def setUp(self):
identifier_parser = ConceptParser()
self.parser = get_gene_modification_language(
concept_fqualified=identifier_parser.identifier_fqualified,
concept_qualified=identifier_parser.identifier_qualified,
)
self.expected = GeneModification('Me')
def test_gmod_default(self, mock):
"""Test a gene modification that uses the BEL default namespace."""
dummy_namespace = n()
dummy_name = n()
node_data = Gene(namespace=dummy_namespace,
name=dummy_name,
variants=[GeneModification('Me')])
self._help_reconstitute(node_data, 2, 1)
def test_canonicalize_variant_dsl(self):
"""Use the __str__ functions in the DSL to create BEL instead of external pybel.canonicalize."""
self.assertEqual('var("p.Val600Glu")', str(Hgvs('p.Val600Glu')))
self.assertEqual('var("p.Val600Glu")',
str(ProteinSubstitution('Val', 600, 'Glu')))
self.assertEqual('pmod(go:0006468 ! "protein phosphorylation")',
str(ProteinModification('Ph')))
self.assertEqual('pmod(TEST:Ph)',
str(ProteinModification('Ph', namespace='TEST')))
self.assertEqual(
'pmod(TEST:Ph, Ser)',
str(ProteinModification('Ph', namespace='TEST', code='Ser')))
self.assertEqual(
'pmod(TEST:Ph, Ser, 5)',
str(
ProteinModification('Ph',
namespace='TEST',
code='Ser',
position=5)))
self.assertEqual(
'pmod(GO:"protein phosphorylation", Thr, 308)',
str(
ProteinModification(name='protein phosphorylation',
namespace='GO',
code='Thr',
position=308)))
self.assertEqual('frag("?")', str(Fragment()))
self.assertEqual('frag("672_713")', str(Fragment(start=672, stop=713)))
self.assertEqual('frag("?", "descr")',
str(Fragment(description='descr')))
self.assertEqual(
'frag("672_713", "descr")',
str(Fragment(start=672, stop=713, description='descr')))
self.assertEqual('gmod(go:0006306 ! "DNA methylation")',
str(GeneModification('Me')))
self.assertEqual('gmod(TEST:Me)',
str(GeneModification('Me', namespace='TEST')))
self.assertEqual(
'gmod(GO:"DNA Methylation")',
str(GeneModification('DNA Methylation', namespace='GO')))
def test_gmod_custom(self, mock):
"""Tests a gene modification that uses a non-default namespace"""
dummy_namespace = 'HGNC'
dummy_name = 'AKT1'
dummy_mod_namespace = 'GO'
dummy_mod_name = 'DNA Methylation'
node_data = Gene(namespace=dummy_namespace,
name=dummy_name,
variants=[
GeneModification(name=dummy_mod_name,
namespace=dummy_mod_namespace)
])
self._help_reconstitute(node_data, 2, 1)
akt1 = hgnc(name='AKT1')
egfr = hgnc(name='EGFR')
fadd = hgnc(name='FADD')
casp8 = hgnc(name='CASP8')
mia = hgnc(name='MIA')
il6 = Protein('HGNC', 'IL6')
adgrb1 = Protein(namespace='HGNC', name='ADGRB1')
adgrb2 = Protein(namespace='HGNC', name='ADGRB2')
adgrb_complex = ComplexAbundance([adgrb1, adgrb2])
achlorhydria = Pathology(namespace='MESHD', name='Achlorhydria')
akt1_rna = akt1.get_rna()
akt1_gene = akt1_rna.get_gene()
akt_methylated = akt1_gene.with_variants(GeneModification('Me'))
akt1_phe_508_del = akt1_gene.with_variants(Hgvs('p.Phe508del'))
cftr = hgnc('CFTR')
cftr_protein_unspecified_variant = cftr.with_variants(HgvsUnspecified())
cftr_protein_phe_508_del = cftr.with_variants(Hgvs('p.Phe508del'))
adenocarcinoma = Pathology('MESHD', 'Adenocarcinoma')
interleukin_23_complex = NamedComplexAbundance('GO', 'interleukin-23 complex')
oxygen_atom = Abundance(namespace='CHEBI', name='oxygen atom')
hydrogen_peroxide = Abundance('CHEBI', 'hydrogen peroxide')
tmprss2_gene = Gene('HGNC', 'TMPRSS2')
tmprss2_erg_gene_fusion = GeneFusion(
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}")