def make_kg2_graph(input_file_name: str, test_mode: bool = False):
ensembl_data = kg2_util.load_json(input_file_name)
nodes = []
edges = []
genebuild_str = ensembl_data['genebuild']
update_date = genebuild_str.split('/')[1]
gene_ctr = 0
ontology_curie_id = ENSEMBL_KB_CURIE_ID
ens_kp_node = kg2_util.make_node(ontology_curie_id, ENSEMBL_KB_URI,
'Ensembl Genes',
kg2_util.BIOLINK_CATEGORY_DATA_FILE,
update_date, ontology_curie_id)
nodes.append(ens_kp_node)
for gene_dict in ensembl_data['genes']:
gene_ctr += 1
if test_mode and gene_ctr > 10000:
break
ensembl_gene_id = gene_dict['id']
description = gene_dict.get('description', None)
gene_symbol = gene_dict.get('name', None)
other_synonyms = []
xrefs = gene_dict.get('xrefs', None)
if xrefs is not None:
other_synonyms = list(
set([
xref['primary_id'] for xref in xrefs
if xref['primary_id'] != ensembl_gene_id
]))
node_dict = make_node(ensembl_gene_id, description, gene_symbol,
update_date, other_synonyms)
nodes.append(node_dict)
ensembl_gene_curie_id = node_dict['id']
taxon_id_int = gene_dict.get('taxon_id', None)
assert taxon_id_int == 9606, "unexpected taxon ID"
edges.append(
kg2_util.make_edge_biolink(
ensembl_gene_curie_id,
kg2_util.CURIE_PREFIX_NCBI_TAXON + ':' + str(taxon_id_int),
kg2_util.EDGE_LABEL_BIOLINK_IN_TAXON, ENSEMBL_KB_CURIE_ID,
update_date))
hgnc_list = gene_dict.get('HGNC', None)
if hgnc_list is not None:
for hgnc_curie in hgnc_list:
edges.append(
kg2_util.make_edge(ensembl_gene_curie_id, hgnc_curie,
kg2_util.CURIE_ID_OWL_SAME_AS,
kg2_util.EDGE_LABEL_OWL_SAME_AS,
ENSEMBL_KB_CURIE_ID, update_date))
return {'nodes': nodes, 'edges': edges}
def make_kg2_graph(input_file_name: str, test_mode: bool = False):
ensembl_data = kg2_util.load_json(input_file_name)
nodes = []
edges = []
genebuild_str = ensembl_data['genebuild']
update_date = genebuild_str.split('/')[1]
gene_ctr = 0
for gene_dict in ensembl_data['genes']:
gene_ctr += 1
if test_mode and gene_ctr > 10000:
break
ensembl_gene_id = gene_dict['id']
description = gene_dict.get('description', None)
gene_symbol = gene_dict.get('name', None)
other_synonyms = []
xrefs = gene_dict.get('xrefs', None)
if xrefs is not None:
other_synonyms = list(set([xref['primary_id'] for xref in xrefs if xref['primary_id'] != ensembl_gene_id]))
node_dict = make_node(ensembl_gene_id,
description,
gene_symbol,
update_date,
other_synonyms)
nodes.append(node_dict)
ensembl_gene_curie_id = node_dict['id']
taxon_id_int = gene_dict.get('taxon_id', None)
assert taxon_id_int == 9606, "unexpected taxon ID"
edges.append(kg2_util.make_edge(ensembl_gene_curie_id,
'NCBITaxon:' + str(taxon_id_int),
'gene_found_in_organism',
ENSEMBL_KB_IRI,
update_date))
hgnc_list = gene_dict.get('HGNC', None)
if hgnc_list is not None:
for hgnc_curie in hgnc_list:
edges.append(kg2_util.make_edge(ensembl_gene_curie_id,
hgnc_curie,
'xref',
ENSEMBL_KB_IRI,
update_date))
return {'nodes': nodes,
'edges': edges}
import argparse
import kg2_util
def make_arg_parser():
arg_parser = argparse.ArgumentParser(
description=
'sample_subgraph.py: sample a smaller subgraph of a KG in JSON format')
arg_parser.add_argument('--test',
dest='test',
action="store_true",
default=False)
arg_parser.add_argument('inputFile', type=str, nargs=1)
arg_parser.add_argument('outputFile', type=str, nargs=1)
return arg_parser
if __name__ == '__main__':
args = make_arg_parser().parse_args()
input_file_name = args.inputFile
output_file_name = args.outputFile
graph = kg2_util.load_json(input_file_name)
nodes = [graph['nodes'][i] for i in range(0, len(graph['nodes']), 5)]
nodes_id_set = set([node['id'] for node in nodes])
edges = [
edge for edge in graph['edges']
if edge['subject'] in nodes_id_set and edge['object'] in nodes_id_set
]
kg2_util.save_json({'nodes': nodes, 'edges': edges}, output_file_name)
