def main():
"""Build NSoC-KG."""
biogrid_version = bioversions.get_version("biogrid")
homolgene_version = bioversions.get_version("homologene")
disgenet_version = bioversions.get_version("disgenet")
excape_version = EXCAPE_VERSION
versions = {
"biogrid": biogrid_version,
"homologene": homolgene_version,
"excape": excape_version,
"disgenet": disgenet_version,
}
statistics = {}
triples_path = NSOCKG_MODULE.join(name="triples.tsv")
with triples_path.open("w") as file:
_excape(statistics, file, excape_version)
_biogrid(statistics, file, biogrid_version)
_homologene(statistics, file, homolgene_version)
_disgenet(statistics, file, disgenet_version)
# Count everything
statistics["total"] = sum(statistics.values())
rows = [(key, versions[key], statistics[key]) for key in sorted(versions)]
rows.append(("total", "", statistics["total"]))
print(tabulate(rows, headers=["Source", "Version", "Edges"]))
metadata_path = NSOCKG_MODULE.join(name="metadata.json")
with metadata_path.open("w") as file:
json.dump(
fp=file,
indent=2,
obj={
"date": datetime.datetime.now().strftime("%Y-%m-%d"),
"exporter": getpass.getuser(),
"versions": versions,
"statistics": statistics,
},
)
# Automatically upload this revision to Zenodo
ensure_zenodo(
key="nsockg",
data=metadata,
paths=[
triples_path,
metadata_path,
],
)
def get_bel() -> pybel.BELGraph:
"""Get the Rhea data."""
version = bioversions.get_version('rhea')
# Parse the RDF file
g = BIO2BEL_MODULE.ensure_rdf('rhea', version, url=URL)
# Get a list of all the reactions in the database
# (the bidirectionalReaction criterion is added to ensure that we only recieve the nondirectional version of a given reaction)
rxns = g.query(
"""
SELECT ?reaction ?id ?reactionEquation WHERE {
?reaction rh:equation ?reactionEquation .
?reaction rh:bidirectionalReaction ?bdr .
?reaction rh:id ?id
}
""",
)
rv = pybel.BELGraph(name='rhea', version=version)
# Loop over reactions, adding reaction nodes to rv as we go
# Rather than converting to a set (time-consuming), just let the PyBEL graph handle the occasional duplicate
for (reaction_uri, reaction_id, reaction_equation) in rxns:
# Retrieve the reactants and products of the reaction
participants = _participants(g, reaction_uri)
# Add a reaction node to the BELGraph
reaction = dsl.Reaction(
participants['reactants'],
participants['products'],
namespace='RHEA',
name=reaction_equation,
identifier=reaction_id,
)
rv.add_node_from_data(reaction)
return rv
def get_df() -> pd.DataFrame:
"""Get the BioGRID identifiers mapping dataframe."""
version = bioversions.get_version('biogrid')
url = f'{BASE_URL}/BIOGRID-{version}/BIOGRID-IDENTIFIERS-{version}.tab.zip'
df = ensure_df(PREFIX, url=url, skiprows=28, dtype=str, version=version)
df['taxonomy_id'] = df['ORGANISM_OFFICIAL_NAME'].map(_lookup)
return df
def ensure(version: Optional[str] = None) -> Path:
"""Ensure the reviewed uniprot names are available."""
if version is None:
version = bioversions.get_version('uniprot')
return RAW_MODULE.ensure(PREFIX,
version,
name='reviewed.tsv.gz',
url=REVIEWED_URL)
def get_chembl_xrefs_df(version: Optional[str] = None) -> pd.DataFrame:
"""Get all ChEBML equivalences."""
if version is None:
version = bioversions.get_version('chembl')
return pd.concat([
get_chembl_compound_equivalences(version=version),
get_chembl_protein_equivalences(version=version),
])
def ensure(version: Optional[str] = None, force: bool = False) -> Path:
"""Ensure the reviewed uniprot names are available."""
if version is None:
version = bioversions.get_version("uniprot")
return RAW_MODULE.ensure(PREFIX,
version,
name="reviewed.tsv.gz",
url=REVIEWED_URL,
force=force)
def test_get(self):
"""Test getters."""
prefixes = [
"reactome",
"kegg",
]
for prefix in prefixes:
with self.subTest(prefix=prefix):
s = bioversions.get_version(prefix)
self.assertIsInstance(s, str)
def get_pubchem_mesh_df(version: Optional[str] = None) -> pd.DataFrame:
"""Get PubChem Compound-MeSH xrefs."""
if version is None:
version = bioversions.get_version("pubchem")
cid_mesh_url = _get_pubchem_extras_url(version, "CID-MeSH")
return pd.DataFrame(
[("pubchem.compound", k, "mesh", v, cid_mesh_url)
for k, v in get_pubchem_id_to_mesh_id(version=version).items()],
columns=XREF_COLUMNS,
)
def get_obo() -> Obo:
"""Get miRBase mature as OBO."""
version = bioversions.get_version("mirbase")
return Obo(
ontology=PREFIX,
name="miRBase Mature",
auto_generated_by=f"bio2obo:{PREFIX}",
data_version=version,
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
)
def get_obo() -> Obo:
"""Get MeSH as OBO."""
version = bioversions.get_version("mesh")
return Obo(
ontology=PREFIX,
name="Medical Subject Headings",
iter_terms=get_terms,
iter_terms_kwargs=dict(version=version),
data_version=version,
auto_generated_by=f"bio2obo:{PREFIX}",
)
def get_obo() -> Obo:
"""Return ChEMBL as OBO."""
version = bioversions.get_version("chembl")
return Obo(
ontology="chembl.compound",
name="ChEMBL",
data_version=version,
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
auto_generated_by=f"bio2obo:{PREFIX}",
)
def get_obo() -> Obo:
"""Get DrugBank Salts as OBO."""
version = bioversions.get_version('drugbank')
return Obo(
ontology=PREFIX,
name='DrugBank Salts',
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
data_version=version,
auto_generated_by=f'bio2obo:{PREFIX}',
)
def get_obo() -> Obo:
"""Get DrugCentral OBO."""
version = bioversions.get_version(PREFIX)
return Obo(
ontology=PREFIX,
name='DrugCentral',
data_version=version,
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
auto_generated_by=f'bio2obo:{PREFIX}',
)
def get_obo() -> Obo:
"""Get miRBase family as OBO."""
version = bioversions.get_version('mirbase')
return Obo(
ontology=PREFIX,
name='miRBase Families',
auto_generated_by=f'bio2obo:{PREFIX}',
data_version=version,
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
)
def get_obo() -> Obo:
"""Get PFAM as OBO."""
version = bioversions.get_version("pfam")
return Obo(
ontology=PREFIX,
name="PFAM",
data_version=version,
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
auto_generated_by=f"bio2obo:{PREFIX}",
)
def get_obo() -> Obo:
"""Get PFAM Clans as OBO."""
version = bioversions.get_version('pfam')
return Obo(
ontology=PREFIX,
name='PFAM Clans',
data_version=version,
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
auto_generated_by=f'bio2obo:{PREFIX}',
)
def get_obo() -> Obo:
"""Get KEGG Genome as OBO."""
version = bioversions.get_version("kegg")
return Obo(
ontology=KEGG_GENOME_PREFIX,
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
name="KEGG Genome",
data_version=version,
auto_generated_by=f"bio2obo:{KEGG_GENOME_PREFIX}",
)
def get_obo() -> Obo:
"""Return ChEMBL as OBO."""
version = bioversions.get_version('chembl')
return Obo(
ontology='chembl.compound',
name='ChEMBL',
data_version=version,
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
auto_generated_by=f'bio2obo:{PREFIX}',
)
def get_obo() -> Obo:
"""Get NPASS as OBO."""
version = bioversions.get_version('npass')
return Obo(
ontology=PREFIX,
name='Natural Products Activity and Species Source Database',
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
auto_generated_by=f'bio2obo:{PREFIX}',
pattern=r'NPC\d+',
)
def get_obo() -> Obo:
"""Get ExPASy as OBO."""
version = bioversions.get_version("expasy")
return Obo(
ontology=PREFIX,
name="ExPASy Enzyme Nomenclature",
iter_terms=get_terms,
iter_terms_kwargs=dict(version=version),
data_version=version,
typedefs=[has_member, has_molecular_function],
auto_generated_by=f"bio2obo:{PREFIX}",
)
def get_obo() -> Obo:
"""Get Rhea as OBO."""
version = bioversions.get_version(PREFIX)
return Obo(
ontology=PREFIX,
name='Rhea',
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
data_version=version,
auto_generated_by=f'bio2obo:{PREFIX}',
typedefs=[has_lr, has_bi, has_rl],
)
def get_obo(force: bool = False) -> Obo:
"""Get DrugBank as OBO."""
version = bioversions.get_version('drugbank')
return Obo(
ontology=PREFIX,
name='DrugBank',
data_version=version,
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version, force=force),
auto_generated_by=f'bio2obo:{PREFIX}',
typedefs=[has_salt],
)
def get_obo(skip_missing: bool = True) -> Obo:
"""Get KEGG Pathways as OBO."""
version = bioversions.get_version('kegg')
return Obo(
ontology=KEGG_PATHWAY_PREFIX,
iter_terms=iter_terms,
iter_terms_kwargs=dict(skip_missing=skip_missing, version=version),
name='KEGG Pathways',
typedefs=[from_kegg_species, from_species, species_specific, has_part],
auto_generated_by=f'bio2obo:{KEGG_PATHWAY_PREFIX}',
data_version=version,
)
def get_obo() -> Obo:
"""Get miRBase as OBO."""
version = bioversions.get_version(PREFIX)
return Obo(
ontology=PREFIX,
name="miRBase",
iter_terms=get_terms,
iter_terms_kwargs=dict(version=version),
typedefs=[from_species, has_mature],
data_version=version,
auto_generated_by=f"bio2obo:{PREFIX}",
)
def get_obo() -> Obo:
"""Get KEGG Genes as OBO."""
version = bioversions.get_version("kegg")
return Obo(
ontology=KEGG_GENES_PREFIX,
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
typedefs=[from_species, from_kegg_species, has_gene_product],
name="KEGG Genes",
data_version=version,
auto_generated_by=f"bio2obo:{KEGG_GENES_PREFIX}",
)
def get_obo() -> Obo:
"""Get MSIG as Obo."""
version = bioversions.get_version(PREFIX)
return Obo(
ontology=PREFIX,
name='Molecular Signatures Database',
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
data_version=version,
auto_generated_by=f'bio2obo:{PREFIX}',
typedefs=[has_part],
)
def get_obo() -> Obo:
"""Get Reactome OBO."""
version = bioversions.get_version('reactome')
return Obo(
ontology=PREFIX,
name='Reactome',
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
typedefs=[from_species, has_part],
data_version=version,
auto_generated_by=f'bio2obo:{PREFIX}',
)
def get_obo() -> Obo:
"""Get InterPro as OBO."""
version = bioversions.get_version(PREFIX)
return Obo(
ontology=PREFIX,
name="InterPro",
data_version=version,
auto_generated_by=f"bio2obo:{PREFIX}",
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
)
def _ensure_cid_name_path(*,
version: Optional[str] = None,
force: bool = False) -> str:
if version is None:
version = bioversions.get_version("pubchem")
# 2 tab-separated columns: compound_id, name
cid_name_url = _get_pubchem_extras_url(version, "CID-Title.gz")
cid_name_path = ensure_path(PREFIX,
url=cid_name_url,
version=version,
force=force)
return cid_name_path
def get_obo() -> Obo:
"""Get WikiPathways as OBO."""
version = bioversions.get_version('uniprot')
return Obo(
ontology=PREFIX,
name='UniProt',
data_version=version,
iter_terms=iter_terms,
iter_terms_kwargs=dict(version=version),
typedefs=[from_species],
auto_generated_by=f'bio2obo:{PREFIX}',
)
