def test_encode_phenotypes_file(self):
input_file = os.path.join(self.parent_dir, "data/test.score-short.txt")
records = parse_input(input_file, self.hpo_network, self.alt2prim)
encoded_phenotypes = encode_phenotypes(
[record["terms"] for record in records], self.phenotype_groups,
self.hpo_network, self.alt2prim)
self.assertEqual(sum(encoded_phenotypes[0]), 4)
def test_score_pairs_age(self):
# Test reading in records files and calculating pairwise scores
# read in records
self.hpo_network = annotate(
self.hpo_network,
self.phenotype_to_diseases,
self.num_diseases_annotated,
self.alt2prim,
ages_distribution_file=self.ages_distribution_file)
records = parse_input(
os.path.join(self.parent_dir, 'data/test.score-short.txt'),
self.hpo_network, self.alt2prim)
# create instance the scorer class
scorer = Scorer(self.hpo_network,
summarization_method='BMWA',
min_score_mask=None)
# select which patients to test in pairwise best_match_weighted_average
input_records = [
x for x in records if x['record_id'] in ['118200', '118210']
]
results = scorer.score_records(
input_records,
input_records,
[
(0, 1),
],
)
self.assertEqual(len(results), 1)
# the right answer =
answer = np.average([0.166, 1.0, 1.0, 0.125, 0.25, 1.0, 1.0],
weights=[0.481, 1.0, 1.0, 0.0446, 1.0, 1.0, 1.0])
self.assertAlmostEqual(float(results[0][2]), answer, 2)
# Test identical records for which one age exist and one doesn't
input_records = [
x for x in records if x['record_id'] in ['118210', '118211']
]
results = scorer.score_records(
input_records,
input_records,
[
(0, 1),
],
)
self.assertEqual(len(results), 1)
self.assertAlmostEqual(float(results[0][2]), 1.0, 1)
def likelihood_moldx(input_file, output_file=None, k_phenotype_groups=1000):
"""
:param input_file: The file path to a file containing three columns. [ID\tkey=value\thpodid,hpoid,hpoid]
:param output_file: The file path to an output file containing the predicted probabilities
:param k_phenotype_groups: The number of phenotype groups to use for encoding phenotypes. The CLI version of phenopy allows for one of [1000, 1500]
"""
try:
obo_file = config.get('hpo', 'obo_file')
except (NoSectionError, NoOptionError):
logger.critical(
'No HPO OBO file found in the configuration file. See "hpo:obo_file" parameter.'
)
sys.exit(1)
try:
disease_to_phenotype_file = config.get('hpo',
'disease_to_phenotype_file')
except (NoSectionError, NoOptionError):
logger.critical(
'No HPO annotated dataset file found in the configuration file.'
' See "hpo:disease_to_phenotype_file" parameter.')
sys.exit(1)
logger.info(f'Loading HPO OBO file: {obo_file}')
hpo_network, alt2prim, _ = \
generate_annotated_hpo_network(obo_file,
disease_to_phenotype_file,
)
# parse input records
input_records = parse_input(input_file, hpo_network, alt2prim)
record_ids = [record["record_id"] for record in input_records]
phenotypes = [record["terms"] for record in input_records]
# predict likelihood of molecular diagnosis
positive_probabilities = predict_likelihood_moldx(
phenotypes,
phenotype_groups=None,
hpo_network=hpo_network,
alt2prim=alt2prim,
k_phenotype_groups=k_phenotype_groups,
)
if output_file is None:
output_file = "phenopy.likelihood_moldx.txt"
try:
with open(output_file, "w") as f:
for sample_id, probability in zip(record_ids,
positive_probabilities):
f.write(f"{sample_id}\t{probability}\n")
except IOError:
sys.exit("Something went wrong writing the probabilities to file")
def test_score_self(self):
# read in records
records = parse_input(
os.path.join(self.parent_dir, 'data/test.score-long.txt'),
self.hpo_network, self.alt2prim)
# limit to records with HPO terms since many test cases don't have the sub-graph terms from tests/data/hp.obo
input_records = [
x for x in records if x['record_id'] in ['213200', '302801']
]
results = self.scorer.score_records(
input_records, input_records,
half_product(len(input_records), len(input_records)))
self.assertEqual(len(results), 3)
# test the score of '213200' - '302801'
self.assertAlmostEqual(float(results[1][2]), 0.3758, 2)
def score(input_file,
output_file='-',
records_file=None,
annotations_file=None,
custom_disease_file=None,
ages_distribution_file=None,
self=False,
summarization_method='BMWA',
scoring_method='HRSS',
threads=1):
"""
Scores similarity of provided HPO annotated entries (see format below) against a set of HPO annotated dataset. By
default scoring happens against diseases annotated by the HPO group. See https://hpo.jax.org/app/download/annotation.
Phenopy also supports scoring the product of provided entries (see "--product") or scoring against a custom records
dataset (see "--records-file).
:param input_file: File with HPO annotated entries, one per line (see format below).
:param output_file: File path where to store the results. [default: - (stdout)]
:param records_file: An entity-to-phenotype annotation file in the same format as "input_file". This file, if
provided, is used to score entries in the "input_file" against entries here. [default: None]
:param annotations_file: An entity-to-phenotype annotation file in the same format as "input_file". This file, if
provided, is used to add information content to the network. [default: None]
:param custom_disease_file: entity Annotation for ranking diseases/genes
:param ages_distribution_file: Phenotypes age summary stats file containing phenotype HPO id, mean_age, and std.
[default: None]
:param self: Score entries in the "input_file" against itself.
:param summarization_method: The method used to summarize the HRSS matrix. Supported Values are best match average
(BMA), best match weighted average (BMWA), and maximum (maximum). [default: BMWA]
:param scoring_method: Either HRSS or Resnik
:param threads: Number of parallel processes to use. [default: 1]
"""
try:
obo_file = config.get('hpo', 'obo_file')
except (NoSectionError, NoOptionError):
logger.critical(
'No HPO OBO file found in the configuration file. See "hpo:obo_file" parameter.'
)
sys.exit(1)
if custom_disease_file is None:
try:
disease_to_phenotype_file = config.get(
'hpo', 'disease_to_phenotype_file')
except (NoSectionError, NoOptionError):
logger.critical(
'No HPO annotated dataset file found in the configuration file.'
' See "hpo:disease_to_phenotype_file" parameter.')
sys.exit(1)
else:
logger.info(
f"using custom disease annotation file: {custom_disease_file}")
disease_to_phenotype_file = custom_disease_file
logger.info(f'Loading HPO OBO file: {obo_file}')
hpo_network, alt2prim, disease_records = \
generate_annotated_hpo_network(obo_file,
disease_to_phenotype_file,
annotations_file=annotations_file,
ages_distribution_file=ages_distribution_file
)
# parse input records
input_records = parse_input(input_file, hpo_network, alt2prim)
# create instance the scorer class
try:
scorer = Scorer(hpo_network,
summarization_method=summarization_method,
scoring_method=scoring_method)
except ValueError as e:
logger.critical(f'Failed to initialize scoring class: {e}')
sys.exit(1)
if self:
score_records = input_records
scoring_pairs = half_product(len(score_records), len(score_records))
else:
if records_file:
score_records = parse_input(records_file, hpo_network, alt2prim)
else:
score_records = disease_records
scoring_pairs = itertools.product(
range(len(input_records)),
range(len(score_records)),
)
results = scorer.score_records(input_records, score_records, scoring_pairs,
threads)
with open_or_stdout(output_file) as output_fh:
output_fh.write('\t'.join(['#query', 'entity_id', 'score']))
output_fh.write('\n')
for result in results:
output_fh.write('\t'.join(str(column) for column in result))
output_fh.write('\n')
def annotate(hpo_network, phenotype_to_diseases, num_diseases_annotated, alt2prim, annotations_file=None, ages_distribution_file=None,
phenotype_disease_frequencies=None):
"""
Cleans the HPO network.
Removes non-phenotype branches of the network, and merges all synonyms into one tag.
:param hpo_network: `networkx.MultiDiGraph` to clean.
:param phenotype_to_diseases: Dictionary mapping HPO terms to diseases.
:param num_diseases_annotated: Number of diseases with HPO annotations.
:param alt2prim: The dict of alternate terms to canonical terms.
:param annotations_file: A list of custom annotation files, in the same format as tests/data/test.score-long.txt
:param ages: age distributions object
:param phenotype_disease_frequencies: dictionary of phenotype to disease frequencies
:param logger: Python `logging` logger instance.
:param ages_distribution_file: Path to phenotypes ages distribution file.
:return: `networkx.MultiDiGraph`
"""
# Before calculating information content, check for custom_annotations_file and load
custom_annos = None
if annotations_file is not None:
custom_annos = {}
for record in parse_input(annotations_file, hpo_network, alt2prim):
for term_id in record['terms']:
if term_id not in custom_annos:
custom_annos[term_id] = []
custom_annos[term_id].append(record['record_id'])
# make ages distributions
ages = None
if ages_distribution_file is not None:
try:
ages = make_age_distributions(ages_distribution_file)
logger.info(
f'Adding custom phenotype age distributions to HPO nodes from file: {ages_distribution_file}'
)
except (FileNotFoundError, PermissionError) as e:
logger.critical(e)
logger.critical(
f'Specified phenotype ages file could not be loaded or does not exist: {e}'
)
exit(1)
for node_id, data in hpo_network.nodes(data=True):
# annotate with information content value
hpo_network.nodes[node_id]['ic'] = calculate_information_content(
node_id,
hpo_network,
phenotype_to_diseases,
num_diseases_annotated,
custom_annos,
)
# annotate with phenotype age distribution
hpo_network.nodes[node_id]['disease_weights'] = {}
if ages is not None and node_id in ages.index:
hpo_network.nodes[node_id]['age_dist'] = ages.loc[node_id]['age_dist']
# add the disease_frequency weights as attributes to the node
if phenotype_disease_frequencies is not None:
if node_id in phenotype_disease_frequencies:
for disease_id, frequency in phenotype_disease_frequencies[node_id].items():
hpo_network.nodes[node_id]['weights']['disease_frequency'][disease_id] = frequency
# annotate with depth value
# hard-coding origin node for now
origin = 'HP:0000001'
hpo_network.nodes[node_id]['depth'] = nx.shortest_path_length(
hpo_network,
node_id,
origin
)
# clean synonyms
synonyms = []
try:
for synonym in data['synonym']:
synonyms.append(synonym)
hpo_network.nodes[node_id]['synonyms'] = re.findall(r'"(.*?)"', ','.join(synonyms))
except KeyError:
# pass if no synonym tags in the node
pass
return hpo_network
