def get_graphs1():
"""
Returns instances of defined graphs.
"""
g1 = NxGraph()
g1.add_edge('B', 'A', **{'predicate': 'biolink:sub_class_of'})
g1.add_edge('C', 'B', **{'predicate': 'biolink:sub_class_of'})
g1.add_edge('D', 'C', **{'predicate': 'biolink:sub_class_of'})
g1.add_edge('D', 'A', **{'predicate': 'biolink:related_to'})
g1.add_edge('E', 'D', **{'predicate': 'biolink:sub_class_of'})
g1.add_edge('F', 'D', **{'predicate': 'biolink:sub_class_of'})
g2 = NxGraph()
g2.name = 'Graph 1'
g2.add_node(
'HGNC:12345',
id='HGNC:12345',
name='Test Gene',
category=['biolink:NamedThing'],
alias='NCBIGene:54321',
same_as='UniProtKB:54321',
)
g2.add_node('B', id='B', name='Node B', category=['biolink:NamedThing'], alias='Z')
g2.add_node('C', id='C', name='Node C', category=['biolink:NamedThing'])
g2.add_edge(
'C',
'B',
edge_key='C-biolink:subclass_of-B',
subject='C',
object='B',
predicate='biolink:subclass_of',
relation='rdfs:subClassOf',
provided_by='Graph 1',
publications=[1],
pubs=['PMID:123456'],
)
g2.add_edge(
'B',
'A',
edge_key='B-biolink:subclass_of-A',
subject='B',
object='A',
predicate='biolink:subclass_of',
relation='rdfs:subClassOf',
provided_by='Graph 1',
)
g2.add_edge(
'C',
'c',
edge_key='C-biolink:exact_match-B',
subject='C',
object='c',
predicate='biolink:exact_match',
relation='skos:exactMatch',
provided_by='Graph 1',
)
return [g1, g2]
def get_graphs():
"""
Returns instances of defined graphs.
"""
g1 = NxGraph()
g1.add_edge("B", "A", **{"predicate": "biolink:sub_class_of"})
g1.add_edge("C", "B", **{"predicate": "biolink:sub_class_of"})
g1.add_edge("D", "C", **{"predicate": "biolink:sub_class_of"})
g1.add_edge("D", "A", **{"predicate": "biolink:related_to"})
g1.add_edge("E", "D", **{"predicate": "biolink:sub_class_of"})
g1.add_edge("F", "D", **{"predicate": "biolink:sub_class_of"})
g2 = NxGraph()
g2.name = "Graph 1"
g2.add_node(
"HGNC:12345",
id="HGNC:12345",
name="Test Gene",
category=["biolink:NamedThing"],
alias="NCBIGene:54321",
same_as="UniProtKB:54321",
)
g2.add_node("B", id="B", name="Node B", category=["biolink:NamedThing"], alias="Z")
g2.add_node("C", id="C", name="Node C", category=["biolink:NamedThing"])
g2.add_edge(
"C",
"B",
edge_key="C-biolink:subclass_of-B",
subject="C",
object="B",
predicate="biolink:subclass_of",
relation="rdfs:subClassOf",
provided_by="Graph 1",
publications=[1],
pubs=["PMID:123456"],
)
g2.add_edge(
"B",
"A",
edge_key="B-biolink:subclass_of-A",
subject="B",
object="A",
predicate="biolink:subclass_of",
relation="rdfs:subClassOf",
provided_by="Graph 1",
)
g2.add_edge(
"C",
"c",
edge_key="C-biolink:exact_match-B",
subject="C",
object="c",
predicate="biolink:exact_match",
relation="skos:exactMatch",
provided_by="Graph 1",
)
return [g1, g2]
def test_validator_explicit_biolink_version():
"""
A fake test to establish a success condition for validation.
"""
G = NxGraph()
G.add_node(
"CHEMBL.COMPOUND:1222250",
id="CHEMBL.COMPOUND:1222250",
name="Dextrose",
category=["Carbohydrate"],
)
G.add_node(
"UBERON:0000001", id="UBERON:0000001", name="fake", category=["NamedThing"]
)
G.add_edge(
"CHEMBL.COMPOUND:1222250",
"UBERON:0000001",
id="CHEMBL.COMPOUND:1222250-part_of-UBERON:0000001",
relation="RO:1",
predicate="part_of",
subject="CHEMBL.COMPOUND:1222250",
object="UBERON:0000001",
category=["biolink:Association"],
)
Validator.set_biolink_model(version="1.8.2")
validator = Validator(verbose=True)
validator.validate(G)
print(validator.get_errors())
assert len(validator.get_errors()) == 0
def test_validator_good():
"""
A fake test to establish a success condition for validation.
"""
G = NxGraph()
G.add_node(
"UniProtKB:P123456", id="UniProtKB:P123456", name="fake", category=["Protein"]
)
G.add_node(
"UBERON:0000001", id="UBERON:0000001", name="fake", category=["NamedThing"]
)
G.add_node(
"UBERON:0000002", id="UBERON:0000002", name="fake", category=["NamedThing"]
)
G.add_edge(
"UBERON:0000001",
"UBERON:0000002",
id="UBERON:0000001-part_of-UBERON:0000002",
relation="RO:1",
predicate="part_of",
subject="UBERON:0000001",
object="UBERON:0000002",
category=["biolink:Association"],
)
validator = Validator(verbose=True)
validator.validate(G)
print(validator.get_errors())
assert len(validator.get_errors()) == 0
def test_validator_good():
"""
A fake test to establish a success condition for validation.
"""
G = NxGraph()
G.add_node('UniProtKB:P123456',
id='UniProtKB:P123456',
name='fake',
category=['Protein'])
G.add_node('UBERON:0000001',
id='UBERON:0000001',
name='fake',
category=['NamedThing'])
G.add_node('UBERON:0000002',
id='UBERON:0000002',
name='fake',
category=['NamedThing'])
G.add_edge(
'UBERON:0000001',
'UBERON:0000002',
id='UBERON:0000001-part_of-UBERON:0000002',
relation='RO:1',
predicate='part_of',
subject='UBERON:0000001',
object='UBERON:0000002',
category=['biolink:Association'],
)
validator = Validator(verbose=True)
e = validator.validate(G)
print(validator.report(e))
assert len(e) == 0
def test_clique_merge8():
"""
Test for clique merge where same_as appear as both node and edge properties.
"""
ppm = {"biolink:Gene": ["HGNC", "NCBIGene", "ENSEMBL", "OMIM"]}
g1 = NxGraph()
g1.add_node("HGNC:1", **{"category": ["biolink:Gene"]})
g1.add_node("OMIM:2", **{"category": ["biolink:Gene"], "same_as": ["HGNC:1"]})
g1.add_node("NCBIGene:3", **{"category": ["biolink:NamedThing"]})
g1.add_node("ENSEMBL:4", **{"category": ["biolink:Gene"], "same_as": ["HGNC:1"]})
g1.add_node(
"ENSEMBL:6", **{"category": ["biolink:Gene"], "same_as": ["NCBIGene:8"]}
)
g1.add_node("HGNC:7", **{"category": ["biolink:Gene"]})
g1.add_node("NCBIGene:8", **{"category": ["biolink:Gene"]})
g1.add_edge(
"NCBIGene:3",
"HGNC:1",
edge_key=generate_edge_key("NCBIGene:3", "biolink:same_as", "HGNC:1"),
**{"predicate": "biolink:same_as", "relation": "owl:equivalentClass"}
)
g1.add_edge(
"ENSEMBL:6",
"NCBIGene:8",
edge_key=generate_edge_key("ENSEMBL:6", "biolink:same_as", "NCBIGene:8"),
**{"predicate": "biolink:same_as", "relation": "owl:equivalentClass"}
)
g1.add_edge(
"HGNC:7",
"NCBIGene:8",
edge_key=generate_edge_key("HGNC:7", "biolink:same_as", "NCBIGene:8"),
**{"predicate": "biolink:same_as", "relation": "owl:equivalentClass"}
)
updated_graph, clique_graph = clique_merge(
target_graph=g1, prefix_prioritization_map=ppm
)
assert updated_graph.number_of_nodes() == 2
assert updated_graph.number_of_edges() == 0
assert updated_graph.has_node("HGNC:1")
assert updated_graph.has_node("HGNC:7")
n1 = updated_graph.nodes()["HGNC:1"]
assert "OMIM:2" in n1["same_as"]
assert "NCBIGene:3" in n1["same_as"]
assert "ENSEMBL:4" in n1["same_as"]
n2 = updated_graph.nodes()["HGNC:7"]
assert "ENSEMBL:6" in n2["same_as"]
assert "NCBIGene:8" in n2["same_as"]
assert not updated_graph.has_node("OMIM:2")
assert not updated_graph.has_node("NCBIGene:3")
assert not updated_graph.has_node("ENSEMBL:4")
assert not updated_graph.has_node("ENSEMBL:6")
assert not updated_graph.has_node("NCBIGene:8")
def test_add_node():
"""
Test adding a node to an NxGraph.
"""
g = NxGraph()
g.add_node('A')
g.add_node('A', name='Node A', description='Node A')
assert g.has_node('A')
def test_add_edge_attribute():
"""
Test adding an edge attribute to an NxGraph.
"""
g = NxGraph()
g.add_edge("A", "B")
g.add_edge_attribute("A", "B", "edge_ab", "predicate",
"biolink:related_to")
def test_add_edge_attribute():
"""
Test adding an edge attribute to an NxGraph.
"""
g = NxGraph()
g.add_edge('A', 'B')
g.add_edge_attribute('A', 'B', 'edge_ab', 'predicate',
'biolink:related_to')
def test_add_node():
"""
Test adding a node to an NxGraph.
"""
g = NxGraph()
g.add_node("A")
g.add_node("A", name="Node A", description="Node A")
assert g.has_node("A")
def test_set_node_attributes():
"""
Test setting node attributes in bulk.
"""
g = NxGraph()
g.add_node("X:1", alias="A:1")
g.add_node("X:2", alias="B:2")
d = {"X:1": {"alias": "ABC:1"}, "X:2": {"alias": "DEF:2"}}
NxGraph.set_node_attributes(g, d)
def test_add_node_attribute():
"""
Test adding a node attribute to an NxGraph.
"""
g = NxGraph()
g.add_node("A")
g.add_node_attribute("A", "provided_by", "test")
n = g.get_node("A")
assert "provided_by" in n and n["provided_by"] == "test"
def test_set_node_attributes():
"""
Test setting node attributes in bulk.
"""
g = NxGraph()
g.add_node("X:1", alias="A:1")
g.add_node("X:2", alias="B:2")
d = {'X:1': {'alias': 'ABC:1'}, 'X:2': {'alias': 'DEF:2'}}
NxGraph.set_node_attributes(g, d)
def test_update_edge_attribute():
"""
Test updating an edge attribute for an edge in an NxGraph.
"""
g = NxGraph()
g.add_edge('A', 'B', 'edge_ab')
g.update_edge_attribute('A', 'B', 'edge_ab', 'source', 'test')
e = g.get_edge('A', 'B', 'edge_ab')
assert 'source' in e and e['source'] == 'test'
def test_add_node_attribute():
"""
Test adding a node attribute to an NxGraph.
"""
g = NxGraph()
g.add_node('A')
g.add_node_attribute('A', 'provided_by', 'test')
n = g.get_node('A')
assert 'provided_by' in n and n['provided_by'] == 'test'
def test_update_edge_attribute():
"""
Test updating an edge attribute for an edge in an NxGraph.
"""
g = NxGraph()
g.add_edge("A", "B", "edge_ab")
g.update_edge_attribute("A", "B", "edge_ab", "source", "test")
e = g.get_edge("A", "B", "edge_ab")
assert "source" in e and e["source"] == "test"
def test_update_node_attribute():
"""
Test updating a node attribute for a node in an NxGraph.
"""
g = NxGraph()
g.add_node('A', name='A', description='Node A')
g.update_node_attribute('A', 'description', 'Modified description')
n = g.get_node('A')
assert 'name' in n and n['name'] == 'A'
assert 'description' in n and n['description'] == 'Modified description'
def test_merge_graphs():
"""
Test for merging 3 graphs into one,
while not preserving conflicting node and edge properties.
"""
graphs = get_graphs()
merged_graph = merge_graphs(NxGraph(), graphs)
assert merged_graph.number_of_nodes() == 6
assert merged_graph.number_of_edges() == 6
assert merged_graph.name not in [x.name for x in graphs]
def test_update_node_attribute():
"""
Test updating a node attribute for a node in an NxGraph.
"""
g = NxGraph()
g.add_node("A", name="A", description="Node A")
g.update_node_attribute("A", "description", "Modified description")
n = g.get_node("A")
assert "name" in n and n["name"] == "A"
assert "description" in n and n["description"] == "Modified description"
def test_validator_bad():
"""
A fake test to establish a fail condition for validation.
"""
G = NxGraph()
G.add_node('x', foo=3)
G.add_node('ZZZ:3', **{'nosuch': 1})
G.add_edge('x', 'y', **{'baz': 6})
validator = Validator(verbose=True)
e = validator.validate(G)
assert len(e) > 0
def test_add_edge():
"""
Test adding an edge to an NxGraph.
"""
g = NxGraph()
g.add_node("A")
g.add_node("B")
g.add_edge("A", "B", predicate="biolink:related_to", provided_by="test")
assert g.has_edge("A", "B")
g.add_edge("B", "C", edge_key="B-biolink:related_to-C", provided_by="test")
assert g.has_edge("B", "C")
def test_validator_bad():
"""
A fake test to establish a fail condition for validation.
"""
G = NxGraph()
G.add_node("x", foo=3)
G.add_node("ZZZ:3", **{"nosuch": 1})
G.add_edge("x", "y", **{"baz": 6})
validator = Validator(verbose=True)
validator.validate(G)
assert len(validator.get_errors()) > 0
def test_add_edge():
"""
Test adding an edge to an NxGraph.
"""
g = NxGraph()
g.add_node('A')
g.add_node('B')
g.add_edge('A', 'B', predicate='biolink:related_to', provided_by='test')
assert g.has_edge('A', 'B')
g.add_edge('B', 'C', edge_key='B-biolink:related_to-C', provided_by='test')
assert g.has_edge('B', 'C')
def test_set_edge_attributes():
"""
Test setting edge attributes in bulk.
"""
g = NxGraph()
g.add_node("X:1", alias="A:1")
g.add_node("X:2", alias="B:2")
g.add_edge("X:2", 'X:1', edge_key='edge1', source="Source 1")
d = {('X:2', 'X:1', 'edge1'): {'source': 'Modified Source 1'}}
NxGraph.set_edge_attributes(g, d)
e = list(g.edges(keys=True, data=True))[0]
assert e[3]['source'] == 'Modified Source 1'
def test_set_edge_attributes():
"""
Test setting edge attributes in bulk.
"""
g = NxGraph()
g.add_node("X:1", alias="A:1")
g.add_node("X:2", alias="B:2")
g.add_edge("X:2", "X:1", edge_key="edge1", source="Source 1")
d = {("X:2", "X:1", "edge1"): {"source": "Modified Source 1"}}
NxGraph.set_edge_attributes(g, d)
e = list(g.edges(keys=True, data=True))[0]
assert e[3]["source"] == "Modified Source 1"
def test_remove_singleton_nodes():
"""
Test the remove singleton nodes operation.
"""
g = NxGraph()
g.add_edge("A", "B")
g.add_edge("B", "C")
g.add_edge("C", "D")
g.add_edge("B", "D")
g.add_node("X")
g.add_node("Y")
assert g.number_of_nodes() == 6
assert g.number_of_edges() == 4
remove_singleton_nodes(g)
assert g.number_of_nodes() == 4
assert g.number_of_edges() == 4
def test_remove_singleton_nodes():
"""
Test the remove singleton nodes operation.
"""
g = NxGraph()
g.add_edge('A', 'B')
g.add_edge('B', 'C')
g.add_edge('C', 'D')
g.add_edge('B', 'D')
g.add_node('X')
g.add_node('Y')
assert g.number_of_nodes() == 6
assert g.number_of_edges() == 4
remove_singleton_nodes(g)
assert g.number_of_nodes() == 4
assert g.number_of_edges() == 4
def test_write_tsv2():
"""
Write a graph to a TSV archive using TsvSink.
"""
graph = NxGraph()
graph.add_node('A', id='A', **{'name': 'Node A'})
graph.add_node('B', id='B', **{'name': 'Node B'})
graph.add_node('C', id='C', **{'name': 'Node C'})
graph.add_node('D', id='D', **{'name': 'Node D'})
graph.add_node('E', id='E', **{'name': 'Node E'})
graph.add_node('F', id='F', **{'name': 'Node F'})
graph.add_edge('B', 'A', **{'subject': 'B', 'object': 'A', 'predicate': 'biolink:sub_class_of'})
graph.add_edge('C', 'B', **{'subject': 'C', 'object': 'B', 'predicate': 'biolink:sub_class_of'})
graph.add_edge('D', 'C', **{'subject': 'D', 'object': 'C', 'predicate': 'biolink:sub_class_of'})
graph.add_edge('D', 'A', **{'subject': 'D', 'object': 'A', 'predicate': 'biolink:related_to'})
graph.add_edge('E', 'D', **{'subject': 'E', 'object': 'D', 'predicate': 'biolink:sub_class_of'})
graph.add_edge('F', 'D', **{'subject': 'F', 'object': 'D', 'predicate': 'biolink:sub_class_of'})
s = TsvSink(
filename=os.path.join(TARGET_DIR, 'test_graph'),
format='tsv',
compression='tar',
node_properties={'id', 'name'},
edge_properties={'subject', 'predicate', 'object', 'relation'},
)
for n, data in graph.nodes(data=True):
s.write_node(data)
for u, v, k, data in graph.edges(data=True, keys=True):
s.write_edge(data)
s.finalize()
assert os.path.exists(os.path.join(TARGET_DIR, 'test_graph.tar'))
s = TsvSink(
filename=os.path.join(TARGET_DIR, 'test_graph'),
format='tsv',
compression='tar.gz',
node_properties={'id', 'name'},
edge_properties={'subject', 'predicate', 'object', 'relation'},
)
for n, data in graph.nodes(data=True):
s.write_node(data)
for u, v, k, data in graph.edges(data=True, keys=True):
s.write_edge(data)
s.finalize()
assert os.path.exists(os.path.join(TARGET_DIR, 'test_graph.tar.gz'))
def test_read_graph2():
"""
Read from an NxGraph using GraphSource.
This test also supplies the provided_by parameter.
"""
graph = NxGraph()
graph.add_node("A", **{"id": "A", "name": "node A"})
graph.add_node("B", **{"id": "B", "name": "node B"})
graph.add_node("C", **{"id": "C", "name": "node C"})
graph.add_edge(
"A", "C", **{
"subject": "A",
"predicate": "biolink:related_to",
"object": "C",
"relation": "biolink:related_to",
})
t = Transformer()
s = GraphSource(t)
g = s.parse(graph=graph,
provided_by="Test Graph",
knowledge_source="Test Graph")
nodes = {}
edges = {}
for rec in g:
if rec:
if len(rec) == 4:
edges[(rec[0], rec[1], rec[2])] = rec[3]
else:
nodes[rec[0]] = rec[1]
assert len(nodes.keys()) == 3
n1 = nodes["A"]
assert n1["id"] == "A"
assert n1["name"] == "node A"
assert "Test Graph" in n1["provided_by"]
assert len(edges.keys()) == 1
e1 = list(edges.values())[0]
assert e1["subject"] == "A"
assert e1["predicate"] == "biolink:related_to"
assert e1["object"] == "C"
assert e1["relation"] == "biolink:related_to"
assert "Test Graph" in e1["knowledge_source"]
def test_read_graph2():
"""
Read from an NxGraph using GraphSource.
This test also supplies the provided_by parameter.
"""
graph = NxGraph()
graph.add_node('A', **{'id': 'A', 'name': 'node A'})
graph.add_node('B', **{'id': 'B', 'name': 'node B'})
graph.add_node('C', **{'id': 'C', 'name': 'node C'})
graph.add_edge(
'A',
'C',
**{
'subject': 'A',
'predicate': 'biolink:related_to',
'object': 'C',
'relation': 'biolink:related_to',
}
)
s = GraphSource()
g = s.parse(graph=graph, provided_by='Test Graph')
nodes = {}
edges = {}
for rec in g:
if rec:
if len(rec) == 4:
edges[(rec[0], rec[1], rec[2])] = rec[3]
else:
nodes[rec[0]] = rec[1]
assert len(nodes.keys()) == 3
n1 = nodes['A']
assert n1['id'] == 'A'
assert n1['name'] == 'node A'
assert 'Test Graph' in n1['provided_by']
assert len(edges.keys()) == 1
e1 = list(edges.values())[0]
assert e1['subject'] == 'A'
assert e1['predicate'] == 'biolink:related_to'
assert e1['object'] == 'C'
assert e1['relation'] == 'biolink:related_to'
assert 'Test Graph' in e1['provided_by']