def _parse_xrefs(s) -> List[Tuple[Reference, str]]:
if pd.isna(s):
return []
rv = []
for xref in s.split("|"):
xref = xref.replace("protein ontology:PR:", "PR:")
xref = xref.replace("protein ontology:PR_", "PR:")
try:
xref_curie, note = xref.split("(")
except ValueError:
logger.warning("xref missing (: %s", xref)
continue
note = note.rstrip(")")
try:
reference = Reference.from_curie(xref_curie)
except ValueError:
logger.warning("can not parse CURIE: %s", xref)
continue
if reference is None:
logger.warning("reference is None after parsing: %s", xref)
continue
rv.append((reference, note))
return rv
def _parse_xrefs(s) -> List[Tuple[Reference, str]]:
if pd.isna(s):
return []
rv = []
for xref in s.split('|'):
xref = xref.replace('protein ontology:PR:', 'PR:')
xref = xref.replace('protein ontology:PR_', 'PR:')
try:
xref_curie, note = xref.split('(')
except ValueError:
logger.warning('xref missing (: %s', xref)
continue
note = note.rstrip(')')
try:
reference = Reference.from_curie(xref_curie)
except ValueError:
logger.warning('can not parse CURIE: %s', xref)
continue
if reference is None:
logger.warning('reference is None after parsing: %s', xref)
continue
rv.append((reference, note))
return rv
def get_terms(version: str, force: bool = False) -> Iterable[Term]:
"""Get the FamPlex terms."""
base_url = f'https://raw.githubusercontent.com/sorgerlab/famplex/{version}'
entities_url = f'{base_url}/entities.csv'
entities_df = ensure_df(PREFIX, url=entities_url, version=version, dtype=str, force=force)
relations_url = f'{base_url}/relations.csv'
relations_df = ensure_df(PREFIX, url=relations_url, version=version, header=None, sep=',', dtype=str, force=force)
definitions_url = f'{base_url}/descriptions.csv'
definitions_df = ensure_df(
PREFIX, url=definitions_url, version=version, header=None, sep=',', dtype=str, force=force,
)
id_to_definition = {
identifier: (definition, provenance)
for identifier, provenance, definition in definitions_df.values
}
# 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:
logger.exception(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)
definition, provenance = id_to_definition.get(entity, (None, None))
term = Term(
reference=reference,
definition=definition,
provenance=[Reference.from_curie(provenance)] if definition is not None else None,
)
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
def get_terms(version: str, force: bool = False) -> Iterable[Term]:
"""Get the FamPlex terms."""
base_url = f"https://raw.githubusercontent.com/sorgerlab/famplex/{version}"
entities_url = f"{base_url}/entities.csv"
entities_df = ensure_df(PREFIX,
url=entities_url,
version=version,
dtype=str,
force=force)
relations_url = f"{base_url}/relations.csv"
relations_df = ensure_df(PREFIX,
url=relations_url,
version=version,
header=None,
sep=",",
dtype=str,
force=force)
definitions_url = f"{base_url}/descriptions.csv"
definitions_df = ensure_df(
PREFIX,
url=definitions_url,
version=version,
header=None,
sep=",",
dtype=str,
force=force,
)
id_to_definition = {
identifier: (definition, provenance)
for identifier, provenance, definition in definitions_df.values
}
id_xrefs = _get_xref_df(version)
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:
logger.exception(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)
definition, provenance = id_to_definition.get(entity, (None, None))
term = Term(
reference=reference,
definition=definition,
provenance=[Reference.from_curie(provenance)]
if definition is not None else None,
)
for xref_reference in id_xrefs.get(entity, []):
term.append_xref(xref_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
def get_terms(force: bool = False,
version: Optional[str] = None) -> Iterable[Term]:
"""Get terms."""
alt_ids_df = ensure_df(
PREFIX,
url=ALTS_URL,
name="alts.tsv",
force=force,
header=None,
names=["alt", "zfin_id"],
version=version,
)
primary_to_alt_ids = defaultdict(set)
for alt_id, zfin_id in alt_ids_df.values:
primary_to_alt_ids[zfin_id].add(alt_id)
human_orthologs = multisetdict(
ensure_df(PREFIX,
url=HUMAN_ORTHOLOGS,
force=force,
header=None,
usecols=[0, 7],
version=version).values)
mouse_orthologs = multisetdict(
ensure_df(PREFIX,
url=MOUSE_ORTHOLOGS,
force=force,
header=None,
usecols=[0, 5],
version=version).values)
fly_orthologs = multisetdict(
ensure_df(PREFIX,
url=FLY_ORTHOLOGS,
force=force,
header=None,
usecols=[0, 5],
version=version).values)
entrez_mappings = dict(
ensure_df(PREFIX,
url=ENTREZ_MAPPINGS,
force=force,
header=None,
usecols=[0, 3],
version=version).values)
uniprot_mappings = multidict(
ensure_df(PREFIX,
url=UNIPROT_MAPPINGS,
force=force,
header=None,
usecols=[0, 3],
version=version).values)
df = ensure_df(
PREFIX,
url=URL,
name="markers.tsv",
force=force,
header=None,
names=MARKERS_COLUMNS,
version=version,
)
df["sequence_ontology_id"] = df["sequence_ontology_id"].map(
lambda x: x[len("SO:"):])
so = {
sequence_ontology_id: Reference.auto(prefix="SO",
identifier=sequence_ontology_id)
for sequence_ontology_id in df["sequence_ontology_id"].unique()
}
for _, reference in sorted(so.items()):
yield Term(reference=reference)
for identifier, name, definition, _entity_type, sequence_ontology_id in tqdm(
df.values):
term = Term.from_triple(
prefix=PREFIX,
identifier=identifier,
name=name,
definition=definition if definition != name else None,
)
term.set_species(identifier="7955", name="Danio rerio")
term.append_parent(so[sequence_ontology_id])
# Entity type is redundant of identifier
# term.append_property("type", entity_type)
for alt_id in primary_to_alt_ids[identifier]:
term.append_alt(alt_id)
entrez_id = entrez_mappings.get(identifier)
if entrez_id:
term.append_xref(Reference("ncbigene", entrez_id))
for uniprot_id in uniprot_mappings.get(identifier, []):
term.append_relationship(has_gene_product,
Reference.auto("uniprot", uniprot_id))
for hgnc_id in human_orthologs.get(identifier, []):
term.append_relationship(orthologous,
Reference.auto("hgnc", hgnc_id))
for mgi_curie in mouse_orthologs.get(identifier, []):
mouse_ortholog = Reference.from_curie(mgi_curie, auto=True)
if mouse_ortholog:
term.append_relationship(orthologous, mouse_ortholog)
for flybase_id in fly_orthologs.get(identifier, []):
term.append_relationship(orthologous,
Reference("flybase", flybase_id))
yield term