def get_ids_for_gene(hgnc_name, **kwargs):
"""Get the curated set of articles for a gene in the Entrez database.
Search parameters for the Gene database query can be passed in as
keyword arguments.
Parameters
----------
hgnc_name : string
The HGNC name of the gene. This is used to obtain the HGNC ID
(using the hgnc_client module) and in turn used to obtain the Entrez
ID associated with the gene. Entrez is then queried for that ID.
"""
# Get the HGNC ID for the HGNC name
hgnc_id = hgnc_client.get_hgnc_id(hgnc_name)
if hgnc_id is None:
raise ValueError('Invalid HGNC name.')
# Get the Entrez ID
entrez_id = hgnc_client.get_entrez_id(hgnc_id)
if entrez_id is None:
raise ValueError('Entrez ID not found in HGNC table.')
# Query the Entrez Gene database
params = {'db': 'gene',
'retmode': 'xml',
'id': entrez_id}
params.update(kwargs)
tree = send_request(pubmed_fetch, params)
if tree is None:
return []
if tree.find('ERROR') is not None:
logger.error(tree.find('ERROR').text)
return []
# Get all PMIDs from the XML tree
id_terms = tree.findall('.//PubMedId')
if id_terms is None:
return []
# Use a set to remove duplicate IDs
ids = list(set([idt.text for idt in id_terms]))
return ids
def get_ids_for_gene(hgnc_name, **kwargs):
"""Get the curated set of articles for a gene in the Entrez database.
Search parameters for the Gene database query can be passed in as
keyword arguments.
Parameters
----------
hgnc_name : string
The HGNC name of the gene. This is used to obtain the HGNC ID
(using the hgnc_client module) and in turn used to obtain the Entrez
ID associated with the gene. Entrez is then queried for that ID.
"""
# Get the HGNC ID for the HGNC name
hgnc_id = hgnc_client.get_hgnc_id(hgnc_name)
if hgnc_id is None:
raise ValueError('Invalid HGNC name.')
# Get the Entrez ID
entrez_id = hgnc_client.get_entrez_id(hgnc_id)
if entrez_id is None:
raise ValueError('Entrez ID not found in HGNC table.')
# Query the Entrez Gene database
params = {'db': 'gene',
'retmode': 'xml',
'id': entrez_id}
params.update(kwargs)
tree = send_request(pubmed_fetch, params)
if tree is None:
return []
if tree.find('ERROR') is not None:
logger.error(tree.find('ERROR').text)
return []
# Get all PMIDs from the XML tree
id_terms = tree.findall('.//PubMedId')
if id_terms is None:
return []
# Use a set to remove duplicate IDs
ids = list(set([idt.text for idt in id_terms]))
return ids
