def test_build_disease_inappropriate_value(key, test_disease):
alias_genes = {}
alias_genes["B3GALT6"] = {"true": 17978, "ids": [17978]}
test_disease[key] = "not_an_int"
# THEN calling build_disease_term(test_disease, alias_genes) a
# ValueError is thrown, caught and converted into a KeyError
with pytest.raises(KeyError):
build_disease_term(test_disease, alias_genes)
def test_build_disease_missing_key(key, test_disease):
## GIVEN a dictionary with disease information and genes
alias_genes = {}
alias_genes["B3GALT6"] = {"true": 17978, "ids": [17978]}
# WHEN deleteing key
test_disease.pop(key)
# THEN calling build_disease_term() will raise KeyError
with pytest.raises(KeyError):
build_disease_term(test_disease, alias_genes)
def test_build_disease_term(adapter):
## GIVEN some disease info and a adapter with a gene
disease_info = {
'mim_number': 615349,
'description': "EHLERS-DANLOS SYNDROME, PROGEROID TYPE, 2",
'hgnc_symbols': set(['B3GALT6']),
'inheritance': set(['AR']),
}
alias_genes = {}
alias_genes['B3GALT6'] = {
'true': 17978,
'ids': [17978],
}
## WHEN building the disease term
disease_obj = build_disease_term(disease_info, alias_genes)
## THEN assert the term is on the correct format
assert disease_obj['_id'] == disease_obj['disease_id'] == "OMIM:615349"
assert disease_obj['inheritance'] == ['AR']
assert disease_obj['genes'] == [17978]
assert disease_obj['source'] == 'OMIM'
assert isinstance(disease_obj, DiseaseTerm)
def test_build_disease_term(adapter):
## GIVEN some disease info and a adapter with a gene
disease_info = {
'mim_number': 615349,
'description': "EHLERS-DANLOS SYNDROME, PROGEROID TYPE, 2",
'hgnc_symbols': set(['B3GALT6']),
'inheritance': set(['AR']),
}
alias_genes = {}
alias_genes['B3GALT6'] = {
'true': 17978,
'ids': [17978],
}
## WHEN building the disease term
disease_obj = build_disease_term(disease_info, alias_genes)
## THEN assert the term is on the correct format
assert disease_obj['_id'] == disease_obj['disease_id'] == "OMIM:615349"
assert disease_obj['inheritance'] == ['AR']
assert disease_obj['genes'] == [17978]
assert disease_obj['source'] == 'OMIM'
assert isinstance(disease_obj, DiseaseTerm)
def load_disease_terms(adapter, genemap_lines, genes, hpo_disease_lines):
"""Load the omim phenotypes into the database
Parse the phenotypes from genemap2.txt and find the associated hpo terms
from ALL_SOURCES_ALL_FREQUENCIES_diseases_to_genes_to_phenotypes.txt.
Args:
adapter(MongoAdapter)
genemap_lines(iterable(str))
genes(dict): Dictionary with all genes found in database
hpo_disease_lines(iterable(str))
"""
disease_terms = get_mim_phenotypes(genemap_lines=genemap_lines)
hpo_diseases = parse_hpo_diseases(hpo_disease_lines)
start_time = datetime.now()
logger.info("Loading the hpo disease...")
for nr_diseases, disease_number in enumerate(disease_terms):
disease_info = disease_terms[disease_number]
disease_id = "OMIM:{0}".format(disease_number)
if disease_id in hpo_diseases:
hpo_terms = hpo_diseases[disease_id]['hpo_terms']
if hpo_terms:
disease_info['hpo_terms'] = hpo_terms
disease_obj = build_disease_term(disease_info, genes)
adapter.load_disease_term(disease_obj)
logger.info("Loading done. Nr of diseases loaded {0}".format(nr_diseases))
logger.info("Time to load diseases: {0}".format(datetime.now() -
start_time))
def test_build_disease_term(adapter, test_disease):
## GIVEN some disease info and a adapter with a gene
alias_genes = {}
alias_genes["B3GALT6"] = {"true": 17978, "ids": [17978]}
## WHEN building the disease term
disease_obj = build_disease_term(test_disease, alias_genes)
## THEN assert the term is on the correct format
assert disease_obj["_id"] == disease_obj["disease_id"] == "OMIM:615349"
assert disease_obj["inheritance"] == ["AR"]
assert disease_obj["genes"] == [17978]
assert disease_obj["source"] == "OMIM"
assert isinstance(disease_obj, DiseaseTerm)
def load_disease_terms(adapter,
genemap_lines,
genes=None,
hpo_disease_lines=None):
"""Load the omim phenotypes into the database
Parse the phenotypes from genemap2.txt and find the associated hpo terms
from https://ci.monarchinitiative.org/view/hpo/job/hpo.annotations/lastSuccessfulBuild/artifact/rare-diseases/util/annotation/phenotype_to_genes.txt
Args:
adapter(MongoAdapter)
genemap_lines(iterable(str))
genes(dict): Dictionary with all genes found in database
hpo_disease_lines(iterable(str))
"""
# Get a map with hgnc symbols to hgnc ids from scout
if not genes:
genes = adapter.genes_by_alias()
# Fetch the disease terms from omim
disease_terms = get_mim_phenotypes(genemap_lines=genemap_lines)
if not hpo_disease_lines:
hpo_disease_lines = fetch_hpo_to_genes_to_disease()
hpo_diseases = parse_hpo_diseases(hpo_disease_lines)
start_time = datetime.now()
nr_diseases = None
LOG.info("Loading the hpo disease...")
for nr_diseases, disease_number in enumerate(disease_terms):
disease_info = disease_terms[disease_number]
disease_id = "OMIM:{0}".format(disease_number)
if disease_id in hpo_diseases:
hpo_terms = hpo_diseases[disease_id]["hpo_terms"]
if hpo_terms:
disease_info["hpo_terms"] = hpo_terms
disease_obj = build_disease_term(disease_info, genes)
adapter.load_disease_term(disease_obj)
LOG.info("Loading done. Nr of diseases loaded {0}".format(nr_diseases))
LOG.info("Time to load diseases: {0}".format(datetime.now() - start_time))
def load_disease_terms(adapter, genemap_lines, genes=None, hpo_disease_lines=None):
"""Load the omim phenotypes into the database
Parse the phenotypes from genemap2.txt and find the associated hpo terms
from ALL_SOURCES_ALL_FREQUENCIES_diseases_to_genes_to_phenotypes.txt.
Args:
adapter(MongoAdapter)
genemap_lines(iterable(str))
genes(dict): Dictionary with all genes found in database
hpo_disease_lines(iterable(str))
"""
# Get a map with hgnc symbols to hgnc ids from scout
if not genes:
genes = adapter.genes_by_alias()
# Fetch the disease terms from omim
disease_terms = get_mim_phenotypes(genemap_lines=genemap_lines)
if not hpo_disease_lines:
hpo_disease_lines = fetch_hpo_phenotype_to_terms()
hpo_diseases = parse_hpo_diseases(hpo_disease_lines)
start_time = datetime.now()
nr_diseases = None
LOG.info("Loading the hpo disease...")
for nr_diseases, disease_number in enumerate(disease_terms):
disease_info = disease_terms[disease_number]
disease_id = "OMIM:{0}".format(disease_number)
if disease_id in hpo_diseases:
hpo_terms = hpo_diseases[disease_id]['hpo_terms']
if hpo_terms:
disease_info['hpo_terms'] = hpo_terms
disease_obj = build_disease_term(disease_info, genes)
adapter.load_disease_term(disease_obj)
LOG.info("Loading done. Nr of diseases loaded {0}".format(nr_diseases))
LOG.info("Time to load diseases: {0}".format(datetime.now() - start_time))
def test_build_disease_term(adapter):
## GIVEN some disease info and a adapter with a gene
disease_info = {
"mim_number": 615349,
"description": "EHLERS-DANLOS SYNDROME, PROGEROID TYPE, 2",
"hgnc_symbols": set(["B3GALT6"]),
"inheritance": set(["AR"]),
}
alias_genes = {}
alias_genes["B3GALT6"] = {"true": 17978, "ids": [17978]}
## WHEN building the disease term
disease_obj = build_disease_term(disease_info, alias_genes)
## THEN assert the term is on the correct format
assert disease_obj["_id"] == disease_obj["disease_id"] == "OMIM:615349"
assert disease_obj["inheritance"] == ["AR"]
assert disease_obj["genes"] == [17978]
assert disease_obj["source"] == "OMIM"
assert isinstance(disease_obj, DiseaseTerm)