def save_network(network: Network, config: Dict):
output_path = config['output-path']
# Save nodes
node_import_files = []
for label in network.node_labels():
file_name = 'nodes_%s.csv' % label.replace(';', '_')
nodes = set(network.get_nodes_by_label(label))
if len(nodes) > 0:
node_import_files.append(file_name)
with io.open(os.path.join(output_path, file_name),
'w',
encoding='utf-8',
newline='') as f:
writer = csv.writer(f, delimiter=',', quotechar='"')
all_attribute_keys = set()
for n in nodes:
all_attribute_keys.update(n.attributes.keys())
all_attribute_keys = sorted(all_attribute_keys)
writer.writerow([
'label_id:ID(Node-ID)', '_id:string', 'ids:string[]',
'names:string[]'
] + ['%s:string' % x for x in all_attribute_keys] + [':LABEL'])
for n in nodes:
row = [
n.label_id, n.id, ';'.join(n.ids), ';'.join(n.names)
]
for key in all_attribute_keys:
row.append(n.attributes[key] if key in
n.attributes else None)
row.append(n.label)
writer.writerow(row)
edge_metadata = {
'HAS_MOLECULAR_FUNCTION': [['source:string', 'pmid:string'],
['source',
'pmid']], # pmid int now not string
'BELONGS_TO_BIOLOGICAL_PROCESS': [['source:string', 'pmid:string'],
['source', 'pmid']],
'IN_CELLULAR_COMPONENT': [['source:string', 'pmid:string'],
['source', 'pmid']],
'INDICATES': [['source:string'], ['source']],
'REGULATES': [['source:string', 'pmid:string'], ['source', 'pmid']],
'TRANSCRIBES': [['source:string'], ['source']],
'CONTRAINDICATES': [['source:string'], ['source']],
'INDUCES': [['source:string'], ['source']],
'CODES': [['source:string', 'pmid:int'], ['source', 'pmid']],
'EQTL': [[
'source:string', 'pvalue:string', 'snp_chr:string',
'cis_trans:string'
], ['source', 'pvalue', 'snp_chr', 'cis_trans']],
'INTERACTS': [['source:string', 'description:string'],
['source', 'description']],
'TARGETS': [[
'source:string', 'known_action:boolean', 'actions:string[]',
'simplified_action:string'
],
[
'source', lambda attr:
('true' if attr['known_action'] else 'false')
if 'known_action' in attr else None,
lambda attr: ';'.join(attr['actions']),
'simplified_action'
]],
'ASSOCIATES_WITH':
[['source:string', 'num_pmids:int', 'num_snps:int', 'score:string'],
['source', 'num_pmids', 'num_snps', 'score']],
'HAS_ADR': [['source:string'], ['source']],
'ASSOCIATED_WITH_ADR': [['source:string'], ['source']]
}
# Save relationships
for x in edge_metadata:
with io.open(os.path.join(output_path, 'rel_%s.csv' % x),
'w',
encoding='utf-8',
newline='') as f:
writer = csv.writer(f, delimiter=',', quotechar='"')
writer.writerow([':START_ID(Node-ID)'] + edge_metadata[x][0] +
[':END_ID(Node-ID)', ':TYPE'])
for e in network.get_edges_by_label(x):
values = []
for l in edge_metadata[x][1]:
if isinstance(l, type(lambda: 0)):
values.append(l(e.attributes))
else:
values.append(e.attributes[l] if l in
e.attributes else None)
source_id = network.get_node_by_id(
e.source_node_id, e.source_node_label).label_id
target_id = network.get_node_by_id(
e.target_node_id, e.target_node_label).label_id
writer.writerow([source_id] + values + [target_id, e.label])
with io.open(os.path.join(output_path, 'create_indices.cypher'),
'w',
encoding='utf-8',
newline='') as f:
unique_labels = set()
for node_label in network.node_labels():
unique_labels.update(set(node_label.split(';')))
for node_label in unique_labels:
f.write('create constraint on (p:%s) assert p._id is unique;\n' %
node_label)
with io.open(os.path.join(output_path, 'import_admin.bat'),
'w',
encoding='utf-8',
newline='') as f:
f.write('@echo off\n')
f.write('net stop neo4j\n')
f.write('rmdir /s "%s"\n' %
os.path.join(config['Neo4j']['database-path'],
config['Neo4j']['database-name']))
f.write('CALL ' +
os.path.join(config['Neo4j']['bin-path'], 'neo4j-admin'))
f.write(' import ' +
'--database %s ' % config['Neo4j']['database-name'] +
' '.join(['--nodes %s' % x
for x in node_import_files]) + ' ' + ' '.join([
'--relationships rel_%s.csv' % x
for x in network.edge_labels()
]) + ' > import.log\n')
f.write('net start neo4j\n')
f.write(os.path.join(config['Neo4j']['bin-path'], 'cypher-shell'))
f.write(
' -u %s -p %s --non-interactive < create_indices.cypher 1>> import.log 2>&1\n'
% (config['Neo4j']['user'], config['Neo4j']['password']))
with io.open(os.path.join(output_path, 'import_admin.sh'),
'w',
encoding='utf-8',
newline='') as f:
f.write(os.path.join(config['Neo4j']['bin-path'], 'neo4j-admin'))
f.write(' import ' +
'--database %s ' % config['Neo4j']['database-name'] +
' '.join(['--nodes %s' % x
for x in node_import_files]) + ' ' + ' '.join([
'--relationships rel_%s.csv' % x
for x in network.edge_labels()
]) + ' > import.log\n')
from_id = association.find('from_code').text
from_name = association.find('from_name').text
to_namespace = association.find('to_namespace').text
to_id = association.find('to_code').text
to_name = association.find('to_name').text
if from_namespace != 'RxNorm' or to_namespace != 'MeSH':
continue
if association_type not in ['induces', 'CI_with', 'may_treat']:
continue
drug_id = 'RxNorm:%s' % from_id
if from_id not in added_rxnorm_drugs:
drug = Drug([drug_id], [from_name])
network.add_node(drug)
added_rxnorm_drugs.add(from_id)
else:
drug = network.get_node_by_id(drug_id, 'Drug')
disease_id = 'MeSH:%s' % to_id
if to_id not in added_mesh_diseases:
disease = Disease([disease_id], [to_name])
network.add_node(disease)
added_mesh_diseases.add(to_id)
else:
disease = network.get_node_by_id(disease_id, 'Disease')
rel = {'source': 'MEDRT'}
if association_type == 'induces':
network.add_edge(Edge(drug, disease, 'INDUCES', rel))
elif association_type == 'CI_with':
network.add_edge(Edge(drug, disease, 'CONTRAINDICATES', rel))
elif association_type == 'may_treat':
network.add_edge(Edge(drug, disease, 'INDICATES', rel))
drug_count += 1
indications = {
x.target_node_id
for x in network.get_node_edges_by_label(drug, 'INDICATES')
}
contraindications = {
x.target_node_id
for x in network.get_node_edges_by_label(
drug, 'CONTRAINDICATES')
}
if not indications.isdisjoint(contraindications):
drug_check_failed_count += 1
for intersection in indications.intersection(
contraindications):
disease = network.get_node_by_id(intersection, 'Disease')
drug_text = '%s<br/>%s' % (node_ids_to_links(
drug.ids), '<br/>'.join(drug.names))
indications_text = '<br/>'.join([
'%s: %s -> %s' %
(x.attributes['source'],
node_ids_to_links([x.source_node_id]),
node_ids_to_links([x.target_node_id]))
for x in network.get_edges_from_to(
drug, disease, 'INDICATES')
])
contraindications_text = '<br/>'.join([
'%s: %s -> %s' %
(x.attributes['source'],
node_ids_to_links([x.source_node_id]),
node_ids_to_links([x.target_node_id]))
id_node = owl_class.find(obo_in_owl_ns + 'id')
obo_ns_node = owl_class.find(obo_in_owl_ns + 'hasOBONamespace')
label_node = owl_class.find(rdfs_ns + 'label')
if id_node is not None and obo_ns_node is not None:
go_class = GOClass([id_node.text], [label_node.text])
network.add_node(go_class)
go_class_ns_lookup[id_node.text] = obo_ns_node.text
for alternative_id_node in owl_class.findall(obo_in_owl_ns + 'hasAlternativeId'):
go_class_redirects[alternative_id_node.text] = id_node.text
with io.open(annotations_file, 'r', encoding='utf-8', newline='') as f:
reader = csv.reader(f, delimiter='\t', quotechar='"')
for row in reader:
if not row[0][0].startswith('!') and row[12] == 'taxon:9606':
gene = Gene(['UniProtKB:%s' % row[1], 'HGNC:%s' % row[2]], [])
network.add_node(gene)
if row[4] not in go_class_ns_lookup:
# print('[WARN] GO id %s is obsolete, redirecting to %s' % (row[4], go_class_redirects[row[4]]))
row[4] = go_class_redirects[row[4]]
label = go_class_ns_lookup[row[4]].upper()
if label == 'MOLECULAR_FUNCTION':
label = 'HAS_' + label
elif label == 'BIOLOGICAL_PROCESS':
label = 'BELONGS_TO_' + label
elif label == 'CELLULAR_COMPONENT':
label = 'IN_' + label
e = Edge(gene, network.get_node_by_id(row[4], 'GOClass'), label, {'source': 'GO,%s' % row[5]})
network.add_edge(e)
network.save('../data/GO/graph.json')
ids = ['DrugCentral:%s' % row[0], 'DrugBank:%s' % row[1]]
if row[2]:
ids.append('RxNorm:%s' % row[2])
network.add_node(Drug(ids, [row[3]]))
with io.open('../data/DrugCentral/drugcentral_indications.csv',
'r',
encoding='utf-8',
newline='') as f:
reader = csv.reader(f, delimiter=',', quotechar='"')
next(reader, None)
for row in reader:
disease = Disease(['SnoMedCT:%s' % row[2],
'UMLS:%s' % row[3]], [row[1]])
network.add_node(disease)
drug = network.get_node_by_id('DrugBank:%s' % row[0], 'Drug')
e = Edge(drug, disease, 'INDICATES', {'source': 'DrugCentral'})
network.add_edge(e)
with io.open('../data/DrugCentral/drugcentral_contraindications.csv',
'r',
encoding='utf-8',
newline='') as f:
reader = csv.reader(f, delimiter=',', quotechar='"')
next(reader, None)
for row in reader:
disease = Disease(['SnoMedCT:%s' % row[2],
'UMLS:%s' % row[3]], [row[1]])
network.add_node(disease)
drug = network.get_node_by_id('DrugBank:%s' % row[0], 'Drug')
e = Edge(drug, disease, 'CONTRAINDICATES', {'source': 'DrugCentral'})
