def add_simple_edge(graph: BELGraph, u, v, edge_types):
"""Add a simple edge into the graph."""
if 'ACTIVATION' in edge_types:
graph.add_increases(
u,
v,
citation=REACTOME_CITATION,
evidence='Extracted from Reactome',
object_modifier=activity() if isinstance(
v, ACTIVITY_ALLOWED_MODIFIERS) else None,
annotations={},
)
elif 'INHIBITION' in edge_types:
graph.add_decreases(
u,
v,
citation=REACTOME_CITATION,
evidence='Extracted from Reactome',
object_modifier=activity() if isinstance(
v, ACTIVITY_ALLOWED_MODIFIERS) else None,
annotations={},
)
else:
log.warning('edge type %s', edge_types)
def make_graph_1() -> BELGraph:
graph = BELGraph(
name='Lab course example',
version='1.1.0',
description='',
authors='LSI',
contact='*****@*****.**',
)
graph.add_node_from_data(protein_a)
graph.add_node_from_data(protein_b)
graph.add_node_from_data(gene_c)
graph.add_node_from_data(rna_d)
graph.add_increases(protein_a,
protein_b,
citation='1',
evidence='Evidence 1',
annotations={'Annotation': 'foo'})
graph.add_increases(rna_d,
protein_a,
citation='2',
evidence='Evidence 2',
annotations={'Annotation': 'foo'})
graph.add_decreases(gene_c,
protein_b,
citation='3',
evidence='Evidence 3',
annotations={'Annotation': 'foo'})
return graph
def test_get_upstream_causal_subgraph(self):
"""Test get_upstream_causal_subgraph."""
a, b, c, d, e, f = [
protein(namespace='test', name=n()) for _ in range(6)
]
universe = BELGraph()
universe.namespace_pattern['test'] = 'test-url'
universe.add_increases(a, b, citation=n(), evidence=n())
universe.add_increases(b, c, citation=n(), evidence=n())
universe.add_association(d, a, citation=n(), evidence=n())
universe.add_increases(e, a, citation=n(), evidence=n())
universe.add_decreases(f, b, citation=n(), evidence=n())
subgraph = get_upstream_causal_subgraph(universe, [a, b])
self.assertIsInstance(subgraph, BELGraph)
self.assert_all_nodes_are_base_entities(subgraph)
self.assertIn('test', subgraph.namespace_pattern)
self.assertEqual('test-url', subgraph.namespace_pattern['test'])
self.assertIn(a, subgraph)
self.assertIn(b, subgraph)
self.assertNotIn(c, subgraph)
self.assertNotIn(d, subgraph)
self.assertIn(e, subgraph)
self.assertIn(f, subgraph)
self.assertEqual(4, subgraph.number_of_nodes())
self.assert_in_edge(e, a, subgraph)
self.assert_in_edge(a, b, subgraph)
self.assert_in_edge(f, b, subgraph)
self.assertEqual(3, subgraph.number_of_edges())
def make_graph_4() -> BELGraph:
"""Make an example graph.
A -> B
B -| C
B -| D
B -| E
B -| F
B -> G
B -> H
B -| H
B -> I
B -- J
"""
graph = BELGraph(
name='Lab course example',
version='1.1.0',
description='',
authors='LSI',
contact='*****@*****.**',
)
graph.add_increases(protein_a, protein_b, n(), n())
graph.add_decreases(protein_b, gene_c, n(), n())
graph.add_decreases(protein_b, rna_d, n(), n())
graph.add_decreases(protein_b, protein_e, n(), n())
graph.add_decreases(protein_b, gene_f, n(), n())
graph.add_increases(protein_b, protein_g, n(), n())
graph.add_decreases(protein_b, protein_h, n(), n())
graph.add_increases(protein_b, protein_h, n(), n())
graph.add_increases(protein_b, protein_i, n(), n())
graph.add_association(protein_b, protein_j, n(), n())
return graph
def add_simple_edge(graph: BELGraph, u: BaseEntity, v: BaseEntity, edge_types, uri_id):
"""Add simple edge to graph.
:param graph: BEL Graph
:param u: source
:param v: target
:param edge_types: edge type dict
:param uri_id: citation URI
"""
if 'Stimulation' in edge_types:
graph.add_increases(
u, v,
citation=uri_id, evidence='Extracted from WikiPathways',
object_modifier=activity() if isinstance(v, ACTIVITY_ALLOWED_MODIFIERS) else None,
annotations={},
)
elif 'Inhibition' in edge_types:
graph.add_decreases(
u, v,
citation=uri_id, evidence='Extracted from WikiPathways',
object_modifier=activity() if isinstance(v, ACTIVITY_ALLOWED_MODIFIERS) else None,
annotations={},
)
elif 'Catalysis' in edge_types:
graph.add_increases(
u, v,
citation=uri_id, evidence='Extracted from WikiPathways',
object_modifier=activity() if isinstance(v, ACTIVITY_ALLOWED_MODIFIERS) else None,
annotations={},
)
elif 'DirectedInteraction' in edge_types:
graph.add_regulates(
u, v,
citation=uri_id,
evidence='Extracted from WikiPathways',
annotations={
'EdgeTypes': edge_types,
},
)
elif 'Interaction' in edge_types:
logger.debug('No interaction subtype for %s', str(uri_id))
elif 'TranscriptionTranslation' in edge_types:
graph.add_translation(u, v)
else:
logger.debug('No handled edge type %s', str(uri_id))
def add_to_bel_graph(self, graph: BELGraph) -> str:
"""Add this relationship as an edge to the BEL graph."""
return graph.add_decreases(
self.compound.as_bel(),
self.umls.as_bel(),
citation='26481350',
evidence='Extracted from SIDER',
annotations={
'Database': 'SIDER',
'SIDER_MEDDRA_TYPE': self.meddra_type.name,
'SIDER_DETECTION': self.detection.name,
}
)
def make_graph_3() -> BELGraph:
"""Make an example graph.
A -> B -| C
D -| F -> C
C -| F
C -- G
"""
graph = BELGraph(
name='Lab course example',
version='1.1.0',
description='',
authors='LSI',
contact='*****@*****.**',
)
graph.add_increases(protein_a, protein_b, n(), n())
graph.add_decreases(protein_b, gene_c, n(), n())
graph.add_decreases(rna_d, gene_f, n(), n())
graph.add_increases(protein_e, gene_f, n(), n())
graph.add_increases(gene_f, gene_c, n(), n())
graph.add_association(gene_c, protein_g, n(), n())
return graph
def test_expand_upstream_causal_subgraph(self):
"""Test expanding on the upstream causal subgraph."""
a, b, c, d, e, f = [
protein(namespace='test', name=i)
for i in string.ascii_lowercase[:6]
]
universe = BELGraph()
universe.add_increases(a, b, citation=n(), evidence=n())
universe.add_increases(b, c, citation=n(), evidence=n())
universe.add_association(d, a, citation=n(), evidence=n())
universe.add_increases(e, a, citation=n(), evidence=n())
universe.add_decreases(f, b, citation=n(), evidence=n())
subgraph = BELGraph()
subgraph.add_increases(a, b, citation=n(), evidence=n())
expand_upstream_causal(universe, subgraph)
self.assertIsInstance(subgraph, BELGraph)
self.assert_all_nodes_are_base_entities(subgraph)
self.assertIn(a, subgraph)
self.assertIn(b, subgraph)
self.assertNotIn(c, subgraph)
self.assertNotIn(d, subgraph)
self.assertIn(e, subgraph)
self.assertIn(f, subgraph)
self.assertEqual(4, subgraph.number_of_nodes())
self.assert_in_edge(e, a, subgraph)
self.assert_in_edge(a, b, subgraph)
self.assert_in_edge(f, b, subgraph)
self.assertEqual(2, len(subgraph[a][b]))
self.assertEqual(4,
subgraph.number_of_edges(),
msg='\n'.join(map(str, subgraph.edges())))
g(HGNC:MTHFR,sub(C,677,T)) pos path(MESH:"Alzheimer Disease")
"""
c2 = '21119889'
e2 = "Two common MTHFR polymorphisms, namely 677C>T (Ala222Val) and 1298A>C (Glu429Ala), are known to reduce MTHFR activity. \
It has been shown that the MTHFR 677T allele is associated with increased total plasma Hcy levels (tHcy) and decreased serum folate levels, mainly in 677TT homozygous subjects.\
the MTHFR 677C>T polymorphism as a candidate AD risk factor"
e2 = str(hash(e2))
mthfr = protein('HGNC', 'MTHFR')
mthfr_c677t = protein('HGNC', 'MTHFR', variants=[protein_substitution('Ala', 222, 'Val')])
mthfr_a1298c = protein('HGNC', 'MTHFR', variants=[protein_substitution('Glu', 429, 'Ala')])
folic_acid = abundance('CHEBI', 'folic acid')
alzheimer_disease = pathology('MESH', 'Alzheimer Disease')
example_graph.add_decreases(mthfr_c677t, mthfr, citation=c2, evidence=e2, object_modifier=activity())
example_graph.add_decreases(mthfr_a1298c, mthfr, citation=c2, evidence=e2, object_modifier=activity())
example_graph.add_negative_correlation(mthfr_c677t, folic_acid, citation=c2, evidence=e2)
example_graph.add_positive_correlation(mthfr_c677t, alzheimer_disease, citation=c2, evidence=e2)
c3 = '17948130'
e3 = 'A polymorphism in the NDUFB6 promoter region that creates a possible DNA methylation site (rs629566, A/G) was ' \
'associated with a decline in muscle NDUFB6 expression with age. Although young subjects with the rs629566 G/G ' \
'genotype exhibited higher muscle NDUFB6 expression, this genotype was associated with reduced expression in' \
' elderly subjects. This was subsequently explained by the finding of increased DNA methylation in the promoter ' \
'of elderly, but not young, subjects carrying the rs629566 G/G genotype. Furthermore, the degree of DNA' \
' methylation correlated negatively with muscle NDUFB6 expression, which in turn was associated with insulin ' \
'sensitivity.'
e3 = str(hash(e3))
rs629566 = gene('DBSNP', 'rs629566', variants=[gmod('Me')])
class TestAnnotation(unittest.TestCase):
"""Tests for getting sub-graphs by annotation."""
def setUp(self):
"""Set up the test case with a pre-populated BEL graph."""
self.graph = BELGraph()
self.graph.namespace_url['test'] = test_namespace_url
self.graph.annotation_url['subgraph'] = test_annotation_url
# A increases/decreases B.
self.graph.add_increases(a,
b,
citation=citation,
evidence=evidence,
annotations={'subgraph': {'1', '2'}})
self.graph.add_decreases(a,
b,
citation=citation,
evidence=evidence,
annotations={'subgraph': {'1'}})
# B increases association with C.
self.graph.add_increases(b,
c,
citation=citation,
evidence=evidence,
annotations={'subgraph': {'1', '2'}})
self.graph.add_association(b,
c,
citation=citation,
evidence=evidence,
annotations={'subgraph': {'2'}})
# C increases D
self.graph.add_increases(c, d, citation=citation, evidence=evidence)
self.graph.add_increases(d,
e,
citation=citation,
evidence=evidence,
annotations={'subgraph': {'1', '2'}})
self.graph.add_qualified_edge(d,
e,
relation=CAUSES_NO_CHANGE,
evidence=evidence,
citation=citation,
annotations={'subgraph': {'1', '2'}})
def test_contradictions_finder(self):
"""Simple test to find contradictions."""
contradictory_edges = get_contradiction_summary(self.graph)
contradictions = [(protein(namespace='test', name='0'),
protein(namespace='test',
name='1'), {'decreases', 'increases'}),
(protein(namespace='test', name='3'),
protein(namespace='test',
name='4'), {'causesNoChange', 'increases'})]
for edge in contradictory_edges:
self.assertIn(edge, contradictions)
def _add_row(
graph: BELGraph,
relation: str,
source_prefix: str,
source_id: str,
source_name: Optional[str],
target_prefix: str,
target_id: str,
target_name: Optional[str],
pubmed_id: str,
int_detection_method: str,
source_database: str,
confidence: str,
) -> None: # noqa:C901
"""Add for every PubMed ID an edge with information about relationship type, source and target.
:param source_database: row value of column source_database
:param graph: graph to add edges to
:param relation: row value of column relation
:param source_prefix: row value of source prefix
:param source_id: row value of source id
:param target_prefix: row value of target prefix
:param target_id: row value of target id
:param pubmed_id: row value of column PubMed_id
:param int_detection_method: row value of column interaction detection method
:param confidence: row value of confidence score column
:return: None
"""
if pubmed_id is None:
pubmed_id = 'database', 'intact'
annotations = {
'psi-mi': relation,
'intact-detection': int_detection_method,
'intact-source': source_database,
'intact-confidence': confidence,
}
# map double spaces to single spaces in relation string
relation = ' '.join(relation.split())
source_dsl = NAMESPACE_TO_DSL.get(source_prefix, pybel.dsl.Protein)
source = source_dsl(
namespace=source_prefix,
identifier=source_id,
name=source_name,
)
target_dsl = NAMESPACE_TO_DSL.get(target_prefix, pybel.dsl.Protein)
target = target_dsl(
namespace=target_prefix,
identifier=target_id,
name=target_name,
)
if relation in PROTEIN_INCREASES_MOD_DICT:
graph.add_increases(
source,
target.with_variants(PROTEIN_INCREASES_MOD_DICT[relation]),
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
subject_modifier=SUBJECT_ACTIVITIES.get(relation),
)
# dna strand elongation
elif relation == 'psi-mi:"MI:0701"(dna strand elongation)':
target_mod = pybel.dsl.Gene(
namespace=target_prefix,
identifier=target_id,
name=target_name,
variants=[
GeneModification(
name='DNA strand elongation',
namespace='go',
identifier='0022616',
),
],
)
graph.add_increases(
source,
target_mod,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
# DECREASES
elif relation in INTACT_DECREASES_ACTIONS:
#: dna cleavage: Covalent bond breakage of a DNA molecule leading to the formation of smaller fragments
if relation == 'psi-mi:"MI:0572"(dna cleavage)':
target_mod = pybel.dsl.Gene(
namespace=target_prefix,
identifier=source_id,
name=target_name,
)
graph.add_decreases(
source,
target_mod,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
#: rna cleavage: Any process by which an RNA molecule is cleaved at specific sites or in a regulated manner
elif relation == 'psi-mi:"MI:0902"(rna cleavage)':
target_mod = pybel.dsl.Rna(
namespace=target_prefix,
identifier=source_id,
name=target_name,
)
graph.add_decreases(
source,
target_mod,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
# cleavage
elif relation in {
#: Covalent bond breakage in a molecule leading to the formation of smaller molecules
'psi-mi:"MI:0194"(cleavage reaction)',
#: Covalent modification of a polypeptide occuring during its maturation or its proteolytic degradation
'psi-mi:"MI:0570"(protein cleavage)',
}:
graph.add_decreases(
source,
target,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
#: Reaction monitoring the cleavage (hydrolysis) or a lipid molecule
elif relation == 'psi-mi:"MI:1355"(lipid cleavage)':
target_mod = target.with_variants(
pybel.dsl.ProteinModification(
name='lipid catabolic process',
namespace='go',
identifier='0016042',
), )
graph.add_decreases(
source,
target_mod,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
object_modifier=pybel.dsl.activity(),
)
#: 'lipoprotein cleavage reaction': Cleavage of a lipid group covalently bound to a protein residue
elif relation == 'psi-mi:"MI:0212"(lipoprotein cleavage reaction)':
target_mod = target.with_variants(
pybel.dsl.ProteinModification(
name='lipoprotein modification',
namespace='go',
identifier='0042160',
), )
graph.add_decreases(
source,
target_mod,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
object_modifier=pybel.dsl.activity(),
)
# deformylation reaction
elif relation == 'psi-mi:"MI:0199"(deformylation reaction)':
target_mod = target.with_variants(
pybel.dsl.ProteinModification(
name='protein formylation',
namespace='go',
identifier='0018256',
), )
graph.add_decreases(
source,
target_mod,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
# protein deamidation
elif relation == 'psi-mi:"MI:2280"(deamidation reaction)':
target_mod = target.with_variants(
pybel.dsl.ProteinModification(
name='protein amidation',
namespace='go',
identifier='0018032',
), )
graph.add_decreases(
source,
target_mod,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
object_modifier=pybel.dsl.activity(),
)
# protein decarboxylation
elif relation == 'psi-mi:"MI:1140"(decarboxylation reaction)':
target_mod = target.with_variants(
pybel.dsl.ProteinModification(
name='protein carboxylation',
namespace='go',
identifier='0018214',
), )
graph.add_decreases(
source,
target_mod,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
# protein deamination:
elif relation == 'psi-mi:"MI:0985"(deamination reaction)':
target_mod = target.with_variants(
pybel.dsl.ProteinModification(
name='amine binding',
namespace='go',
identifier='0043176',
), )
graph.add_decreases(
source,
target_mod,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
# protein modification
elif relation in PROTEIN_DECREASES_MOD_DICT:
target_mod = target.with_variants(
PROTEIN_DECREASES_MOD_DICT[relation])
graph.add_decreases(
source,
target_mod,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
else:
raise ValueError(
f"The relation {relation} is not in DECREASE relations.")
# ASSOCIATION:
elif relation in INTACT_ASSOCIATION_ACTIONS:
graph.add_association(
source,
target,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
# REGULATES:
elif relation in INTACT_REGULATES_ACTIONS:
graph.add_regulates(
source,
target,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
# BINDS
elif relation in INTACT_BINDS_ACTIONS:
graph.add_binds(
source,
target,
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
# no specified relation
else:
raise ValueError(
f"Unspecified relation {relation} between {source} and {target}")
def _add_my_row(graph: BELGraph, row) -> None:
relation = row['relation']
source_uniprot_id = row['source']
target_uniprot_id = row['target']
pubmed_ids = row['pubmed_ids']
pubmed_ids = pubmed_ids.split('|')
source = pybel.dsl.Protein(
namespace='uniprot',
identifier=source_uniprot_id,
name=get_mnemonic(source_uniprot_id),
)
target = pybel.dsl.Protein(
namespace='uniprot',
identifier=target_uniprot_id,
name=get_mnemonic(target_uniprot_id),
)
for pubmed_id in pubmed_ids:
if relation == 'deubiquitination':
target_ub = target.with_variants(
pybel.dsl.ProteinModification('Ub'))
graph.add_decreases(
source,
target_ub,
citation=pubmed_id,
evidence='From intact',
)
elif relation == 'ubiqutination':
target_ub = target.with_variants(
pybel.dsl.ProteinModification('Ub'))
graph.add_increases(
source,
target_ub,
citation=...,
evidence='From intact',
)
elif relation == 'degratation':
graph.add_decreases(
source,
target,
citation=...,
evidence='From intact',
)
elif relation == 'activates':
graph.add_increases(
source,
target,
...,
object_modifier=pybel.dsl.activity(),
)
elif relation == 'co-expressed':
graph.add_correlation(
pybel.dsl.Rna(
namespace='uniprot',
identifier=source_uniprot_id,
name=get_mnemonic(source_uniprot_id),
),
pybel.dsl.Rna(
namespace='uniprot',
identifier=target_uniprot_id,
name=get_mnemonic(target_uniprot_id),
),
annotations=dict(cell_line={'HEK2': True}),
)