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 get_df(version: str) -> pd.DataFrame:
"""Get a combine ComplexPortal dataframe."""
url_base = f'ftp://ftp.ebi.ac.uk/pub/databases/intact/complex/{version}/complextab'
urls = [f'{url_base}/{species}.tsv' for species in SPECIES]
dfs = [
ensure_df(PREFIX, url=url, version=version, na_values={'-'}, names=COLUMNS, header=0, dtype=DTYPE)
for url in urls
]
return pd.concat(dfs)
def get_df() -> pd.DataFrame:
"""Get a combine ComplexPortal dataframe."""
dfs = [
ensure_df(PREFIX,
url,
version=VERSION,
na_values={'-'},
names=COLUMNS,
header=0,
dtype=DTYPE) for url in URLS
]
return pd.concat(dfs)
def get_chembl_compound_equivalences_raw(usecols=None,
version: Optional[str] = None
) -> pd.DataFrame:
"""Get the chemical representations raw dataframe."""
if version is None:
version = bioversions.get_version('chembl')
base_url = f'ftp://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/releases/chembl_{version}'
url = f'{base_url}/chembl_{version}_chemreps.txt.gz'
return ensure_df(CHEMBL_COMPOUND_PREFIX,
url=url,
sep='\t',
usecols=usecols)
def get_chembl_protein_equivalences(
version: Optional[str] = None) -> pd.DataFrame:
"""Get ChEMBL protein equivalences."""
if version is None:
version = bioversions.get_version('chembl')
url = f'ftp://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/releases/chembl_{version}/chembl_uniprot_mapping.txt'
df = ensure_df(
CHEMBL_TARGET_PREFIX,
url=url,
sep='\t',
usecols=[0, 1],
names=[TARGET_ID, SOURCE_ID], # switch around
)
df.loc[:, SOURCE_PREFIX] = 'chembl.target'
df.loc[:, TARGET_PREFIX] = 'uniprot'
df.loc[:, PROVENANCE] = f'chembl{version}'
df = df[XREF_COLUMNS]
return df
def iter_terms(version: str) -> Iterable[Term]:
"""Iterate over DrugCentral terms."""
df = ensure_df(PREFIX, url=URL, version=version)
for smiles, inchi, inchi_key, drugcentral_id, drugcentral_name, cas in df.values:
if pd.isna(smiles) or pd.isna(inchi) or pd.isna(inchi_key):
logger.warning('missing data for drugcentral:%s', drugcentral_id)
continue
xrefs = [
Reference(prefix='smiles', identifier=smiles),
Reference(prefix='inchi', identifier=inchi),
Reference(prefix='inchikey', identifier=inchi_key),
]
if pd.notna(cas):
xrefs.append(Reference(prefix='cas', identifier=cas))
yield Term(
reference=Reference(prefix=PREFIX,
identifier=drugcentral_id,
name=drugcentral_name),
xrefs=xrefs,
)
def get_df() -> pd.DataFrame:
"""Get the BioGRID identifiers mapping dataframe."""
df = ensure_df(PREFIX, URL, skiprows=28, dtype=str)
df['taxonomy_id'] = df['ORGANISM_OFFICIAL_NAME'].map(_lookup)
return df
def get_terms(version: str) -> Iterable[Term]:
"""Get the FamPlex terms."""
entities_url = f'https://raw.githubusercontent.com/sorgerlab/famplex/{version}/entities.csv'
entities_df = ensure_df(PREFIX,
url=entities_url,
version=version,
dtype=str)
relations_url = f'https://raw.githubusercontent.com/sorgerlab/famplex/{version}/relations.csv'
relations_df = ensure_df(PREFIX,
url=relations_url,
version=version,
header=None,
sep=',',
dtype=str)
# TODO add xrefs
# xrefs_url = f'https://raw.githubusercontent.com/sorgerlab/famplex/{version}/equivalences.csv'
# xrefs_df = ensure_df(PREFIX, url=xrefs_url, version=version, header=None, sep=',', dtype=str)
hgnc_name_to_id = get_name_id_mapping('hgnc')
in_edges = defaultdict(list)
out_edges = defaultdict(list)
for h_ns, h_name, r, t_ns, t_name in relations_df.values:
if h_ns == 'HGNC':
h_identifier = hgnc_name_to_id.get(h_name)
if h_identifier is None:
logger.warning(
'[%s] could not look up HGNC identifier for gene: %s',
PREFIX, h_name)
h = Reference(prefix='hgnc', identifier=h_identifier, name=h_name)
elif h_ns == 'FPLX':
h = Reference(prefix='fplx', identifier=h_name, name=h_name)
elif h_ns == 'UP':
continue
else:
print(h_ns)
raise
if t_ns == 'HGNC':
t_identifier = hgnc_name_to_id.get(t_name)
if t_identifier is None:
logger.warning(
'[%s] could not look up HGNC identifier for gene: %s',
PREFIX, t_name)
t = Reference(prefix='hgnc', identifier=t_identifier, name=t_name)
elif t_ns == 'FPLX':
t = Reference(prefix='fplx', identifier=t_name, name=t_name)
elif h_ns == 'UP':
continue
else:
raise
out_edges[h].append((r, t))
in_edges[t].append((r, h))
for entity, in entities_df.values:
reference = Reference(prefix=PREFIX, identifier=entity, name=entity)
term = Term(reference=reference)
for r, t in out_edges.get(reference, []):
if r == 'isa' and t.prefix == 'fplx':
term.append_parent(t)
elif r == 'isa':
term.append_relationship(is_a, t)
elif r == 'partof':
term.append_relationship(part_of, t)
else:
logging.warning('unhandled relation %s', r)
for r, h in in_edges.get(reference, []):
if r == 'isa':
term.append_relationship(has_member, h)
elif r == 'partof':
term.append_relationship(has_part, h)
else:
logging.warning('unhandled relation %s', r)
yield term