def _parse(i, lines: Iterable[Tuple[str, str]]) -> Optional[Term]:
dd_: DefaultDict[str, List[str]] = defaultdict(list)
for key, value in lines:
dd_[key].append(value)
dd: Mapping[str, List[str]] = dict(dd_)
if "//" in dd:
return None
accessions = dd["AC"]
labels = dd.get("ID")
reference = Reference(
prefix="uniprot.ptm",
identifier=accessions[0],
name=labels[0] if labels else None,
)
term = Term(reference=reference)
for line in dd.get("DR", []):
line = line.rstrip(".")
for x, y in [
("MOD; ", "PSI-MOD; MOD:"),
("CHEBI; ", "ChEBI; CHEBI:"),
]:
if line.startswith(y):
line = x + line[len(y):]
ref = Reference.from_curie(line.replace("; ", ":"))
if ref:
term.append_xref(ref)
else:
tqdm.write(f"Failure on xref {line}")
return term
def get_terms(version: str, force: bool = False) -> Iterable[Term]:
"""Get terms."""
definitions = _get_definitions(version=version, force=force)
abbr_to_taxonomy = _get_organisms(version=version, force=force)
names_df = _get_names(version=version, force=force)
human_orthologs = _get_human_orthologs(version=version, force=force)
missing_taxonomies = set()
so = {}
for gtype in names_df[names_df.columns[1]].unique():
so_id = GTYPE_TO_SO.get(gtype)
if so_id is None:
logger.warning(
"FlyBase gene type is missing mapping to Sequence Ontology (SO): %s",
gtype)
else:
so[gtype] = Reference.auto("SO", so_id)
for _, reference in sorted(so.items()):
yield Term(reference=reference)
for organism, gtype, identifier, symbol, name in tqdm(names_df.values):
term = Term.from_triple(
prefix=PREFIX,
identifier=identifier,
name=symbol if pd.notna(symbol) else None,
definition=definitions.get(identifier),
)
if gtype and pd.notna(gtype) and gtype in so:
term.append_parent(so[gtype])
if pd.notna(name):
term.append_synonym(name)
for hgnc_curie in human_orthologs.get(identifier, []):
if not hgnc_curie or pd.isna(hgnc_curie):
continue
hgnc_ortholog = Reference.from_curie(hgnc_curie, auto=True)
if hgnc_ortholog is None:
tqdm.write(
f"fb:{identifier} had invalid ortholog: {hgnc_curie}")
else:
term.append_relationship(orthologous, hgnc_ortholog)
taxonomy_id = abbr_to_taxonomy.get(organism)
if taxonomy_id is not None:
term.append_relationship(from_species,
Reference(NCBITAXON_PREFIX, taxonomy_id))
elif organism not in missing_taxonomies:
tqdm.write(f"missing mapping for species abbreviation: {organism}")
missing_taxonomies.add(organism)
yield term
if missing_taxonomies:
tqdm.write(
f"there were {len(missing_taxonomies)} missing taxa in flybase genes"
)
def _extract_references(s: str) -> Iterable[Reference]:
for curie in s.split(','):
reference = Reference.from_curie(curie)
if reference is not None:
yield reference