def get_terms(version: str, force: bool = False) -> Iterable[Term]:
"""Get terms."""
orthologs_df = ensure_df(PREFIX,
url=ORTHOLOGS_URL,
force=force,
header=None,
version=version)
identifier_to_hgnc_ids = defaultdict(set)
hgnc_symbol_to_id = pyobo.get_name_id_mapping("hgnc")
for identifier, hgnc_symbols in orthologs_df.values:
if hgnc_symbols == "NONE":
continue
for hgnc_symbol in hgnc_symbols.split("|"):
hgnc_id = hgnc_symbol_to_id.get(hgnc_symbol)
if hgnc_id is not None:
identifier_to_hgnc_ids[identifier].add(hgnc_id)
df = ensure_df(PREFIX, url=URL, force=force, header=None, version=version)
so = {
gtype: Reference.auto("SO", POMBASE_TO_SO[gtype])
for gtype in sorted(df[df.columns[6]].unique())
}
for _, reference in sorted(so.items()):
yield Term(reference=reference)
for identifier, _, symbol, chromosome, name, uniprot_id, gtype, synonyms in tqdm(
df.values):
term = Term.from_triple(
prefix=PREFIX,
identifier=identifier,
name=symbol if pd.notna(symbol) else None,
definition=name if pd.notna(name) else None,
)
term.append_property("chromosome", chromosome[len("chromosome_"):])
term.append_parent(so[gtype])
term.set_species(identifier="4896", name="Schizosaccharomyces pombe")
for hgnc_id in identifier_to_hgnc_ids.get(identifier, []):
term.append_relationship(orthologous,
Reference.auto("hgnc", hgnc_id))
if uniprot_id and pd.notna(uniprot_id):
term.append_relationship(has_gene_product,
Reference.auto("uniprot", uniprot_id))
if synonyms and pd.notna(synonyms):
for synonym in synonyms.split(","):
term.append_synonym(Synonym(synonym))
yield 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"
)