def query(query: str, input_dir: str, output_dir: str) -> None:
"""Perform a query of knowledge graph using a class contained in query_utils
Args:
query: A query class containing instructions for performing a query
input_dir: Directory where any input files required to execute query are
located (typically 'data', where transformed and merged graph files are)
output_dir: Directory to output results of query
Returns:
None.
"""
run_query(query=query, input_dir=input_dir, output_dir=output_dir)
def query(yaml: str,
output_dir: str,
query_key: str = 'query',
endpoint_key: str = 'endpoint',
outfile_ext: str = ".tsv") -> None:
"""Perform a query of knowledge graph using a class contained in query_utils
Args:
yaml: A YAML file containing a SPARQL query (see queries/sparql/ for examples)
output_dir: Directory to output results of query
query_key: the key in the yaml file containing the query string
endpoint_key: the key in the yaml file containing the sparql endpoint URL
outfile_ext: file extension for output file [.tsv]
Returns:
None.
"""
query = parse_query_yaml(yaml)
result_dict = run_query(query=query[query_key],
endpoint=query[endpoint_key])
if not os.path.exists(output_dir):
os.makedirs(output_dir)
outfile = os.path.join(
output_dir,
os.path.splitext(os.path.basename(yaml))[0] + outfile_ext)
result_dict_to_tsv(result_dict, outfile)
def query(yaml: str, output_dir: str,
query_key: str='query', endpoint_key: str='endpoint',
outfile_ext: str=".tsv") -> None:
"""Perform a query of knowledge graph using a class contained in query_utils
Args:
yaml: A rq file containing a SPARQL query in grlc format:
https://github.com/CLARIAH/grlc/blob/master/README.md
output_dir: Directory to output results of query
query_key: the key in the yaml file containing the query string
endpoint_key: the key in the yaml file containing the sparql endpoint URL
outfile_ext: file extension for output file [.tsv]
Returns:
None.
"""
query = parse_query_rq(yaml)
result_dict = run_query(query=query[query_key], endpoint=query[endpoint_key])
if not os.path.exists(output_dir):
os.makedirs(output_dir)
outfile = os.path.join(output_dir, os.path.splitext(os.path.basename(yaml))[0] +
outfile_ext)
result_dict_to_tsv(result_dict, outfile)
if not os.path.exists(kg_tar):
wget.download('http://kg-hub.berkeleybop.io/kg-covid-19.tar.gz', data_dir)
with tarfile.open(kg_tar) as tar:
tar.extractall(data_dir)
for path in [intact_path, sars_genes_path, drug_central]:
node_file = '/'.join([data_dir, path, 'nodes.tsv'])
edge_file = '/'.join([data_dir, path, 'edges.tsv'])
node_url = '/'.join(['http://kg-hub.berkeleybop.io', path, 'nodes.tsv'])
edge_url = '/'.join(['http://kg-hub.berkeleybop.io', path, 'edges.tsv'])
if not os.path.exists(node_file):
wget.download(node_url, node_file)
if not os.path.exists(edge_file):
wget.download(edge_url, edge_file)
run_query('TargetCandidates', input_dir=data_dir, output_dir=data_dir)
target_info = read_csv('data/target_candidates.tsv', sep="\t")
pnnl_data = read_csv('data/pnnl/PNNLTargetList_2020_06_08 - TargetList_2020_06_05.tsv', sep="\t")
pnnl_data.rename(columns={'Uniprot': 'protein ID'}, inplace=True)
pnnl_data['protein ID'] = \
pnnl_data['protein ID'].apply(lambda x: "{}{}".format('UniProtKB:', x))
target_info.drop(['confidence score','comments'], axis=1, inplace=True)
target_info = pd.concat([pnnl_data, target_info], axis=0, join='outer', ignore_index=False, keys=None,
levels=None, names=None, verify_integrity=False, copy=True)
host_only = False