def test_read_nt4():
"""
Read from an RDF N-Triple file using RdfSource, with user defined
node property predicates.
"""
node_property_predicates = {
f"https://www.example.org/UNKNOWN/{x}"
for x in ['fusion', 'homology', 'combined_score', 'cooccurence']
}
source = RdfSource()
source.set_node_property_predicates(node_property_predicates)
g = source.parse(filename=os.path.join(RESOURCE_DIR, 'rdf', 'test3.nt'),
format='nt')
nodes, edges = process_stream(g)
assert len(nodes.keys()) == 7
assert len(edges.keys()) == 6
n1 = nodes['ENSEMBL:ENSG0000000000001']
assert n1['type'] == 'SO:0000704'
assert len(n1['category']) == 4
assert 'biolink:Gene' in n1['category']
assert 'biolink:GenomicEntity' in n1['category']
assert 'biolink:NamedThing' in n1['category']
assert n1['name'] == 'Test Gene 123'
assert n1['description'] == 'This is a Test Gene 123'
assert 'Test Dataset' in n1['provided_by']
n2 = nodes['ENSEMBL:ENSG0000000000002']
assert n2['type'] == 'SO:0000704'
assert len(n2['category']) == 4
assert 'biolink:Gene' in n2['category']
assert 'biolink:GenomicEntity' in n2['category']
assert 'biolink:NamedThing' in n1['category']
assert n2['name'] == 'Test Gene 456'
assert n2['description'] == 'This is a Test Gene 456'
assert 'Test Dataset' in n2['provided_by']
e1 = edges['ENSEMBL:ENSP0000000000001', 'ENSEMBL:ENSP0000000000002'][0]
assert e1['subject'] == 'ENSEMBL:ENSP0000000000001'
assert e1['object'] == 'ENSEMBL:ENSP0000000000002'
assert e1['predicate'] == 'biolink:interacts_with'
assert e1['relation'] == 'biolink:interacts_with'
assert e1['type'] == 'biolink:Association'
assert e1['id'] == 'urn:uuid:fcf76807-f909-4ccb-b40a-3b79b49aa518'
assert e1['fusion'] == '0'
assert e1['homology'] == '0.0'
assert e1['combined_score'] == '490.0'
assert e1['cooccurence'] == '332'
e2 = edges['ENSEMBL:ENSP0000000000001', 'UniProtKB:X0000001'][0]
assert e2['subject'] == 'ENSEMBL:ENSP0000000000001'
assert e2['object'] == 'UniProtKB:X0000001'
assert e2['predicate'] == 'biolink:same_as'
assert e2['relation'] == 'owl:equivalentClass'
e3 = edges['ENSEMBL:ENSP0000000000001', 'MONDO:0000001'][0]
assert e3['subject'] == 'ENSEMBL:ENSP0000000000001'
assert e3['object'] == 'MONDO:0000001'
assert e3['predicate'] == 'biolink:treats'
assert e3['relation'] == 'RO:0002606'
def test_read_neo(clean_slate):
"""
Read a graph from a Neo4j instance.
"""
driver = GraphDatabase(
DEFAULT_NEO4J_URL, username=DEFAULT_NEO4J_USERNAME, password=DEFAULT_NEO4J_PASSWORD
)
for q in queries:
driver.query(q)
s = NeoSource()
g = s.parse(
uri=DEFAULT_NEO4J_URL, username=DEFAULT_NEO4J_USERNAME, password=DEFAULT_NEO4J_PASSWORD
)
nodes, edges = process_stream(g)
assert len(nodes.keys()) == 3
assert len(edges.keys()) == 2
n1 = nodes['A']
assert n1['id'] == 'A'
assert n1['name'] == 'A'
assert 'category' in n1 and 'biolink:NamedThing' in n1['category']
e1 = edges[('A', 'C')][0]
assert e1['subject'] == 'A'
assert e1['object'] == 'C'
assert e1['predicate'] == 'biolink:related_to'
assert e1['relation'] == 'biolink:related_to'
def test_read_nt1():
"""
Read from an RDF N-Triple file using RdfSource.
"""
s = RdfSource()
g = s.parse(os.path.join(RESOURCE_DIR, 'rdf', 'test1.nt'))
nodes, edges = process_stream(g)
assert len(nodes) == 2
assert len(edges) == 1
n1 = nodes['ENSEMBL:ENSG0000000000001']
assert n1['type'] == 'SO:0000704'
assert len(n1['category']) == 4
assert 'biolink:Gene' in n1['category']
assert 'biolink:GenomicEntity' in n1['category']
assert 'biolink:NamedThing' in n1['category']
assert n1['name'] == 'Test Gene 123'
assert n1['description'] == 'This is a Test Gene 123'
assert 'Test Dataset' in n1['provided_by']
n2 = nodes['ENSEMBL:ENSG0000000000002']
assert n2['type'] == 'SO:0000704'
assert len(n2['category']) == 4
assert 'biolink:Gene' in n2['category']
assert 'biolink:GenomicEntity' in n2['category']
assert 'biolink:NamedThing' in n1['category']
assert n2['name'] == 'Test Gene 456'
assert n2['description'] == 'This is a Test Gene 456'
assert 'Test Dataset' in n2['provided_by']
e = list(edges.values())[0][0]
assert e['subject'] == 'ENSEMBL:ENSG0000000000001'
assert e['object'] == 'ENSEMBL:ENSG0000000000002'
assert e['predicate'] == 'biolink:interacts_with'
assert e['relation'] == 'biolink:interacts_with'
def test_read_nt6():
prefix_map = {
'HGNC':
'https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/',
'OMIM': 'http://omim.org/entry/',
}
node_property_predicates = {
'http://purl.obolibrary.org/obo/RO_0002558',
'http://purl.org/dc/elements/1.1/source',
'https://monarchinitiative.org/frequencyOfPhenotype',
}
predicate_mapping = {
'https://monarchinitiative.org/frequencyOfPhenotype':
'frequency_of_phenotype'
}
filename = os.path.join(RESOURCE_DIR, 'rdf', 'oban-test.nt')
source = RdfSource()
source.set_prefix_map(prefix_map)
source.set_node_property_predicates(node_property_predicates)
source.set_predicate_mapping(predicate_mapping)
g = source.parse(filename=filename, format='nt')
nodes, edges = process_stream(g)
assert len(nodes.keys()) == 14
assert len(edges.keys()) == 7
n1 = nodes['HP:0000505']
assert len(n1['category']) == 1
assert 'biolink:NamedThing' in n1['category']
e1 = edges['OMIM:166400', 'HP:0000006'][0]
assert e1['subject'] == 'OMIM:166400'
assert e1['object'] == 'HP:0000006'
assert e1['relation'] == 'RO:0000091'
assert e1['type'] == 'OBAN:association'
assert e1['has_evidence'] == 'ECO:0000501'
e2 = edges['ORPHA:93262', 'HP:0000505'][0]
assert e2['subject'] == 'ORPHA:93262'
assert e2['object'] == 'HP:0000505'
assert e2['relation'] == 'RO:0002200'
assert e2['type'] == 'OBAN:association'
assert e2['frequency_of_phenotype'] == 'HP:0040283'
def test_load1():
"""
Read a SSSOM formatted file.
"""
source = SssomSource()
g = source.parse(filename=os.path.join(RESOURCE_DIR, 'sssom_example1.tsv'), format='sssom')
nodes, edges = process_stream(g)
assert len(nodes.keys()) == 18
assert len(edges.keys()) == 9
assert nodes['MP:0012051']['id'] == 'MP:0012051'
assert nodes['HP:0001257']['id'] == 'HP:0001257'
e = edges['MP:0012051', 'HP:0001257'][0]
assert e['subject'] == 'MP:0012051'
assert e['object'] == 'HP:0001257'
assert e['predicate'] == 'biolink:same_as'
assert e['confidence'] == '1.0'
def test_load3():
"""
Read a SSSOM formatted file that has metadata provided in headers.
"""
source = SssomSource()
g = source.parse(filename=os.path.join(RESOURCE_DIR, 'sssom_example3.tsv'), format='sssom')
nodes, edges = process_stream(g)
assert len(nodes) == 20
assert len(edges) == 10
e = edges['MA:0000168', 'UBERON:0000955'][0]
assert 'mapping_provider' in e and e['mapping_provider'] == 'https://www.mousephenotype.org'
assert 'mapping_set_group' in e and e['mapping_set_group'] == 'impc_mouse_morphology'
assert 'mapping_set_id' in e and e['mapping_set_id'] == 'ma_uberon_impc_pat'
assert (
'mapping_set_title' in e
and e['mapping_set_title']
== 'The IMPC Mouse Morphology Mappings: Gross Pathology & Tissue Collection Test (Anatomy)'
)
assert 'creator_id' in e and e['creator_id'] == 'https://orcid.org/0000-0000-0000-0000'
assert 'license' in e and e['license'] == 'https://creativecommons.org/publicdomain/zero/1.0/'
assert 'curie_map' not in e
def test_load2():
"""
Read a SSSOM formatted file, with more metadata on mappings.
"""
source = SssomSource()
g = source.parse(filename=os.path.join(RESOURCE_DIR, 'sssom_example2.tsv'), format='sssom')
nodes, edges = process_stream(g)
assert len(nodes.keys()) == 18
assert len(edges.keys()) == 9
n1 = nodes['MP:0002152']
assert n1['id'] == 'MP:0002152'
n2 = nodes['HP:0012443']
assert n2['id'] == 'HP:0012443'
e = edges['MP:0002152', 'HP:0012443'][0]
assert e['subject'] == 'MP:0002152'
assert e['subject_label'] == 'abnormal brain morphology'
assert e['object'] == 'HP:0012443'
assert e['object_label'] == 'Abnormality of brain morphology'
assert e['predicate'] == 'biolink:exact_match'
assert e['match_type'] == 'SSSOMC:Lexical'
assert e['reviewer_id'] == 'orcid:0000-0000-0000-0000'