with open(url) as f:
pathway = KGML_parser.read(f, 'r')
# Maps from the reaction id (e.g. rn:R05134) to the Node Objects that are part of this reaction
reactionToNode = dict()
# Maps from the internal pathway id (e.g. 23) to the compound id (e.g. C00010)
compoundDict = dict()
for gene in pathway.genes:
for geneName in gene.name.split(' '):
gene_id = geneName[4:]
if gene_id not in nodes:
gName = gene_id
if gene_id in geneNames:
gName = geneNames[gene_id]
importer.add_node(['_Network_Node', 'Gene'], gene_id,
{'name': gName, 'idType': 'ENTREZ',
'url': 'http://www.kegg.jp/dbget-bin/www_bget?hsa:' + gene_id})
# node = Node('NETWORK_NODE', 'Gene', id=name, idType='GENE_SYMBOL', name=name)
# n = batch.create(node)
nodes.add(gene_id)
genesInReaction = set()
if gene.reaction not in reactionToNode:
reactionToNode[gene.reaction] = genesInReaction
else:
genesInReaction = reactionToNode[gene.reaction]
genesInReaction.add(gene_id)
currentNodes.add(gene_id)
# print(reactionToNode)
nodes = doc["nodes"]
for node in nodes:
if node["Label"] is not None:
if node["Label"] in set_ids:
setId = set_ids[node["Label"]]
else:
current_set_id += 1
setId = str(current_set_id)
set_ids[node["Label"]] = setId
importer.add_node(['_Network_Node', 'Structure'],
str(node["StructureID"]), {
'name': str(node["StructureID"]),
'labels': [setId]
})
importer.add_node(['_Set_Node', 'Label'], setId,
{'name': str(node["Label"])})
importer.add_edge('ConsistsOf', setId, str(node["StructureID"]),
{}, 'Label')
else:
importer.add_node(['_Network_Node', 'Structure'],
str(node["StructureID"]), {
'name': str(node["StructureID"]),
'labels': []
})
edges = doc["edges"]
set_ids = dict()
current_set_id = 0;
nodes = doc["nodes"]
for node in nodes:
if node["Label"] is not None:
if node["Label"] in set_ids:
setId = set_ids[node["Label"]]
else:
current_set_id += 1
setId = str(current_set_id)
set_ids[node["Label"]] = setId
importer.add_node(['_Network_Node', 'Structure'], str(node["StructureID"]),
{'name': str(node["StructureID"]), 'labels': [setId]})
importer.add_node(['_Set_Node', 'Label'], setId,
{'name': str(node["Label"])})
importer.add_edge('ConsistsOf', setId, str(node["StructureID"]), {}, 'Label')
else:
importer.add_node(['_Network_Node', 'Structure'], str(node["StructureID"]),
{'name': str(node["StructureID"]), 'labels': []})
edges = doc["edges"]
for edge in edges:
importer.add_edge('Edge', str(edge["SourceStructureID"]), str(edge["TargetStructureID"]), {'_isNetworkEdge': True,
'Type': edge["Type"],
'Label': edge["Label"]})
reactionToNode = dict()
# Maps from the internal pathway id (e.g. 23) to the compound id (e.g. C00010)
compoundDict = dict()
for gene in pathway.genes:
for geneName in gene.name.split(' '):
gene_id = geneName[4:]
if gene_id not in nodes:
gName = gene_id
if gene_id in geneNames:
gName = geneNames[gene_id]
importer.add_node(
['_Network_Node', 'Gene'], gene_id, {
'name':
gName,
'idType':
'ENTREZ',
'url':
'http://www.kegg.jp/dbget-bin/www_bget?hsa:' +
gene_id
})
# node = Node('NETWORK_NODE', 'Gene', id=name, idType='GENE_SYMBOL', name=name)
# n = batch.create(node)
nodes.add(gene_id)
genesInReaction = set()
if gene.reaction not in reactionToNode:
reactionToNode[gene.reaction] = genesInReaction
else:
genesInReaction = reactionToNode[gene.reaction]
genesInReaction.add(gene_id)
