diff --git a/.dockerignore b/.dockerignore
index 6b8710a711f3b689885aa5c26c6c06bde348e82b..c7eda2bee653e65357adbfa8b640920e027c8640 100644
--- a/.dockerignore
+++ b/.dockerignore
@@ -1 +1,3 @@
.git
+data
+venv
diff --git a/.gitignore b/.gitignore
index 61228f1f1878cc5e7103c4c491bf97302e8b513c..eba7b164c2dfcb3290ff160e2ad49bead31fc2d2 100644
--- a/.gitignore
+++ b/.gitignore
@@ -7,10 +7,10 @@ venv/
*.DS_Store
db.sqlite3
supervisord.log
-supervisord.log
supervisord.pid
docker-entrypoint.lock
celerybeat-schedule.bak
celerybeat-schedule.dat
celerybeat-schedule.dir
docker-django.env.prodnetworks.zip
+data/Networks/
diff --git a/README.md b/README.md
index 3a8396b51f8b9e8fd9ad22a7c80c597f1180997a..b72c7768c8c22e5e5815273162a16d8aa4bd8bcd 100755
--- a/README.md
+++ b/README.md
@@ -26,3 +26,7 @@ python3 manage.py make_graphs
### Docker DEV environment (building is optional)
``docker-compose -f docker-compose.yml up -d --build``
+
+### Data folder
+Static datasets are mounted from a directory now, instead of fusing them into the image. Download them from the following link and put them into the data folder that is mounted by the docker-compose.yml:
+https://wolken.zbh.uni-hamburg.de/index.php/s/gywnL3HP26CWrgA
diff --git a/docker-compose.yml b/docker-compose.yml
index 0b285adb1c0c876bdcc3a06ce301d9c452f25960..abf89f1adbd8fb2fc40467a5a4b1ebd71f744e09 100755
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -13,7 +13,7 @@ services:
restart: always
volumes:
- drugstone_db_schema_volume:/usr/src/drugstone/drugstone/migrations
- - drugstone_data_volume:/usr/src/drugstone/data
+ - ./data:/usr/src/drugstone/data
ports:
- 8001:8000
networks:
@@ -60,7 +60,7 @@ services:
container_name: drugstone_celery
hostname: drugstone_celery
volumes:
- - drugstone_data_volume:/usr/src/drugstone/data
+ - ./data:/usr/src/drugstone/data
env_file:
- './docker-django.env.dev'
depends_on:
diff --git a/drugstone/management/commands/import_from_nedrex.py b/drugstone/management/commands/import_from_nedrex.py
index bc09491bb6f232a8f6bce5dbf71ef5866b9932a4..dd8a434264392a77306afa48bb1b282af9cea010 100644
--- a/drugstone/management/commands/import_from_nedrex.py
+++ b/drugstone/management/commands/import_from_nedrex.py
@@ -256,8 +256,8 @@ class NedrexImporter:
iter_edge_collection('drug_has_target', add_dpi)
models.ProteinDrugInteraction.objects.bulk_create(bulk)
- new_datasets = [dataset].extend(source_datasets.values())
- DatasetLoader.remove_old_pdi_data(new_datasets, licenced)
+ # new_datasets = [dataset].extend(source_datasets.values())
+ # DatasetLoader.remove_old_pdi_data(new_datasets, licenced)
return len(bulk)
def import_protein_protein_interactions(self, dataset: PPIDataset, update):
@@ -316,8 +316,8 @@ class NedrexImporter:
iter_ppi(add_ppi)
models.ProteinProteinInteraction.objects.bulk_create(bulk)
- new_datasets = [dataset, source_datasets.values()]
- DatasetLoader.remove_old_ppi_data(new_datasets, licenced)
+ # new_datasets = [dataset, source_datasets.values()]
+ # DatasetLoader.remove_old_ppi_data(new_datasets, licenced)
return len(bulk)
def import_protein_disorder_associations(self, dataset, update):
@@ -367,8 +367,8 @@ class NedrexImporter:
iter_edge_collection('gene_associated_with_disorder', add_pdis)
models.ProteinDisorderAssociation.objects.bulk_create(bulk)
- new_datasets = [dataset, source_datasets.values()]
- DatasetLoader.remove_old_pdis_data(new_datasets, licenced)
+ # new_datasets = [dataset, source_datasets.values()]
+ # DatasetLoader.remove_old_pdis_data(new_datasets, licenced)
return len(bulk)
def import_drug_disorder_indications(self, dataset, update):
@@ -416,6 +416,6 @@ class NedrexImporter:
iter_edge_collection('drug_has_indication', add_drdis)
models.DrugDisorderIndication.objects.bulk_create(bulk)
- new_datasets = [dataset, source_datasets.values()]
- DatasetLoader.remove_old_drdi_data(new_datasets, licenced)
+ # new_datasets = [dataset, source_datasets.values()]
+ # DatasetLoader.remove_old_drdi_data(new_datasets, licenced)
return len(bulk)
diff --git a/drugstone/management/commands/populate_db.py b/drugstone/management/commands/populate_db.py
index 4df7c6a14b3b63fbe61436033eeb4c7c97402b89..5bc37ed7e45baa944bfe1542aa0f9040c3fd4915 100755
--- a/drugstone/management/commands/populate_db.py
+++ b/drugstone/management/commands/populate_db.py
@@ -10,8 +10,8 @@ from drugstone.management.includes.DataPopulator import DataPopulator
from .import_from_nedrex import NedrexImporter
from drugstone.management.includes.NodeCache import NodeCache
from drugstone.management.includes import DatasetLoader
-from ..includes.DatasetLoader import remove_old_pdi_data, remove_old_ppi_data, remove_old_pdis_data, \
- remove_old_drdi_data
+# from ..includes.DatasetLoader import remove_old_pdi_data, remove_old_ppi_data, remove_old_pdis_data, \
+# remove_old_drdi_data
class DatabasePopulator:
diff --git a/drugstone/management/includes/DataLoader.py b/drugstone/management/includes/DataLoader.py
index af969892fbe1f84ecdae3ab3eb36cf25e8a569dc..958d45a2fcaec6dbeb8310b89647c990d904c3d4 100755
--- a/drugstone/management/includes/DataLoader.py
+++ b/drugstone/management/includes/DataLoader.py
@@ -226,7 +226,7 @@ class DataLoader:
# @staticmethod
# def load_pdis_disgenet() -> pd.DataFrame:
- # """Loads the DisGeNET PDis associations with UniprotAC Numbers and Mondo IDs
+ # """Loads the DisGeNET PDis associations with Uniprot Numbers and Mondo IDs
#
# Returns:
# pd.DataFrame: columns "protein_name", "disorder_name" and "score"
diff --git a/drugstone/management/includes/DatasetLoader.py b/drugstone/management/includes/DatasetLoader.py
index 859fc1179fcd55d0c6e68675aad9a851d69ee31d..062b7d99dc62655b7f7ebc7cd8e4f8435fd6abe5 100644
--- a/drugstone/management/includes/DatasetLoader.py
+++ b/drugstone/management/includes/DatasetLoader.py
@@ -300,61 +300,69 @@ def is_licenced_drdi_source(source):
return False
-def remove_old_pdi_data(new_datasets, licenced):
- for dataset in new_datasets:
- print("Deleting all except "+str(dataset))
- try:
- for d in models.PDIDataset.objects.filter(name=dataset.name, licenced=licenced):
- print("Testing: "+str(d))
- if d != dataset:
- print("Deleting: "+str(d))
- d.delete()
- except Exception as e:
- print("Error when trying to delete old datasets")
- print(e)
- continue
-
-
-def remove_old_ppi_data(new_datasets, licenced):
- for dataset in new_datasets:
- print("Deleting all except " + str(dataset))
- try:
- for d in models.PPIDataset.objects.filter(name=dataset.name, licenced=licenced):
- print("Testing: " + str(d))
- if d != dataset:
- print("Deleting: " + str(d))
- d.delete()
- except Exception as e:
- print("Error when trying to delete old datasets")
- print(e)
- continue
-
-
-def remove_old_pdis_data(new_datasets, licenced):
- for dataset in new_datasets:
- print("Deleting all except " + str(dataset))
- try:
- for d in models.PDisDataset.objects.filter(name=dataset.name, licenced=licenced):
- print("Testing: " + str(d))
- if d != dataset:
- print("Deleting: " + str(d))
- d.delete()
- except Exception as e:
- print("Error when trying to delete old datasets")
- print(e)
- continue
-
-
-def remove_old_drdi_data(new_datasets, licenced):
- for dataset in new_datasets:
- print("Deleting all except " + str(dataset))
- try:
- for d in models.DrDiDataset.objects.filter(name=dataset.name, licenced=licenced):
- print("Testing: " + str(d))
- if d != dataset:
- print("Deleting: " + str(d))
- d.delete()
- except Exception as e:
- print("Error when trying to delete old datasets")
- print(e)
- continue
+# def remove_old_pdi_data(new_datasets, licenced):
+# if new_datasets is None:
+# return
+# for dataset in new_datasets:
+# print("Deleting all except "+str(dataset))
+# try:
+# for d in models.PDIDataset.objects.filter(name=dataset.name, licenced=licenced):
+# print("Testing: "+str(d))
+# if d != dataset:
+# print("Deleting: "+str(d))
+# d.delete()
+# except Exception as e:
+# print("Error when trying to delete old datasets")
+# print(e)
+# continue
+
+
+# def remove_old_ppi_data(new_datasets, licenced):
+# if new_datasets is None:
+# return
+# for dataset in new_datasets:
+# print("Deleting all except " + str(dataset))
+# try:
+# for d in models.PPIDataset.objects.filter(name=dataset.name, licenced=licenced):
+# print("Testing: " + str(d))
+# if d != dataset:
+# print("Deleting: " + str(d))
+# d.delete()
+# except Exception as e:
+# print("Error when trying to delete old datasets")
+# print(e)
+# continue
+
+
+# def remove_old_pdis_data(new_datasets, licenced):
+# if new_datasets is None:
+# return
+# for dataset in new_datasets:
+# print("Deleting all except " + str(dataset))
+# try:
+# for d in models.PDisDataset.objects.filter(name=dataset.name, licenced=licenced):
+# print("Testing: " + str(d))
+# if d != dataset:
+# print("Deleting: " + str(d))
+# d.delete()
+# except Exception as e:
+# print("Error when trying to delete old datasets")
+# print(e)
+# continue
+
+
+# def remove_old_drdi_data(new_datasets, licenced):
+# if new_datasets is None:
+# return
+# for dataset in new_datasets:
+# print("Deleting all except " + str(dataset))
+# try:
+# for d in models.DrDiDataset.objects.filter(name=dataset.name, licenced=licenced):
+# print("Testing: " + str(d))
+# if d != dataset:
+# print("Deleting: " + str(d))
+# d.delete()
+# except Exception as e:
+# print("Error when trying to delete old datasets")
+# print(e)
+# continue
diff --git a/drugstone/serializers.py b/drugstone/serializers.py
index 7fca1113fde8c48be9bc9d6d06be5b462541f490..3805f42ca025ff7e5b7fa071aeee24dfadb5ad78 100755
--- a/drugstone/serializers.py
+++ b/drugstone/serializers.py
@@ -30,7 +30,7 @@ class DrDisDatasetSerializer(serializers.ModelSerializer):
class ProteinNodeSerializer(serializers.ModelSerializer):
drugstone_id = serializers.SerializerMethodField()
- uniprot_ac = serializers.SerializerMethodField()
+ uniprot = serializers.SerializerMethodField()
symbol = serializers.SerializerMethodField()
ensg = serializers.SerializerMethodField()
entrez = serializers.SerializerMethodField()
@@ -38,7 +38,7 @@ class ProteinNodeSerializer(serializers.ModelSerializer):
def get_drugstone_id(self, obj):
return [f'p{obj.id}']
- def get_uniprot_ac(self, obj):
+ def get_uniprot(self, obj):
return [obj.uniprot_code]
def get_symbol(self, obj):
@@ -61,19 +61,19 @@ class ProteinNodeSerializer(serializers.ModelSerializer):
class Meta:
model = Protein
- fields = ['drugstone_id', 'uniprot_ac', 'symbol', 'protein_name', 'entrez', 'ensg']
+ fields = ['drugstone_id', 'uniprot', 'symbol', 'protein_name', 'entrez', 'ensg']
class ProteinSerializer(serializers.ModelSerializer):
drugstone_id = serializers.SerializerMethodField()
- uniprot_ac = serializers.SerializerMethodField()
+ uniprot = serializers.SerializerMethodField()
symbol = serializers.SerializerMethodField()
ensg = serializers.SerializerMethodField()
def get_drugstone_id(self, obj):
return f'p{obj.id}'
- def get_uniprot_ac(self, obj):
+ def get_uniprot(self, obj):
return obj.uniprot_code
def get_symbol(self, obj):
@@ -93,7 +93,7 @@ class ProteinSerializer(serializers.ModelSerializer):
class Meta:
model = Protein
- fields = ['drugstone_id', 'uniprot_ac', 'symbol', 'protein_name', 'entrez', 'ensg']
+ fields = ['drugstone_id', 'uniprot', 'symbol', 'protein_name', 'entrez', 'ensg']
class DrugSerializer(serializers.ModelSerializer):
diff --git a/drugstone/util/query_db.py b/drugstone/util/query_db.py
index 1a63b069a6c1bb835ad1a64140352f997a5e2cc6..a589cf2b551d85cfbdbbfa8e4ff7a604202785f1 100644
--- a/drugstone/util/query_db.py
+++ b/drugstone/util/query_db.py
@@ -30,7 +30,7 @@ def query_proteins_by_identifier(node_ids: Set[str], identifier: str) -> Tuple[L
protein_attribute = 'symbol'
q_list = map(lambda n: Q(gene__iexact=n), node_ids)
elif identifier == 'uniprot':
- protein_attribute = 'uniprot_ac'
+ protein_attribute = 'uniprot'
q_list = map(lambda n: Q(uniprot_code__iexact=n), node_ids)
elif identifier == 'ensg' or identifier == 'ensembl':
protein_attribute = 'ensg'
@@ -66,7 +66,7 @@ def query_proteins_by_identifier(node_ids: Set[str], identifier: str) -> Tuple[L
def get_protein_ids(id_space, proteins):
if (id_space == 'uniprot'):
- return [p['uniprot_ac'] for p in proteins]
+ return [p['uniprot'] for p in proteins]
if (id_space == 'ensg' or id_space == 'ensembl'):
return [p['ensg'] for p in proteins]
if (id_space == 'symbol'):
diff --git a/drugstone/views.py b/drugstone/views.py
index 5024babdb97b772f2e90d2b6e3bf2beff13c5a88..45ff92405eaa2e2388aed9e92dfccbfc2d47d34b 100755
--- a/drugstone/views.py
+++ b/drugstone/views.py
@@ -60,10 +60,6 @@ class TaskView(APIView):
parameters = request.data['parameters']
licenced = parameters.get('licenced', False)
- print(models.PDIDataset.objects.all())
-
- print(get_ppi_ds(parameters.get('ppi_dataset', DEFAULTS['ppi']), licenced))
- print(get_pdi_ds(parameters.get('pdi_dataset', DEFAULTS['pdi']), licenced))
# find databases based on parameter strings
parameters['ppi_dataset'] = PPIDatasetSerializer().to_representation(
@@ -172,7 +168,6 @@ def map_nodes(request) -> Response:
# change data structure to dict in order to be quicker when merging
nodes_mapped_dict = {id.upper(): node for node in nodes_mapped for id in node[id_key]}
- print(nodes_mapped_dict)
# merge fetched data with given data to avoid data loss
for node in nodes:
@@ -231,13 +226,29 @@ def create_network(request) -> Response:
return Response(id)
+def latest_datasets(ds):
+ dataset_dict = {}
+ for d in ds:
+ name = d.name + "_" + str(d.licenced)
+ if name not in dataset_dict:
+ dataset_dict[name] = d
+ continue
+ if dataset_dict[name].version < d.version:
+ dataset_dict[name] = d
+ return dataset_dict.values()
+
+
@api_view(['GET'])
def get_datasets(request) -> Response:
datasets = {}
- datasets['protein-protein'] = PPIDatasetSerializer(many=True).to_representation(PPIDataset.objects.all())
- datasets['protein-drug'] = PDIDatasetSerializer(many=True).to_representation(PDIDataset.objects.all())
- datasets['protein-disorder'] = PDisDatasetSerializer(many=True).to_representation(PDisDataset.objects.all())
- datasets['drug-disorder'] = DrDisDatasetSerializer(many=True).to_representation(DrDiDataset.objects.all())
+ datasets['protein-protein'] = PPIDatasetSerializer(many=True).to_representation(
+ latest_datasets(PPIDataset.objects.all()))
+ datasets['protein-drug'] = PDIDatasetSerializer(many=True).to_representation(
+ latest_datasets(PDIDataset.objects.all()))
+ datasets['protein-disorder'] = PDisDatasetSerializer(many=True).to_representation(
+ latest_datasets(PDisDataset.objects.all()))
+ datasets['drug-disorder'] = DrDisDatasetSerializer(many=True).to_representation(
+ latest_datasets(DrDiDataset.objects.all()))
return Response(datasets)
@@ -275,6 +286,7 @@ def result_view(request) -> Response:
if not node_types:
node_types = {}
node_attributes['node_types'] = node_types
+
is_seed = node_attributes.get('is_seed')
if not is_seed:
is_seed = {}
@@ -336,7 +348,7 @@ def result_view(request) -> Response:
else:
continue
- nodes_mapped, _ = query_proteins_by_identifier(protein_nodes, identifier)
+ nodes_mapped, identifier = query_proteins_by_identifier(protein_nodes, identifier)
nodes_mapped_dict = {node[identifier][0]: node for node in nodes_mapped}
@@ -366,11 +378,10 @@ def result_view(request) -> Response:
for node_id, detail in node_details.items():
if 'drugstoneType' in detail and detail['drugstoneType'] == 'protein':
- detail['symbol'] = list(set(detail['symbol']))
- detail['entrez'] = list(set(detail['entrez']))
- detail['uniprot_ac'] = list(set(detail['uniprot_ac']))
- if 'ensg' in detail:
- detail['ensg'] = list(set(detail['ensg']))
+ detail['symbol'] = list(set(detail['symbol'])) if 'symbol' in detail else []
+ detail['entrez'] = list(set(detail['entrez'])) if 'entrez' in detail else []
+ detail['uniprot'] = list(set(detail['uniprot'])) if 'uniprot' in detail else []
+ detail['ensg'] = list(set(detail['ensg'])) if 'ensg' in detail else []
edges = parameters['input_network']['edges']
@@ -420,7 +431,7 @@ def result_view(request) -> Response:
for i in proteins:
new_i = {
'id': i['id'],
- 'uniprot_ac': i['uniprot_ac'] if 'uniprot_ac' in i else [],
+ 'uniprot': i['uniprot'] if 'uniprot' in i else [],
'gene': i['symbol'] if 'symbol' in i else [],
'name': i['protein_name'] if 'protein_name' in i else [],
'ensembl': i['ensg'] if 'ensg' in i else [],
@@ -463,9 +474,11 @@ def graph_export(request) -> Response:
Recieve whole graph data and write it to graphml file. Return the
file ready to download.
"""
- remove_node_properties = ['color', 'shape', 'border_width', 'group_name', 'border_width_selected', 'shadow',
- 'group_id', 'drugstone_type', 'font', 'x', 'y']
- remove_edge_properties = ['group_name', 'color', 'dashes', 'shadow', 'id']
+ remove_node_properties = ['color', 'shape', 'border_width', 'group', 'border_width_selected', 'shadow',
+ 'group_id', 'drugstone_type', 'font', 'x', 'y', '_group']
+ rename_node_properties = {'group_name': 'group'}
+ remove_edge_properties = ['group', 'color', 'dashes', 'shadow', 'id']
+ rename_edge_properties = {'group_name': 'group'}
nodes = request.data.get('nodes', [])
edges = request.data.get('edges', [])
fmt = request.data.get('fmt', 'graphml')
@@ -476,6 +489,10 @@ def graph_export(request) -> Response:
for prop in remove_node_properties:
if prop in node:
del node[prop]
+ for k, v in rename_node_properties.items():
+ if k in node:
+ node[v] = node[k]
+ del node[k]
for key in list(node.keys()):
if isinstance(node[key], list) or isinstance(node[key], dict):
node[key] = json.dumps(node[key])
@@ -497,6 +514,10 @@ def graph_export(request) -> Response:
for prop in remove_edge_properties:
if prop in e:
del e[prop]
+ for k, v in rename_edge_properties.items():
+ if k in e:
+ e[v] = e[k]
+ del e[k]
for key in e:
if isinstance(e[key], list) or isinstance(e[key], dict):
e[key] = json.dumps(e[key])
diff --git a/requirements.txt b/requirements.txt
index e2ca8b1400cb459de5d3df84f22a841954ed7b9c..499918e26a46bf66835ed4667503036bfe5c2a35 100755
--- a/requirements.txt
+++ b/requirements.txt
@@ -3,9 +3,9 @@ celery==5.2.7
certifi==2022.12.7
chardet==3.0.4
click==8.1.3
-cryptography==38.0.3
+cryptography==39.0.1
decorator==4.4.2
-Django==3.2.16
+Django==3.2.17
django-cors-headers==3.4.0
django-redis==4.11.0
django-rq-dashboard==0.3.3
diff --git a/scripts/docker-entrypoint.sh b/scripts/docker-entrypoint.sh
index 13501e0d43ebdc4537a2d7ccddfc9dc857a2ab8e..079cbada214c70e54dc849f59a97778350a4839e 100755
--- a/scripts/docker-entrypoint.sh
+++ b/scripts/docker-entrypoint.sh
@@ -11,4 +11,5 @@ else
python3 manage.py populate_db --update -a
python3 manage.py make_graphs
fi
+
/usr/bin/supervisord -c "/etc/supervisor/conf.d/supervisord.conf"
diff --git a/tasks/quick_task.py b/tasks/quick_task.py
index 899674d8e327360e85b9844439d63300edaf2a0c..a49536e512c7479990cee36221f04dac77fda790 100755
--- a/tasks/quick_task.py
+++ b/tasks/quick_task.py
@@ -1,7 +1,8 @@
from tasks.task_hook import TaskHook
+
def quick_task(task_hook: TaskHook):
- def run_closeness(parameters, network):
+ def run_closeness(parameters, network, original_seeds=None):
from .closeness_centrality import closeness_centrality
def closeness_progress(progress, status):
@@ -9,6 +10,8 @@ def quick_task(task_hook: TaskHook):
def closeness_set_result(result):
result["network"]["edges"].extend(network["edges"])
+ if original_seeds is not None:
+ result['node_attributes']['is_seed'] = original_seeds
task_hook.set_results(result)
# Prepare intermediate hook
@@ -20,7 +23,6 @@ def quick_task(task_hook: TaskHook):
# Run closeness centrality
closeness_centrality(closeness_task_hook)
-
def run_multi_steiner(parameters):
from .multi_steiner import multi_steiner
@@ -35,7 +37,7 @@ def quick_task(task_hook: TaskHook):
if len(seeds) == 0:
task_hook.set_results({"network": {"nodes": [], "edges": []}})
return
-
+ og_seeds = parameters.get('seeds')
parameters.update({
"seeds": seeds,
"result_size": 10,
@@ -43,7 +45,11 @@ def quick_task(task_hook: TaskHook):
"target": "drug",
"include_non_approved_drugs": True
})
- run_closeness(parameters, result["network"])
+ is_seed = result.get('node_attributes')
+ run_closeness(parameters, result["network"], result['node_attributes']['is_seed'])
+ # parameters.update({
+ # "seeds": og_seeds
+ # })
parameters["num_trees"] = 1
parameters["hub_penalty"] = 1
diff --git a/tasks/util/scores_to_results.py b/tasks/util/scores_to_results.py
index b690db510699139e7c8a368c80103a892018440b..cb474961e14aecd4d4b6fc96f15c633bfac72ee5 100755
--- a/tasks/util/scores_to_results.py
+++ b/tasks/util/scores_to_results.py
@@ -12,14 +12,14 @@ def scores_to_results(
pdi_dataset,
filterPaths
):
-
r"""Transforms the scores to the required result format."""
node_name_attribute = "internal_id" # nodes in the input network which is created from RepoTrialDB have primaryDomainId as name attribute
if target == "drug":
candidates = [(node, scores[node]) for node in drug_ids if scores[node] > 0]
else:
- candidates = [(node, scores[node]) for node in range(g.num_vertices()) if scores[node] > 0 and node not in set(seed_ids)]
+ candidates = [(node, scores[node]) for node in range(g.num_vertices()) if
+ scores[node] > 0 and node not in set(seed_ids)]
best_candidates = [item[0] for item in sorted(candidates, key=lambda item: item[1], reverse=True)[:result_size]]
# Concatenate best result candidates with seeds and compute induced subgraph.
# since the result size filters out nodes, the result network is not complete anymore.
@@ -29,7 +29,7 @@ def scores_to_results(
intermediate_nodes = set()
returned_edges = set()
- returned_nodes = set(seed_ids) # return seed_ids in any case
+ returned_nodes = set(seed_ids) # return seed_ids in any case
# return only the path to a drug with the shortest distance
accepted_candidates = set()
@@ -44,11 +44,15 @@ def scores_to_results(
vertices, edges = gtt.shortest_path(g, candidate, seed_id)
drug_in_path = False
+ seed_in_path = False
for vertex in vertices:
if g.vertex_properties["type"][int(vertex)] == "drug" and vertex != candidate:
drug_in_path = True
break
- if drug_in_path:
+ if int(vertex) in seed_ids and int(vertex) != seed_id:
+ seed_in_path = True
+ break
+ if drug_in_path or seed_in_path:
continue
accepted_candidates.add(g.vertex_properties[node_name_attribute][int(candidate)])
for vertex in vertices:
@@ -58,7 +62,8 @@ def scores_to_results(
intermediate_nodes.add(g.vertex_properties[node_name_attribute][int(vertex)])
returned_nodes.add(int(vertex))
for edge in edges:
- if ((edge.source(), edge.target()) not in returned_edges) or ((edge.target(), edge.source()) not in returned_edges):
+ if (((edge.source(), edge.target()) not in returned_edges) or (
+ (edge.target(), edge.source()) not in returned_edges)) and int(edge.target()) in returned_nodes and int(edge.source()) in returned_nodes:
returned_edges.add((edge.source(), edge.target()))
else:
for candidate in best_candidates:
@@ -66,11 +71,15 @@ def scores_to_results(
vertices, edges = gtt.shortest_path(g, candidate, seed_id)
drug_in_path = False
+ seed_in_path = False
for vertex in vertices:
if g.vertex_properties["type"][int(vertex)] == "drug" and vertex != candidate:
drug_in_path = True
break
- if drug_in_path:
+ if int(vertex) in seed_ids and int(vertex) != seed_id:
+ seed_in_path = True
+ break
+ if drug_in_path or seed_in_path:
continue
accepted_candidates.add(g.vertex_properties[node_name_attribute][int(candidate)])
for vertex in vertices:
@@ -80,18 +89,22 @@ def scores_to_results(
intermediate_nodes.add(g.vertex_properties[node_name_attribute][int(vertex)])
returned_nodes.add(int(vertex))
for edge in edges:
- if ((edge.source(), edge.target()) not in returned_edges) or ((edge.target(), edge.source()) not in returned_edges):
+ if (((edge.source(), edge.target()) not in returned_edges) or (
+ (edge.target(), edge.source()) not in returned_edges)) and int(
+ edge.target()) in returned_nodes and int(edge.source()) in returned_nodes:
returned_edges.add((edge.source(), edge.target()))
for node in accepted_candidates:
if node in intermediate_nodes:
intermediate_nodes.remove(node)
subgraph = {
- "nodes":[g.vertex_properties[node_name_attribute][node] for node in returned_nodes],
- "edges": [{"from": g.vertex_properties[node_name_attribute][source], "to": g.vertex_properties[node_name_attribute][target]} for source, target in returned_edges],
- }
+ "nodes": [g.vertex_properties[node_name_attribute][node] for node in returned_nodes],
+ "edges": [{"from": g.vertex_properties[node_name_attribute][source],
+ "to": g.vertex_properties[node_name_attribute][target]} for source, target in returned_edges],
+ }
# Compute node attributes.
- node_types = {g.vertex_properties[node_name_attribute][node]: g.vertex_properties["type"][node] for node in returned_nodes}
+ node_types = {g.vertex_properties[node_name_attribute][node]: g.vertex_properties["type"][node] for node in
+ returned_nodes}
is_seed = {g.vertex_properties[node_name_attribute][node]: node in set(seed_ids) for node in returned_nodes}
returned_scores = {g.vertex_properties[node_name_attribute][node]: scores[node] for node in returned_nodes}