def mappings():
"""Find single mapped entries."""
df = get_xrefs_df()
idx = (df['target_db'] == 'pr') & (df['type'] == 'protein')
protein_pr_errors = get_single_mappings(df, idx)
if protein_pr_errors:
click.secho('Some entries only mapped to Protein Ontology', fg='red', bold=True)
_p(protein_pr_errors)
idx = (df['target_db'] == 'go') & (df['type'] == 'protein complex')
go_complex_errors = get_single_mappings(df, idx)
if go_complex_errors:
click.secho('Some complexes only mapped to Gene Ontology', fg='red', bold=True)
_p(go_complex_errors)
idx = (df['target_db'] == 'mesh')
mesh_errors = get_single_mappings(df, idx)
if mesh_errors:
click.secho('Some roles only mapped to MeSH', fg='red', bold=True)
_p(mesh_errors)
idx = (df['type'] == 'molecular function')
mf_errors = get_single_mappings(df, idx)
if mf_errors:
click.secho('Some roles only mapped to molecular function', fg='red', bold=True)
_p(mf_errors)
if any([
protein_pr_errors,
go_complex_errors,
mesh_errors,
mf_errors,
]):
sys.exit(1)
def main():
"""Run the MeSH curation pipeline."""
xrefs_df = get_xrefs_df()
mesh_xrefs_df = xrefs_df[xrefs_df['source_db'] == 'mesh']
curated_mesh_ids = set(mesh_xrefs_df['source_id'])
terms = {
identifier: (name, suffix.strip('s'))
for identifier, name in pyobo.get_id_name_mapping('mesh').items()
if identifier not in curated_mesh_ids and identifier not in BLACKLIST
for suffix in SUFFIXES if name.lower().endswith(suffix)
}
for i, (identifier, (name,
suffix)) in enumerate(sorted(terms.items(),
key=lambda t: t[1][0]),
start=1):
print('mesh', identifier, name, suffix, '?', '?', '?', '?', sep='\t')
def main(show_ungrounded: bool, output: Optional[TextIO]):
"""Run the MeSH curation pipeline."""
xrefs_df = get_xrefs_df()
mesh_xrefs_df = xrefs_df[xrefs_df['source_db'] == 'mesh']
curated_mesh_ids = set(mesh_xrefs_df['source_id'])
terms = {
identifier: (name, name[:-len(suffix)], suffix.strip('s'))
for identifier, name in pyobo.get_id_name_mapping('mesh').items()
if identifier not in curated_mesh_ids and identifier not in BLACKLIST
for suffix in SUFFIXES if name.lower().endswith(suffix)
}
it = sorted(terms.items(), key=lambda t: t[1][0])
it = tqdm(it, desc='making MeSH curation sheet')
for i, (identifier, (name, search_text, suffix)) in enumerate(it, start=1):
for row in yield_gilda('mesh', identifier, name, suffix, search_text,
show_ungrounded or output is not None):
print(*row, sep='\t', file=output)
BIOCHEMICAL_ROLE_CHEBI_ID = '52206'
PATHWAY_INHIBITOR_CHEBI_ID = '76932'
ENZYME_INHIBITOR_CHEBI_ID = '23924'
AGONIST_CHEBI_ID = '48705'
INVERSE_AGONIST_CHEBI_ID = '90847'
INHIBITOR_CHEBI_ID = '35222'
ANTAGONIST_CHEBI_ID = '48706'
BLACKLIST = [
'48001', # protein synthesis inhibitor
'64106', # protein kinase agonist
]
chebi_obo = pyobo.get('chebi')
chebi_id_to_name = pyobo.get_id_name_mapping('chebi')
XREFS_DF = get_xrefs_df()
CURATED_ROLE_CHEBI_IDS = {
source_id[len('CHEBI:'):]
for source_db, source_id in XREFS_DF[['source_db', 'source_id']].values
if source_db == 'chebi'
}
IRRELEVANT_ROLE_CHEBI_IDS = set(
itt.chain.from_iterable(
chebi_obo.descendants(chebi_id[len('CHEBI'):])
for chebi_id in get_irrelevant_roles_df().identifier
if chebi_id[len('CHEBI'):] in chebi_obo.hierarchy))
def _get_inhibitors_reclassification() -> pd.DataFrame:
return pd.read_csv(RECLASSIFICATION_PATH, sep='\t', comment='#')
def get_relations_df() -> pd.DataFrame:
"""Assemble the relations dataframe."""
xrefs_df = get_xrefs_df()
logger.info('loading famplex mapping')
famplex_id_to_members = defaultdict(list)
famplex_relations_df = pd.read_csv(FAMPLEX_RELATIONS_URL)
for source_id, source_name, rel, target_db, target_name in famplex_relations_df.values:
if source_id.lower() == 'hgnc' and rel == 'isa' and target_db.lower() == 'fplx':
try:
hgnc_id = hgnc_name_to_id[source_name]
except KeyError:
logger.warning(f'Could not find {source_name} for fplx:{target_name}')
continue
famplex_id_to_members[target_name].append((hgnc_id, source_name))
logger.info('getting enzyme classes')
expasy_graph, ec_code_to_children = get_expasy_closure()
logger.info('getting ec2go')
ec2go = get_ec2go()
logger.info('inferring over target hierarchies')
x = defaultdict(list)
for source_db, source_id, _, modulation, target_type, target_db, target_id, target_name in xrefs_df.values:
if source_db != 'chebi':
continue
if target_db == 'hgnc':
# Append original
x[source_db, source_id].append((modulation, 'protein', 'hgnc', target_id, target_name))
# Append inferred
for uniprot_id, uniprot_name in get_uniprot_id_names(target_id):
x[source_db, source_id].append((modulation, 'protein', 'uniprot', uniprot_id, uniprot_name))
elif target_db == 'fplx':
# Append original
x[source_db, source_id].append((modulation, target_type, target_db, target_id, target_name))
# Append inferred
for hgnc_id, hgnc_symbol in famplex_id_to_members.get(target_id, []):
x[source_db, source_id].append((modulation, 'protein', 'hgnc', hgnc_id, hgnc_symbol))
for uniprot_id, uniprot_name in get_uniprot_id_names(hgnc_id):
x[source_db, source_id].append((modulation, 'protein', 'uniprot', uniprot_id, uniprot_name))
elif target_db == 'ec-code':
children_ec_codes = ec_code_to_children.get(target_id)
if children_ec_codes is None:
# this is the case for about 15 entries
logger.info(f'could not find children of {target_db}:{target_id}')
continue
for sub_target_db, sub_target_id, sub_target_name in children_ec_codes:
target_type = DB_TO_TYPE[sub_target_db]
x[source_db, source_id].append((
modulation, target_type, sub_target_db, sub_target_id, sub_target_name,
))
for go_id, go_name in ec2go.get(target_id, []):
x[source_db, source_id].append((
modulation, 'molecular function', 'go', go_id, go_name,
))
else:
x[source_db, source_id].append((modulation, target_type, target_db, target_id, target_name))
logger.info('inferring over role hiearchies')
db_to_role_to_chemical_curies = {
'chebi': get_chebi_role_to_children(),
}
db_to_id_mapping = {
'chebi': get_id_name_mapping('chebi'),
}
#: A set of databases to remove the prefix from
remove_prefix = {'chebi'}
rows = []
for (role_db, role_id), entries in x.items():
if role_db in remove_prefix and role_id.lower().startswith(f'{role_db}:'.lower()):
role_id = role_id[len(f'{role_db}:'):]
# TODO map role_db, role_id to set of sub_role_db, sub_role_id
sub_role_curies = {(role_db, role_id)}
for modulation, target_type, target_db, target_id, target_name in entries:
chemical_curies = set(itt.chain.from_iterable(
db_to_role_to_chemical_curies[sub_role_db].get(sub_role_id, [])
for sub_role_db, sub_role_id in sub_role_curies
))
if not chemical_curies:
logger.debug('no inference for %s:%s', role_db, role_id)
continue
for chemical_db, chemical_id in chemical_curies:
rows.append((
chemical_db, chemical_id, db_to_id_mapping[chemical_db][chemical_id],
modulation, target_type, target_db, target_id, target_name,
))
return pd.DataFrame(rows, columns=XREFS_COLUMNS)
def rewrite_repo_readme():
"""Rewrite the summary of curated content in the repository's readme, automatically."""
df = get_xrefs_df()
summary_df = df.groupby(['source_db', 'modulation', 'type', 'target_db']).size().reset_index()
summary_df.columns = ['Source Database', 'Modulation', 'Target Type', 'Target Database', 'Count']
summary_df.to_csv(os.path.join(EXPORT_DIRECTORY, 'curated_summary.tsv'), sep='\t', index=False)
modulation_summary_df = df.groupby('modulation').size().reset_index()
modulation_summary_df.columns = ['Modulation', 'Count']
modulation_summary_df.to_csv(
os.path.join(EXPORT_DIRECTORY, 'curated_summary_by_modulation.tsv'), sep='\t', index=False,
)
type_summary_df = df.groupby('type').size().reset_index()
type_summary_df.columns = ['Target Type', 'Count']
type_summary_df.to_csv(
os.path.join(EXPORT_DIRECTORY, 'curated_summary_by_type.tsv'), sep='\t', index=False,
)
namespace_summary_df = df.groupby('target_db').size().reset_index()
namespace_summary_df.columns = ['Target Database', 'Count']
namespace_summary_df.to_csv(
os.path.join(EXPORT_DIRECTORY, 'curated_summary_by_namespace.tsv'), sep='\t', index=False,
)
logger.info('Plotting modulation and target type summary')
fig, (lax, rax) = plt.subplots(nrows=1, ncols=2, figsize=(12, 5))
g = sns.barplot(y="Modulation", x='Count', data=modulation_summary_df, ax=lax)
g.set_xscale("log")
g = sns.barplot(y="Target Type", x='Count', data=type_summary_df, ax=rax)
g.set_xscale("log")
plt.tight_layout()
plt.savefig(os.path.join(EXPORT_DIRECTORY, 'curated_summary.png'), dpi=300)
text = f'There are {len(df.index)} curated roles as of export on {time.asctime()}\n\n'
text += tabulate(modulation_summary_df.values, ['Modulation', 'Count'], tablefmt='rst')
text += '\n\n'
text += tabulate(type_summary_df.values, ['Target Entity Type', 'Count'], tablefmt='rst')
text += '\n\n'
text += tabulate(namespace_summary_df.values, ['Target Database', 'Count'], tablefmt='rst')
text += '\n'
path = os.path.join(HERE, 'README.rst')
with open(path) as file:
readme = [line.rstrip() for line in file]
for i, line in enumerate(readme):
if line == 'Summary':
start = i + 2
break
else:
raise ValueError('could not find summary block')
for i, line in enumerate(readme):
if line == 'Axioms':
end = i
break
else:
raise ValueError('could not find end block')
with open(path, 'w') as file:
for line in readme[:start]:
print(line, file=file)
print(text, file=file)
for line in readme[end:]:
print(line, file=file)