From 59d8febe149d52ff3af028dbcf30340ad0c1338a Mon Sep 17 00:00:00 2001
From: AndiMajore <andi.majore@googlemail.com>
Date: Sat, 9 Jul 2022 02:30:59 +0200
Subject: [PATCH] small update but not all fixed
Former-commit-id: 9a544d3f4e0d6988be142678c41e287e4e669685 [formerly a54f02195d5fcb8eaae8a961cd91e5dc5a2305d5]
Former-commit-id: 7afc43bd1da646344f8fea1e0e6a3702c4995c72
---
Dockerfile | 1 -
docker-compose.yml | 4 +-
.../management/commands/import_from_nedrex.py | 8 +-
.../management/includes/DatasetLoader.py | 115 +++++++++++++++---
scripts/docker-entrypoint.sh | 2 +-
tasks/quick_task.py | 1 +
tasks/trust_rank.py | 2 -
tasks/util/read_graph_tool_graph.py | 31 +++--
tasks/util/scores_to_results.py | 2 +
9 files changed, 132 insertions(+), 34 deletions(-)
diff --git a/Dockerfile b/Dockerfile
index 6856398..5bafbf3 100755
--- a/Dockerfile
+++ b/Dockerfile
@@ -27,7 +27,6 @@ COPY ./supervisord.conf /etc/supervisor/conf.d/supervisord.conf
COPY ./python_nedrex/ /usr/src/drugstone/python_nedrex/
RUN pip install /usr/src/drugstone/python_nedrex/
-RUN mkdir store
COPY . /usr/src/drugstone/
diff --git a/docker-compose.yml b/docker-compose.yml
index 67a5150..a496008 100755
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -14,7 +14,6 @@ services:
volumes:
- drugstone_db_schema_volume:/usr/src/drugstone/drugstone/migrations
- drugstone_data_volume:/usr/src/drugstone/data
- - drugstone_store_volume:/usr/src/drugstone/store
ports:
- 8001:8000
networks:
@@ -102,5 +101,4 @@ volumes:
drugstone_db_schema_volume:
# external: true
drugstone_data_volume:
-# external: true
- drugstone_store_volume:
\ No newline at end of file
+# external: true
\ No newline at end of file
diff --git a/drugstone/management/commands/import_from_nedrex.py b/drugstone/management/commands/import_from_nedrex.py
index 650b8fc..72a20f3 100644
--- a/drugstone/management/commands/import_from_nedrex.py
+++ b/drugstone/management/commands/import_from_nedrex.py
@@ -198,7 +198,7 @@ class NedrexImporter:
e = models.ProteinDrugInteraction(pdi_dataset=dataset, drug=drug, protein=protein)
if not update or e.__hash__() not in existing:
bulk.add(e)
- for source in edge['databases']:
+ for source in edge['dataSources']:
bulk.add(models.ProteinDrugInteraction(pdi_dataset=source_datasets[source], drug=drug, protein=protein))
except KeyError:
pass
@@ -237,7 +237,7 @@ class NedrexImporter:
e = models.ProteinProteinInteraction(ppi_dataset=dataset, from_protein=protein1, to_protein=protein2)
if not update or e.__hash__() not in existing:
bulk.append(e)
- for source in edge['assertedBy']:
+ for source in edge['dataSources']:
bulk.append(
models.ProteinProteinInteraction(ppi_dataset=source_datasets[source], from_protein=protein1,
to_protein=protein2))
@@ -268,7 +268,7 @@ class NedrexImporter:
score=edge['score'])
if not update or e.__hash__() not in existing:
bulk.add(e)
- for source in edge['assertedBy']:
+ for source in edge['dataSources']:
bulk.add(
models.ProteinDisorderAssociation(pdis_dataset=source_datasets[source], protein=protein, disorder=disorder,
score=edge['score']))
@@ -298,7 +298,7 @@ class NedrexImporter:
e = models.DrugDisorderIndication(drdi_dataset=dataset, drug=drug, disorder=disorder)
if not update or e.__hash__() not in existing:
bulk.add(e)
- for source in edge['assertedBy']:
+ for source in edge['dataSources']:
bulk.add(
models.DrugDisorderIndication(drdi_dataset=source_datasets[source], drug=drug, disorder=disorder))
except KeyError:
diff --git a/drugstone/management/includes/DatasetLoader.py b/drugstone/management/includes/DatasetLoader.py
index 51710f8..8238a6a 100644
--- a/drugstone/management/includes/DatasetLoader.py
+++ b/drugstone/management/includes/DatasetLoader.py
@@ -1,3 +1,5 @@
+from requests.exceptions import RetryError
+
from drugstone import models
from python_nedrex.static import get_metadata
@@ -23,28 +25,46 @@ def get_ppi_apid():
def get_ppi_nedrex_biogrid(url):
+ version = get_today_version()
+ try:
+ version = get_metadata()['source_databases']['biogrid']['date']
+ except RetryError:
+ pass
+
dataset, _ = models.PPIDataset.objects.get_or_create(
name='BioGRID',
link=url,
- version=get_metadata()['source_databases']['biogrid']['date']
+ version=version
)
return dataset
def get_ppi_nedrex_iid(url):
+ version = get_today_version()
+ try:
+ version = get_metadata()['source_databases']['iid']['date']
+ except RetryError:
+ pass
+
dataset, _ = models.PPIDataset.objects.get_or_create(
name='IID',
link=url,
- version=get_metadata()['source_databases']['iid']['date']
+ version=version
)
return dataset
def get_ppi_nedrex_intact(url):
+ version = get_today_version()
+ try:
+ version = get_metadata()['source_databases']['intact']['date']
+ except RetryError:
+ pass
+
dataset, _ = models.PPIDataset.objects.get_or_create(
name='IntAct',
link=url,
- version=get_metadata()['source_databases']['intact']['date']
+ version=version
)
return dataset
@@ -59,37 +79,61 @@ def get_ppi_biogrid():
def get_drug_target_nedrex(url):
+ version = get_today_version()
+ try:
+ version = get_metadata()['version'],
+ except RetryError:
+ pass
+
dataset, _ = models.PDIDataset.objects.get_or_create(
name='NeDRex',
link=url,
- version=get_metadata()['version'],
+ version=version
)
return dataset
def get_ppi_nedrex(url):
+ version = get_today_version()
+ try:
+ version = get_metadata()['version'],
+ except RetryError:
+ pass
+
dataset, _ = models.PPIDataset.objects.get_or_create(
name='NeDRex',
link=url,
- version=get_metadata()['version'],
+ version=version
)
return dataset
def get_protein_disorder_nedrex(url):
+ version = get_today_version()
+ try:
+ version = get_metadata()['version'],
+ except RetryError:
+ pass
+
dataset, _ = models.PDisDataset.objects.get_or_create(
name='NeDRex',
link=url,
- version=get_metadata()['version'],
+ version=version
)
return dataset
def get_drug_disorder_nedrex(url):
+ version = get_today_version()
+ try:
+ version = get_metadata()['version'],
+ except RetryError:
+ pass
+
dataset, _ = models.DrDiDataset.objects.get_or_create(
name='NeDRex',
link=url,
- version=get_metadata()['version'],
+ version=version
)
return dataset
@@ -138,62 +182,103 @@ def get_drug_disorder_drugbank():
)
return dataset
+def get_today_version():
+ import datetime
+ now = datetime.date.today()
+ version = f'{now.year}-{now.month}-{now.day}_temp'
+ return version
def get_dis_prot_nedrex_disgenet(url):
+ version = get_today_version()
+ try:
+ version = get_metadata()['source_databases']['disgenet']['date']
+ except RetryError:
+ pass
+
dataset, _ = models.PDisDataset.objects.get_or_create(
name='DisGeNET',
link=url,
- version=get_metadata()['source_databases']['disgenet']['date']
+ version=version
)
return dataset
def get_dis_prot_nedrex_omim(url):
+ version = get_today_version()
+ try:
+ version = get_metadata()['source_databases']['omim']['date']
+ except RetryError:
+ pass
+
dataset, _ = models.PDisDataset.objects.get_or_create(
name='OMIM',
link=url,
- version=get_metadata()['source_databases']['omim']['date']
+ version=version
)
return dataset
def get_drdis_nedrex_drugcentral(url):
+ version = get_today_version()
+ try:
+ version = get_metadata()['source_databases']['drug_central']['date']
+ except RetryError:
+ pass
+
dataset, _ = models.DrDiDataset.objects.get_or_create(
name='Drug Central',
link=url,
- version=get_metadata()['source_databases']['drug_central']['date']
+ version=version
)
return dataset
def get_drdis_nedrex_ctd(url):
+ version = get_today_version()
+ try:
+ version = get_metadata()['source_databases']['ctd']['date']
+ except RetryError:
+ pass
+
dataset, _ = models.DrDiDataset.objects.get_or_create(
name='CTD',
link=url,
- version=get_metadata()['source_databases']['ctd']['date']
+ version=version
)
return dataset
def get_pdr_nedrex_drugcentral(url):
+ version = get_today_version()
+ try:
+ version = get_metadata()['source_databases']['drug_central']['date']
+ except RetryError:
+ pass
+
dataset, _ = models.PDIDataset.objects.get_or_create(
name='Drug Central',
link=url,
- version=get_metadata()['source_databases']['drug_central']['date']
+ version=version
)
return dataset
def get_pdr_nedrex_drugbank(url):
+ version = get_today_version()
+ try:
+ version = get_metadata()['source_databases']['drugbank']['date']
+ except RetryError:
+ pass
+
dataset, _ = models.PDIDataset.objects.get_or_create(
name='DrugBank',
link=url,
- version=get_metadata()['source_databases']['drugbank']['date']
+ version=version
)
return dataset
def get_pdr_nedrex_datasets(url):
- return {'DrugBank': get_pdr_nedrex_drugbank(url), 'DrugCentral': get_pdr_nedrex_drugcentral(url)}
+ return {'drugbank': get_pdr_nedrex_drugbank(url), 'drugcentral': get_pdr_nedrex_drugcentral(url)}
def get_drdis_nedrex_datasets(url):
- return {'ctd':get_drdis_nedrex_ctd(url), 'Drug Central':get_drdis_nedrex_drugcentral(url)}
+ return {'ctd':get_drdis_nedrex_ctd(url), 'drugcentral':get_drdis_nedrex_drugcentral(url)}
def get_ppi_nedrex_datasets(url):
return {'biogrid':get_ppi_nedrex_biogrid(url), 'iid':get_ppi_nedrex_iid(url), 'intact':get_ppi_nedrex_intact(url)}
diff --git a/scripts/docker-entrypoint.sh b/scripts/docker-entrypoint.sh
index 0245a23..db7a2d3 100755
--- a/scripts/docker-entrypoint.sh
+++ b/scripts/docker-entrypoint.sh
@@ -4,7 +4,7 @@ python3 manage.py makemigrations drugstone
python3 manage.py migrate
python3 manage.py createfixtures
python3 manage.py cleanuptasks
-python3 manage.py populate_db --update -a
+#python3 manage.py populate_db --update -a
#python3 manage.py make_graphs
/usr/bin/supervisord -c "/etc/supervisor/conf.d/supervisord.conf"
diff --git a/tasks/quick_task.py b/tasks/quick_task.py
index e4a9c5b..21f4cbf 100755
--- a/tasks/quick_task.py
+++ b/tasks/quick_task.py
@@ -45,6 +45,7 @@ def quick_task(task_hook: TaskHook):
"result_size": 20,
"include_non_approved_drugs": True,
"include_indirect_drugs": False,
+ "target":"drug"
})
tr_task_hook = TaskHook(parameters, task_hook.data_directory, progress, set_result)
diff --git a/tasks/trust_rank.py b/tasks/trust_rank.py
index 890c6a5..42950ec 100755
--- a/tasks/trust_rank.py
+++ b/tasks/trust_rank.py
@@ -200,8 +200,6 @@ def trust_rank(task_hook: TaskHook):
task_hook.set_progress(0 / 4.0, "Parsing input.")
file_path = os.path.join(task_hook.data_directory, f"internal_{ppi_dataset['name']}_{pdi_dataset['name']}.gt")
g, seed_ids, drug_ids = read_graph_tool_graph(file_path, seeds, max_deg, include_indirect_drugs, include_non_approved_drugs, search_target)
- print(seed_ids)
- print(drug_ids)
task_hook.set_progress(1 / 4.0, "Computing edge weights.")
weights = edge_weights(g, hub_penalty, inverse=True)
diff --git a/tasks/util/read_graph_tool_graph.py b/tasks/util/read_graph_tool_graph.py
index 1e9caf2..bf26636 100755
--- a/tasks/util/read_graph_tool_graph.py
+++ b/tasks/util/read_graph_tool_graph.py
@@ -37,7 +37,7 @@ def read_graph_tool_graph(file_path, seeds, max_deg, include_indirect_drugs=Fals
The graph indices for all drug nodes
"""
# Read the graph.
-
+ print(f"loading {file_path} for {target}")
g = gt.load_graph(file_path)
# g = gtt.extract_largest_component(gg, directed=False, prune=True) # this line is added since we need to work with the LCC of the graphs for all algorithms
@@ -47,16 +47,20 @@ def read_graph_tool_graph(file_path, seeds, max_deg, include_indirect_drugs=Fals
# Delete all nodes that are not contained in the selected datasets and have degrees higher than max_deg
deleted_nodes = []
for node in range(g.num_vertices()):
+ #Remove all unconnected nodes TODO probably already skip when creating .gt files
+ if g.vertex(node).out_degree() == 0 and target == 'drug':
+ deleted_nodes.append(node)
# if not g.vertex_properties["name"][node] in set(seeds) and g.vertex(node).out_degree() > max_deg:
- if not g.vertex_properties[node_name_attribute][node] in set(seeds) and g.vertex(node).out_degree() > max_deg:
+ elif not g.vertex_properties[node_name_attribute][node] in set(seeds) and (g.vertex(node).out_degree() > max_deg):
deleted_nodes.append(node)
# remove all drugs from graph if we are not looking for drugs
elif target != 'drug' and g.vertex_properties["type"][node] == d_type:
deleted_nodes.append(node)
g.remove_vertex(deleted_nodes, fast=True)
- # Retrieve internal IDs of seed_ids and viral_protein_ids.
+ # Retrieve internal IDs of seed_ids
seeds = set(seeds)
+ print(seeds)
seed_ids = []
drug_ids = []
is_matched = {protein: False for protein in seeds}
@@ -64,7 +68,7 @@ def read_graph_tool_graph(file_path, seeds, max_deg, include_indirect_drugs=Fals
node_type = g.vertex_properties["type"][node]
if g.vertex_properties[node_name_attribute][node] in seeds:
seed_ids.append(node)
- is_matched[g.vertex_properties[node_name_attribute][node]] = True
+ is_matched[g.vertex_properties[node_name_attribute][node]] = node
if node_type == d_type:
if include_non_approved_drugs:
drug_ids.append(node)
@@ -74,9 +78,11 @@ def read_graph_tool_graph(file_path, seeds, max_deg, include_indirect_drugs=Fals
drug_ids.append(node)
# Check that all seed seeds have been matched and throw error, otherwise.
+ # print(deleted_nodes)
+ print(seed_ids)
for protein, found in is_matched.items():
if not found:
- raise ValueError("Invaliddd seed protein {}. No node named {} in {}.".format(protein, protein, file_path))
+ raise ValueError("Invalid seed protein {}. No node named {} in {}.".format(protein, protein, file_path))
# Delete edges that should be ignored or are not contained in the selected dataset.
deleted_edges = []
@@ -87,8 +93,6 @@ def read_graph_tool_graph(file_path, seeds, max_deg, include_indirect_drugs=Fals
direct_drugs.add(edge.target())
elif g.vertex_properties["type"][edge.source()] == d_type and edge.target() in seed_ids:
direct_drugs.add(edge.source())
- for drug in direct_drugs:
- print(int(drug))
for edge in g.edges():
if g.edge_properties["type"][edge] == 'drug-protein':
if g.vertex_properties["type"][edge.target()] == d_type:
@@ -113,6 +117,17 @@ def read_graph_tool_graph(file_path, seeds, max_deg, include_indirect_drugs=Fals
for edge in deleted_edges:
g.remove_edge(edge)
g.set_fast_edge_removal(fast=False)
-
+ print("Drugs")
+ print(drug_ids)
+ print("Vertices")
+ vertices = 0
+ for _ in g.vertices():
+ vertices += 1
+ print(f'\t{vertices}')
+ print("Edges")
+ edges = 0
+ for _ in g.edges():
+ edges+=1
+ print(f'\t{edges}')
# Return the graph and the indices of the seed_ids and the seeds.
return g, seed_ids, drug_ids
diff --git a/tasks/util/scores_to_results.py b/tasks/util/scores_to_results.py
index f09b161..4f47663 100755
--- a/tasks/util/scores_to_results.py
+++ b/tasks/util/scores_to_results.py
@@ -23,6 +23,7 @@ def scores_to_results(
else:
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]]
+ print(f'Candidate list length: {len(best_candidates)}')
# Concatenate best result candidates with seeds and compute induced subgraph.
# since the result size filters out nodes, the result network is not complete anymore.
@@ -82,6 +83,7 @@ def scores_to_results(
for edge in edges:
if ((edge.source(), edge.target()) not in returned_edges) or ((edge.target(), edge.source()) not in returned_edges):
returned_edges.add((edge.source(), edge.target()))
+ print(f'Returned nodes number: {len(returned_nodes)}')
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],
--
GitLab