def make_edges(xrefs, nodes_to_species, test_mode):
edges = []
edge_count = 0
for node_id in xrefs:
edge_count += 1
if test_mode and edge_count > 1000:
break
for xref_id in xrefs[node_id]:
if xref_id.startswith(CURIE_PREFIX_HGNC) or \
xref_id.startswith(CURIE_PREFIX_NCBI_GENE):
edge = kg2_util.make_edge_biolink(
node_id, xref_id, kg2_util.EDGE_LABEL_BIOLINK_SAME_AS,
MIRBASE_KB_CURIE_ID, None)
edges.append(edge)
else:
edge = kg2_util.make_edge_biolink(
node_id, xref_id, kg2_util.EDGE_LABEL_BIOLINK_RELATED_TO,
MIRBASE_KB_CURIE_ID, None)
edges.append(edge)
taxon_edge_count = 0
for node_id in nodes_to_species:
taxon_edge_count += 1
if test_mode and taxon_edge_count > 1000:
break
taxon_edge = kg2_util.make_edge_biolink(
node_id, nodes_to_species[node_id],
kg2_util.EDGE_LABEL_BIOLINK_IN_TAXON, MIRBASE_KB_CURIE_ID, None)
edges.append(taxon_edge)
return edges
def format_same_as_edge(kegg_id, external_id, update_date):
edge = kg2_util.make_edge_biolink(format_id(kegg_id),
external_id,
kg2_util.EDGE_LABEL_BIOLINK_SAME_AS,
KEGG_PROVIDED_BY,
update_date)
return edge
def make_edges(input_file: str, test_mode: bool):
edges = []
count = 0
non_befree_count = 0
with open(input_file, 'r') as input_tsv:
tsvreader = csv.reader(input_tsv, delimiter='\t')
for line in tsvreader:
count += 1
if count == 1:
continue
if test_mode and non_befree_count >= TEST_MODE_LIMIT:
break
[
subject_id, _, _, _, object_id, _, _, _, _, score,
evidence_score, created_date, update_date, pmid, source
] = line
if source != 'BEFREE':
non_befree_count += 1
subject_id = format_id(subject_id,
kg2_util.CURIE_PREFIX_NCBI_GENE)
object_id = format_id(object_id, kg2_util.CURIE_PREFIX_UMLS)
predicate = kg2_util.EDGE_LABEL_BIOLINK_GENE_ASSOCIATED_WITH_CONDITION
edge = kg2_util.make_edge_biolink(subject_id, object_id,
predicate, DISGENET_KB_CURIE,
update_date)
publication = kg2_util.CURIE_PREFIX_PMID + ':' + pmid
edge['publications'] = [publication]
edges.append(edge)
return edges
def make_edges(records: list, nodes_dict: dict):
ret_list = []
for record_dict in records:
accession = record_dict['AC'][0]
curie_id = kg2_util.CURIE_PREFIX_UNIPROT + ':' + accession
organism_int = record_dict['organism']
update_date = nodes_dict[curie_id]['update_date']
ret_list.append(
kg2_util.make_edge_biolink(
curie_id,
kg2_util.CURIE_PREFIX_NCBI_TAXON + ':' + str(organism_int),
kg2_util.EDGE_LABEL_BIOLINK_IN_TAXON,
UNIPROTKB_PROVIDED_BY_CURIE_ID, update_date))
record_xrefs = record_dict.get('DR', None)
if record_xrefs is not None:
for xref_str in record_xrefs:
hgnc_match = REGEX_HGNC.match(xref_str)
if hgnc_match is not None:
hgnc_curie = hgnc_match[1]
ret_list.append(
kg2_util.make_edge_biolink(
hgnc_curie, curie_id,
kg2_util.EDGE_LABEL_BIOLINK_HAS_GENE_PRODUCT,
UNIPROTKB_PROVIDED_BY_CURIE_ID, update_date))
gene_id_match = REGEX_NCBIGeneID.match(xref_str)
if gene_id_match is not None:
ncbi_curie = kg2_util.CURIE_PREFIX_NCBI_GENE + \
':' + gene_id_match[1]
ret_list.append(
kg2_util.make_edge_biolink(
ncbi_curie, curie_id,
kg2_util.EDGE_LABEL_BIOLINK_HAS_GENE_PRODUCT,
UNIPROTKB_PROVIDED_BY_CURIE_ID, update_date))
for node_id, node_dict in nodes_dict.items():
xrefs = node_dict['xrefs']
if xrefs is not None and len(xrefs) > 0:
for xref_curie in sorted(list(xrefs)):
ret_list.append(
kg2_util.make_edge_biolink(
node_id, xref_curie,
kg2_util.EDGE_LABEL_BIOLINK_PHYSICALLY_INTERACTS_WITH,
UNIPROTKB_PROVIDED_BY_CURIE_ID, update_date))
del node_dict['xrefs']
return ret_list
def format_edge(subject_id: str, object_id: str, predicate_label: str):
relation_curie = kg2_util.predicate_label_to_curie(
predicate_label, REACTOME_RELATION_CURIE_PREFIX)
if predicate_label == kg2_util.EDGE_LABEL_BIOLINK_SAME_AS:
return kg2_util.make_edge_biolink(subject_id, object_id,
predicate_label,
REACTOME_KB_CURIE_ID, None)
return kg2_util.make_edge(subject_id, object_id, relation_curie,
predicate_label, REACTOME_KB_CURIE_ID)
def format_edge(subject_id, object_id, predicate, update_date):
relation_curie = kg2_util.predicate_label_to_curie(
predicate, DRUGCENTRAL_RELATION_CURIE_PREFIX)
if predicate == kg2_util.EDGE_LABEL_BIOLINK_SAME_AS:
return kg2_util.make_edge_biolink(subject_id, object_id, predicate,
DRUGCENTRAL_SOURCE, update_date)
else:
return kg2_util.make_edge(subject_id, object_id, relation_curie,
predicate, DRUGCENTRAL_SOURCE, update_date)
def make_node_and_edges(article: dict, mesh_predicate_label: str):
nodes = []
edges = []
article_citation = article["MedlineCitation"]
pmid = kg2_util.CURIE_PREFIX_PMID + ":" + article_citation["PMID"]["#text"]
update_date = extract_date(article_citation["DateRevised"])
if pmid in pmids:
# These aren't necessary yet, but it might be someday, so I wrote
# and tested a couple of functions to extract them
#authors = get_authors(article_citation)
#journal = get_journal(article_citation)
name = article_citation["Article"]["ArticleTitle"]
if isinstance(name, dict):
try:
name = name["#text"]
except:
temp_name = name
for key in temp_name:
name = temp_name[key]["#text"]
try:
created_date = extract_date(
article_citation["Article"]["ArticleDate"])
except:
created_date = None
iri = PMID_BASE_IRI + article_citation["PMID"]["#text"]
node = kg2_util.make_node(pmid, iri, name,
BIOLINK_CATEGORY_PUBLICATION, update_date,
PMID_PROVIDED_BY_CURIE_ID)
node["creation_date"] = created_date
nodes.append(node)
try:
for mesh_topic in (
article_citation["MeshHeadingList"]["MeshHeading"]):
mesh_id = kg2_util.CURIE_PREFIX_MESH + ":" + \
mesh_topic["DescriptorName"]["@UI"]
edge = kg2_util.make_edge_biolink(pmid, mesh_id,
mesh_predicate_label,
PMID_PROVIDED_BY_CURIE_ID,
update_date)
edges.append(edge)
except:
mesh_id = None
return [{"nodes": nodes, "edges": edges}, update_date]
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_hmdb_edge(subject_id: str, object_id: str, subject_prefix: str,
object_prefix: str, predicate_label: str, update_date: str,
publications_info: dict):
relation_curie = kg2_util.predicate_label_to_curie(predicate_label,
CURIE_PREFIX_HMDB)
subject = subject_prefix + ":" + subject_id
object = object_id
if object_prefix is not None:
object = object_prefix + ":" + object_id
if predicate_label == kg2_util.EDGE_LABEL_BIOLINK_SAME_AS:
edge = kg2_util.make_edge_biolink(subject, object, predicate_label,
HMDB_PROVIDED_BY_CURIE_ID,
update_date)
else:
edge = kg2_util.make_edge(subject, object, relation_curie,
predicate_label, HMDB_PROVIDED_BY_CURIE_ID,
update_date)
edge["publications_info"] = publications_info
return edge
def make_kg2_graph(input_file_name: str, test_mode: bool = False):
nodes = []
edges = []
gene_ctr = 0
update_date = os.path.getmtime(input_file_name)
ontology_curie_id = NCBI_KB_CURIE_ID
ens_kp_node = kg2_util.make_node(ontology_curie_id, NCBI_KB_URL,
'NCBI Genes',
kg2_util.BIOLINK_CATEGORY_DATA_FILE,
update_date, ontology_curie_id)
nodes.append(ens_kp_node)
with open(input_file_name, 'r') as input_file:
for line in input_file:
if line.startswith('#'):
continue
gene_ctr += 1
if test_mode and gene_ctr > 10000:
break
fields = line.rstrip("\n").split("\t")
fields = [(field if field.strip() != '-' else None)
for field in fields]
[
taxon_id_str, ncbi_gene_id, gene_symbol, locus_tag,
synonyms_str, db_xrefs, chromosome, map_location, description,
type_of_gene, symbol_auth, full_name_auth, nomenc_status,
other_desig, modify_date, feature_type
] = fields
taxon_id_int = int(taxon_id_str)
if taxon_id_int != kg2_util.NCBI_TAXON_ID_HUMAN:
# skip neanderthal- and denisovan-specific genes
continue
node_synonyms = list()
if synonyms_str is not None:
node_synonyms += synonyms_str.split('|')
if other_desig is not None:
node_synonyms += other_desig.split('|')
if symbol_auth is not None and symbol_auth != gene_symbol:
node_synonyms = [symbol_auth] + node_synonyms
node_synonyms = list(set(node_synonyms))
full_name = full_name_auth
if full_name is None:
full_name = description
if type_of_gene != "unknown" or (db_xrefs is None) or (not db_xrefs.startswith("MIM:")) or \
nomenc_status is not None:
category_label = kg2_util.BIOLINK_CATEGORY_GENE
else:
full_name = 'Genetic locus associated with ' + full_name
category_label = kg2_util.BIOLINK_CATEGORY_GENOMIC_ENTITY
if full_name.startswith('microRNA'):
category_label = kg2_util.BIOLINK_CATEGORY_MICRORNA
node_dict = make_node(ncbi_gene_id, full_name, gene_symbol,
modify_date, category_label, node_synonyms)
node_curie_id = node_dict['id']
type_str = 'Type:' + type_of_gene
node_description = ''
if description is not None and description != full_name_auth:
node_description = description + '; '
node_description += type_str
if nomenc_status is not None:
nomenc_tag = 'official'
else:
nomenc_tag = 'unofficial'
if map_location is not None:
node_description += '; Locus:' + map_location
node_description += '; NameStatus:' + nomenc_tag
node_dict['description'] = node_description
nodes.append(node_dict)
org_curie = kg2_util.CURIE_PREFIX_NCBI_TAXON + ':' + taxon_id_str
predicate_label = 'in_taxon'
edge_dict = kg2_util.make_edge_biolink(node_curie_id, org_curie,
predicate_label,
NCBI_KB_CURIE_ID,
modify_date)
edges.append(edge_dict)
if db_xrefs is not None:
xrefs_list = db_xrefs.split('|')
for xref_curie in xrefs_list:
if xref_curie.startswith('HGNC:HGNC:'):
xref_curie = kg2_util.CURIE_PREFIX_HGNC + ':' + xref_curie.replace(
'HGNC:', '')
elif xref_curie.startswith('Ensembl:'):
xref_curie = xref_curie.upper()
elif xref_curie.startswith('MIM:'):
xref_curie = kg2_util.CURIE_PREFIX_OMIM + ':' + xref_curie.replace(
'MIM:', '')
elif xref_curie.startswith('miRBase:'):
xref_curie = kg2_util.CURIE_PREFIX_MIRBASE + ':' + xref_curie.replace(
'miRBase:', '')
edges.append(
kg2_util.make_edge(node_curie_id, xref_curie,
kg2_util.CURIE_ID_OWL_SAME_AS,
kg2_util.EDGE_LABEL_OWL_SAME_AS,
NCBI_KB_CURIE_ID, modify_date))
return {'nodes': nodes, 'edges': edges}
cursor.execute(sql)
results = cursor.fetchall()
for (action_type, description, parent_type) in results:
name = action_type.lower()
predicate_label = name.replace(' ', '_')
curie_id = kg2_util.CURIE_PREFIX_CHEMBL_MECHANISM + ':' + predicate_label
node_dict = make_node(curie_id,
CHEMBL_BASE_IRI_PREDICATE + predicate_label,
name,
kg2_util.BIOLINK_CATEGORY_RELATIONSHIP_TYPE,
description, [], [], update_date)
nodes.append(node_dict)
parent_label = parent_type.lower().replace(' ', '_')
parent_curie_id = kg2_util.CURIE_PREFIX_CHEMBL_MECHANISM + ':' + parent_label
new_edge = kg2_util.make_edge_biolink(
curie_id, parent_curie_id, kg2_util.EDGE_LABEL_BIOLINK_SUBCLASS_OF,
CHEMBL_KB_CURIE_ID, update_date)
edges.append(new_edge)
# get target-to-target subset_of relationships
sql = '''select distinct
t1.chembl_id,
target_relations.relationship,
t2.chembl_id
from
(target_dictionary as t1 inner join
target_relations on t1.tid = target_relations.tid) inner join
target_dictionary as t2 on t2.tid = target_relations.related_tid'''
if test_mode:
sql += str_sql_row_limit_test_mode
