
for key in ['BIRTH_DATE', 'REPORT_DATE']:
if key not in c:
continue
# extract the expression value.
lkey, lval = next(iter(c[key].keys())), next(iter(c[key].values()))
try:
c[key][lkey] = datetime.datetime.strptime(
lval.replace(" GMT", ""), '%a, %d %b %Y %H:%M:%S')
except ValueError:
c[key][lkey] = dateutil.parser.parse(lval)
# expand oncotree
if 'ONCOTREE_PRIMARY_DIAGNOSIS_NAME' in item['clinical_filter']:
txt = item['clinical_filter']['ONCOTREE_PRIMARY_DIAGNOSIS_NAME']
if txt == "_LIQUID_" or txt == "_SOLID_":
node1 = oncotreenx.lookup_text(onco_tree, "Lymph")
node2 = oncotreenx.lookup_text(onco_tree, "Blood")
nodes1 = list(nx.dfs_tree(onco_tree, node1))
nodes2 = list(nx.dfs_tree(onco_tree, node2))
nodes = list(set(nodes1).union(set(nodes2)))
if txt == "_SOLID_":
all_nodes = set(list(onco_tree.nodes()))
tmp_nodes = all_nodes - set(nodes)
nodes = list(tmp_nodes)
clin_txt_1 = "%s cancers" % txt.replace("_", "").title()
else:
clin_txt_1 = "%s" % txt
node = oncotreenx.lookup_text(onco_tree, txt)
if onco_tree.has_node(node):
nodes = list(nx.dfs_tree(onco_tree, node))
nodes_txt = [onco_tree.node[n]['text'] for n in nodes]
c['ONCOTREE_PRIMARY_DIAGNOSIS_NAME'] = {'$in': nodes_txt}
g = {}
gen_txt = []
if 'genomic_filter' in item:
gen_tmp = json.dumps(item['genomic_filter'])
for key, val in REREPLACEMENTS.items():
gen_tmp = gen_tmp.replace(key, val)
g = json.loads(gen_tmp)
# add TRUE_HUGO_SYMBOL value mutational signature filter queries
if 'TRUE_HUGO_SYMBOL' in g and g['TRUE_HUGO_SYMBOL'] == {'$in': ['']}:
g['TRUE_HUGO_SYMBOL'] = None
sv_test = False
mut_test = False
cnv_test = False
if 'VARIANT_CATEGORY' in item['genomic_filter']:
variant_category = item['genomic_filter']['VARIANT_CATEGORY']
if isinstance(variant_category, dict):
for x in variant_category.values():
if "SV" in set(x):
sv_test = True
if "CNV" in set(x):
cnv_test = True
if "MUTATION" in set(x):
mut_test = True
elif item['genomic_filter']['VARIANT_CATEGORY'] == 'SV':
sv_test = True
elif item['genomic_filter']['VARIANT_CATEGORY'] == 'CNV':
cnv_test = True
elif item['genomic_filter']['VARIANT_CATEGORY'] == 'MUTATION':
mut_test = True
# build text.
exon_txt = ""
protein_txt = ""
if mut_test:
gen_txt.append("Mutation")
if 'TRUE_EXON_CHANGE' in item['genomic_filter']:
exon_txt = item['genomic_filter']['TRUE_EXON_CHANGE']
if 'TRUE_PROTEIN_CHANGE' in item['genomic_filter']:
protein_txt = item['genomic_filter']['TRUE_PROTEIN_CHANGE']
if cnv_test:
if 'CNV_CALL' in g:
if isinstance(g['CNV_CALL'], dict):
gen_txt += next(iter(g['CNV_CALL'].values()))
else:
gen_txt.append(g['CNV_CALL'])
if sv_test:
gen_txt.append("Structural rearrangement")
if 'MMR_STATUS' in item['genomic_filter']:
gen_txt.append(item['genomic_filter']['MMR_STATUS'])
if 'TABACCO_STATUS' in item['genomic_filter']:
gen_txt.append('Tobacco Mutational Signature')
if 'TEMOZOLOMIDE_STATUS' in item['genomic_filter']:
gen_txt.append('Temozolomide Mutational Signature')
if 'POLE_STATUS' in item['genomic_filter']:
gen_txt.append('PolE Mutational Signature')
if 'APOBEC_STATUS' in item['genomic_filter']:
gen_txt.append('APOBEC Mutational Signature')
if 'UVA_STATUS' in item['genomic_filter']:
gen_txt.append('UVA Mutational Signature')
clauses = []
if mut_test:
clause = {
'VARIANT_CATEGORY': 'MUTATION',
'TRUE_HUGO_SYMBOL': g['TRUE_HUGO_SYMBOL']
}
if 'WILDTYPE' in g:
clause['WILDTYPE'] = g['WILDTYPE']
if 'TRUE_PROTEIN_CHANGE' in g:
clause['TRUE_PROTEIN_CHANGE'] = g['TRUE_PROTEIN_CHANGE']
clauses.append(clause)
if cnv_test:
clause = {
'VARIANT_CATEGORY': 'CNV',
'TRUE_HUGO_SYMBOL': g['TRUE_HUGO_SYMBOL'],
}
if 'CNV_CALL' in g:
clause['CNV_CALL'] = g['CNV_CALL']
if 'WILDTYPE' in g:
clause['WILDTYPE'] = g['WILDTYPE']
clauses.append(clause)
if sv_test:
true_hugo = item['genomic_filter']['TRUE_HUGO_SYMBOL']
if isinstance(true_hugo, dict):
genes = next(iter(true_hugo.values()))
else:
genes = [true_hugo]
to_add = list()
for gene in genes:
if gene in synonyms:
to_add += synonyms[gene]
genes = genes + to_add
abc = '|'.join([
rf"(.*\W{gene}\W.*)|(^{gene}\W.*)|(.*\W{gene}$)"
for gene in genes
])
clauses.append({'STRUCTURAL_VARIANT_COMMENT': {"$regex": abc}})
clauses.append({'LEFT_PARTNER_GENE': {'$in': genes}})
clauses.append({'RIGHT_PARTNER_GENE': {'$in': genes}})
if len(clauses) > 0:
g = {"$or": clauses}
for key in item['genomic_filter']:
special_clauses = {
'STRUCTURAL_VARIANT_COMMENT', 'VARIANT_CATEGORY',
'TRUE_HUGO_SYMBOL', 'CNV_CALL', 'WILDTYPE',
'TRUE_PROTEIN_CHANGE'
}
if key in special_clauses:
continue
g[key] = item['genomic_filter'][key]
get_recursively(g, "GMT")
if 'TRUE_HUGO_SYMBOL' in item['genomic_filter']:
if isinstance(item['genomic_filter']['TRUE_HUGO_SYMBOL'], dict):
genes = next(
iter(item['genomic_filter']['TRUE_HUGO_SYMBOL'].values()))
else:
genes = [item['genomic_filter']['TRUE_HUGO_SYMBOL']]
genes = [str(i) for i in genes]
genes = ', '.join(genes)
if len(gen_txt) > 1:
gen_txt = "%s: %s" % (genes, ', '.join(gen_txt))
else:
if exon_txt == "" and protein_txt == "":
gen_txt = "%s %s" % (genes, ', '.join(gen_txt))
elif exon_txt != "":
gen_txt = "%s exon %s" % (genes, exon_txt)
else:
gen_txt = "%s %s" % (genes, protein_txt)
return c, g, (gen_txt, [clin_txt_1, clin_txt_2_age, clin_txt_2_gender])
def prepare_criteria(item):
onco_tree = oncotreenx.build_oncotree(settings.DATA_ONCOTREE_FILE)
c = {}
clin_txt_1 = ""
clin_txt_2_gender = ""
clin_txt_2_age = ""
if 'clinical_filter' in item:
clin_tmp = json.dumps(item['clinical_filter'])
for key, val in REREPLACEMENTS.items():
clin_tmp = clin_tmp.replace(key, val)
c = json.loads(clin_tmp)
if 'GENDER' in item['clinical_filter']:
clin_txt_2_gender = item['clinical_filter']['GENDER']
if 'BIRTH_DATE' in item['clinical_filter']:
op = item['clinical_filter']['BIRTH_DATE'].keys()[0]
val = item['clinical_filter']['BIRTH_DATE'].values()[0]
try:
val = datetime.datetime.strptime(val.replace(" GMT", ""), '%a, %d %b %Y %H:%M:%S')
except ValueError:
val = dateutil.parser.parse(val)
# compute the age.
today = datetime.date.today()
tmp = today.year - val.year - ((today.month, today.day) < (val.month, val.day - 1))
val = tmp
if op.count("gte") > 0:
clin_txt_2_age = "< %s" % val
else:
clin_txt_2_age = "> %s" % val
# parse date-times.
for key in ['BIRTH_DATE', 'REPORT_DATE']:
if key not in c:
continue
# extract the expression value.
lkey, lval = c[key].keys()[0], c[key].values()[0]
try:
c[key][lkey] = datetime.datetime.strptime(lval.replace(" GMT", ""), '%a, %d %b %Y %H:%M:%S')
except ValueError:
c[key][lkey] = dateutil.parser.parse(lval)
# expand oncotree
if 'ONCOTREE_PRIMARY_DIAGNOSIS_NAME' in item['clinical_filter']:
txt = item['clinical_filter']['ONCOTREE_PRIMARY_DIAGNOSIS_NAME']
if txt == "_LIQUID_" or txt == "_SOLID_":
node1 = oncotreenx.lookup_text(onco_tree, "Lymph")
node2 = oncotreenx.lookup_text(onco_tree, "Blood")
nodes1 = list(nx.dfs_tree(onco_tree, node1))
nodes2 = list(nx.dfs_tree(onco_tree, node2))
nodes = list(set(nodes1).union(set(nodes2)))
if txt == "_SOLID_":
all_nodes = set(list(onco_tree.nodes()))
tmp_nodes = all_nodes - set(nodes)
nodes = list(tmp_nodes)
clin_txt_1 = "%s cancers" % txt.replace("_", "").title()
else:
clin_txt_1 = "%s" % txt
node = oncotreenx.lookup_text(onco_tree, txt)
if onco_tree.has_node(node):
nodes = list(nx.dfs_tree(onco_tree, node))
nodes_txt = [onco_tree.node[n]['text'] for n in nodes]
c['ONCOTREE_PRIMARY_DIAGNOSIS_NAME'] = {'$in': nodes_txt}
g = {}
gen_txt = []
if 'genomic_filter' in item:
gen_tmp = json.dumps(item['genomic_filter'])
for key, val in REREPLACEMENTS.items():
gen_tmp = gen_tmp.replace(key, val)
g = json.loads(gen_tmp)
# add TRUE_HUGO_SYMBOL value mutational signature filter queries
if 'TRUE_HUGO_SYMBOL' in g and g['TRUE_HUGO_SYMBOL'] == {'$in': ['']}:
g['TRUE_HUGO_SYMBOL'] = None
sv_test = False
mut_test = False
cnv_test = False
if 'VARIANT_CATEGORY' in item['genomic_filter']:
variant_category = item['genomic_filter']['VARIANT_CATEGORY']
if isinstance(variant_category, dict):
for x in variant_category.values():
if "SV" in set(x):
sv_test = True
if "CNV" in set(x):
cnv_test = True
if "MUTATION" in set(x):
mut_test = True
elif item['genomic_filter']['VARIANT_CATEGORY'] == 'SV':
sv_test = True
elif item['genomic_filter']['VARIANT_CATEGORY'] == 'CNV':
cnv_test = True
elif item['genomic_filter']['VARIANT_CATEGORY'] == 'MUTATION':
mut_test = True
# build text.
exon_txt = ""
protein_txt = ""
if mut_test:
gen_txt.append("Mutation")
if 'TRUE_EXON_CHANGE' in item['genomic_filter']:
exon_txt = item['genomic_filter']['TRUE_EXON_CHANGE']
if 'TRUE_PROTEIN_CHANGE' in item['genomic_filter']:
protein_txt = item['genomic_filter']['TRUE_PROTEIN_CHANGE']
if cnv_test:
if 'CNV_CALL' in g:
if isinstance(g['CNV_CALL'], dict):
gen_txt += g['CNV_CALL'].values()[0]
else:
gen_txt.append(g['CNV_CALL'])
if sv_test:
gen_txt.append("Structural rearrangement")
if 'MMR_STATUS' in item['genomic_filter']:
gen_txt.append(item['genomic_filter']['MMR_STATUS'])
if 'TABACCO_STATUS' in item['genomic_filter']:
gen_txt.append('Tobacco Mutational Signature')
if 'TEMOZOLOMIDE_STATUS' in item['genomic_filter']:
gen_txt.append('Temozolomide Mutational Signature')
if 'POLE_STATUS' in item['genomic_filter']:
gen_txt.append('PolE Mutational Signature')
if 'APOBEC_STATUS' in item['genomic_filter']:
gen_txt.append('APOBEC Mutational Signature')
if 'UVA_STATUS' in item['genomic_filter']:
gen_txt.append('UVA Mutational Signature')
clauses = []
if mut_test:
clause = {
'VARIANT_CATEGORY': 'MUTATION',
'TRUE_HUGO_SYMBOL': g['TRUE_HUGO_SYMBOL']
}
if 'WILDTYPE' in g:
clause['WILDTYPE'] = g['WILDTYPE']
if 'TRUE_PROTEIN_CHANGE' in g:
clause['TRUE_PROTEIN_CHANGE'] = g['TRUE_PROTEIN_CHANGE']
clauses.append(clause)
if cnv_test:
clause = {
'VARIANT_CATEGORY': 'CNV',
'TRUE_HUGO_SYMBOL': g['TRUE_HUGO_SYMBOL'],
}
if 'CNV_CALL' in g:
clause['CNV_CALL'] = g['CNV_CALL']
if 'WILDTYPE' in g:
clause['WILDTYPE'] = g['WILDTYPE']
clauses.append(clause)
if sv_test:
true_hugo = item['genomic_filter']['TRUE_HUGO_SYMBOL']
if isinstance(true_hugo, dict):
genes = true_hugo.values()[0]
else:
genes = [true_hugo]
to_add = list()
for gene in genes:
if gene in synonyms:
to_add += synonyms[gene]
genes = genes + to_add
sv_clauses = []
for gene in genes:
abc = "(.*\W%s\W.*)|(^%s\W.*)|(.*\W%s$)" % (gene, gene, gene)
sv_clauses.append(re.compile(abc, re.IGNORECASE))
clause = {
'STRUCTURAL_VARIANT_COMMENT': {"$in": sv_clauses}
}
clauses.append(clause)
if len(clauses) > 0:
g = {
"$or": clauses
}
for key in item['genomic_filter']:
special_clauses = {
'STRUCTURAL_VARIANT_COMMENT',
'VARIANT_CATEGORY',
'TRUE_HUGO_SYMBOL',
'CNV_CALL',
'WILDTYPE',
'TRUE_PROTEIN_CHANGE'
}
if key in special_clauses:
continue
g[key] = item['genomic_filter'][key]
get_recursively(g, "GMT")
if 'TRUE_HUGO_SYMBOL' in item['genomic_filter']:
if isinstance(item['genomic_filter']['TRUE_HUGO_SYMBOL'], dict):
genes = item['genomic_filter']['TRUE_HUGO_SYMBOL'].values()[0]
else:
genes = [item['genomic_filter']['TRUE_HUGO_SYMBOL']]
genes = [str(i) for i in genes]
genes = ', '.join(genes)
if len(gen_txt) > 1:
gen_txt = "%s: %s" % (genes, ', '.join(gen_txt))
else:
if exon_txt == "" and protein_txt == "":
gen_txt = "%s %s" % (genes, ', '.join(gen_txt))
elif exon_txt != "":
gen_txt = "%s exon %s" % (genes, exon_txt)
else:
gen_txt = "%s %s" % (genes, protein_txt)
return c, g, (gen_txt, [clin_txt_1, clin_txt_2_age, clin_txt_2_gender])
def autocomplete_query():
# parse parameters
status, val = parse_resource_field()
# parse the value.
value = request.args.get("value")
gene = request.args.get("gene")
# bad args.
if status == 1:
return val
# good args.
resource, field = val
# get the type.
if resource == "genomic":
schema = data_model.genomic_schema[field]['type']
else:
schema = data_model.clinical_schema[field]['type']
# special cases.
if resource == 'clinical' and field == 'ONCOTREE_PRIMARY_DIAGNOSIS_NAME':
# make oncotree.
onco_tree = oncotreenx.build_oncotree(settings.DATA_ONCOTREE_FILE)
# loop over every-node and do text match.
hit_set = set()
for n in onco_tree.nodes():
#TODO: Verify this doesn't need a decode
a = onco_tree.node[n]['text'].lower()
b = value.lower()
if a.count(b) > 0:
# get predecessors and ancestors
hit_set.add(n)
hit_set = hit_set.union(set(onco_tree.predecessors(n)))
hit_set = hit_set.union(set(onco_tree.successors(n)))
# remove root.
if 'root' in hit_set:
hit_set.remove('root')
# convert to full text.
results = [onco_tree.node[n]['text'] for n in hit_set]
else:
# only support string and integer.
if schema not in set(['string', 'integer']):
data = json.dumps({'error': 'unsupported field type: %s' % schema})
resp = Response(response=data,
status=400,
mimetype="application/json")
return resp
# handle string.
db = app.data.driver.db
if schema == "string":
# finalize search term.
term = '.*%s.*' % value
# first make query.
if gene is None:
query = db[resource].find({
field: {'$regex': term, '$options': '-i'}
})
else:
query = db[resource].find({"$and": [
{field: {'$regex': term, '$options': '-i'}},
{"$or": [
{'TRUE_HUGO_SYMBOL': gene},
{'CNV_HUGO_SYMBOL': gene},
]}
]})
else:
# finalize the search term.
term = "/^%s.*/.test(this.%s)" % (value, field)
# first make the query
if gene is None:
query = db[resource].find({"$and": [
{'$where': term},
]})
else:
query = db[resource].find({"$and": [
{'$where': term},
{"$or": [
{'TRUE_HUGO_SYMBOL': gene},
{'CNV_HUGO_SYMBOL': gene},
]}
]})
# extract distinct from query
results = query.distinct(field)
# remove non.
tmp = set(results)
if None in tmp:
tmp.remove(None)
results = list(tmp)
# encode response.
data = json.dumps({'resource': resource, 'field': field, 'values': results})
resp = Response(response=data,
status=200,
mimetype="application/json")
return resp
def test_expand_liquid_oncotree(self):
onco_tree = oncotreenx.build_oncotree(file_path=TUMOR_TREE)
l, s, = expand_liquid_oncotree(onco_tree)
assert 'Leukemia' in l
assert 'Leukemia' not in s
def test_expand_liquid_oncotree(self):
onco_tree = oncotreenx.build_oncotree(file_path=TUMOR_TREE)
l, s, = expand_liquid_oncotree(onco_tree)
assert 'Leukemia' in l
assert 'Leukemia' not in s
def setup(self):
self.g = build_oncotree(file_path="data/tumor_types.txt")
