def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
"""Iterate over terms from GWAS Central Phenotype."""
for n in trange(1, 11000, desc=f"{PREFIX} download"):
try:
path = ensure_path(
PREFIX,
"phenotype",
version=version,
url=
f"https://www.gwascentral.org/phenotype/HGVPM{n}?format=json",
name=f"HGVPM{n}.json",
force=force,
)
except OSError as e:
tqdm.write(f"{n}: {e}")
continue
with open(path) as file:
j = json.load(file)
description = j.get("description")
if description is not None:
description = description.strip().replace("\n", " ")
term = Term(
reference=Reference(PREFIX, j["identifier"], j["name"]),
definition=description,
)
yield term
def _get_version() -> str:
"""Get the version of the current data."""
zip_path = ensure_path(PREFIX, url=URL)
with zipfile.ZipFile(zip_path) as zip_file:
for x in zip_file.filelist:
if x.filename.endswith('.sqlite'):
return x.filename[len('itisSqlite'):-len('/ITIS.sqlite')]
raise ValueError('could not find a file with the version in it')
def get_path(version: str):
"""Get the path to the extracted ChEMBL SQLite database."""
url = f'ftp://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/releases/chembl_{version}/chembl_{version}_sqlite.tar.gz'
path = ensure_path(PREFIX, url=url, version=version)
name = f'chembl_{version}/chembl_{version}_sqlite/chembl_{version}.db'
d = prefix_directory_join(PREFIX, version=version)
op = os.path.join(d, name)
if not os.path.exists(op):
with tarfile.open(path, mode='r', encoding='utf-8') as tar_file:
tar_file.extractall(d)
return op
def iter_terms(force: bool = False) -> Iterable[Term]:
"""Iterate over UniProt PTM Terms."""
path = ensure_path(PREFIX, url=URL, force=force)
with open(path) as file:
lines = list(file)
it: Iterable[Tuple[str, str]] = ((line[:2], line[2:].strip())
for line in lines[47:-5])
for i, (_, term_lines) in enumerate(
itt.groupby(it, key=lambda p: p[0] == "//")):
term = _parse(i, term_lines)
if term:
yield term
def iterate_terms(version: str) -> Iterable[Term]:
"""Iterate over GWAS Central Study terms."""
path = ensure_path(PREFIX, url=URL, version=version)
with tarfile.open(path) as tar_file:
for tar_info in tar_file:
if not tar_info.path.endswith(".xml"):
continue
with tar_file.extractfile(tar_info) as file:
try:
tree = ElementTree.parse(file)
except ElementTree.ParseError:
logger.warning("malformed XML in %s", tar_info.path)
continue
yield _get_term_from_tree(tree)
def iterate_terms(version: str, force: bool = False) -> Iterable[Term]:
"""Iterate over GWAS Central Study terms."""
url = f"http://www.gwascentral.org/docs/GC_{version}.tar.gz"
path = ensure_path(PREFIX, url=url, version=version, force=force)
with tarfile.open(path) as tar_file:
for tar_info in tar_file:
if not tar_info.path.endswith(".xml"):
continue
with tar_file.extractfile(tar_info) as file: # type:ignore
try:
tree = ElementTree.parse(file)
except ElementTree.ParseError:
logger.warning("malformed XML in %s", tar_info.path)
continue
yield _get_term_from_tree(tree)
def iter_terms() -> Iterable[Term]:
"""Get ITIS terms."""
zip_path = ensure_path(PREFIX, url=URL)
version = _get_version()
sqlite_dir = prefix_directory_join(PREFIX, version=version)
sqlite_path = prefix_directory_join(PREFIX,
name='ITIS.sqlite',
version=version)
if not os.path.exists(sqlite_path):
with zipfile.ZipFile(zip_path) as zip_file:
for x in zip_file.filelist:
if x.filename.endswith('.sqlite'):
zip_file.extract(x, sqlite_dir)
shutil.move(
os.path.join(sqlite_dir, f'itisSqlite{version}',
'ITIS.sqlite'), sqlite_path)
os.rmdir(os.path.join(sqlite_dir, f'itisSqlite{version}'))
if not os.path.exists(sqlite_path):
raise FileNotFoundError(f'file missing: {sqlite_path}')
conn = sqlite3.connect(sqlite_path)
with closing(conn.cursor()) as cursor:
cursor.execute(LONGNAMES_QUERY)
id_to_reference = {
str(identifier): Reference(prefix=PREFIX,
identifier=str(identifier),
name=name)
for identifier, name in cursor.fetchall()
}
with closing(conn.cursor()) as cursor:
cursor.execute(HIERARCHY_QUERY)
id_to_parents = multidict(
(str(child), str(parent)) for child, parent in cursor.fetchall())
for identifier, reference in id_to_reference.items():
parents = []
for parent_identifier in id_to_parents.get(identifier, []):
if parent_identifier == '0': # this means it's a plant
continue
parents.append(id_to_reference[parent_identifier])
term = Term(
reference=reference,
parents=parents,
)
yield term
def iter_terms(version: str) -> Iterable[Term]:
"""Iterate over terms from GWAS Central Phenotype."""
for n in trange(1, 11000, desc=f'{PREFIX} download'):
try:
path = ensure_path(
PREFIX,
'phenotype',
version=version,
url=f'https://www.gwascentral.org/phenotype/HGVPM{n}?format=json',
name=f'HGVPM{n}.json',
)
except OSError as e:
tqdm.write(f'{n}: {e}')
continue
with open(path) as file:
j = json.load(file)
term = Term(
reference=Reference(PREFIX, j['identifier'], j['name']),
definition=j['description'].strip().replace('\n', ' '),
)
yield term
def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
"""Get ITIS terms."""
zip_path = ensure_path(PREFIX, url=URL, force=force, version=version)
sqlite_dir = prefix_directory_join(PREFIX, version=version)
sqlite_path = prefix_directory_join(PREFIX, name="itis.sqlite", version=version)
if not os.path.exists(sqlite_path):
with zipfile.ZipFile(zip_path) as zip_file:
for file in zip_file.filelist:
if file.filename.endswith(".sqlite") and not file.is_dir():
zip_file.extract(file, sqlite_dir)
shutil.move(os.path.join(sqlite_dir, file.filename), sqlite_path)
os.rmdir(os.path.join(sqlite_dir, os.path.dirname(file.filename)))
if not os.path.exists(sqlite_path):
raise FileNotFoundError(f"file missing: {sqlite_path}")
conn = sqlite3.connect(sqlite_path.as_posix())
with closing(conn.cursor()) as cursor:
cursor.execute(LONGNAMES_QUERY)
id_to_reference = {
str(identifier): Reference(prefix=PREFIX, identifier=str(identifier), name=name)
for identifier, name in cursor.fetchall()
}
with closing(conn.cursor()) as cursor:
cursor.execute(HIERARCHY_QUERY)
id_to_parents = multidict((str(child), str(parent)) for child, parent in cursor.fetchall())
for identifier, reference in id_to_reference.items():
parents = []
for parent_identifier in id_to_parents.get(identifier, []):
if parent_identifier == "0": # this means it's a plant
continue
parents.append(id_to_reference[parent_identifier])
term = Term(
reference=reference,
parents=parents,
)
yield term
def iter_terms(version: str,
synonym_abb,
autodownload: bool = False) -> Iterable[Term]:
"""Iterate over UMLS terms."""
name = f"umls-{version}-mrconso.zip"
url = f"https://download.nlm.nih.gov/umls/kss/{version}/{name}"
if autodownload:
# FIXME needs automated scrapy step where you put in user/password
path = ensure_path(PREFIX, url=url, version=version)
else:
path = RAW_MODULE.get(PREFIX, version, name=name)
if not path.exists():
raise FileNotFoundError(
f"UMLS needs to be downloaded manually still and moved to {path}. "
f"See https://www.nlm.nih.gov/research/umls/index.html", )
with zipfile.ZipFile(path) as zip_file:
with zip_file.open("MRCONSO.RRF", mode="r") as file:
it = tqdm(file, unit_scale=True, desc="[umls] parsing")
lines = (line.decode("utf-8").strip().split("|") for line in it)
for cui, cui_lines in itt.groupby(lines,
key=operator.itemgetter(0)):
df = pd.DataFrame(list(cui_lines), columns=RRF_COLUMNS)
df = df[df["LAT - Language"] == "ENG"]
idx = ((df["ISPREF - is preferred"] == "Y")
& (df["TS - Term Status"] == "P")
& (df["STT - String Type"] == "PF"), )
pref_rows_df = df.loc[idx]
if len(pref_rows_df.index) != 1:
it.write(
f"no preferred term for umls:{cui}. got {len(pref_rows_df.index)}"
)
continue
df["TTY - Term Type in Source"] = df[
"TTY - Term Type in Source"].map(synonym_abb.__getitem__)
_r = pref_rows_df.iloc[0]
sdf = df[[
"SAB - source name", "CODE", "TTY - Term Type in Source",
"STR"
]]
synonyms = []
xrefs = []
for source, identifier, synonym_type, synonym in sdf.values:
norm_source = normalize_prefix(source)
if norm_source is None or not identifier:
provenance = []
else:
ref = Reference(prefix=norm_source,
identifier=identifier)
provenance = [ref]
xrefs.append(ref)
synonyms.append(
Synonym(
name=synonym,
provenance=provenance,
type=SynonymTypeDef.from_text(synonym_type),
))
xrefs = sorted(set(xrefs),
key=lambda reference:
(reference.prefix, reference.identifier))
term = Term(
reference=Reference(prefix=PREFIX,
identifier=cui,
name=_r["STR"]),
synonyms=synonyms,
xrefs=xrefs,
)
yield term
def get_terms(version: Optional[str] = None,
force: bool = False) -> Iterable[Term]: # noqa:C901
"""Get HGNC terms."""
if version is None:
version = datetime.date.today().strftime("%Y-%m-01")
unhandled_entry_keys: typing.Counter[str] = Counter()
unhandle_locus_types: DefaultDict[str, Dict[str, Term]] = defaultdict(dict)
path = ensure_path(
PREFIX,
url=DEFINITIONS_URL_FMT.format(version=version),
force=force,
version=version,
name="hgnc_complete_set.json",
)
with open(path) as file:
entries = json.load(file)["response"]["docs"]
yield from sorted(
{
Term(reference=Reference.auto("SO", so_id))
for so_id in sorted(LOCUS_TYPE_TO_SO.values()) if so_id
},
key=attrgetter("identifier"),
)
statuses = set()
for entry in tqdm(entries,
desc=f"Mapping {PREFIX}",
unit="gene",
unit_scale=True):
name, symbol, identifier = (
entry.pop("name"),
entry.pop("symbol"),
entry.pop("hgnc_id")[len("HGNC:"):],
)
status = entry.pop("status")
if status == "Approved":
is_obsolete = False
elif status not in statuses:
statuses.add(status)
logger.warning("UNHANDLED %s", status)
is_obsolete = True
else:
raise ValueError(
f"Unhandled status for hgnc:{identifier}: {status}")
term = Term(
definition=name,
reference=Reference(prefix=PREFIX,
identifier=identifier,
name=symbol),
is_obsolete=is_obsolete,
)
for uniprot_id in entry.pop("uniprot_ids", []):
term.append_relationship(
has_gene_product,
Reference.auto("uniprot", uniprot_id),
)
for ec_code in entry.pop("enzyme_id", []):
if "-" in ec_code:
continue # only add concrete annotations
term.append_relationship(
gene_product_member_of,
Reference.auto("eccode", ec_code),
)
for rna_central_ids in entry.pop("rna_central_id", []):
for rna_central_id in rna_central_ids.split(","):
term.append_relationship(
transcribes_to,
Reference(prefix="rnacentral",
identifier=rna_central_id.strip()),
)
mirbase_id = entry.pop("mirbase", None)
if mirbase_id:
term.append_relationship(
transcribes_to,
Reference.auto(
"mirbase",
mirbase_id,
),
)
snornabase_id = entry.pop("snornabase", None)
if snornabase_id:
term.append_relationship(
transcribes_to,
Reference(prefix="snornabase", identifier=snornabase_id))
for rgd_curie in entry.pop("rgd_id", []):
if not rgd_curie.startswith("RGD:"):
logger.warning(
f"hgnc:{identifier} had bad RGD CURIE: {rgd_curie}")
continue
rgd_id = rgd_curie[len("RGD:"):]
term.append_relationship(
orthologous,
Reference.auto(prefix="rgd", identifier=rgd_id),
)
for mgi_curie in entry.pop("mgd_id", []):
if not mgi_curie.startswith("MGI:"):
logger.warning(
f"hgnc:{identifier} had bad MGI CURIE: {mgi_curie}")
continue
mgi_id = mgi_curie[len("MGI:"):]
if not mgi_id:
continue
term.append_relationship(
orthologous,
Reference.auto(prefix="mgi", identifier=mgi_id),
)
for xref_prefix, key in gene_xrefs:
xref_identifiers = entry.pop(key, None)
if xref_identifiers is None:
continue
if not isinstance(xref_identifiers, list):
xref_identifiers = [xref_identifiers]
for xref_identifier in xref_identifiers:
term.append_xref(
Reference(prefix=xref_prefix,
identifier=str(xref_identifier)))
for pubmed_id in entry.pop("pubmed_id", []):
term.append_provenance(
Reference(prefix="pubmed", identifier=str(pubmed_id)))
gene_group_ids = entry.pop("gene_group_id", [])
gene_groups = entry.pop("gene_group", [])
for gene_group_id, gene_group_label in zip(gene_group_ids,
gene_groups):
term.append_relationship(
member_of,
Reference(
prefix="hgnc.genegroup",
identifier=str(gene_group_id),
name=gene_group_label,
),
)
for alias_symbol in entry.pop("alias_symbol", []):
term.append_synonym(
Synonym(name=alias_symbol, type=alias_symbol_type))
for alias_name in entry.pop("alias_name", []):
term.append_synonym(Synonym(name=alias_name, type=alias_name_type))
for previous_symbol in entry.pop("previous_symbol", []):
term.append_synonym(
Synonym(name=previous_symbol, type=previous_symbol_type))
for previous_name in entry.pop("prev_name", []):
term.append_synonym(
Synonym(name=previous_name, type=previous_name_type))
for prop in ["location"]:
value = entry.pop(prop, None)
if value:
term.append_property(prop, value)
locus_type = entry.pop("locus_type")
locus_group = entry.pop("locus_group")
so_id = LOCUS_TYPE_TO_SO.get(locus_type)
if so_id:
term.append_parent(Reference.auto("SO", so_id))
else:
term.append_parent(Reference.auto("SO", "0000704")) # gene
unhandle_locus_types[locus_type][identifier] = term
term.append_property("locus_type", locus_type)
term.append_property("locus_group", locus_group)
term.set_species(identifier="9606", name="H**o sapiens")
for key in entry:
unhandled_entry_keys[key] += 1
yield term
with open(prefix_directory_join(PREFIX, name="unhandled.json"),
"w") as file:
json.dump(
{
k: {hgnc_id: term.name
for hgnc_id, term in v.items()}
for k, v in unhandle_locus_types.items()
},
file,
indent=2,
)
with open(prefix_directory_join(PREFIX, name="unhandled.md"), "w") as file:
for k, v in sorted(unhandle_locus_types.items()):
t = tabulate(
[(
hgnc_id,
term.name,
term.is_obsolete,
term.link,
", ".join(p.link for p in term.provenance if p.link),
) for hgnc_id, term in sorted(v.items())],
headers=["hgnc_id", "name", "obsolete", "link", "provenance"],
tablefmt="github",
)
print(f"## {k} ({len(v)})", file=file) # noqa: T201
print(t, "\n", file=file) # noqa: T201
unhandle_locus_type_counter = Counter(
{locus_type: len(d)
for locus_type, d in unhandle_locus_types.items()})
logger.warning("Unhandled locus types:\n%s",
tabulate(unhandle_locus_type_counter.most_common()))
logger.warning("Unhandled keys:\n%s",
tabulate(unhandled_entry_keys.most_common()))
