def _add_my_row(
graph: BELGraph,
relation: str,
source_ncbigene_id: str,
target_ncbigene_id: str,
pubmed_id: str,
int_detection_method: str,
source_database: str,
confidence: str,
) -> None: # noqa:C901
"""Add an edge with information about relationship type, source, and target for every PubMed ID.
:param graph: graph to add edges to
:param relation: row value of column relation
:param source_ncbigene_id: row value of column source
:param target_ncbigene_id: row value of column target
:param pubmed_id: row value of column pubmed_id
:param int_detection_method: row value of column interaction detection method
"""
annotations = {
'psi-mi': relation,
'biogrid-detection': int_detection_method,
'biogrid-source': source_database,
'biogrid-confidence': confidence,
}
if relation in BIOGRID_GENE_ASSOCIATION:
graph.add_association(
pybel.dsl.Gene(namespace='ncbigene',
identifier=source_ncbigene_id),
pybel.dsl.Gene(namespace='ncbigene',
identifier=target_ncbigene_id),
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
elif relation in BIOGRID_ASSOCIATION_ACTIONS:
graph.add_association(
pybel.dsl.Protein(namespace='ncbigene',
identifier=source_ncbigene_id),
pybel.dsl.Protein(namespace='ncbigene',
identifier=target_ncbigene_id),
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
elif relation in BIOGRID_BINDS_ACTIONS:
graph.add_binds(
pybel.dsl.Protein(namespace='ncbigene',
identifier=source_ncbigene_id),
pybel.dsl.Protein(namespace='ncbigene',
identifier=target_ncbigene_id),
citation=pubmed_id,
evidence=EVIDENCE,
annotations=annotations,
)
else:
raise ValueError(f'Unhandled BioGrid relation: {relation}')
def _add_rows(df: pd.DataFrame, graph: BELGraph) -> None:
for _, row in df.iterrows():
effect = row['effect']
if effect == 0:
continue # no binding. Could add negative BEL later
tf_protein = pybel.dsl.Protein(
namespace='hgnc',
identifier=row['tf_hgnc_id'],
name=row['tf_hgnc_symbol'],
)
target_rna = pybel.dsl.Rna(
namespace='hgnc',
identifier=row['target_hgnc_id'],
name=row['target_hgnc_symbol'],
)
target_gene = target_rna.get_gene()
if 'pmids' in row:
citations = [pmid.strip() for pmid in row['pmids'].split(',')]
else:
citations = ['31340985']
evidence = 'From TFregulons'
for citation in citations:
graph.add_binds(
tf_protein,
target_gene,
citation=citation,
evidence=evidence,
)
if effect == 1:
binds_dna_adder, affects_expression_adder = graph.add_directly_increases, graph.add_increases
else:
binds_dna_adder, affects_expression_adder = graph.add_directly_decreases, graph.add_decreases
binds_dna_adder(
pybel.dsl.ComplexAbundance([tf_protein, target_gene]),
target_rna,
citation=citation,
evidence=evidence,
)
affects_expression_adder(
tf_protein,
target_rna,
citation=citation,
evidence=evidence,
)
graph.add_transcription(target_gene, target_rna)
def get_graph_from_cx(network_uuid: str, cx: CX) -> BELGraph: # noqa: C901
"""Get a PID network from NDEx."""
metadata = {}
for entry in iterate_aspect(cx, 'networkAttributes'):
member_name = entry['n']
if member_name == 'name':
metadata['name'] = entry['v']
elif member_name == 'version':
metadata['version'] = entry['v']
elif member_name == 'description':
metadata['description'] = entry['v']
graph = BELGraph(**metadata)
id_to_type = {}
id_to_members = {}
id_to_alias = {}
# TODO nodeAttributes have list of protein definitions for some things
for entry in iterate_aspect(cx, 'nodeAttributes'):
node_id = entry['po']
member_name = entry['n']
if member_name == 'type':
id_to_type[node_id] = entry['v']
elif member_name == 'alias':
id_to_alias[node_id] = entry['v']
elif member_name == 'member':
id_to_members[node_id] = entry['v']
else:
logger.warning(f'unhandled node attribute: {member_name}')
id_to_citations = {}
for entry in iterate_aspect(cx, 'edgeAttributes'):
if entry['n'] == 'citation':
id_to_citations[entry['po']] = [
x[len('pubmed:'):] for x in entry['v']
]
id_to_dsl = {}
for node in iterate_aspect(cx, 'nodes'):
node_id = node['@id']
reference = node['r']
if reference in MAPPING:
id_to_dsl[node_id] = [MAPPING[reference]]
continue
if node_id in id_to_members:
node_type = id_to_type[node_id]
members = id_to_members[node_id]
if node_type != 'proteinfamily':
logger.warning(
f'unhandled node: {node_id} type={node_type} members={members}'
)
_rv = []
for member in members:
if not member.startswith('hgnc.symbol:'):
logger.warning(
f'unhandled member for node: {node_id} -> {member}')
continue
member_name = member[len('hgnc.symbol:'):]
member_identifier = _get_hgnc_id_from_name(member_name)
if member_identifier is None:
logger.warning(
f'unhandled member for node: {node_id} -> {member}')
continue
_rv.append(
pybel.dsl.Protein(namespace='hgnc',
identifier=member_identifier,
name=member_name))
id_to_dsl[node_id] = _rv
continue
if ':' not in reference:
logger.warning(f'no curie: {node_id} {reference}')
UNMAPPED.add(reference)
continue
prefix, identifier = reference.split(':')
if prefix == 'hprd':
# nodes.write(f'unhandled hprd:{identifier}')
continue
elif prefix == 'cas':
# nodes.write(f'unhandled cas:{identifier}')
continue # not sure what to do with this
elif prefix == 'CHEBI':
name = get_name('chebi', identifier)
id_to_dsl[node_id] = [
pybel.dsl.Abundance(namespace='chebi',
identifier=identifier,
name=name)
]
elif prefix == 'uniprot':
name = node['n']
hgnc_id = _get_hgnc_id_from_name(name)
if hgnc_id:
name = _get_gene_name(identifier)
if name is None:
logger.warning('could not map uniprot to name')
if identifier is None:
logger.warning(f'could not map HGNC symbol {name}')
continue
id_to_dsl[node_id] = [
pybel.dsl.Protein(namespace='hgnc',
identifier=identifier,
name=name)
]
else:
logger.warning(f'unexpected prefix: {prefix}')
continue
for edge in iterate_aspect(cx, 'edges'):
source_id, target_id = edge['s'], edge['t']
if source_id not in id_to_dsl or target_id not in id_to_dsl:
continue
edge_type = edge['i']
edge_id = edge['@id']
sources = id_to_dsl[source_id]
targets = id_to_dsl[target_id]
citations = id_to_citations.get(edge_id, [('ndex', network_uuid)])
for source, target, citation in product(sources, targets, citations):
if edge_type == 'in-complex-with':
graph.add_binds(source,
target,
citation=citation,
evidence=edge_id)
elif edge_type == 'controls-phosphorylation-of':
graph.add_regulates(
source,
target.with_variants(pybel.dsl.ProteinModification('Ph')),
citation=citation,
evidence=edge_id,
)
elif edge_type in {
'controls-transport-of', 'controls-transport-of-chemical'
}:
graph.add_regulates(
source,
target,
citation=citation,
evidence=edge_id,
# object_modifier=pybel.dsl.translocation(),
)
elif edge_type == 'chemical-affects':
graph.add_regulates(
source,
target,
citation=citation,
evidence=edge_id,
object_modifier=pybel.dsl.activity(),
)
elif edge_type in {
'controls-expression-of', 'controls-production-of',
'consumption-controlled-by', 'controls-state-change-of',
'catalysis-precedes'
}:
graph.add_regulates(source,
target,
citation=citation,
evidence=edge_id)
elif edge_type == 'used-to-produce':
graph.add_node_from_data(
pybel.dsl.Reaction(
reactants=source,
products=target,
))
elif edge_type == 'reacts-with':
graph.add_binds(source,
target,
citation=citation,
evidence=edge_id)
# graph.add_node_from_data(pybel.dsl.Reaction(
# reactants=[source, target],
# ))
else:
logger.warning(
f'unhandled edge type: {source} {edge_type} {target}')
return graph
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}")