def populate_map_with_edges(self):
for from_edge in self.edges:
from_node_sequence = from_edge.get_start()
vertex = self.nodes_map[from_node_sequence]
has = has = self.has_in_list(from_edge)
if not has:
self.node_to_edges[vertex.get_sequence()].append(from_edge)
residual_edge = Edge(from_edge.get_end(), from_edge.get_start(), 0)
self.residual_network[from_edge.get_end()].append(residual_edge)
if not from_edge.get_start() in self.floyd_warshall_map:
self.floyd_warshall_map[from_edge.get_start()] = {}
self.floyd_warshall_map[from_edge.get_start()][
from_edge.get_end()] = from_edge.get_weight()
if not self.is_directed:
to_edge = Edge(from_edge.get_end(), from_edge.get_start(),
from_edge.get_weight())
has = self.has_in_list(to_edge)
if not has:
self.node_to_edges[to_edge.get_start()].append(to_edge)
#TODO fill map when not directed
for node in self.get_nodes():
if not node.get_sequence() in self.floyd_warshall_map:
self.floyd_warshall_map[node.get_sequence()] = {}
def add_lane(lane_id, source_location_number, destination_location_number):
lane_1_edge = Edge(lane_id, nodes_vertex_list[source_location_number],
nodes_vertex_list[destination_location_number], 1)
edges_vertex_list.append(lane_1_edge)
lane_2_edge = Edge(lane_id, nodes_vertex_list[destination_location_number],
nodes_vertex_list[source_location_number], 1)
edges_vertex_list.append(lane_2_edge)
def add_lane(self, lane_id, source_loc_no, dest_loc_no):
lane1 = Edge(lane_id, self.nodes_list[source_loc_no],
self.nodes_list[dest_loc_no], 1)
self.edges_list.append(lane1)
lane2 = Edge(lane_id, self.nodes_list[dest_loc_no],
self.nodes_list[source_loc_no], 1)
self.edges_list.append(lane2)
def get_common_genes(disease_pairs, networks, writing_files):
new_networks = []
for index, disease_pair in enumerate(disease_pairs):
network = networks[index]
d1_genes, d2_genes = get_genes(disease_pair)
common_genes = d1_genes.intersection(d2_genes)
d1 = Disease([disease_pair[0]], [])
network.add_node(d1)
d2 = Disease([disease_pair[1]], [])
network.add_node(d2)
for g_id in common_genes:
gene = Gene([g_id], [])
network.add_node(gene)
network.add_edge(Edge(gene, d1, 'ASSOCIATES_WITH', {}))
network.add_edge(Edge(gene, d2, 'ASSOCIATES_WITH', {}))
if len(common_genes) > 0 and writing_files:
temp_id1 = disease_pair[0].replace(':', '-')
temp_id2 = disease_pair[1].replace(':', '-')
path = '../analysis/disease_pairs/' + temp_id1 + '_' + temp_id2
try:
os.mkdir(path)
except FileExistsError:
pass
with io.open(path + '/' + temp_id1 + '_' + temp_id2 + '_common_genes.tsv', 'w', encoding='utf-8', newline='') as common_genes_file:
common_genes_file.write('#Common genes of ' + disease_pair[0] + ' and ' + disease_pair[1] + '\n')
for gene in common_genes:
common_genes_file.write(gene + '\n')
new_networks.append(network)
print('Done getting genes')
return new_networks
def draw(self):
glMatrixMode(GL_MODELVIEW)
glPushMatrix()
glMultMatrixf(self._identity_mat)
glColor3f(self._color[0],self._color[1],self._color[2])
for edge in self._edges:
Edge.draw_edge(Edge(self._vertices[edge[0]],self._vertices[edge[1]]))
glPopMatrix()
def get_common_variants(disease_pairs, networks, writing_files):
new_networks = []
for index, disease_pair in enumerate(disease_pairs):
network = networks[index]
d1 = Disease([disease_pair[0]], [])
network.add_node(d1)
d2 = Disease([disease_pair[1]], [])
network.add_node(d2)
common_variants = [] # each variant is an array
query = """ MATCH (d1:Disease)--(v:Variant)--(d2:Disease) WHERE {d1_id} in d1.ids AND {d2_id} in d2.ids RETURN v.`_id` """
results = session.run(query, parameters={'d1_id': disease_pair[0], 'd2_id': disease_pair[1]})
for result in results:
v_id = result['v.`_id`']
common_variants.append([v_id, 'disease associated'])
variant = Variant([v_id], [])
network.add_node(variant)
network.add_edge(Edge(d1, variant, 'ASSOCIATES_WITH', {}))
network.add_edge(Edge(d2, variant, 'ASSOCIATES_WITH', {}))
# variants associated to common genes
d1_genes, d2_genes = get_genes(disease_pair)
common_genes_ids = d1_genes.intersection(d2_genes)
for gene_id in common_genes_ids:
query = """ MATCH (g:Gene)-[a]-(v:Variant) WHERE {g_id} in g.ids RETURN v.`_id`, type(a) """
results = session.run(query, parameters={'g_id': gene_id})
for result in results:
v_id = result['v.`_id`']
type = result['type(a)'] # can be CODES or EQTL
variant_pair = v_id + '-' + gene_id
common_variants.append([variant_pair, 'gene associated'])
variant = Variant([v_id], [])
network.add_node(variant)
gene = Gene([gene_id], [])
network.add_node(gene)
network.add_edge(Edge(gene, variant, type, {}))
network.add_edge(Edge(gene, d1, 'ASSOCIATES_WITH', {}))
network.add_edge(Edge(gene, d2, 'ASSOCIATES_WITH', {}))
new_networks.append(network)
if len(common_variants) > 0 and writing_files:
temp_id1 = disease_pair[0].replace(':', '-')
temp_id2 = disease_pair[1].replace(':', '-')
path = '../analysis/disease_pairs/' + temp_id1 + '_' + temp_id2
try:
os.mkdir(path)
except FileExistsError:
pass
with io.open(path + '/' + temp_id1 + '_' + temp_id2 + '_common_variants.tsv', 'w', encoding='utf-8',
newline='') as common_variants_file:
common_variants_file.write(
'#Common variants associated with ' + disease_pair[0] + ' and ' + disease_pair[1] + '\n')
for variant in common_variants:
common_variants_file.write(variant[0] + '\t' + variant[1] + '\n')
print('Done getting variants')
return new_networks
def populate_edges(edges_representation):
edges = []
for representation in edges_representation:
start = representation[0]
end = representation[1]
weight = representation[2]
edge = Edge(start, end, weight)
edges.append(edge)
return edges
def get_transpose_graph(self):
edges = []
for edge in self.edges:
transposed_edge = Edge(edge.get_end(), edge.get_start(),
edge.get_weight())
edges.append(transposed_edge)
transposed_graph = Graph(self.root, self.nodes, edges,
self.is_directed)
return transposed_graph
def generate(filePath):
number_of_cities, costs, reliabilities = readValueFromFile(filePath)
city_list = alphabet_list[0:int(number_of_cities)]
edge_list = list()
row = 0
col = 1
for reliability, cost in zip(reliabilities, costs):
edge_list.append(
Edge(city_list[row], city_list[col], float(cost),
float(reliability)))
if (col == len(city_list) - 1):
row = row + 1
col = row + 1
else:
col = col + 1
return city_list, edge_list
def draw(self):
glMatrixMode(GL_MODELVIEW)
glPushMatrix()
gluLookAt(-2, 2, -6, 0, 0, 0, 0, 1, 0)
glMultMatrixf(self._identity_mat)
color = 0
colors = [(1, 0, 0), (1, 1, 0), (0, 1, 1), (1, 0, 0), (1, 1, 0),
(0, 1, 1)]
for edge in self._edges:
glColor3f(colors[color][0], colors[color][1], colors[color][2])
if color > 2:
Edge.draw_dotted_edge(
Edge(self._vertices[edge[0]], self._vertices[edge[1]]))
else:
Edge.draw_edge(
Edge(self._vertices[edge[0]], self._vertices[edge[1]]))
color += 1
glPopMatrix()
if row[0] in external_id_lookup:
drug_ids.extend(external_id_lookup[row[0]])
drug = Drug(drug_ids, [row[1]])
network.add_node(drug)
gene_ids = ['HGNC:%s' % row[2]]
if row[4]:
gene_ids.append(row[4])
gene = Gene(gene_ids, [row[3]])
network.add_node(gene)
rel = {
'source': 'DrugBank',
'known_action': row[5] == 1,
'actions': row[6].split(',') if row[6] else [],
'simplified_action': row[7]
}
network.add_edge(Edge(drug, gene, 'TARGETS', rel))
for row in interactions_results:
drug1 = Drug(['DrugBank:%s' % row[0]], [row[1]])
network.add_node(drug1)
drug2 = Drug(['DrugBank:%s' % row[2]], [row[3]])
network.add_node(drug2)
rel = {
'source': 'DrugBank',
'description': row[4]
}
network.add_edge(Edge(drug1, drug2, 'INTERACTS', rel))
adr_id_counter = 1
for row in snp_adrs_results:
# drugbank_id, gene_symbol, rs_id, adverse_reaction, description, pubmed_id
adr = AdverseDrugReaction(['GenCoNet:DrugBank_ADR_%s' % adr_id_counter], [])
adr_id_counter += 1
def get_common_rnas(disease_pairs, networks, writing_files):
new_networks = []
for index, disease_pair in enumerate(disease_pairs):
network = networks[index]
d1 = Disease([disease_pair[0]], [])
network.add_node(d1)
d2 = Disease([disease_pair[1]], [])
network.add_node(d2)
d1_genes_ids, d2_genes_ids = get_genes(disease_pair)
# this differentiation is done to get the correct number of regulated, in this subgraph present genes
d1_only_genes_ids = d1_genes_ids.difference(d2_genes_ids)
d2_only_genes_ids = d2_genes_ids.difference(d1_genes_ids)
common_genes_ids = d1_genes_ids.intersection(d2_genes_ids)
common_rnas = {} #dict with the RNA name as key and the regulated genes as an array as value
for gene_id in common_genes_ids:
query = """ MATCH (g:Gene)-[:REGULATES]-(r:RNA) WHERE {gene_id} IN g.ids RETURN distinct(r.`_id`) """
results = session.run(query, parameters={'gene_id': gene_id})
for result in results:
rna_id = result['(r.`_id`)']
if rna_id in common_rnas:
gene_ids = common_rnas[rna_id]
gene_ids.append(gene_id)
common_rnas[rna_id] = gene_ids
else:
common_rnas[rna_id] = [gene_id]
gene = Gene([gene_id], [])
network.add_node(gene)
rna = RNA([rna_id], [])
network.add_node(rna)
network.add_edge(Edge(rna, gene, 'REGULATES', {}))
network.add_edge(Edge(gene, d1, 'ASSOCIATES_WITH', {}))
network.add_edge(Edge(gene, d2, 'ASSOCIATES_WITH', {}))
rnas_d1_only_genes = {}
for gene_id in d1_only_genes_ids:
query = """ MATCH (g:Gene)-[:REGULATES]-(r:RNA) WHERE {gene_id} IN g.ids RETURN distinct(r.`_id`) """
results = session.run(query, parameters={'gene_id': gene_id})
for result in results:
rna_id = result['(r.`_id`)']
if rna_id in rnas_d1_only_genes:
gene_ids = rnas_d1_only_genes[rna_id]
gene_ids.append(gene_id)
rnas_d1_only_genes[rna_id] = gene_ids
else:
rnas_d1_only_genes[rna_id] = [gene_id]
rnas_d2_only_genes = {}
for gene_id in d2_only_genes_ids:
query = """ MATCH (g:Gene)-[:REGULATES]-(r:RNA) WHERE {gene_id} IN g.ids RETURN distinct(r.`_id`) """
results = session.run(query, parameters={'gene_id': gene_id})
for result in results:
rna_id = result['(r.`_id`)']
if rna_id in rnas_d2_only_genes:
gene_ids = rnas_d2_only_genes[rna_id]
gene_ids.append(gene_id)
rnas_d2_only_genes[rna_id] = gene_ids
else:
rnas_d2_only_genes[rna_id] = [gene_id]
#common_rnas = {'A':1, 'B':1, 'D':1}
#rnas_d1_only_genes = {'A':2, 'B':1, 'E':1}
#rnas_d2_only_genes = {'A':2, 'C':1, 'E':1}
for rna_id in rnas_d1_only_genes:
if rna_id in common_rnas:
# common_rnas have already been added to the network, here the number of regulated genes is updated
common_rnas[rna_id] = common_rnas[rna_id] + rnas_d1_only_genes[rna_id]
elif rna_id in rnas_d2_only_genes:
# RNA regulates genes associated to d1 and genes associated to d2, RNA does not regulate a common gene
common_rnas[rna_id] = rnas_d1_only_genes[rna_id] + rnas_d2_only_genes[rna_id]
g1_ids = rnas_d1_only_genes[rna_id]
g2_ids = rnas_d2_only_genes[rna_id]
rna = RNA([rna_id], [])
network.add_node(rna)
for g_id in g1_ids:
gene = Gene([g_id], [])
network.add_node(gene)
network.add_edge(Edge(gene, d1, 'ASSOCIATES_WITH', {}))
network.add_edge(Edge(rna, gene, 'REGULATES', {}))
for g_id in g2_ids:
gene = Gene([g_id], [])
network.add_node(gene)
network.add_edge(Edge(gene, d2, 'ASSOCIATES_WITH', {}))
network.add_edge(Edge(rna, gene, 'REGULATES', {}))
del rnas_d2_only_genes[rna_id]
for rna_id in rnas_d2_only_genes:
if rna_id in common_rnas:
# common_rnas have already been added to the network, here the number of regulated genes is updated
common_rnas[rna_id] = common_rnas[rna_id] + rnas_d2_only_genes[rna_id]
# for each RNA add an array of RNAs, which regulate this RNA. MRNAs are not included
for rna_id in common_rnas:
second_rnas = []
query = """MATCH (r:RNA)-[:REGULATES]-(n:RNA) WHERE {r_id} IN r.ids AND NOT n.label_id CONTAINS "MRNA" RETURN distinct(n.`_id`) """
results = session.run(query, parameters={'r_id': rna_id})
rna = RNA([rna_id], [])
network.add_node(rna)
for result in results:
second_rna_id = result['(n.`_id`)']
second_rnas.append(second_rna_id)
second_rna = RNA([second_rna_id], [])
network.add_node(second_rna)
network.add_edge(Edge(second_rna, rna, 'REGULATES', {}))
# the value of common_rnas is now changed to an array where at the first position the array with the regulated
# genes from this subgraph is stored and at the second position the array with RNAs regulating the RNA is stored
common_rnas[rna_id] = [common_rnas[rna_id], second_rnas]
new_networks.append(network)
if len(common_rnas) > 0 and writing_files:
temp_id1 = disease_pair[0].replace(':', '-')
temp_id2 = disease_pair[1].replace(':', '-')
path = '../analysis/disease_pairs/' + temp_id1 + '_' + temp_id2
try:
os.mkdir(path)
except FileExistsError:
pass
with io.open(path + '/' + temp_id1 + '_' + temp_id2 + '_common_rnas.tsv', 'w', encoding='utf-8', newline='') as common_rnas_file:
common_rnas_file.write('#Common rnas of ' + disease_pair[0] + ' and ' + disease_pair[1] + '\tsorted by number of regulated genes\tRegulated genes\tRNAs regulating the RNA\n')
for key, value in sorted(common_rnas.items(), key=lambda item: len(item[1][0]), reverse=True):
# sort by the number of genes in this subgraph which are regulated by the RNA
regulated_genes = str(value[0])
regulated_genes = regulated_genes.replace('[', '')
regulated_genes = regulated_genes.replace(']', '')
regulated_genes = regulated_genes.replace('\'', '')
second_rnas = str(value[1])
second_rnas = second_rnas.replace('[', '')
second_rnas = second_rnas.replace(']', '')
second_rnas = second_rnas.replace('\'', '')
common_rnas_file.write(key + '\t' + str(len(value[0])) + '\t' + regulated_genes + '\t' + second_rnas + '\n')
print('Done getting RNAs')
return new_networks
def get_common_drugs(disease_pairs, networks, writing_files):
new_networks = []
for index, disease_pair in enumerate(disease_pairs):
network = networks[index]
d1 = Disease([disease_pair[0]], [])
network.add_node(d1)
d2 = Disease([disease_pair[1]], [])
network.add_node(d2)
# the drug INDICATES, CONTRAINDICATES or INDUCES both diseases
common_drugs = set()
query = """ MATCH (d1:Disease)-[a]-(n:Drug)--(d2:Disease) WHERE {d1_id} IN d1.ids AND {d2_id} IN d2.ids RETURN distinct(type(a)), n.`_id` """
results = session.run(query, parameters={'d1_id': disease_pair[0], 'd2_id': disease_pair[1]})
for result in results:
drug_id = result['n.`_id`']
type = result['(type(a))']
common_drugs.add(drug_id)
drug = Drug([drug_id], [])
network.add_node(drug)
network.add_edge(Edge(drug, d1, type, {}))
query = """ MATCH (d1:Disease)--(n:Drug)-[a]-(d2:Disease) WHERE {d1_id} IN d1.ids AND {d2_id} IN d2.ids RETURN distinct(type(a)), n.`_id` """
results = session.run(query, parameters={'d1_id': disease_pair[0], 'd2_id': disease_pair[1]})
for result in results:
drug_id = result['n.`_id`']
type = result['(type(a))']
common_drugs.add(drug_id)
drug = Drug([drug_id], [])
network.add_node(drug)
network.add_edge(Edge(drug, d2, type, {}))
# the drug targets a gene of one disease and is associated to the other disease
query = """ MATCH (d1:Disease)-[a]-(n:Drug)-[:TARGETS]-(g:Gene)-[:ASSOCIATES_WITH]-(d2:Disease) WHERE {d1_id} IN d1.ids AND {d2_id} IN d2.ids RETURN distinct(type(a)), n.`_id`, g.`_id` """
results = session.run(query, parameters={'d1_id': disease_pair[0], 'd2_id': disease_pair[1]})
for result in results:
drug_id = result['n.`_id`']
type = result['(type(a))']
common_drugs.add(drug_id)
drug = Drug([drug_id], [])
network.add_node(drug)
network.add_edge(Edge(drug, d1, type, {}))
gene_id = result['g.`_id`']
gene = Gene([gene_id], [])
network.add_node(gene)
network.add_edge(Edge(drug, gene, 'TARGETS', {'actions': []}))
network.add_edge(Edge(gene, d2, 'ASSOCIATES_WITH', {}))
query = """ MATCH (d2:Disease)-[a]-(n:Drug)-[:TARGETS]-(g:Gene)-[:ASSOCIATES_WITH]-(d1:Disease) WHERE {d1_id} IN d1.ids AND {d2_id} IN d2.ids RETURN distinct(type(a)), n.`_id`, g.`_id` """
results = session.run(query, parameters={'d1_id': disease_pair[0], 'd2_id': disease_pair[1]})
for result in results:
drug_id = result['n.`_id`']
type = result['(type(a))']
common_drugs.add(drug_id)
drug = Drug([drug_id], [])
network.add_node(drug)
network.add_edge(Edge(drug, d2, type, {}))
gene_id = result['g.`_id`']
gene = Gene([gene_id], [])
network.add_node(gene)
network.add_edge(Edge(drug, gene, 'TARGETS', {'actions': []}))
network.add_edge(Edge(gene, d1, 'ASSOCIATES_WITH', {}))
# the drug targets one gene which is associated to both diseases or the drug targets two different genes
# where each gene is associated to one of the diseases
query = """ MATCH (d1:Disease)-[:ASSOCIATES_WITH]-(g1:Gene)-[:TARGETS]-(n:Drug)-[:TARGETS]-(g2:Gene)-
[:ASSOCIATES_WITH]-(d2:Disease) WHERE {d1_id} IN d1.ids AND {d2_id} IN d2.ids RETURN n.`_id`, g1.`_id`, g2.`_id` """
results = session.run(query, parameters={'d1_id': disease_pair[0], 'd2_id': disease_pair[1]})
for result in results:
drug_id = result['n.`_id`']
common_drugs.add(drug_id)
g1_id = result['g1.`_id`']
g2_id = result['g2.`_id`']
g1 = Gene([g1_id], [])
network.add_node(g1)
network.add_edge(Edge(g1, d1, 'ASSOCIATES_WITH', {}))
drug = Drug([drug_id], [])
network.add_node(drug)
network.add_edge(Edge(drug, g1, 'TARGETS', {'actions': []}))
g2 = Gene([g2_id], [])
network.add_node(g2)
network.add_edge(Edge(drug, g2, 'TARGETS', {'actions': []}))
network.add_edge(Edge(g2, d2, 'ASSOCIATES_WITH', {}))
new_networks.append(network)
if len(common_drugs) > 0 and writing_files:
temp_id1 = disease_pair[0].replace(':', '-')
temp_id2 = disease_pair[1].replace(':', '-')
path = '../analysis/disease_pairs/' + temp_id1 + '_' + temp_id2
try:
os.mkdir(path)
except FileExistsError:
pass
with io.open(path + '/' + temp_id1 + '_' + temp_id2 + '_common_drugs.tsv', 'w', encoding='utf-8', newline='') as common_drugs_file:
common_drugs_file.write('#Common drugs of ' + disease_pair[0] + ' and ' + disease_pair[1] + '\n')
for drug in common_drugs:
common_drugs_file.write(drug + '\n')
print('Done getting drugs')
return new_networks
#!/usr/bin/env python3
import io
import csv
from model.network import Network
from model.drug import Drug
from model.disease import Disease
from model.edge import Edge
network = Network()
with io.open('../data/PubMed/drug_disease.csv',
'r',
encoding='utf-8',
newline='') as f:
reader = csv.reader(f, delimiter=',', quotechar='"')
next(reader, None)
for row in reader:
drug = Drug(['DrugBank:%s' % row[1]], [row[0]])
disease = Disease([row[4]], [row[3]])
network.add_node(drug)
network.add_node(disease)
network.add_edge(
Edge(drug, disease, row[2], {
'source': 'PubMed',
'pmid': row[5]
}))
network.save('../data/PubMed/graph.json')
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))
network.save('../data/MED-RT/graph.json')
pmid = row[8].split(':')
pmid = pmid[1]
source_database = row[12]
source_database = source_database.replace('\"', '')
if (mirna_rnacentral_id + '$' +
gene_hgnc_id) in edge_source_target_lookup:
reg_edges = network.get_edges_from_to(
mirna, gene, 'REGULATES')
for reg_edge in reg_edges:
if reg_edge.attributes['source'] == (
'EBI-GOA-miRNA, ' + source_database):
pmid = reg_edge.attributes['pmid'] + ', ' + pmid
network.delete_edge(reg_edge)
e = Edge(
mirna, gene, 'REGULATES', {
'source':
'EBI-GOA-miRNA, ' + source_database,
'pmid': pmid
})
network.add_edge(e)
edge_source_target_lookup.append(
mirna_rnacentral_id + '$' + gene_hgnc_id)
else:
e = Edge(
mirna, gene, 'REGULATES', {
'source': 'EBI-GOA-miRNA, ' + source_database,
'pmid': pmid
})
network.add_edge(e)
edge_source_target_lookup.append(mirna_rnacentral_id +
'$' + gene_hgnc_id)
# GOs
network = Network()
drug_lookup = {}
with io.open(drug_file, 'r', encoding='utf-8', newline='') as f:
reader = csv.reader(f, delimiter='\t', quotechar='"')
for row in reader:
drug_lookup[row[0].strip()] = row[1].strip()
# 1: STITCH compound id (flat, see above)
# 2: UMLS concept id as it was found on the label
# 3: method of detection: NLP_indication / NLP_precondition / text_mention
# 4: concept name
# 5: MedDRA concept type (LLT = lowest level term, PT = preferred term; in a few cases the term is neither LLT nor PT)
# 6: UMLS concept id for MedDRA term
# 7: MedDRA concept name
# All side effects found on the labels are given as LLT. Additionally, the PT is shown. There is at least one
# PT for every LLT, but sometimes the PT is the same as the LLT.
with io.open(file, 'r', encoding='utf-8', newline='') as f:
reader = csv.reader(f, delimiter='\t', quotechar='"')
for row in reader:
pubchem_id = row[0][4::].lstrip('0')
drug = Drug(['PubChem:CID%s' % pubchem_id], [drug_lookup[row[0]]] if row[0] in drug_lookup else [])
network.add_node(drug)
disease = Disease(['UMLS:%s' % row[1], 'UMLS:%s' % row[5]], [row[3], row[6]])
network.add_node(disease)
network.add_edge(Edge(drug, disease, 'INDICATES', {'source': 'SIDER'}))
network.save('../data/SIDER/graph.json')
network = Network()
with io.open(file, 'r', encoding='utf-8', newline='') as f:
reader = csv.reader(f, delimiter='\t', quotechar='"')
next(reader, None)
for row in reader:
row = [x.strip() for x in row]
if not row[0] or not row[7] or not row[8]:
continue
gene_ids = {'HGNC:%s' % row[0]}
if row[2]:
gene_ids.add('Entrez:%s' % row[2])
gene = Gene(gene_ids, [])
network.add_node(gene)
drug_name = row[7].replace('(%s)' % row[8], '').replace(row[8],
'').strip()
drug = Drug(['ChEMBL:%s' % row[8]], [drug_name] if drug_name else [])
network.add_node(drug)
rel = {
'source': 'DGIdb,%s' % row[3],
'actions': [row[4]],
}
if row[9]:
pubmed_ids = ','.join(
['PMID:%s' % x for x in row[9].strip().split(',')])
rel['source'] += ',%s' % pubmed_ids
network.add_edge(Edge(drug, gene, 'TARGETS', rel))
network.save('../data/DGIdb/graph.json')
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')
# 30 OR or BETA
# 31 95% CI (TEXT)
# 32 PLATFORM [SNPS PASSING QC]
# 33 CNV
loc_pattern = re.compile(r'LOC[0-9]+')
with io.open(file, 'r', encoding='utf-8', newline='') as f:
reader = csv.reader(f, delimiter='\t', quotechar='"')
next(reader, None)
for row in reader:
if not row[14]:
continue
gene_ids = row[14].replace(' x ', ', ').replace(' - ',
', ').split(', ')
print(row[14])
print('\t', gene_ids)
for gene_id in gene_ids:
if loc_pattern.fullmatch(gene_id) is not None:
continue
gene = Gene(['HGNC:%s' % gene_id], [])
network.add_node(gene)
for variant_id in {x.strip() for x in row[21].split(';')}:
variant = Variant(['dbSNP:%s' % variant_id], [])
network.add_node(variant)
network.add_edge(
Edge(gene, variant, 'CODES', {
'source': 'GWASCatalog',
'pmid': row[1]
}))
network.save('../data/GWAS-Catalog/graph.json')
def load_from_dict(self, source: {}):
py_class_map = {}
for label in source['node_types']:
if ';' not in label:
module_name = source['node_types'][label]
module = __import__(module_name)
for package in module_name.split('.')[1:]:
module = getattr(module, package)
py_class_map[label] = getattr(module, label)
for node in source['nodes']:
node_instance: Node
if ';' not in node['_label']:
class_ = py_class_map[node['_label']]
node_instance = class_(node['ids'], node['names'])
elif 'RNA' in node['_label']:
label = node['_label']
if 'CircRNA' in label:
node_instance = CircRNA(node['ids'], node['names'])
elif 'ERNA' in label:
node_instance = ERNA(node['ids'], node['names'])
elif 'LncRNA' in label:
node_instance = LncRNA(node['ids'], node['names'])
elif 'MiRNA' in label:
node_instance = MiRNA(node['ids'], node['names'])
elif 'MRNA' in label:
node_instance = MRNA(node['ids'], node['names'])
elif 'NcRNA' in label:
node_instance = NcRNA(node['ids'], node['names'])
elif 'PiRNA' in label:
node_instance = PiRNA(node['ids'], node['names'])
elif 'Pseudogene' in label:
node_instance = Pseudogene(node['ids'], node['names'])
elif 'Ribozyme' in label:
node_instance = Ribozyme(node['ids'], node['names'])
elif 'RRNA' in label:
node_instance = RRNA(node['ids'], node['names'])
elif 'ScaRNA' in label:
node_instance = ScaRNA(node['ids'], node['names'])
elif 'ScRNA' in label:
node_instance = ScRNA(node['ids'], node['names'])
elif 'SnoRNA' in label:
node_instance = SnoRNA(node['ids'], node['names'])
elif 'SnRNA' in label:
node_instance = SnRNA(node['ids'], node['names'])
else:
node_instance = RNA(node['ids'], node['names'])
else:
print('[Err ] Failed to load node with multiple labels', node)
continue
for key in node.keys():
if key not in ['_id', 'ids', 'names', '_label']:
node_instance.attributes[key] = node[key]
self.add_node(node_instance)
for edge in source['edges']:
params = dict(edge)
del params['_source_id']
del params['_source_label']
del params['_target_id']
del params['_target_label']
del params['_label']
source_node = self.get_node_by_id(edge['_source_id'],
edge['_source_label'])
if source_node is None:
print(
'Failed to load edge: could not find source node with label %s and id %s'
% (edge['_source_label'], edge['_source_id']))
target_node = self.get_node_by_id(edge['_target_id'],
edge['_target_label'])
if target_node is None:
print(
'Failed to load edge: could not find target node with label %s and id %s'
% (edge['_target_label'], edge['_target_id']))
self.add_edge(
Edge(source_node, target_node, edge['_label'], params))
drug_names.append(prop[1])
elif property_defs[prop[0]] == 'UMLS_CUI':
drug_ids.append('UMLS:%s' % prop[1])
elif property_defs[prop[0]] == 'Synonym':
drug_names.append(prop[1])
drug_names = [
x.replace('[VA Product]', '').strip() for x in drug_names
]
drug = Drug(drug_ids, drug_names)
network.add_node(drug)
for role in concept['roles']:
role_name = role_defs[role[0]]
rel = {'source': 'NDFRT'}
if role_name == 'induces {NDFRT}':
network.add_edge(
Edge(drug, ('NDFRT:%s' % role[1], 'Disease'), 'INDUCES',
rel))
elif role_name == 'CI_with {NDFRT}':
network.add_edge(
Edge(drug, ('NDFRT:%s' % role[1], 'Disease'),
'CONTRAINDICATES', rel))
elif role_name == 'may_treat {NDFRT}':
network.add_edge(
Edge(drug, ('NDFRT:%s' % role[1], 'Disease'), 'INDICATES',
rel))
elif concept['kind'] == kind_defs_rev['DISEASE_KIND']:
disease_ids = ['NDFRT:%s' % concept['code']]
disease_names = [concept['name']]
for prop in concept['properties']:
if property_defs[prop[0]] == 'SNOMED_CID':
disease_ids.append('SnoMedCT:%s' % prop[1])
elif property_defs[prop[0]] == 'UMLS_CUI':
def get_given_drugs_related_info(disease_pairs, drugs): # first disease pair with first drug array
all_networks = [] # contains an array for each disease pair
for index, disease_pair in enumerate(disease_pairs):
networks_per_drug = [] # contains a network for each drug
pair_drugs_ids = drugs[index]
temp_id1 = disease_pair[0].replace(':', '-')
temp_id2 = disease_pair[1].replace(':', '-')
path = '../analysis/disease_pairs/' + temp_id1 + '_' + temp_id2
for drug_id in pair_drugs_ids:
try:
os.mkdir(path)
except FileExistsError:
pass
network = Network()
d1 = Disease([disease_pair[0]], [])
network.add_node(d1)
d2 = Disease([disease_pair[1]], [])
network.add_node(d2)
drug = Drug([drug_id], [])
network.add_node(drug)
temp_drug_id = drug_id.replace(':', '-')
with io.open(path + '/' + temp_id1 + '_' + temp_id2 + '_' + temp_drug_id + '_results.txt', 'w', encoding='utf-8', newline='') as results_file:
results_file.write('In this file all information about the connection between ' + disease_pair[0] +
' and ' + disease_pair[1] + ' and the drug ' + drug_id + ' is summarized:\n')
# the drug INDICATES, CONTRAINDICATES or INDUCES the disease
query = """ MATCH (d:Disease)-[a]-(n:Drug) WHERE {d1_id} IN d.ids AND {n_id} in n.ids RETURN distinct(type(a)) """
d1_results = session.run(query, parameters={'d1_id': disease_pair[0], 'n_id': drug_id})
for result in d1_results:
results_file.write(drug_id + ' ' + result['(type(a))'] + ' ' + disease_pair[0] + '\n')
network.add_edge(Edge(drug, d1, result['(type(a))'], {}))
query = """ MATCH (d:Disease)-[a]-(n:Drug) WHERE {d2_id} IN d.ids AND {n_id} in n.ids RETURN distinct(type(a)) """
d2_results = session.run(query, parameters={'d2_id': disease_pair[1], 'n_id': drug_id})
for result in d2_results:
results_file.write(drug_id + ' ' + result['(type(a))'] + ' ' + disease_pair[1] + '\n')
network.add_edge(Edge(drug, d2, result['(type(a))'], {}))
# the drug targets a gene which is associated to the disease
d1_genes = set()
query = """ MATCH (n:Drug)-[:TARGETS]-(g:Gene)-[:ASSOCIATES_WITH]-(d:Disease) WHERE {d1_id} IN d.ids AND {n_id} in n.ids RETURN g.`_id` """
d1_results = session.run(query, parameters={'d1_id': disease_pair[0], 'n_id': drug_id})
for gene in d1_results:
d1_genes.add(gene['g.`_id`'])
g = Gene([gene['g.`_id`']], [])
network.add_node(g)
network.add_edge(Edge(drug, g, 'TARGETS', {'actions': []})) #TODO
network.add_edge(Edge(g, d1, 'ASSOCIATES_WITH', {}))
d2_genes = set()
query = """ MATCH (n:Drug)-[:TARGETS]-(g:Gene)-[:ASSOCIATES_WITH]-(d:Disease) WHERE {d2_id} IN d.ids AND {n_id} in n.ids RETURN g.`_id` """
d2_results = session.run(query, parameters={'d2_id': disease_pair[1], 'n_id': drug_id})
for gene in d2_results:
d2_genes.add(gene['g.`_id`'])
g = Gene([gene['g.`_id`']], [])
network.add_node(g)
network.add_edge(Edge(drug, g, 'TARGETS', {'actions': []})) #TODO
network.add_edge(Edge(g, d2, 'ASSOCIATES_WITH', {}))
common_drug_genes = d1_genes.intersection(d2_genes) # genes associated to the drug and both diseases
# relevant_genes are all genes associated to at least one disease and the drug, below the common genes
# with the most disease associated references are added
relevant_genes = d1_genes.union(d2_genes)
if len(d1_genes) > 0:
nbr = str(len(d1_genes))
d1_genes = str(d1_genes)
d1_genes = d1_genes.replace('{', '')
d1_genes = d1_genes.replace('}', '')
d1_genes = d1_genes.replace('\'', '')
results_file.write(drug_id + ' targets following ' + nbr + ' genes which are associated to ' + disease_pair[0] + ': ' + d1_genes + '\n')
if len(d2_genes) > 0:
nbr = str(len(d2_genes))
d2_genes = str(d2_genes)
d2_genes = d2_genes.replace('{', '')
d2_genes = d2_genes.replace('}', '')
d2_genes = d2_genes.replace('\'', '')
results_file.write(drug_id + ' targets following ' + nbr + ' genes which are associated to ' + disease_pair[1] + ': ' + d2_genes + '\n')
if len(common_drug_genes) > 0:
nbr = str(len(common_drug_genes))
cdgs = str(common_drug_genes)
cdgs = cdgs.replace('{', '')
cdgs = cdgs.replace('}', '')
cdgs = cdgs.replace('\'', '')
results_file.write('The disease pair has ' + nbr + ' common genes which are targeted by the drug: ' + cdgs + '\n')
# add the common genes with the most disease associated references
# no given num_pmids is similar to num_pmids = 0
all_d1_genes, all_d2_genes = get_genes(disease_pair)
all_common_genes = all_d1_genes.intersection(all_d2_genes)
relevant_common_genes = [] # the genes with the most cited gene-disease association, threshold 10
if len(all_common_genes) > 0:
results_file.write('The disease pair has ' + str(len(all_common_genes)) + ' common genes, not considering the connection to the drug.'
' Following genes have the most references regarding their connection to both diseases:\n')
for gene in all_common_genes:
query = """ MATCH (d1:Disease)-[a]-(g:Gene) WHERE {g_id} IN g.ids AND {d1_id} IN d1.ids RETURN a.num_pmids """
results = session.run(query, parameters={'g_id': gene, 'd1_id': disease_pair[0]})
num_pmids = 0
for result in results: # multiple edges to the same gene
temp = result['a.num_pmids']
if temp is not None:
num_pmids = num_pmids + temp
query = """ MATCH (d2:Disease)-[a]-(g:Gene) WHERE {g_id} IN g.ids AND {d2_id} IN d2.ids RETURN a.num_pmids """
results = session.run(query, parameters={'g_id': gene, 'd2_id': disease_pair[1]})
for result in results: # multiple edges to the same gene
temp = result['a.num_pmids']
if temp is not None:
num_pmids = num_pmids + temp
relevant_common_genes.append([gene, num_pmids])
# sort by number of pmids
relevant_common_genes = sorted(relevant_common_genes, key=lambda item: item[1], reverse=True)
relevant_common_genes = relevant_common_genes[:10] # threshold
rcgs = str(relevant_common_genes)
rcgs = rcgs[1:-1]
rcgs = rcgs.replace('\'', '')
results_file.write(rcgs + '\n')
for g in relevant_common_genes:
gene = Gene([g[0]], [])
network.add_node(gene)
network.add_edge(Edge(gene, d1, 'ASSOCIATES_WITH', {}))
network.add_edge(Edge(gene, d2, 'ASSOCIATES_WITH', {}))
relevant_genes.add(g[0])
# add the common disease associated variants with most references
# no given num_pmids is similar to num_pmids = 0
disease_variants = {}
query = """ MATCH (d1:Disease)-[a]-(v:Variant)--(d2:Disease) WHERE {d1_id} in d1.ids AND {d2_id} in d2.ids RETURN distinct(a.num_pmids), v.`_id` """
results = session.run(query, parameters={'d1_id': disease_pair[0], 'd2_id': disease_pair[1]})
for variant in results:
num_pmids = variant['(a.num_pmids)']
if num_pmids is None:
num_pmids = 0
var_id = variant['v.`_id`']
if var_id in disease_variants:
temp = disease_variants[var_id]
disease_variants[var_id] = temp + num_pmids
else:
disease_variants[var_id] = num_pmids
query = """ MATCH (d2:Disease)-[a]-(v:Variant)--(d1:Disease) WHERE {d1_id} in d1.ids AND {d2_id} in d2.ids RETURN distinct(a.num_pmids), v.`_id` """
results = session.run(query, parameters={'d1_id': disease_pair[0], 'd2_id': disease_pair[1]})
for variant in results:
num_pmids = variant['(a.num_pmids)']
if num_pmids is None:
num_pmids = 0
var_id = variant['v.`_id`']
if var_id in disease_variants:
temp = disease_variants[var_id]
disease_variants[var_id] = temp + num_pmids
else:
disease_variants[var_id] = num_pmids
dvs = ''
i = 0
for key, value in sorted(disease_variants.items(), key=lambda item: item[1], reverse=True):
if i < 9: # threshold
num_pmids = disease_variants[key]
variant = Variant([key], [])
network.add_node(variant)
network.add_edge(Edge(variant, d1, 'ASSOCIATES_WITH', {}))
network.add_edge(Edge(variant, d2, 'ASSOCIATES_WITH', {}))
dvs = dvs + key + ':' + str(num_pmids) + ' PMIDs, '
i += 1
dvs = dvs[:-2]
# add the gene associated variants with smallest pvalues
# if no pvalue is given, pvalue is set to 1
gene_variants = []
for gene in relevant_genes:
query = """ MATCH (g:Gene)-[a]-(v:Variant) WHERE {g_id} in g.ids RETURN v.`_id`, a.pvalue, type(a) """
results = session.run(query, parameters={'g_id': gene})
for variant in results:
pvalue = variant['a.pvalue']
if pvalue is None:
pvalue = 1
else:
pvalue = float(pvalue)
gene_variants.append([variant['v.`_id`'] + '-' + gene, pvalue, variant['type(a)']])
gene_variants = sorted(gene_variants, key=lambda item: item[1])
gene_variants = gene_variants[:10] # threshold
for v in gene_variants:
temp = v[0].split('-')
v_id = temp[0]
g_id = temp[1]
variant = Variant([v_id], [])
network.add_node(variant)
gene = Gene([g_id], [])
network.add_node(gene)
network.add_edge(Edge(gene, variant, v[2], {'pvalue': v[1]}))
if len(gene_variants) > 0:
gvs = str(gene_variants)
gvs = gvs[1:-1]
gvs = gvs.replace('\'', '')
else:
gvs = ''
if len(disease_variants) > 0 or len(gene_variants) > 0:
results_file.write('The disease pair has at least ' + str(i) + ' variants associated to both diseases: ' +
dvs + ' and at least ' + str(len(gene_variants)) + ' gene associated variants: ' + gvs + '\n')
# dict with RNA name as key and an array as value
# first array position is the number of regulated genes, second position is an array with the gene names
relevant_rnas = {}
for gene in relevant_genes:
query = """ MATCH (r:RNA)--(g:Gene) WHERE {g_id} in g.ids AND NOT r.label_id CONTAINS "MRNA" return r.`_id` """
results = session.run(query, parameters={'g_id': gene})
for result in results:
key = result['r.`_id`']
if key in relevant_rnas:
value = relevant_rnas[key]
genes = value[1]
if gene not in genes:
genes.add(gene)
relevant_rnas[key] = [value[0] + 1, genes]
else:
genes = set()
genes.add(gene)
relevant_rnas[key] = [1, genes]
if len(relevant_rnas) > 0:
i = 0
for key, value in sorted(relevant_rnas.items(), key=lambda item: item[1], reverse=True):
# sort by the number of regulated genes
if i > 9: # threshold
break
elif value[0] > 1: # only add and print RNAs which regulate more than one gene
if i == 0:
results_file.write('RNAs with the number and names of the genes they regulate: \n')
rna_id = key
for gene_id in value[1]:
rna = RNA([rna_id], [])
network.add_node(rna)
gene = Gene([gene_id], [])
network.add_node(gene)
network.add_edge(Edge(rna, gene, 'REGULATES', {}))
regulated_genes = str(value[1])
regulated_genes = regulated_genes[1:-1]
regulated_genes = regulated_genes.replace('\'', '')
results_file.write(rna_id + '\t' + str(value[0]) + '\t' + regulated_genes + '\n')
i += 1
# append regulating RNAs to one RNA which regulates the most genes, MRNAs are not added
for key, value in sorted(relevant_rnas.items(), key=lambda item: item[1], reverse=True):
if value[0] > 1:
most_relevant_rna = RNA([key], [])
network.add_node(most_relevant_rna)
query = """ MATCH (r:RNA)--(n:RNA) WHERE {r_id} in r.ids AND NOT n.label_id CONTAINS "MRNA" RETURN n.`_id`, labels(n) """
results = session.run(query, parameters={'r_id': key})
reg_rnas = ''
for result in results:
rna_id = result['n.`_id`']
types = result['labels(n)']
for type in types:
if type != 'RNA':
if type == 'CircRNA':
rna = CircRNA([rna_id], [])
if type == 'ERNA':
rna = ERNA([rna_id], [])
if type == 'LncRNA':
rna = LncRNA([rna_id], [])
if type == 'MiRNA':
rna = MiRNA([rna_id], [])
if type == 'NcRNA':
rna = NcRNA([rna_id], [])
if type == 'PiRNA':
rna = PiRNA([rna_id], [])
if type == 'Pseudogene':
rna = Pseudogene([rna_id], [])
if type == 'Ribozyme':
rna = Ribozyme([rna_id], [])
if type == 'RRNA':
rna = RRNA([rna_id], [])
if type == 'ScaRNA':
rna = ScaRNA([rna_id], [])
if type == 'ScRNA':
rna = ScRNA([rna_id], [])
if type == 'SnoRNA':
rna = SnoRNA([rna_id], [])
if type == 'SnRNA':
rna = SnRNA([rna_id], [])
network.add_node(rna)
network.add_edge(Edge(rna, most_relevant_rna, 'REGULATES', {}))
reg_rnas = reg_rnas + rna_id + ', '
reg_rnas = reg_rnas[:-2]
results_file.write(key + ' is the RNA which regulates the most genes in this subgraph. It is regulated by ' + reg_rnas + '.\n')
break
json_file = path + '/' + temp_id1 + '_' + temp_id2 + '_' + temp_drug_id + '_graph.json'
network.save(json_file)
draw_drug_subgraph(json_file)
networks_per_drug.append(network)
all_networks.append(networks_per_drug)
return all_networks
next(reader, None)
for row in reader:
if value_empty(row[1]) or value_empty(row[13]):
continue
variant = Variant(['dbSNP:%s' % row[1]], [])
network.add_node(variant)
for gene_id in row[13].split(','):
gene = Gene(['HGNC:%s' % gene_id], [])
network.add_node(gene)
rel = {
'source': 'PMID:24013639',
'pvalue': row[0],
'snp_chr': row[2],
'cis_trans': row[7]
}
network.add_edge(Edge(gene, variant, 'EQTL', rel))
with io.open(file_trans, 'r', encoding='utf-8', newline='') as f:
reader = csv.reader(f, delimiter='\t', quotechar='"')
next(reader, None)
for row in reader:
if value_empty(row[1]) or value_empty(row[16]):
continue
variant = Variant(['dbSNP:%s' % row[1]], [])
network.add_node(variant)
for gene_id in row[16].split(','):
gene = Gene(['HGNC:%s' % gene_id], [])
network.add_node(gene)
rel = {
'source': 'PMID:24013639',
'pvalue': row[0],
def getEdge(self, fr, to):
index = self.edges.index(Edge(fr, to))
if index != -1:
return self.edges[index]
else:
return None
network = Network()
# 0 Location
# 1 Phenotype
# 2 Phenotype MIM number
# 3 Inheritance
# 4 Phenotype mapping key
# 5 Gene/Locus
# 6 Gene/Locus MIM number
with io.open('../data/OMIM/filtered_associations.csv',
'r',
encoding='utf-8',
newline='') as f:
reader = csv.reader(f, delimiter=',', quotechar='"')
next(reader, None)
for row in reader:
disease = Disease(['OMIM:%s' % row[2]], [])
network.add_node(disease)
gene = Gene(['HGNC:%s' % row[5]], []) # , 'OMIM:%s' % row[6]
network.add_node(gene)
rel = {
'source': 'OMIM',
'location': row[0],
'phenotype': row[1],
'inheritance': row[2],
'phenotype_mapping_key': row[4]
}
network.add_edge(Edge(gene, disease, 'ASSOCIATES_WITH', rel))
network.save('../data/OMIM/graph.json')
reader = csv.reader(f, delimiter='\t', quotechar='"')
next(reader, None)
for row in reader:
if row[3] == 'H**o sapiens' and row[6] == 'H**o sapiens' and float(
row[7]) > 0.9:
interactor_a_name = row[1]
interactor_a_type = row[2]
interactor_b_name = row[4]
interactor_b_type = row[5]
interactor_a = add_rna(interactor_a_name, interactor_a_type,
node_lookup)
interactor_b = add_rna(interactor_b_name, interactor_b_type,
node_lookup)
if interactor_a is not None and interactor_b is not None:
if interactor_a_type == 'mRNA':
gene = Gene([interactor_a.id], [])
network.add_node(gene)
e = Edge(gene, interactor_a, 'TRANSCRIBES', {})
network.add_edge(e)
elif interactor_b_type == 'mRNA':
gene = Gene([interactor_b.id], [])
network.add_node(gene)
e = Edge(gene, interactor_b, 'TRANSCRIBES', {})
network.add_edge(e)
e = Edge(interactor_a, interactor_b, 'REGULATES',
{'source': 'RNAInter'})
network.add_edge(e)
network.save('../data/RNAInter/graph.json')
Button(SCREEN_SIZE[0] - 110, 230, 50, 8, 'test_image.png'),
Button(SCREEN_SIZE[0] - 50, 290, 50, 9, 'test_image.png'),
Button(SCREEN_SIZE[0] - 110, 290, 50, 10, 'test_image.png'),
]
vertex0 = Vertex(1, -1, -1)
vertex1 = Vertex(1, 1, -1)
vertex2 = Vertex(-1, 1, -1)
vertex3 = Vertex(-1, -1, -1)
vertex4 = Vertex(1, -1, 1)
vertex5 = Vertex(1, 1, 1)
vertex6 = Vertex(-1, -1, 1)
vertex7 = Vertex(-1, 1, 1)
edges = (
Edge(vertex0, vertex1),
Edge(vertex0, vertex3),
Edge(vertex0, vertex4),
Edge(vertex2, vertex1),
Edge(vertex2, vertex3),
Edge(vertex2, vertex7),
Edge(vertex6, vertex3),
Edge(vertex6, vertex4),
Edge(vertex6, vertex7),
Edge(vertex5, vertex1),
Edge(vertex5, vertex4),
Edge(vertex5, vertex7),
Edge(Vertex(0, 0, 0), Vertex(-2, 0, 0)),
Edge(Vertex(0, 0, 0), Vertex(0, 2, 0)),
Edge(Vertex(0, 0, 0), Vertex(0, 0, -2)),
)
gene_hgnc_id = 'HGNC:' + row[3]
gene_entrez_id = int(row[4])
gene_entrez_id = 'Entrez:' + str(gene_entrez_id)
pmid = int(row[8])
pmid = str(pmid)
with io.open(mirna_to_URS_mapping_file, 'r', encoding='utf-8', newline='') as mapping_file:
mapping_reader = csv.reader(mapping_file, delimiter='\t')
next(mapping_reader, None)
for mapping_row in mapping_reader:
if mirna_name == mapping_row[2]:
mirna_rnacentral_id = mapping_row[0]
mirna = MiRNA([mirna_rnacentral_id], [mirna_name])
network.add_node(mirna)
gene = Gene([gene_hgnc_id, gene_entrez_id], [])
network.add_node(gene)
if (mirna_rnacentral_id + '$' + gene_hgnc_id) in edge_source_target_lookup:
edges = network.get_edges_from_to(mirna, gene, 'REGULATES')
for edge in edges:
pmid = edge.attributes['pmid'] + ', ' + str(pmid)
network.delete_edge(edge)
e = Edge(mirna, gene, 'REGULATES', {'source': 'miRTarBase', 'pmid': pmid})
network.add_edge(e)
edge_source_target_lookup.append(mirna_rnacentral_id + '$' + gene_hgnc_id)
else:
e = Edge(mirna, gene, 'REGULATES', {'source': 'miRTarBase', 'pmid': pmid})
network.add_edge(e)
edge_source_target_lookup.append(mirna_rnacentral_id + '$' + gene_hgnc_id)
break
network.save('data/miRTarBase/graph.json')
next(reader, None)
for row in reader:
variant_ids = {'PharmGKB:%s' % row[0]}
if row[1]:
variant_ids.add('dbSNP:%s' % row[1])
variant = Variant(variant_ids, [])
variant.attributes['location'] = row[4]
network.add_node(variant)
if row[2] and len(row[2]) > 0:
for gene_id in [
'PharmGKB:%s' % x.strip() for x in row[2].split(',')
]:
gene = Gene([gene_id], [])
network.add_node(gene)
network.add_edge(
Edge(gene, variant, "CODES", {'source': 'PharmGKB'}))
with open_file_in_zip('../data/PharmGKB/phenotypes.zip',
'phenotypes.tsv') as f:
reader = csv.reader(f, delimiter='\t', quotechar='"')
next(reader, None)
for row in reader:
disease_ids = {'PharmGKB:%s' % row[0]}
disease_names = {row[1]}
for id_name_pair in process_disease_external_vocabulary(
split_list(row[4])):
disease_ids.add(id_name_pair[0])
if id_name_pair[1] is not None:
disease_names.add(id_name_pair[1])
disease = Disease(disease_ids, disease_names)
network.add_node(disease)