# Fusion print('[INFO] Network fusion') for graph in graphs: print('[INFO] Add network', graph) with io.open(graph, 'r', encoding='utf-8', newline='') as f: g = json.loads(f.read()) network.load_from_dict(g) # Mapping print('[INFO] Add disease mappings') all_disease_ids = set() for node in network.get_nodes_by_label('Disease'): all_disease_ids.update(node.ids) for disease_id in all_disease_ids: mapped_ids, mapped_names = mondo_mapper.map_from(disease_id) if mapped_ids: network.add_node(Disease(mapped_ids, mapped_names)) # Cleanup print('[INFO] Prune network') network.prune() print('[INFO] Merge duplicate node names') merge_duplicate_node_names(network) print('[INFO] Merge duplicate edges') network.merge_duplicate_edges() # Export print('[INFO] Export network') directory_utils.create_clean_directory(config['output-path']) with io.open(os.path.join(config['output-path'], 'graph.json'), 'w', encoding='utf-8', newline='') as f: f.write(json.dumps(network.to_dict(), separators=(',', ':')))
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')
mirna_rnacentral_id = mirna_rnacentral[1] mirna_hgnc_id = 'None' with io.open(mirna_mapping_file, 'r', encoding='utf-8', newline='') as mm: mirna_mapping_reader = csv.reader(mm, delimiter='\t') next(mirna_mapping_reader, None) for mirna_mapping_row in mirna_mapping_reader: if mirna_mapping_row[0] == mirna_rnacentral_id: mirna_hgnc_id = mirna_mapping_row[2] break mirna_name = re.split('[" ]', row[4]) mirna_name = mirna_name[4] if mirna_hgnc_id != 'None': mirna = MiRNA([mirna_rnacentral_id, mirna_hgnc_id], [mirna_name]) network.add_node(mirna) else: mirna = MiRNA([mirna_rnacentral_id], [mirna_name]) network.add_node(mirna) # genes gene_ensembl = row[1].split(':') gene_ensembl_id = gene_ensembl[1] gene_hgnc_id = 'None' with io.open(gene_mapping_file, 'r', encoding='utf-8', newline='') as gm: gene_mapping_reader = csv.reader(gm, delimiter='\t') next(gene_mapping_reader, None) for gene_mapping_row in gene_mapping_reader: if gene_mapping_row[2] == gene_ensembl_id: gene_hgnc_id = 'HGNC:' + gene_mapping_row[1] break
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
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')
def value_empty(s: str) -> bool: return not s or s.strip() == '-' network = Network() with io.open(file_cis, '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[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:
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')
if 'Weak' not in row[7] and row[2] == 'H**o sapiens' and row[5] == 'H**o sapiens': mirna_name = row[1] 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
f.write(response.read()) 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')
reader = csv.reader(f, delimiter='\t', quotechar='"') next(reader, None) for row in reader: # Only parse drugs and not drug classes for now if row[5] == 'Drug': drug_ids = {'PharmGKB:%s' % row[0]} drug_ids.update(process_drug_cross_references(split_list(row[6]))) for rx_norm_id in split_list(row[21]): drug_ids.add('RxNorm:%s' % rx_norm_id) for atc_code in split_list(row[22]): drug_ids.add('AtcCode:%s' % atc_code) for compound_id in split_list(row[23]): drug_ids.add('PubChem:CID%s' % compound_id) drug = Drug(drug_ids, [row[1]]) drug.attributes['type'] = row[5] network.add_node(drug) with open_file_in_zip('../data/PharmGKB/genes.zip', 'genes.tsv') as f: reader = csv.reader(f, delimiter='\t', quotechar='"') next(reader, None) # 0 - PharmGKB Accession Id # 1 - NCBI Gene ID # 2 - HGNC ID # 3 - Ensembl Id # 4 - Name # 5 - Symbol # 6 - Alternate Names # 7 - Alternate Symbols # 8 - Is VIP # 9 - Has Variant Annotation # 10 - Cross-references
reader = csv.reader(f, delimiter=',', quotechar='"') next(reader, None) for row in reader: snp_adrs_results.append(row) external_id_lookup = {} for row in external_id_results: external_id_lookup[row[0]] = [x for x in row[1::] if x] network = Network() for row in targets_results: drug_ids = ['DrugBank:%s' % row[0]] 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)
next(reader, None) for row in reader: # 0 SUPERDRUG_ID # 1 PREFERRED_NAME # 2 ATC # 3 CHEMBL_ID # 4 DRUGBANK_ID # 5 KEGG_ID # 6 PUBCHEM_CID # 7 CASRN drug_ids = [] # ['SuperDrug:%s' % row[0]] # if row[2] != not_available_text: # drug_ids.extend(['AtcCode:%s' % x for x in row[2].split(';')]) if row[3] != not_available_text: for chembl_id in {x.strip() for x in row[3].split(';')}: drug_ids.append('ChEMBL:%s' % chembl_id) if row[4] != not_available_text: drug_ids.append('DrugBank:%s' % row[4]) else: # For now, only use mappings including DrugBank continue # if row[5] != not_available_text: # drug_ids.append('Kegg:%s' % row[5]) if row[6] != not_available_text: for pubchem_id in {x.strip() for x in row[6].split(';')}: drug_ids.append('PubChem:CID%s' % pubchem_id) if len(drug_ids) > 1: network.add_node(Drug(drug_ids, [row[1]])) network.save('../data/SuperDrug2/graph.json')
from model.drug import Drug from model.disease import Disease from model.edge import Edge network = Network() with io.open('../data/DrugCentral/drugcentral_mappings.csv', 'r', encoding='utf-8', newline='') as f: reader = csv.reader(f, delimiter=',', quotechar='"') next(reader, None) for row in reader: 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)
# 3 - DPI # 4 - diseaseId # 5 - diseaseName # 6 - diseaseType # 7 - diseaseClass # 8 - diseaseSemanticType # 9 - score # 10 - EI # 11 - YearInitial # 12 - YearFinal # 13 - NofPmids # 14 - NofSnps # 15 - source if int(row[13]) >= PUBMED_COUNT_THRESHOLD: gene = Gene(['HGNC:%s' % row[1]], []) network.add_node(gene) disease = Disease(['UMLS:%s' % row[4]], [row[5]]) network.add_node(disease) rel = { 'source': 'DisGeNet,%s' % row[15], 'num_pmids': int(row[13]), 'num_snps': int(row[14]), 'score': row[9] } network.add_edge(Edge(gene, disease, 'ASSOCIATES_WITH', rel)) with io.open('../data/DisGeNet/curated_variant_disease_associations.tsv', 'r', encoding='utf-8', newline='') as f: reader = csv.reader(f, delimiter='\t', quotechar='"')