def test_get_mim_phenotypes_file(genemap_handle):
phenotypes = get_mim_phenotypes(genemap_lines=genemap_handle)
for i, mim_nr in enumerate(phenotypes):
assert phenotypes[mim_nr]['mim_number']
assert i > 0
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_get_mim_phenotypes_file(genemap_handle):
phenotypes = get_mim_phenotypes(genemap_lines=genemap_handle)
for i, mim_nr in enumerate(phenotypes):
assert phenotypes[mim_nr]['mim_number']
assert i > 0
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_get_mim_phenotypes():
## GIVEN a small testdata set
# This will return a dictionary with mim number as keys and
# phenotypes as values
## WHEN parsing the phenotypes
phenotypes = get_mim_phenotypes(genemap_lines=GENEMAP_LINES)
## THEN assert they where parsed in a correct way
# There was only one line in GENEMAP_LINES that have two phenotypes
# so we expect that there should be two phenotypes
assert len(phenotypes) == 2
term = phenotypes[615349]
assert term['inheritance'] == set(['AR'])
assert term['hgnc_symbols'] == set(['B3GALT6'])
def test_get_mim_phenotypes():
## GIVEN a small testdata set
# This will return a dictionary with mim number as keys and
# phenotypes as values
## WHEN parsing the phenotypes
phenotypes = get_mim_phenotypes(genemap_lines=GENEMAP_LINES)
## THEN assert they where parsed in a correct way
# There was only one line in GENEMAP_LINES that have two phenotypes
# so we expect that there should be two phenotypes
assert len(phenotypes) == 2
term = phenotypes[615349]
assert term['inheritance'] == set(['AR'])
assert term['hgnc_symbols'] == set(['B3GALT6'])
