def test_get_disease_tags_from_results(self):
config = IniParser().read_ini(MY_INI_FILE)
feature_id = self.get_random_feature_id()
criteria_details = GeneCriteria.get_criteria_details(feature_id, config=config)
dis_codes = GeneCriteria.get_disease_codes_from_results(criteria_details)
self.assertTrue(len(dis_codes) > 0, 'Got disease codes')
def test_get_criteria_details(self):
config = IniParser().read_ini(MY_INI_FILE)
idx = ElasticSettings.idx('GENE_CRITERIA')
available_criterias = GeneCriteria.get_available_criterias(config=config)['gene']
idx_type = ','.join(available_criterias)
doc_by_idx_type = ElasticUtils.get_rdm_docs(idx, idx_type, size=1)
self.assertTrue(len(doc_by_idx_type) > 0)
feature_id = getattr(doc_by_idx_type[0], 'qid')
criteria_details = GeneCriteria.get_criteria_details(feature_id, config=config)
hits = criteria_details['hits']
first_hit = hits[0]
_type = first_hit['_type']
_index = first_hit['_index']
_id = first_hit['_id']
_source = first_hit['_source']
disease_tag = _source['disease_tags'][0]
self.assertTrue(feature_id, _id)
self.assertIn(_type, idx_type)
self.assertTrue(idx, _index)
self.assertIn(disease_tag, list(_source.keys()))
fdetails = _source[disease_tag][0]
self.assertIn('fid', fdetails.keys())
self.assertIn('fname', fdetails.keys())
def test_gene_in_region(self):
''' Test process_gene_in_region. '''
config = IniParser().read_ini(MY_INI_FILE)
# pass a region document
criteria_results = GeneCriteria.gene_in_region(self.region_doc_full, config=config, result_container={})
expected_dict = {'ENSG00000279625': {'IBD': [{'fid': '1p36.12_008', 'fname': '1p36.12'}],
'UC': [{'fid': '1p36.12_008', 'fname': '1p36.12'}]}}
self.assertEqual(criteria_results, expected_dict, 'Got regions in gene as expected')
criteria_results_17q = GeneCriteria.gene_in_region(self.region_doc_17q, config=config,
result_container={})
self.assertTrue(len(criteria_results_17q) > 20, "Got back results greater than the default size")
def test_get_disease_tags_as_codes(self):
feature_id = 'ENSG00000134242'
disease_docs = GeneCriteria.get_disease_tags(feature_id)
disease_codes = GeneCriteria.get_disease_tags_as_codes(feature_id)
self.assertEqual(len(disease_docs), len(disease_codes), 'Got the same disease code size')
print(len(disease_docs))
print(len(disease_codes))
doc1 = disease_docs[0]
dis1 = disease_codes[0]
self.assertTrue(isinstance(doc1, disease.document.DiseaseDocument), 'Got the disease doc')
self.assertTrue(isinstance(dis1, str), 'Got the disease code')
def test_available_criterias(self):
config = IniParser().read_ini(MY_INI_FILE)
available_criterias = GeneCriteria.get_available_criterias(config=config)
expected_dict = {'gene': ['cand_gene_in_study', 'gene_in_region', 'is_gene_in_mhc', 'cand_gene_in_region']}
self.assertIsNotNone(available_criterias, 'Criterias as not none')
self.assertIn('cand_gene_in_study', available_criterias['gene'])
self.assertEqual(available_criterias.keys(), expected_dict.keys(), 'Dic keys equal')
def test_get_disease_tags(self):
# feature_id = self.get_random_feature_id()
feature_id = 'ENSG00000134242'
disease_docs = GeneCriteria.get_disease_tags(feature_id)
disease_tags = [getattr(disease_doc, 'code') for disease_doc in disease_docs]
self.assertTrue(len(disease_tags) > 0, 'disease_tags present')
def get_random_feature_id(self):
config = IniParser().read_ini(MY_INI_FILE)
idx = ElasticSettings.idx('GENE_CRITERIA')
available_criterias = GeneCriteria.get_available_criterias(config=config)['gene']
idx_type = ','.join(available_criterias)
doc_by_idx_type = ElasticUtils.get_rdm_docs(idx, idx_type, size=1)
self.assertTrue(len(doc_by_idx_type) > 0)
feature_id = getattr(doc_by_idx_type[0], 'qid')
return feature_id
def test_tag_feature_to_disease(self):
''' Test tag_feature_to_disease. '''
config = IniParser().read_ini(MY_INI_FILE)
result1 = GeneCriteria.tag_feature_to_disease(self.region_doc_full, "gene_in_region", config, {})
# one region tagged to UC and IBD
expected_result = {'ENSG00000279625': {'IBD': [{'fname': '1p36.12', 'fid': '1p36.12_008'}],
'UC': [{'fname': '1p36.12', 'fid': '1p36.12_008'}]}}
self.assertEqual(result1, expected_result, 'Got back expected result')
result2 = GeneCriteria.tag_feature_to_disease(self.study_doc_full, "cand_gene_in_study", config, {})
expected_result = {'ENSG00000160801': {'RA': [{'fname': 'Clatfield XY', 'fid': 'GDXHsS00005'}],
'T1D': [{'fname': 'Clatfield XY', 'fid': 'GDXHsS00005'}]},
'ENSG00000163599': {'RA': [{'fname': 'Clatfield XY', 'fid': 'GDXHsS00005'}],
'T1D': [{'fname': 'Clatfield XY', 'fid': 'GDXHsS00005'}]},
'ENSG00000110800': {'RA': [{'fname': 'Clatfield XY', 'fid': 'GDXHsS00005'}],
'T1D': [{'fname': 'Clatfield XY', 'fid': 'GDXHsS00005'}]}}
self.assertEqual(result2, expected_result, 'Got back expected result')
def test_get_all_criteria_disease_tags(self):
feature_id1 = 'ENSG00000134242'
feature_id2 = 'ENSG00000227609'
criteria_disease_tags = GeneCriteria.get_all_criteria_disease_tags([feature_id1,
feature_id2])
self.assertIn(feature_id1, criteria_disease_tags)
self.assertIn(feature_id2, criteria_disease_tags)
self.assertIn('all', criteria_disease_tags[feature_id1])
self.assertIn('all', criteria_disease_tags[feature_id2])
def test_exonic_index_snp_in_gene(self):
''' Test exonic_index_snp_in_gene. '''
config = IniParser().read_ini(MY_INI_FILE)
# pass a region document
criteria_results = GeneCriteria.exonic_index_snp_in_gene(self.region_hit,
config=config, result_container={})
expected_result = {'ENSG00000226167': {'RA': [{'fid': 'rs2476601',
'fnotes': {'linkname': 'Eyre S', 'linkid': 'GDXHsS00019'},
'fname': 'rs2476601'}]},
'ENSG00000134242': {'RA': [{'fid': 'rs2476601',
'fnotes': {'linkname': 'Eyre S', 'linkid': 'GDXHsS00019'},
'fname': 'rs2476601'}]}}
self.assertEqual(criteria_results, expected_result, 'Got back expected result')
def criteria_disease_tags(cls, request, qids):
''' Get criteria disease tags for a given ensembl ID for all criterias. '''
criteria_disease_tags = GeneCriteria.get_all_criteria_disease_tags(qids)
return criteria_disease_tags
def criteria_details(request):
''' Get criteria details for a given ensembl ID. '''
ens_id = request.POST.get('feature_id')
criteria_details = GeneCriteria.get_criteria_details(ens_id)
return JsonResponse(criteria_details)
def test_cand_gene_in_study(self):
config = IniParser().read_ini(MY_INI_FILE)
input_doc = {'_source': {'diseases': ['T1D', 'MS'],
'genes': ['ENSG00000110848', 'ENSG00000160791', 'ENSG00000163599'],
'study_id': 'GDXHsS00004', 'authors': ['Barrett', 'Type 1 Diabetes Genetics Consortium'],
'authors': [
{
'name': "Barrett",
'initials': "JC"
},
{
'name': "Type 1 Diabetes Genetics Consortium",
'initials': ""
}
]},
'_type': 'studies',
'_index': 'studies_latest', '_id': 'GDXHsS00004', '_score': 0.0}
expected_doc = {'ENSG00000110848': {'T1D': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}],
'MS': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}]},
'ENSG00000160791': {'T1D': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}],
'MS': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}]},
'ENSG00000163599': {'T1D': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}],
'MS': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}]}}
result_doc = GeneCriteria.cand_gene_in_study(input_doc, config=config, result_container={})
self.assertEqual(expected_doc, result_doc, 'dicts are equal and as expected')
input_doc = {'_source': {'diseases': ['RA', 'T1D'],
'genes': ['ENSG00000110800', 'ENSG00000160801', 'ENSG00000163599'],
'study_id': 'GDXHsS00005',
'authors': [
{
'name': "Clatfield",
'initials': "XY"
},
{
'name': "Type 1 Diabetes Genetics Consortium",
'initials': ""
}
]},
'_type': 'studies',
'_index': 'studies_latest', '_id': 'GDXHsS00005', '_score': 0.0}
expected_doc = {'ENSG00000160801': {'RA': [{'fid': 'GDXHsS00005', 'fname': 'Clatfield XY'}],
'T1D': [{'fid': 'GDXHsS00005', 'fname': 'Clatfield XY'}]},
'ENSG00000163599': {'RA': [{'fid': 'GDXHsS00005', 'fname': 'Clatfield XY'}],
'MS': [{'fid': 'GDXHsS00004', 'fname': 'Barrett JC'}],
'T1D': [{'fid': 'GDXHsS00004', 'fname': 'Barrett JC'},
{'fid': 'GDXHsS00005', 'fname': 'Clatfield XY'}]},
'ENSG00000160791': {'T1D': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}],
'MS': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}]},
'ENSG00000110800': {'RA': [{'fid': 'GDXHsS00005', 'fname': 'Clatfield XY'}],
'T1D': [{'fid': 'GDXHsS00005', 'fname': 'Clatfield XY'}]},
'ENSG00000110848': {'T1D': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}],
'MS': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}]}}
updated_doc = GeneCriteria.cand_gene_in_study(input_doc, config=config, result_container=result_doc)
self.assertEqual(expected_doc, updated_doc, 'dicts are equal and as expected')
input_doc = {'_source': {'diseases': ['AA'],
'genes': ['ENSG00000110900'],
'study_id': 'GDXHsS00006', 'authors': [{'name': 'AaTestAuthor', 'initials': 'TT'}]},
'_type': 'studies',
'_index': 'studies_latest', '_id': 'GDXHsS00006', '_score': 0.0}
expected_doc = {'ENSG00000160801': {'RA': [{'fid': 'GDXHsS00005', 'fname': 'Clatfield XY'}],
'T1D': [{'fid': 'GDXHsS00005', 'fname': 'Clatfield XY'}]},
'ENSG00000163599': {'RA': [{'fid': 'GDXHsS00005', 'fname': 'Clatfield XY'}],
'MS': [{'fid': 'GDXHsS00004', 'fname': 'Barrett JC'}],
'T1D': [{'fid': 'GDXHsS00004', 'fname': 'Barrett JC'},
{'fid': 'GDXHsS00005', 'fname': 'Clatfield XY'}]},
'ENSG00000160791': {'T1D': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}],
'MS': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}]},
'ENSG00000110800': {'RA': [{'fid': 'GDXHsS00005', 'fname': 'Clatfield XY'}],
'T1D': [{'fid': 'GDXHsS00005', 'fname': 'Clatfield XY'}]},
'ENSG00000110900': {'AA': [{'fid': 'GDXHsS00006', 'fname': 'AaTestAuthor TT'}]},
'ENSG00000110848': {'T1D': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}],
'MS': [{'fname': 'Barrett JC', 'fid': 'GDXHsS00004'}]}}
updated_doc = GeneCriteria.cand_gene_in_study(input_doc, config=config, result_container=result_doc)
self.assertEqual(expected_doc, updated_doc, 'dicts are equal and as expected')