def test_search():
root = "HP:0000118"
with gzip.open(annotations, 'rt') as annot_file:
annot_map = flat_to_annotations(annot_file)
with gzip.open(closures, 'rt') as closure_file:
graph = build_ic_graph_from_closures(closure_file, root, annot_map)
profile_a = ("HP:0000403,HP:0000518,HP:0000565,HP:0000767,"
"HP:0000872,HP:0001257,HP:0001263,HP:0001290,"
"HP:0001629,HP:0002019,HP:0002072".split(','))
search_results = search(profile_a, annot_map, graph, 'phenodigm')
assert search_results.results[0].id == 'ORPHA:94125'
assert search_results.results[0].score > 50
assert search_results.results[0].rank == 1
ICSemSim,
SemanticDist,
build_graph_from_closure_file,
build_graph_from_rdflib,
build_ic_graph_from_closures,
build_ic_graph_from_iri,
flat_to_annotations,
)
ontology = Path(__file__).parent / 'resources' / 'mock-hpo' / 'ontology.ttl'
closures = Path(__file__).parent / 'resources' / 'mock-hpo' / 'closures.tsv'
annotations = Path(
__file__).parent / 'resources' / 'mock-hpo' / 'annotations.tsv'
with open(annotations, 'r') as annot_file:
annotation_map = flat_to_annotations(annot_file)
epsilon = 1e-3
graph_sim_tests = [
("self.graph_semsim.jaccard_sim(annotation_map['1'], annotation_map['2'])",
0.3),
("self.graph_semsim.cosine_sim(annotation_map['1'], annotation_map['2'])",
0.474),
]
ic_sim_tests = [
("self.semantic_sim.resnik_sim(annotation_map['1'], annotation_map['2'])",
0.693),
(
"self.semantic_sim.resnik_sim(annotation_map['1'], annotation_map['2'], matrix_metric=MatrixMetric.MAX)",
required=False,
default=int(multiprocessing.cpu_count() / 2))
args = parser.parse_args()
output = open(args.output, 'w')
annotation_file = Path(
__file__).parents[1] / 'data' / 'synthetic' / 'gold-standard.tsv.gz'
closures = Path(__file__).parents[1] / 'data' / 'hp-closures.tsv'
root = "HP:0000118"
logger.info("Loading closures")
with gzip.open(annotation_file, 'rt') as annot_file:
annotations = flat_to_annotations(annot_file)
logger.info("Building graph")
with open(closures, 'r') as closure_file:
graph = build_ic_graph_from_closures(closure_file, root, annotations)
ic_sim = ICSemSim(graph)
# Dictionaries used for constructing synthetic patient objects
simulated_profiles: Dict[str, Set[str]] = defaultdict(set)
synth_to_disease: Dict[str, str] = {}
synthetic_profiles: List[SyntheticProfile] = []
# Confusion matrix per rank
confusion_by_rank: Dict[int, List[int]] = {}
from pumpkin_py import get_methods, ICSemSim,GraphSemSim, \
flat_to_annotations, build_ic_graph_from_closures
print("available sim methods")
print(get_methods())
closures = Path(__file__).parent / 'resources' / 'upheno-closures.tsv.gz'
annotations = Path(__file__).parent / 'resources' / 'all-annotations.tsv.gz'
g2p = Path(__file__).parent / 'resources' / 'Mm_gene_phenotype.txt.gz'
root = "UPHENO:0001001"
print("Loading closures")
with gzip.open(annotations, 'rt') as annot_file:
annot_map = flat_to_annotations(annot_file)
with gzip.open(closures, 'rt') as closure_file:
graph = build_ic_graph_from_closures(closure_file, root, annot_map)
with gzip.open(g2p, 'rt') as annot_file:
mouse_genes = flat_to_annotations(annot_file)
ic_sim = ICSemSim(graph)
graph_sim = GraphSemSim(graph)
profile_a = "HP:0000403,HP:0000518,HP:0000565,HP:0000767," \
"HP:0000872,HP:0001257,HP:0001263,HP:0001290," \
"HP:0001629,HP:0002019,HP:0002072".split(',')