diff --git a/.gitignore b/.gitignore
index af2b847af25782ddc7b99e033dee329464c2713a..9b7a0cc8c6293439a9362491381845f592bbdc48 100644
--- a/.gitignore
+++ b/.gitignore
@@ -15,3 +15,5 @@ celerybeat-schedule.dir
docker-django.env.prodnetworks.zip
data/Networks/
docker-django.env
+.prettierrc
+.vscode/
diff --git a/drugstone/management/includes/DataLoader.py b/drugstone/management/includes/DataLoader.py
index 958d45a2fcaec6dbeb8310b89647c990d904c3d4..cd1fbb57de485735496c3161c693d6e697034fa4 100755
--- a/drugstone/management/includes/DataLoader.py
+++ b/drugstone/management/includes/DataLoader.py
@@ -3,41 +3,41 @@ import json
class DataLoader:
- PATH_PROTEINS = 'data/Proteins/'
+ PATH_PROTEINS = "data/Proteins/"
# PATH_DRUGS = 'data/Drugs/'
- PATH_EXPR = 'data/Expression/'
+ PATH_EXPR = "data/Expression/"
# PATH_DISORDERS = 'data/Disorders/'
- PATH_PDI = 'data/PDI/'
- PATH_PPI = 'data/PPI/'
+ PATH_PDI = "data/PDI/"
+ PATH_PPI = "data/PPI/"
# PATH_PDi = 'data/PDi/'
- PATH_DDi = 'data/DrDi/'
+ PATH_DDi = "data/DrDi/"
# Proteins
# PROTEINS_COVEX = 'protein_list.csv'
- ENTREZ_TO_ENSG = 'entrez_to_ensg.json'
+ ENTREZ_TO_ENSG = "entrez_to_ensg.json"
# Disorders
# DISORDERS_MONDO = 'disorders.tsv'
- #Drugs
+ # Drugs
# DRUG_FILE = 'drug-file.txt'
- #Expressions
- EXPR_FILE = 'gene_tissue_expression.gct'
+ # Expressions
+ EXPR_FILE = "gene_tissue_expression.gct"
# Protein-Protein-Interactions
- PPI_APID = 'apid_9606_Q2.txt'
+ PPI_APID = "apid_9606_Q2.txt"
# PPI_BIOGRID = 'BIOGRID-ORGANISM-Homo_sapiens-3.5.187.mitab.txt'
- PPI_STRING = 'string_interactions.csv'
+ PPI_STRING = "string_interactions.csv"
# Protein-Drug-Interactions
- PDI_CHEMBL = 'chembl_drug_gene_interactions_uniq.csv'
- PDI_DGIDB = 'DGIdb_drug_gene_interactions.csv'
+ PDI_CHEMBL = "chembl_drug_gene_interactions_uniq.csv"
+ PDI_DGIDB = "DGIdb_drug_gene_interactions.csv"
# PDI_DRUGBANK = 'drugbank_drug_gene_interactions_uniq.csv'
# Protein-Disorder-Interaction
# PDi_DISGENET = 'disgenet-protein_disorder_association.tsv'
# Drug-Disorder-Indictation
- DDi_DRUGBANK = 'drugbank-drug_disorder_indication.tsv'
+ DDi_DRUGBANK = "drugbank-drug_disorder_indication.tsv"
@staticmethod
def _clean_entrez(x):
@@ -47,46 +47,9 @@ class DataLoader:
except Exception:
return x
- # @staticmethod
- # def _clean_mondo(x):
- # # convert to string if not empty
- # try:
- # return str(int(x))
- # except Exception:
- # return x
-
- # @staticmethod
- # def load_proteins() -> pd.DataFrame:
- # """Loads the list of proteins used in CoVex
- #
- # Returns:
- # pd.DataFrame: columns 'protein_ac', 'gene_name', 'protein_name', 'entrez_id'
- # """
- #
- # df = pd.read_csv(f'{DataLoader.PATH_PROTEINS}{DataLoader.PROTEINS_COVEX}')
- # df['entrez_id'] = df['entrez_id'].map(DataLoader._clean_entrez)
- # return df
-
- # @staticmethod
- # def load_drugs()-> pd.DataFrame:
- # return pd.read_csv(f'{DataLoader.PATH_DRUGS}{DataLoader.DRUG_FILE}', sep='\t')
-
@staticmethod
def load_expressions() -> pd.DataFrame:
- return pd.read_csv(f'{DataLoader.PATH_EXPR}{DataLoader.EXPR_FILE}', sep='\t')
-
-
- # @staticmethod
- # def load_disorders() -> pd.DataFrame:
- # """Loads the list of disorders used in Nedrex
- #
- # Returns:
- # pd.DataFrame: columns 'mondo_id', 'disorder_name', 'icd_10'
- # """
- #
- # df = pd.read_csv(f'{DataLoader.PATH_DISORDERS}{DataLoader.DISORDERS_MONDO}', sep='\t')
- # df['mondo_id'] = df['mondo_id'].map(DataLoader._clean_mondo)
- # return df
+ return pd.read_csv(f"{DataLoader.PATH_EXPR}{DataLoader.EXPR_FILE}", sep="\t")
@staticmethod
def load_ensg() -> dict:
@@ -96,7 +59,9 @@ class DataLoader:
dict with {entrez1: [ensg1, ensg2], ...}
"""
- f = open(f'{DataLoader.PATH_PROTEINS}{DataLoader.ENTREZ_TO_ENSG}', )
+ f = open(
+ f"{DataLoader.PATH_PROTEINS}{DataLoader.ENTREZ_TO_ENSG}",
+ )
data = json.load(f)
return data
@@ -107,100 +72,12 @@ class DataLoader:
Returns:
pd.DataFrame: columns 'entrez_a', 'entrez_b'
"""
- df = pd.read_csv(f'{DataLoader.PATH_PPI}{DataLoader.PPI_STRING}', index_col=0)
- df['entrez_a'] = df['entrez_a'].map(DataLoader._clean_entrez)
- df['entrez_b'] = df['entrez_b'].map(DataLoader._clean_entrez)
+ df = pd.read_csv(f"{DataLoader.PATH_PPI}{DataLoader.PPI_STRING}", index_col=0)
+ df["entrez_a"] = df["entrez_a"].map(DataLoader._clean_entrez)
+ df["entrez_b"] = df["entrez_b"].map(DataLoader._clean_entrez)
df = df.drop_duplicates()
return df
- # @staticmethod
- # def load_ppi_biogrid() -> pd.DataFrame:
- # """Loads the Biogrid PPI interactions with Entex IDs
- #
- # Returns:
- # pd.DataFrame: columns 'entrez_a', 'entrez_b'
- # """
- # df = pd.read_csv(f'{DataLoader.PATH_PPI}{DataLoader.PPI_BIOGRID}', sep='\t')[
- # ['#ID Interactor A', 'ID Interactor B', 'Interaction Detection Method', 'Publication Identifiers',
- # 'Interaction Types', 'Confidence Values']]
- #
- # def parse_interactor(x):
- # # format entrez protein/locuslink:6416
- # # wanted: 6416
- # return x.split(':')[-1]
- #
- # def parse_publication_identifiers(x):
- # # format: pubmed:9006895
- # # wanted: 9006895
- # return x.split(':')[-1]
- #
- # def parse_interaction_detection_method_get_id(x):
- # # format: psi-mi:"MI:0018"(two hybrid)
- # # wanted: MI:0018
- # return x.split('"')[1]
- #
- # def parse_interaction_detection_method_get_name(x):
- # # format: psi-mi:"MI:0018"(two hybrid)
- # # wanted: two hybrid
- # return x.split('(')[1][:-1]
- #
- # def parse_interaction_types_get_id(x):
- # # format: psi-mi:"MI:0407"(direct interaction)
- # # wanted: MI:0407
- # return x.split('"')[1]
- #
- # def parse_interaction_types_get_name(x):
- # # format: psi-mi:"MI:0407"(direct interaction)
- # # wanted: direct interaction
- # return x.split('(')[1][:-1]
- #
- # def parse_confidence_value(x):
- # # format: score:7.732982515 or '-'
- # # wanted: 7.732982515 or '-'
- # if x == '-':
- # return '-'
- # else:
- # return x.split(':')[1]
- #
- # df['#ID Interactor A'] = df['#ID Interactor A'].map(parse_interactor)
- # df['ID Interactor B'] = df['ID Interactor B'].map(parse_interactor)
- #
- # df['Interaction Detection Method ID'] = df['Interaction Detection Method'].map(
- # parse_interaction_detection_method_get_id)
- # df['Interaction Detection Method Name'] = df['Interaction Detection Method'].map(
- # parse_interaction_detection_method_get_name)
- # df = df.drop('Interaction Detection Method', axis=1)
- #
- # df['Publication Identifiers'] = df['Publication Identifiers'].map(parse_publication_identifiers)
- #
- # df['Interaction Types ID'] = df['Interaction Types'].map(parse_interaction_types_get_id)
- # df['Interaction Types Name'] = df['Interaction Types'].map(parse_interaction_types_get_name)
- # df = df.drop('Interaction Types', axis=1)
- #
- # df['Confidence Values'] = df['Confidence Values'].map(parse_confidence_value)
- #
- # # remove dirty data (entrez id is sometimes protein name
- # to_remove = ['P0DTC1', 'P0DTD2', 'Q7TLC7']
- # df = df[~df['#ID Interactor A'].isin(to_remove)]
- #
- # df = df.rename(
- # columns={
- # '#ID Interactor A': 'entrez_a',
- # 'ID Interactor B': 'entrez_b',
- # 'Publication Identifiers': 'pubmed_id',
- # 'Confidence Values': 'confidence_value',
- # 'Interaction Detection Method ID': 'detection_method_psi_mi',
- # 'Interaction Detection Method Name': 'detection_method_name',
- # 'Interaction Types ID': 'type_psi_mi',
- # 'Interaction Types Name': 'type_name'
- # }
- # )
- #
- # df['entrez_a'] = df['entrez_a'].map(DataLoader._clean_entrez)
- # df['entrez_b'] = df['entrez_b'].map(DataLoader._clean_entrez)
- #
- # return df
-
@staticmethod
def load_ppi_apid() -> pd.DataFrame:
"""Loads the APID PPI interactions with Uniprot ACs
@@ -208,12 +85,13 @@ class DataLoader:
Returns:
pd.DataFrame: columns 'from_protein_ac', 'to_protein_ac'
"""
- df = pd.read_csv(f'{DataLoader.PATH_PPI}{DataLoader.PPI_APID}', index_col=0, sep='\t')
- df = df.rename(columns={
- 'UniprotID_A': 'from_protein_ac',
- 'UniprotID_B': 'to_protein_ac'
- })
- return df[['from_protein_ac', 'to_protein_ac']]
+ df = pd.read_csv(
+ f"{DataLoader.PATH_PPI}{DataLoader.PPI_APID}", index_col=0, sep="\t"
+ )
+ df = df.rename(
+ columns={"UniprotID_A": "from_protein_ac", "UniprotID_B": "to_protein_ac"}
+ )
+ return df[["from_protein_ac", "to_protein_ac"]]
@staticmethod
def load_pdi_chembl() -> pd.DataFrame:
@@ -222,16 +100,7 @@ class DataLoader:
Returns:
pd.DataFrame: columns "drug_id" and "protein_ac"
"""
- return pd.read_csv(f'{DataLoader.PATH_PDI}{DataLoader.PDI_CHEMBL}')
-
- # @staticmethod
- # def load_pdis_disgenet() -> pd.DataFrame:
- # """Loads the DisGeNET PDis associations with Uniprot Numbers and Mondo IDs
- #
- # Returns:
- # pd.DataFrame: columns "protein_name", "disorder_name" and "score"
- # """
- # return pd.read_csv(f'{DataLoader.PATH_PDi}{DataLoader.PDi_DISGENET}', sep='\t', dtype={'disorder_name':str, 'protein_name':str, 'score':float})
+ return pd.read_csv(f"{DataLoader.PATH_PDI}{DataLoader.PDI_CHEMBL}")
@staticmethod
def load_drdis_drugbank() -> pd.DataFrame:
@@ -240,7 +109,11 @@ class DataLoader:
Returns:
pd.DataFrame: columns "drugbank_id" and "mondo_id"
"""
- return pd.read_csv(f'{DataLoader.PATH_DDi}{DataLoader.DDi_DRUGBANK}', sep='\t', dtype={'drugbank_id':str, 'mondo_id':str})
+ return pd.read_csv(
+ f"{DataLoader.PATH_DDi}{DataLoader.DDi_DRUGBANK}",
+ sep="\t",
+ dtype={"drugbank_id": str, "mondo_id": str},
+ )
@staticmethod
def load_pdi_dgidb() -> pd.DataFrame:
@@ -249,17 +122,6 @@ class DataLoader:
Returns:
pd.DataFrame: columns "drug_id" and "entrez_id"
"""
- df = pd.read_csv(f'{DataLoader.PATH_PDI}{DataLoader.PDI_DGIDB}', index_col=0)
- df['entrez_id'] = df['entrez_id'].map(DataLoader._clean_entrez)
+ df = pd.read_csv(f"{DataLoader.PATH_PDI}{DataLoader.PDI_DGIDB}", index_col=0)
+ df["entrez_id"] = df["entrez_id"].map(DataLoader._clean_entrez)
return df
-
- # @staticmethod
- # def load_pdi_drugbank() -> pd.DataFrame:
- # """Loads the drugbank PDI interactions with DrugBank drug IDs and Entrez Gene IDs
- #
- # Returns:
- # pd.DataFrame: columns "drug_id" and "entrez_id"
- # """
- # df = pd.read_csv(f'{DataLoader.PATH_PDI}{DataLoader.PDI_DRUGBANK}').dropna()
- # df['entrez_id'] = df['entrez_id'].map(DataLoader._clean_entrez)
- # return df
diff --git a/drugstone/management/includes/DataPopulator.py b/drugstone/management/includes/DataPopulator.py
index 4a4a570b230ee4b7e1067dc1b7332049daec152d..988bd65c4ad5f43e2c3fbc0f81d4fc04a37ae87c 100755
--- a/drugstone/management/includes/DataPopulator.py
+++ b/drugstone/management/includes/DataPopulator.py
@@ -4,18 +4,16 @@ from drugstone.management.includes.NodeCache import NodeCache
class DataPopulator:
-
def __init__(self, cache: NodeCache):
self.cache = cache
def populate_expressions(self, update):
-
self.cache.init_proteins()
df = DataLoader.load_expressions()
tissues_models = dict()
for tissue_name in df.columns.values[2:]:
- tissue,_ = models.Tissue.objects.get_or_create(name=tissue_name)
+ tissue, _ = models.Tissue.objects.get_or_create(name=tissue_name)
tissues_models[tissue_name] = tissue
proteins_linked = 0
@@ -27,15 +25,17 @@ class DataPopulator:
size = 0
for _, row in df.iterrows():
- gene_name = row['Description']
+ gene_name = row["Description"]
for protein_model in self.cache.get_proteins_by_gene(gene_name):
proteins_linked += 1
if not update or self.cache.is_new_protein(protein_model):
for tissue_name, tissue_model in tissues_models.items():
- expr = models.ExpressionLevel(protein=protein_model,
- tissue=tissue_model,
- expression_level=row[tissue_name])
+ expr = models.ExpressionLevel(
+ protein=protein_model,
+ tissue=tissue_model,
+ expression_level=row[tissue_name],
+ )
id = hash(expr)
if id in uniq:
continue
@@ -49,8 +49,8 @@ class DataPopulator:
models.ExpressionLevel.objects.bulk_create(bulk)
return size + len(bulk)
- def populate_ensg(self,update) -> int:
- """ Populates the Ensembl-Gene table in the django database.
+ def populate_ensg(self, update) -> int:
+ """Populates the Ensembl-Gene table in the django database.
Also maps the added ensg entries to the corresponding proteins.
Handles loading the data and passing it to the django database
@@ -71,7 +71,7 @@ class DataPopulator:
return len(bulk)
def populate_ppi_string(self, dataset, update) -> int:
- """ Populates the Protein-Protein-Interactions from STRINGdb
+ """Populates the Protein-Protein-Interactions from STRINGdb
Handles loading the data and passing it to the django database
Returns:
@@ -84,23 +84,28 @@ class DataPopulator:
for _, row in df.iterrows():
try:
# try fetching proteins
- proteins_a = self.cache.get_proteins_by_entrez(row['entrez_a'])
- proteins_b = self.cache.get_proteins_by_entrez(row['entrez_b'])
+ proteins_a = self.cache.get_proteins_by_entrez(row["entrez_a"])
+ proteins_b = self.cache.get_proteins_by_entrez(row["entrez_b"])
except KeyError:
continue
for protein_a in proteins_a:
for protein_b in proteins_b:
- if not update or (self.cache.is_new_protein(protein_a) or self.cache.is_new_protein(protein_b)):
- bulk.append(models.ProteinProteinInteraction(
- ppi_dataset=dataset,
- from_protein=protein_a,
- to_protein=protein_b
- ))
+ if not update or (
+ self.cache.is_new_protein(protein_a)
+ or self.cache.is_new_protein(protein_b)
+ ):
+ bulk.append(
+ models.ProteinProteinInteraction(
+ ppi_dataset=dataset,
+ from_protein=protein_a,
+ to_protein=protein_b,
+ )
+ )
models.ProteinProteinInteraction.objects.bulk_create(bulk)
return len(bulk)
def populate_ppi_apid(self, dataset, update) -> int:
- """ Populates the Protein-Protein-Interactions from Apid
+ """Populates the Protein-Protein-Interactions from Apid
Handles loading the data and passing it to the django database
Returns:
@@ -113,17 +118,22 @@ class DataPopulator:
for _, row in df.iterrows():
try:
# try fetching proteins
- protein_a = self.cache.get_protein_by_uniprot(row['from_protein_ac'])
- protein_b = self.cache.get_protein_by_uniprot(row['to_protein_ac'])
+ protein_a = self.cache.get_protein_by_uniprot(row["from_protein_ac"])
+ protein_b = self.cache.get_protein_by_uniprot(row["to_protein_ac"])
except KeyError:
# continue if not found
continue
- if not update or (self.cache.is_new_protein(protein_a) or self.cache.is_new_protein(protein_b)):
- bulk.add(models.ProteinProteinInteraction(
- ppi_dataset=dataset,
- from_protein=protein_a,
- to_protein=protein_b
- ))
+ if not update or (
+ self.cache.is_new_protein(protein_a)
+ or self.cache.is_new_protein(protein_b)
+ ):
+ bulk.add(
+ models.ProteinProteinInteraction(
+ ppi_dataset=dataset,
+ from_protein=protein_a,
+ to_protein=protein_b,
+ )
+ )
models.ProteinProteinInteraction.objects.bulk_create(bulk)
return len(bulk)
@@ -158,8 +168,8 @@ class DataPopulator:
# models.ProteinProteinInteraction.objects.bulk_create(bulk)
# return len(bulk)
- def populate_pdi_chembl(self,dataset, update) -> int:
- """ Populates the Protein-Drug-Interactions from Chembl
+ def populate_pdi_chembl(self, dataset, update) -> int:
+ """Populates the Protein-Drug-Interactions from Chembl
Handles Loading the data and passing it to the django database
Returns:
@@ -172,22 +182,24 @@ class DataPopulator:
bulk = set()
for _, row in df.iterrows():
try:
- protein = self.cache.get_protein_by_uniprot(row['protein_ac'])
+ protein = self.cache.get_protein_by_uniprot(row["protein_ac"])
except KeyError:
# continue if not found
continue
try:
# try fetching drug
- drug = self.cache.get_drug_by_drugbank(row['drug_id'])
+ drug = self.cache.get_drug_by_drugbank(row["drug_id"])
except KeyError:
# continue if not found
continue
- if not update or (self.cache.is_new_protein(protein) or self.cache.is_new_drug(drug)):
- bulk.add(models.ProteinDrugInteraction(
- pdi_dataset=dataset,
- protein=protein,
- drug=drug
- ))
+ if not update or (
+ self.cache.is_new_protein(protein) or self.cache.is_new_drug(drug)
+ ):
+ bulk.add(
+ models.ProteinDrugInteraction(
+ pdi_dataset=dataset, protein=protein, drug=drug
+ )
+ )
models.ProteinDrugInteraction.objects.bulk_create(bulk)
return len(bulk)
@@ -227,7 +239,7 @@ class DataPopulator:
# return len(bulk)
def populate_drdis_drugbank(self, dataset, update) -> int:
- """ Populates the Drug-Disorder-Indications from DrugBank
+ """Populates the Drug-Disorder-Indications from DrugBank
Handles Loading the data and passing it to the django database
Returns:
@@ -241,29 +253,33 @@ class DataPopulator:
for _, row in df.iterrows():
try:
# try fetching protein
- drug = self.cache.get_drug_by_drugbank(row['drugbank_id'])
+ drug = self.cache.get_drug_by_drugbank(row["drugbank_id"])
except KeyError:
print(f"Did not find drug: {row['drugbank_id']}")
# continue if not found
continue
try:
# try fetching drug
- disorder = self.cache.get_disorder_by_mondo(row['mondo_id'])
+ disorder = self.cache.get_disorder_by_mondo(row["mondo_id"])
except KeyError:
print(f"Did not find drug: {row['mondo_id']}")
# continue if not found
continue
- if not update or (self.cache.is_new_drug(drug) or self.cache.is_new_disease(disorder)):
- bulk.add(models.DrugDisorderIndication(
- drdi_dataset=dataset,
- drug=drug,
- disorder=disorder,
- ))
+ if not update or (
+ self.cache.is_new_drug(drug) or self.cache.is_new_disease(disorder)
+ ):
+ bulk.add(
+ models.DrugDisorderIndication(
+ drdi_dataset=dataset,
+ drug=drug,
+ disorder=disorder,
+ )
+ )
models.DrugDisorderIndication.objects.bulk_create(bulk)
return len(bulk)
- def populate_pdi_dgidb(self,dataset, update) -> int:
- """ Populates the Protein-Drug-Interactions from DGIdb
+ def populate_pdi_dgidb(self, dataset, update) -> int:
+ """Populates the Protein-Drug-Interactions from DGIdb
Handles Loading the data and passing it to the django database
Returns:
@@ -276,20 +292,22 @@ class DataPopulator:
bulk = set()
for _, row in df.iterrows():
try:
- proteins = self.cache.get_proteins_by_entrez(row['entrez_id'])
+ proteins = self.cache.get_proteins_by_entrez(row["entrez_id"])
except KeyError:
continue
try:
- drug = self.cache.get_drug_by_drugbank(row['drug_id'])
+ drug = self.cache.get_drug_by_drugbank(row["drug_id"])
except KeyError:
continue
for protein in proteins:
- if not update or (self.cache.is_new_protein(protein) or self.cache.is_new_drug(drug)):
- bulk.add(models.ProteinDrugInteraction(
- pdi_dataset=dataset,
- protein=protein,
- drug=drug
- ))
+ if not update or (
+ self.cache.is_new_protein(protein) or self.cache.is_new_drug(drug)
+ ):
+ bulk.add(
+ models.ProteinDrugInteraction(
+ pdi_dataset=dataset, protein=protein, drug=drug
+ )
+ )
models.ProteinDrugInteraction.objects.bulk_create(bulk)
return len(bulk)
diff --git a/drugstone/management/includes/DatasetLoader.py b/drugstone/management/includes/DatasetLoader.py
index 062b7d99dc62655b7f7ebc7cd8e4f8435fd6abe5..7d11d5695f5fc911dc43c3b768d381da8a899114 100644
--- a/drugstone/management/includes/DatasetLoader.py
+++ b/drugstone/management/includes/DatasetLoader.py
@@ -8,30 +8,24 @@ LICENSE_FILE = "./data/license.txt"
def get_ppi_string():
dataset, _ = models.PPIDataset.objects.get_or_create(
- name='STRING',
- link='https://string-db.org/',
- version='11.0',
- licenced=False
+ name="STRING", link="https://string-db.org/", version="11.0", licenced=False
)
return dataset
def get_ppi_apid():
dataset, _ = models.PPIDataset.objects.get_or_create(
- name='APID',
- link='http://cicblade.dep.usal.es:8080/APID/',
- version='January 2019',
- licenced=False
+ name="APID",
+ link="http://cicblade.dep.usal.es:8080/APID/",
+ version="January 2019",
+ licenced=False,
)
return dataset
def get_ppi_biogrid():
dataset, _ = models.PPIDataset.objects.get_or_create(
- name='BioGRID',
- link='https://thebiogrid.org/',
- version='4.0',
- licenced=False
+ name="BioGRID", link="https://thebiogrid.org/", version="4.0", licenced=False
)
return dataset
@@ -39,7 +33,7 @@ def get_ppi_biogrid():
def get_nedrex_version():
version = get_today_version()
try:
- real_version = get_metadata()['version']
+ real_version = get_metadata()["version"]
if real_version != "0.0.0":
version = real_version
except RetryError:
@@ -48,56 +42,44 @@ def get_nedrex_version():
def get_nedrex_source_version(source):
- metadata = get_metadata()['source_databases']
+ metadata = get_metadata()["source_databases"]
# TODO remove once fixed in nedrex db
- if 'drug_central' in metadata:
- metadata['drugcentral'] = metadata['drug_central']
+ if "drug_central" in metadata:
+ metadata["drugcentral"] = metadata["drug_central"]
- return metadata[source]['date']
+ return metadata[source]["date"]
def get_drug_target_nedrex(url, licenced):
dataset, _ = models.PDIDataset.objects.get_or_create(
- name='NeDRex',
- link=url,
- version=get_nedrex_version(),
- licenced=licenced
+ name="NeDRex", link=url, version=get_nedrex_version(), licenced=licenced
)
return dataset
def get_ppi_nedrex(url, licenced):
dataset, _ = models.PPIDataset.objects.get_or_create(
- name='NeDRex',
- link=url,
- version=get_nedrex_version(),
- licenced=licenced
+ name="NeDRex", link=url, version=get_nedrex_version(), licenced=licenced
)
return dataset
def get_protein_disorder_nedrex(url, licenced):
dataset, _ = models.PDisDataset.objects.get_or_create(
- name='NeDRex',
- link=url,
- version=get_nedrex_version(),
- licenced=licenced
+ name="NeDRex", link=url, version=get_nedrex_version(), licenced=licenced
)
return dataset
def get_drug_disorder_nedrex(url, licenced):
dataset, _ = models.DrDiDataset.objects.get_or_create(
- name='NeDRex',
- link=url,
- version=get_nedrex_version(),
- licenced=licenced
+ name="NeDRex", link=url, version=get_nedrex_version(), licenced=licenced
)
return dataset
def write_license(text):
- with open(LICENSE_FILE, 'w') as fh:
+ with open(LICENSE_FILE, "w") as fh:
fh.write(text)
@@ -107,76 +89,71 @@ def update_license():
write_license(license)
return license
except RetryError:
- print(f'License could not be retreived.')
+ print("License could not be retreived.")
return ""
def import_license():
try:
license = ""
- with open(LICENSE_FILE, 'r') as fh:
+ with open(LICENSE_FILE, "r") as fh:
for line in fh:
license += line
return license
except FileNotFoundError:
- print(f'No license doc there yet! Make sure to run an update first!')
+ print("No license doc there yet! Make sure to run an update first!")
return ""
def get_drug_target_chembl():
dataset, _ = models.PDIDataset.objects.get_or_create(
- name='ChEMBL',
- link='https://www.ebi.ac.uk/chembl/',
- version='27',
- licenced=False
+ name="ChEMBL",
+ link="https://www.ebi.ac.uk/chembl/",
+ version="27",
+ licenced=False,
)
return dataset
def get_drug_target_dgidb():
dataset, _ = models.PDIDataset.objects.get_or_create(
- name='DGIdb',
- link='https://www.dgidb.org/',
- version='4.2.0',
- licenced=False
+ name="DGIdb", link="https://www.dgidb.org/", version="4.2.0", licenced=False
)
return dataset
def get_drug_target_drugbank():
dataset, _ = models.PDIDataset.objects.get_or_create(
- name='DrugBank',
- link='https://go.drugbank.com/',
- version='5.1.7',
- licenced=True
+ name="DrugBank", link="https://go.drugbank.com/", version="5.1.7", licenced=True
)
return dataset
def get_disorder_protein_disgenet():
dataset, _ = models.PDisDataset.objects.get_or_create(
- name='DisGeNET',
- link='https://www.disgenet.org/home/',
- version='6.0',
- licenced=False
+ name="DisGeNET",
+ link="https://www.disgenet.org/home/",
+ version="6.0",
+ licenced=False,
)
return dataset
def get_drug_disorder_drugbank():
dataset, _ = models.DrDiDataset.objects.get_or_create(
- name='DrugBank',
- link='https://go.drugbank.com/',
- version='5.1.8',
- licenced=False
+ name="DrugBank",
+ link="https://go.drugbank.com/",
+ version="5.1.8",
+ licenced=False,
)
return dataset
def get_today_version():
import datetime
+
now = datetime.date.today()
- version = f'{now.year}-{now.month}-{now.day}_temp'
+ version = f"{now.year}-{now.month}-{now.day}_temp"
return version
@@ -188,10 +165,7 @@ def get_ppi_nedrex_dataset(url, licenced, source):
pass
dataset, _ = models.PPIDataset.objects.get_or_create(
- name=source,
- link=url,
- version=version,
- licenced=licenced
+ name=source, link=url, version=version, licenced=licenced
)
return dataset
@@ -204,10 +178,7 @@ def get_pdi_nedrex_dataset(url, licenced, source):
pass
dataset, _ = models.PDIDataset.objects.get_or_create(
- name=source,
- link=url,
- version=version,
- licenced=licenced
+ name=source, link=url, version=version, licenced=licenced
)
return dataset
@@ -220,10 +191,7 @@ def get_pdis_nedrex_dataset(url, licenced, source):
pass
dataset, _ = models.PDisDataset.objects.get_or_create(
- name=source,
- link=url,
- version=version,
- licenced=licenced
+ name=source, link=url, version=version, licenced=licenced
)
return dataset
@@ -236,10 +204,7 @@ def get_drdi_nedrex_dataset(url, licenced, source):
pass
dataset, _ = models.DrDiDataset.objects.get_or_create(
- name=source,
- link=url,
- version=version,
- licenced=licenced
+ name=source, link=url, version=version, licenced=licenced
)
return dataset
@@ -253,7 +218,7 @@ def is_licenced_ppi_source(source):
try:
models.PPIDataset.objects.get(name=source, version=version, licenced=False).link
- except:
+ except Exception:
return True
return False
@@ -267,7 +232,7 @@ def is_licenced_pdi_source(source):
try:
models.PDIDataset.objects.get(name=source, version=version, licenced=False).link
- except:
+ except Exception:
return True
return False
@@ -280,8 +245,10 @@ def is_licenced_pdis_source(source):
pass
try:
- models.PDisDataset.objects.get(name=source, version=version, licenced=False).link
- except:
+ models.PDisDataset.objects.get(
+ name=source, version=version, licenced=False
+ ).link
+ except Exception:
return True
return False
@@ -294,75 +261,9 @@ def is_licenced_drdi_source(source):
pass
try:
- models.DrDiDataset.objects.get(name=source, version=version, licenced=False).link
- except:
+ models.DrDiDataset.objects.get(
+ name=source, version=version, licenced=False
+ ).link
+ except Exception:
return True
return False
-
-
-# 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/models.py b/drugstone/models.py
index 3c664322705ea5ab5c211f6ce6beabaebf9e4185..ea9e12432de70e219f3f93a3e7beec810923e41a 100755
--- a/drugstone/models.py
+++ b/drugstone/models.py
@@ -7,64 +7,66 @@ from django.db import models
class PPIDataset(models.Model):
id = models.AutoField(primary_key=True)
- name = models.CharField(max_length=128, default='', unique=False)
- link = models.CharField(max_length=128, default='', unique=False)
- version = models.CharField(max_length=128, default='', unique=False)
+ name = models.CharField(max_length=128, default="", unique=False)
+ link = models.CharField(max_length=128, default="", unique=False)
+ version = models.CharField(max_length=128, default="", unique=False)
licenced = models.BooleanField(default=True)
def __str__(self):
return f'{self.name}-{self.version}_{"licenced" if self.licenced else "unlicenced"}'
class Meta:
- unique_together = ('name', 'version', 'licenced')
+ unique_together = ("name", "version", "licenced")
class PDIDataset(models.Model):
id = models.AutoField(primary_key=True)
- name = models.CharField(max_length=128, default='', unique=False)
- link = models.CharField(max_length=128, default='', unique=False)
- version = models.CharField(max_length=128, default='', unique=False)
+ name = models.CharField(max_length=128, default="", unique=False)
+ link = models.CharField(max_length=128, default="", unique=False)
+ version = models.CharField(max_length=128, default="", unique=False)
licenced = models.BooleanField(default=True)
def __str__(self):
return f'{self.name}-{self.version}_{"licenced" if self.licenced else "unlicenced"}'
class Meta:
- unique_together = ('name', 'version','licenced')
+ unique_together = ("name", "version", "licenced")
class PDisDataset(models.Model):
id = models.AutoField(primary_key=True)
- name = models.CharField(max_length=128, default='', unique=False)
- link = models.CharField(max_length=128, default='', unique=False)
- version = models.CharField(max_length=128, default='', unique=False)
+ name = models.CharField(max_length=128, default="", unique=False)
+ link = models.CharField(max_length=128, default="", unique=False)
+ version = models.CharField(max_length=128, default="", unique=False)
licenced = models.BooleanField(default=True)
def __str__(self):
return f'{self.name}-{self.version}_{"licenced" if self.licenced else "unlicenced"}'
class Meta:
- unique_together = ('name', 'version', 'licenced')
+ unique_together = ("name", "version", "licenced")
class DrDiDataset(models.Model):
id = models.AutoField(primary_key=True)
- name = models.CharField(max_length=128, default='', unique=False)
- link = models.CharField(max_length=128, default='', unique=False)
- version = models.CharField(max_length=128, default='', unique=False)
+ name = models.CharField(max_length=128, default="", unique=False)
+ link = models.CharField(max_length=128, default="", unique=False)
+ version = models.CharField(max_length=128, default="", unique=False)
licenced = models.BooleanField(default=True)
def __str__(self):
return f'{self.name}-{self.version}_{"licenced" if self.licenced else "unlicenced"}'
class Meta:
- unique_together = ('name', 'version', 'licenced')
+ unique_together = ("name", "version", "licenced")
class EnsemblGene(models.Model):
id = models.AutoField(primary_key=True)
name = models.CharField(max_length=15) # starts with ENSG...
- protein = models.ForeignKey('Protein', on_delete=models.CASCADE, related_name='ensg')
+ protein = models.ForeignKey(
+ "Protein", on_delete=models.CASCADE, related_name="ensg"
+ )
class Protein(models.Model):
@@ -72,22 +74,29 @@ class Protein(models.Model):
# are either 6 or 10 characters long
id = models.AutoField(primary_key=True)
uniprot_code = models.CharField(max_length=10)
- gene = models.CharField(max_length=127, default='') # symbol
- protein_name = models.CharField(max_length=255, default='')
- entrez = models.CharField(max_length=15, default='')
- drugs = models.ManyToManyField('Drug', through='ProteinDrugInteraction',
- related_name='interacting_drugs')
- tissue_expression = models.ManyToManyField('Tissue', through='ExpressionLevel',
- related_name='interacting_drugs')
+ gene = models.CharField(max_length=127, default="") # symbol
+ protein_name = models.CharField(max_length=255, default="")
+ entrez = models.CharField(max_length=15, default="")
+ drugs = models.ManyToManyField(
+ "Drug", through="ProteinDrugInteraction", related_name="interacting_drugs"
+ )
+ tissue_expression = models.ManyToManyField(
+ "Tissue", through="ExpressionLevel", related_name="interacting_drugs"
+ )
class Meta:
- unique_together = ('uniprot_code', 'gene', 'entrez')
+ unique_together = ("uniprot_code", "gene", "entrez")
def __str__(self):
return self.gene
def __eq__(self, other):
- return self.uniprot_code == other.uniprot_code and self.gene == other.gene and self.protein_name == other.protein_name and self.entrez == other.entrez
+ return (
+ self.uniprot_code == other.uniprot_code
+ and self.gene == other.gene
+ and self.protein_name == other.protein_name
+ and self.entrez == other.entrez
+ )
def __ne__(self, other):
return not self.__eq__(other)
@@ -104,20 +113,20 @@ class Protein(models.Model):
class ExpressionLevel(models.Model):
id = models.AutoField(primary_key=True)
- tissue = models.ForeignKey('Tissue', on_delete=models.CASCADE)
- protein = models.ForeignKey('Protein', on_delete=models.CASCADE)
+ tissue = models.ForeignKey("Tissue", on_delete=models.CASCADE)
+ protein = models.ForeignKey("Protein", on_delete=models.CASCADE)
expression_level = models.FloatField()
class Meta:
- unique_together = ('tissue', 'protein')
+ unique_together = ("tissue", "protein")
def __hash__(self):
- return hash(f'{self.tissue_id}_{self.protein_id}')
+ return hash(f"{self.tissue_id}_{self.protein_id}")
class Tissue(models.Model):
id = models.AutoField(primary_key=True)
- name = models.CharField(max_length=128, default='', unique=True)
+ name = models.CharField(max_length=128, default="", unique=True)
def __str__(self):
return self.name
@@ -126,19 +135,26 @@ class Tissue(models.Model):
class Disorder(models.Model):
id = models.AutoField(primary_key=True)
mondo_id = models.CharField(max_length=7)
- label = models.CharField(max_length=256, default='') # symbol
- icd10 = models.CharField(max_length=512, default='')
+ label = models.CharField(max_length=256, default="") # symbol
+ icd10 = models.CharField(max_length=512, default="")
proteins = models.ManyToManyField(
- 'Protein', through='ProteinDisorderAssociation', related_name='associated_proteins')
+ "Protein",
+ through="ProteinDisorderAssociation",
+ related_name="associated_proteins",
+ )
class Meta:
- unique_together = ('mondo_id', 'label', 'icd10')
+ unique_together = ("mondo_id", "label", "icd10")
def __str__(self):
return self.label
def __eq__(self, other):
- return self.mondo_id == other.mondo_id and self.label == other.label and self.icd10 == other.icd10
+ return (
+ self.mondo_id == other.mondo_id
+ and self.label == other.label
+ and self.icd10 == other.icd10
+ )
def __ne__(self, other):
return not self.__eq__(other)
@@ -155,17 +171,21 @@ class Disorder(models.Model):
class Drug(models.Model):
id = models.AutoField(primary_key=True)
drug_id = models.CharField(max_length=10, unique=True)
- name = models.CharField(max_length=256, default='')
- status = models.CharField(max_length=128, default='')
+ name = models.CharField(max_length=256, default="")
+ status = models.CharField(max_length=128, default="")
# in_trial = models.BooleanField(default=False)
# in_literature = models.BooleanField(default=False)
- links = models.CharField(max_length=16 * 1024, default='')
+ links = models.CharField(max_length=16 * 1024, default="")
def __str__(self):
return self.drug_id
def __eq__(self, other):
- return self.drug_id == other.drug_id and self.name == other.name and self.status == other.status
+ return (
+ self.drug_id == other.drug_id
+ and self.name == other.name
+ and self.status == other.status
+ )
def __ne__(self, other):
return not self.__eq__(other)
@@ -183,19 +203,27 @@ class Drug(models.Model):
class ProteinDisorderAssociation(models.Model):
id = models.BigAutoField(primary_key=True)
pdis_dataset = models.ForeignKey(
- 'PDisDataset', null=True, on_delete=models.CASCADE, related_name='pdis_dataset_relation')
- protein = models.ForeignKey('Protein', on_delete=models.CASCADE)
- disorder = models.ForeignKey('Disorder', on_delete=models.CASCADE)
+ "PDisDataset",
+ null=True,
+ on_delete=models.CASCADE,
+ related_name="pdis_dataset_relation",
+ )
+ protein = models.ForeignKey("Protein", on_delete=models.CASCADE)
+ disorder = models.ForeignKey("Disorder", on_delete=models.CASCADE)
score = models.FloatField()
class Meta:
- unique_together = ('pdis_dataset', 'protein', 'disorder')
+ unique_together = ("pdis_dataset", "protein", "disorder")
def __str__(self):
- return f'{self.pdis_dataset}-{self.protein}-{self.disorder}'
+ return f"{self.pdis_dataset}-{self.protein}-{self.disorder}"
def __eq__(self, other):
- return self.pdis_dataset_id == other.pdis_dataset_id and self.protein_id == other.protein_id and self.disorder_id == other.disorder_id
+ return (
+ self.pdis_dataset_id == other.pdis_dataset_id
+ and self.protein_id == other.protein_id
+ and self.disorder_id == other.disorder_id
+ )
def __ne__(self, other):
return not self.__eq__(other)
@@ -207,18 +235,26 @@ class ProteinDisorderAssociation(models.Model):
class DrugDisorderIndication(models.Model):
id = models.AutoField(primary_key=True)
drdi_dataset = models.ForeignKey(
- 'DrDiDataset', null=True, on_delete=models.CASCADE, related_name='drdi_dataset_relation')
- drug = models.ForeignKey('Drug', on_delete=models.CASCADE)
- disorder = models.ForeignKey('Disorder', on_delete=models.CASCADE)
+ "DrDiDataset",
+ null=True,
+ on_delete=models.CASCADE,
+ related_name="drdi_dataset_relation",
+ )
+ drug = models.ForeignKey("Drug", on_delete=models.CASCADE)
+ disorder = models.ForeignKey("Disorder", on_delete=models.CASCADE)
class Meta:
- unique_together = ('drdi_dataset', 'drug', 'disorder')
+ unique_together = ("drdi_dataset", "drug", "disorder")
def __str__(self):
- return f'{self.drdi_dataset}-{self.drug}-{self.disorder}'
+ return f"{self.drdi_dataset}-{self.drug}-{self.disorder}"
def __eq__(self, other):
- return self.drdi_dataset_id == other.drdi_dataset_id and self.drug_id == other.drug_id and self.disorder_id == other.disorder_id
+ return (
+ self.drdi_dataset_id == other.drdi_dataset_id
+ and self.drug_id == other.drug_id
+ and self.disorder_id == other.disorder_id
+ )
def __ne__(self, other):
return not self.__eq__(other)
@@ -230,34 +266,46 @@ class DrugDisorderIndication(models.Model):
class ProteinProteinInteraction(models.Model):
id = models.BigAutoField(primary_key=True)
ppi_dataset = models.ForeignKey(
- 'PPIDataset', null=True, on_delete=models.CASCADE, related_name='ppi_dataset_relation')
- from_protein = models.ForeignKey('Protein', on_delete=models.CASCADE, related_name='interacting_proteins_out')
- to_protein = models.ForeignKey('Protein', on_delete=models.CASCADE, related_name='interacting_proteins_in')
+ "PPIDataset",
+ null=True,
+ on_delete=models.CASCADE,
+ related_name="ppi_dataset_relation",
+ )
+ from_protein = models.ForeignKey(
+ "Protein", on_delete=models.CASCADE, related_name="interacting_proteins_out"
+ )
+ to_protein = models.ForeignKey(
+ "Protein", on_delete=models.CASCADE, related_name="interacting_proteins_in"
+ )
def validate_unique(self, exclude=None):
p1p2_q = ProteinProteinInteraction.objects.filter(
from_protein=self.from_protein,
to_protein=self.to_protein,
- ppi_dataset=self.ppi_dataset
+ ppi_dataset=self.ppi_dataset,
)
p2p1_q = ProteinProteinInteraction.objects.filter(
from_protein=self.to_protein,
to_protein=self.from_protein,
- ppi_dataset=self.ppi_dataset
+ ppi_dataset=self.ppi_dataset,
)
if p1p2_q.exists() or p2p1_q.exists():
- raise ValidationError('Protein-Protein interaction must be unique!')
+ raise ValidationError("Protein-Protein interaction must be unique!")
def save(self, *args, **kwargs):
self.validate_unique()
super(ProteinProteinInteraction, self).save(*args, **kwargs)
def __str__(self):
- return f'{self.ppi_dataset}-{self.from_protein}-{self.to_protein}'
+ return f"{self.ppi_dataset}-{self.from_protein}-{self.to_protein}"
def __eq__(self, other):
- return self.ppi_dataset_id == other.ppi_dataset_id and self.from_protein_id == other.from_protein_id and self.to_protein_id == other.to_protein_id
+ return (
+ self.ppi_dataset_id == other.ppi_dataset_id
+ and self.from_protein_id == other.from_protein_id
+ and self.to_protein_id == other.to_protein_id
+ )
def __ne__(self, other):
return not self.__eq__(other)
@@ -269,18 +317,26 @@ class ProteinProteinInteraction(models.Model):
class ProteinDrugInteraction(models.Model):
id = models.BigAutoField(primary_key=True)
pdi_dataset = models.ForeignKey(
- PDIDataset, null=True, on_delete=models.CASCADE, related_name='pdi_dataset_relation')
- protein = models.ForeignKey('Protein', on_delete=models.CASCADE)
- drug = models.ForeignKey('Drug', on_delete=models.CASCADE)
+ PDIDataset,
+ null=True,
+ on_delete=models.CASCADE,
+ related_name="pdi_dataset_relation",
+ )
+ protein = models.ForeignKey("Protein", on_delete=models.CASCADE)
+ drug = models.ForeignKey("Drug", on_delete=models.CASCADE)
class Meta:
- unique_together = ('pdi_dataset', 'protein', 'drug')
+ unique_together = ("pdi_dataset", "protein", "drug")
def __str__(self):
- return f'{self.pdi_dataset}-{self.protein}-{self.drug}'
+ return f"{self.pdi_dataset}-{self.protein}-{self.drug}"
def __eq__(self, other):
- return self.pdi_dataset_id == other.pdi_dataset_id and self.protein_id == other.protein_id and self.drug_id == other.drug_id
+ return (
+ self.pdi_dataset_id == other.pdi_dataset_id
+ and self.protein_id == other.protein_id
+ and self.drug_id == other.drug_id
+ )
def __ne__(self, other):
return not self.__eq__(other)
@@ -292,7 +348,9 @@ class ProteinDrugInteraction(models.Model):
class Task(models.Model):
token = models.CharField(max_length=32, unique=True, primary_key=True)
created_at = models.DateTimeField(auto_now_add=True)
- target = models.CharField(max_length=32, choices=[('drug', 'Drug'), ('drug-target', 'Drug Target')])
+ target = models.CharField(
+ max_length=32, choices=[("drug", "Drug"), ("drug-target", "Drug Target")]
+ )
algorithm = models.CharField(max_length=128)
parameters = models.TextField()
@@ -312,7 +370,7 @@ class Task(models.Model):
class Network(models.Model):
id = models.CharField(primary_key=True, max_length=32, unique=True)
created_at = models.DateTimeField(auto_now_add=True)
- nodes = models.TextField(null=True, default='')
- edges = models.TextField(null=True, default='')
- config = models.TextField(null=True, default='')
- groups = models.TextField(null=True, default='')
+ nodes = models.TextField(null=True, default="")
+ edges = models.TextField(null=True, default="")
+ config = models.TextField(null=True, default="")
+ groups = models.TextField(null=True, default="")
diff --git a/drugstone/serializers.py b/drugstone/serializers.py
index 3805f42ca025ff7e5b7fa071aeee24dfadb5ad78..16033056c7ee13801301ef4f6a4ce09e0e988f8f 100755
--- a/drugstone/serializers.py
+++ b/drugstone/serializers.py
@@ -2,31 +2,43 @@
import json
from rest_framework import serializers
from drugstone import models
-from drugstone.models import Protein, Task, Drug, ProteinDrugInteraction, \
- Tissue, ProteinProteinInteraction, Network, ProteinDisorderAssociation, Disorder, DrugDisorderIndication
+from drugstone.models import (
+ Protein,
+ Task,
+ Drug,
+ ProteinDrugInteraction,
+ Tissue,
+ ProteinProteinInteraction,
+ Network,
+ ProteinDisorderAssociation,
+ Disorder,
+ DrugDisorderIndication,
+)
class PDIDatasetSerializer(serializers.ModelSerializer):
class Meta:
model = models.PDIDataset
- fields = '__all__'
+ fields = "__all__"
class PPIDatasetSerializer(serializers.ModelSerializer):
class Meta:
model = models.PPIDataset
- fields = '__all__'
+ fields = "__all__"
+
class PDisDatasetSerializer(serializers.ModelSerializer):
class Meta:
model = models.PDisDataset
- fields = '__all__'
+ fields = "__all__"
class DrDisDatasetSerializer(serializers.ModelSerializer):
class Meta:
model = models.DrDiDataset
- fields = '__all__'
+ fields = "__all__"
+
class ProteinNodeSerializer(serializers.ModelSerializer):
drugstone_id = serializers.SerializerMethodField()
@@ -36,7 +48,7 @@ class ProteinNodeSerializer(serializers.ModelSerializer):
entrez = serializers.SerializerMethodField()
def get_drugstone_id(self, obj):
- return [f'p{obj.id}']
+ return [f"p{obj.id}"]
def get_uniprot(self, obj):
return [obj.uniprot_code]
@@ -44,7 +56,7 @@ class ProteinNodeSerializer(serializers.ModelSerializer):
def get_symbol(self, obj):
return [obj.gene]
- def get_entrez(self,obj):
+ def get_entrez(self, obj):
return [obj.entrez]
def get_ensg(self, obj) -> str:
@@ -61,7 +73,7 @@ class ProteinNodeSerializer(serializers.ModelSerializer):
class Meta:
model = Protein
- fields = ['drugstone_id', 'uniprot', 'symbol', 'protein_name', 'entrez', 'ensg']
+ fields = ["drugstone_id", "uniprot", "symbol", "protein_name", "entrez", "ensg"]
class ProteinSerializer(serializers.ModelSerializer):
@@ -71,7 +83,7 @@ class ProteinSerializer(serializers.ModelSerializer):
ensg = serializers.SerializerMethodField()
def get_drugstone_id(self, obj):
- return f'p{obj.id}'
+ return f"p{obj.id}"
def get_uniprot(self, obj):
return obj.uniprot_code
@@ -93,7 +105,7 @@ class ProteinSerializer(serializers.ModelSerializer):
class Meta:
model = Protein
- fields = ['drugstone_id', 'uniprot', 'symbol', 'protein_name', 'entrez', 'ensg']
+ fields = ["drugstone_id", "uniprot", "symbol", "protein_name", "entrez", "ensg"]
class DrugSerializer(serializers.ModelSerializer):
@@ -102,17 +114,17 @@ class DrugSerializer(serializers.ModelSerializer):
label = serializers.SerializerMethodField()
def get_drugstone_id(self, obj):
- return f'dr{obj.id}'
+ return f"dr{obj.id}"
def get_trial_links(self, obj):
- return [] if obj.links == '' else obj.links.split(';')
+ return [] if obj.links == "" else obj.links.split(";")
def get_label(self, obj):
return obj.name
class Meta:
model = Drug
- fields = ['drugstone_id', 'drug_id', 'label', 'status', 'trial_links']
+ fields = ["drugstone_id", "drug_id", "label", "status", "trial_links"]
class DisorderSerializer(serializers.ModelSerializer):
@@ -121,17 +133,17 @@ class DisorderSerializer(serializers.ModelSerializer):
disorder_id = serializers.SerializerMethodField()
def get_drugstone_id(self, obj):
- return f'di{obj.id}'
+ return f"di{obj.id}"
def get_icd_10(self, obj):
- return obj.icd10[1:len(obj.icd10)-1].split(',')
+ return obj.icd10[1 : len(obj.icd10) - 1].split(",")
def get_disorder_id(self, obj):
return obj.mondo_id
class Meta:
model = Disorder
- fields = ['drugstone_id', 'label', 'icd_10', 'disorder_id']
+ fields = ["drugstone_id", "label", "icd_10", "disorder_id"]
class ProteinProteinInteractionSerializer(serializers.ModelSerializer):
@@ -143,14 +155,14 @@ class ProteinProteinInteractionSerializer(serializers.ModelSerializer):
return obj.ppi_dataset.name
def get_protein_a(self, obj):
- return f'p{obj.from_protein.id}'
+ return f"p{obj.from_protein.id}"
def get_protein_b(self, obj):
- return f'p{obj.to_protein.id}'
+ return f"p{obj.to_protein.id}"
class Meta:
model = ProteinProteinInteraction
- fields = ['dataset', 'protein_a', 'protein_b']
+ fields = ["dataset", "protein_a", "protein_b"]
class ProteinDrugInteractionSerializer(serializers.ModelSerializer):
@@ -162,14 +174,14 @@ class ProteinDrugInteractionSerializer(serializers.ModelSerializer):
return obj.pdi_dataset.name
def get_protein(self, obj):
- return f'p{obj.protein.id}'
+ return f"p{obj.protein.id}"
def get_drug(self, obj):
- return f'dr{obj.drug.id}'
+ return f"dr{obj.drug.id}"
class Meta:
model = ProteinDrugInteraction
- fields = ['dataset', 'protein', 'drug']
+ fields = ["dataset", "protein", "drug"]
class ProteinDisorderAssociationSerializer(serializers.ModelSerializer):
@@ -182,17 +194,17 @@ class ProteinDisorderAssociationSerializer(serializers.ModelSerializer):
return obj.pdis_dataset.name
def get_protein(self, obj):
- return f'p{obj.protein.id}'
+ return f"p{obj.protein.id}"
def get_disorder(self, obj):
- return f'di{obj.disorder.id}'
+ return f"di{obj.disorder.id}"
def get_score(self, obj):
return float(obj.score)
class Meta:
model = ProteinDisorderAssociation
- fields = ['dataset', 'protein', 'disorder', 'score']
+ fields = ["dataset", "protein", "disorder", "score"]
class DrugDisorderIndicationSerializer(serializers.ModelSerializer):
@@ -204,14 +216,14 @@ class DrugDisorderIndicationSerializer(serializers.ModelSerializer):
return obj.drdi_dataset.name
def get_drug(self, obj):
- return f'dr{obj.drug.id}'
+ return f"dr{obj.drug.id}"
def get_disorder(self, obj):
- return f'di{obj.disorder.id}'
+ return f"di{obj.disorder.id}"
class Meta:
model = DrugDisorderIndication
- fields = ['dataset', 'drug', 'disorder']
+ fields = ["dataset", "drug", "disorder"]
class TaskSerializer(serializers.ModelSerializer):
@@ -222,8 +234,20 @@ class TaskSerializer(serializers.ModelSerializer):
class Meta:
model = Task
- fields = ['algorithm', 'target', 'parameters', 'job_id', 'worker_id', 'progress', 'status', 'created_at',
- 'started_at', 'finished_at', 'done', 'failed']
+ fields = [
+ "algorithm",
+ "target",
+ "parameters",
+ "job_id",
+ "worker_id",
+ "progress",
+ "status",
+ "created_at",
+ "started_at",
+ "finished_at",
+ "done",
+ "failed",
+ ]
class NetworkSerializer(serializers.ModelSerializer):
@@ -233,7 +257,8 @@ class NetworkSerializer(serializers.ModelSerializer):
class Meta:
model = Network
- fields = '__all__'
+ fields = "__all__"
+
# def get_nodes(self,obj):
# return json.loads(obj.nodes)
@@ -248,16 +273,25 @@ class NetworkSerializer(serializers.ModelSerializer):
class TaskStatusSerializer(serializers.ModelSerializer):
class Meta:
model = Task
- fields = ['algorithm', 'target', 'progress', 'status', 'created_at', 'started_at', 'finished_at', 'done',
- 'failed']
+ fields = [
+ "algorithm",
+ "target",
+ "progress",
+ "status",
+ "created_at",
+ "started_at",
+ "finished_at",
+ "done",
+ "failed",
+ ]
class TissueSerializer(serializers.ModelSerializer):
drugstone_id = serializers.SerializerMethodField()
def get_drugstone_id(self, obj):
- return f'{obj.id}'
+ return f"{obj.id}"
class Meta:
model = Tissue
- fields = ['drugstone_id', 'name']
+ fields = ["drugstone_id", "name"]
diff --git a/drugstone/settings/settings.py b/drugstone/settings/settings.py
index 7ac243950d59e330e63ccf4a4f6d5125e3666499..460dba97ebad82e1c25e45fcc55eebf8d92ade82 100755
--- a/drugstone/settings/settings.py
+++ b/drugstone/settings/settings.py
@@ -21,77 +21,77 @@ BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
# See https://docs.djangoproject.com/en/3.0/howto/deployment/checklist/
# SECURITY WARNING: keep the secret key used in production secret!
-SECRET_KEY = os.environ.get('SECRET_KEY')
+SECRET_KEY = os.environ.get("SECRET_KEY")
# SECURITY WARNING: don't run with debug turned on in production!
-DEBUG = os.environ.get('DEBUG') == '1'
+DEBUG = os.environ.get("DEBUG") == "1"
ALLOWED_HOSTS = [
- 'localhost',
- '127.0.0.1',
- 'drugstone-backend.zbh.uni-hamburg.de',
- 'drugst.one'
+ "localhost",
+ "127.0.0.1",
+ "drugstone-backend.zbh.uni-hamburg.de",
+ "drugst.one",
]
# Application definition
INSTALLED_APPS = [
- 'django.contrib.admin',
- 'django.contrib.auth',
- 'django.contrib.contenttypes',
- 'django.contrib.sessions',
- 'django.contrib.messages',
- 'django.contrib.staticfiles',
- 'corsheaders',
- 'drugstone',
- 'rest_framework',
+ "django.contrib.admin",
+ "django.contrib.auth",
+ "django.contrib.contenttypes",
+ "django.contrib.sessions",
+ "django.contrib.messages",
+ "django.contrib.staticfiles",
+ "corsheaders",
+ "drugstone",
+ "rest_framework",
]
MIDDLEWARE = [
- 'corsheaders.middleware.CorsMiddleware',
- 'django.middleware.security.SecurityMiddleware',
- 'django.contrib.sessions.middleware.SessionMiddleware',
- 'django.middleware.common.BrokenLinkEmailsMiddleware',
- 'django.middleware.common.CommonMiddleware',
- 'django.middleware.csrf.CsrfViewMiddleware',
- 'django.contrib.auth.middleware.AuthenticationMiddleware',
- 'django.contrib.messages.middleware.MessageMiddleware',
- 'django.middleware.clickjacking.XFrameOptionsMiddleware',
+ "corsheaders.middleware.CorsMiddleware",
+ "django.middleware.security.SecurityMiddleware",
+ "django.contrib.sessions.middleware.SessionMiddleware",
+ "django.middleware.common.BrokenLinkEmailsMiddleware",
+ "django.middleware.common.CommonMiddleware",
+ "django.middleware.csrf.CsrfViewMiddleware",
+ "django.contrib.auth.middleware.AuthenticationMiddleware",
+ "django.contrib.messages.middleware.MessageMiddleware",
+ "django.middleware.clickjacking.XFrameOptionsMiddleware",
]
-ROOT_URLCONF = 'drugstone.urls'
+ROOT_URLCONF = "drugstone.urls"
TEMPLATES = [
{
- 'BACKEND': 'django.template.backends.django.DjangoTemplates',
- 'DIRS': [],
- 'APP_DIRS': True,
- 'OPTIONS': {
- 'context_processors': [
- 'django.template.context_processors.debug',
- 'django.template.context_processors.request',
- 'django.contrib.auth.context_processors.auth',
- 'django.contrib.messages.context_processors.messages',
+ "BACKEND": "django.template.backends.django.DjangoTemplates",
+ "DIRS": [],
+ "APP_DIRS": True,
+ "OPTIONS": {
+ "context_processors": [
+ "django.template.context_processors.debug",
+ "django.template.context_processors.request",
+ "django.contrib.auth.context_processors.auth",
+ "django.contrib.messages.context_processors.messages",
],
},
},
]
-WSGI_APPLICATION = 'drugstone.wsgi.application'
+WSGI_APPLICATION = "drugstone.wsgi.application"
# Database
# https://docs.djangoproject.com/en/3.0/ref/settings/#databases
DATABASES = {
- 'default': {
- 'ENGINE': os.environ.get('SQL_ENGINE', 'django.db.backends.postgresql'),
- 'NAME': os.environ.get('SQL_DATABASE'),
- 'USER': os.environ.get('SQL_USER'),
- 'PASSWORD': os.environ.get('SQL_PASSWORD'),
- 'HOST': os.environ.get('SQL_HOST'),
- 'PORT': os.environ.get('SQL_PORT'),
+ "default": {
+ "ENGINE": os.environ.get("SQL_ENGINE", "django.db.backends.postgresql"),
+ "NAME": os.environ.get("SQL_DATABASE"),
+ "USER": os.environ.get("SQL_USER"),
+ "PASSWORD": os.environ.get("SQL_PASSWORD"),
+ "HOST": os.environ.get("SQL_HOST"),
+ "PORT": os.environ.get("SQL_PORT"),
}
}
@@ -101,16 +101,16 @@ DATABASES = {
AUTH_PASSWORD_VALIDATORS = [
{
- 'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
+ "NAME": "django.contrib.auth.password_validation.UserAttributeSimilarityValidator",
},
{
- 'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
+ "NAME": "django.contrib.auth.password_validation.MinimumLengthValidator",
},
{
- 'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
+ "NAME": "django.contrib.auth.password_validation.CommonPasswordValidator",
},
{
- 'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
+ "NAME": "django.contrib.auth.password_validation.NumericPasswordValidator",
},
]
@@ -118,9 +118,9 @@ AUTH_PASSWORD_VALIDATORS = [
# Internationalization
# https://docs.djangoproject.com/en/3.0/topics/i18n/
-LANGUAGE_CODE = 'en-us'
+LANGUAGE_CODE = "en-us"
-TIME_ZONE = 'UTC'
+TIME_ZONE = "UTC"
USE_I18N = True
@@ -133,50 +133,46 @@ CORS_ORIGIN_ALLOW_ALL = True
# Static files (CSS, JavaScript, Images)
# https://docs.djangoproject.com/en/3.0/howto/static-files/
-STATIC_URL = '/static/'
+STATIC_URL = "/static/"
REST_FRAMEWORK = {
-
- 'DEFAULT_RENDERER_CLASSES': (
- 'djangorestframework_camel_case.render.CamelCaseJSONRenderer',
- 'djangorestframework_camel_case.render.CamelCaseBrowsableAPIRenderer',
+ "DEFAULT_RENDERER_CLASSES": (
+ "djangorestframework_camel_case.render.CamelCaseJSONRenderer",
+ "djangorestframework_camel_case.render.CamelCaseBrowsableAPIRenderer",
),
-
- 'DEFAULT_PARSER_CLASSES': (
- 'djangorestframework_camel_case.parser.CamelCaseJSONParser',
+ "DEFAULT_PARSER_CLASSES": (
+ "djangorestframework_camel_case.parser.CamelCaseJSONParser",
),
-
- 'DEFAULT_PERMISSION_CLASSES': [
- 'rest_framework.permissions.AllowAny',
- ]
-
+ "DEFAULT_PERMISSION_CLASSES": [
+ "rest_framework.permissions.AllowAny",
+ ],
}
-SESSION_ENGINE = 'django.contrib.sessions.backends.cache'
+SESSION_ENGINE = "django.contrib.sessions.backends.cache"
CACHES = {
- 'default': {
- 'BACKEND': 'django_redis.cache.RedisCache',
- 'LOCATION': f'redis://{os.environ.get("REDIS_HOST")}: \
+ "default": {
+ "BACKEND": "django_redis.cache.RedisCache",
+ "LOCATION": f'redis://{os.environ.get("REDIS_HOST")}: \
{os.environ.get("REDIS_PORT")}/1',
- 'OPTIONS': {
- 'CLIENT_CLASS': 'django_redis.client.DefaultClient',
- }
+ "OPTIONS": {
+ "CLIENT_CLASS": "django_redis.client.DefaultClient",
+ },
}
}
EMAIL_HOST = "exchange.uni-hamburg.de"
EMAIL_PORT = 587
-EMAIL_HOST_USER="taa0368"
+EMAIL_HOST_USER = "taa0368"
EMAIL_ADDRESS = "tools-cosybio.zbh@uni-hamburg.de"
-EMAIL_HOST_PASSWORD = os.environ.get('EMAIL_HOST_PASSWORD')
+EMAIL_HOST_PASSWORD = os.environ.get("EMAIL_HOST_PASSWORD")
EMAIL_USE_SSL = False
EMAIL_USE_TLS = True
-CELERY_BROKER_URL = os.environ.get('CELERY_BROKER_URL')
+CELERY_BROKER_URL = os.environ.get("CELERY_BROKER_URL")
# timezones: https://en.wikipedia.org/wiki/List_of_tz_database_time_zones
-CELERY_TIMEZONE = 'Europe/Berlin'
+CELERY_TIMEZONE = "Europe/Berlin"
-DEFAULTS = { 'ppi': 'NeDRex', 'pdi': 'NeDRex', 'pdis': 'NeDRex', 'drdi': 'NeDRex'}
+DEFAULTS = {"ppi": "NeDRex", "pdi": "NeDRex", "pdis": "NeDRex", "drdi": "NeDRex"}
diff --git a/drugstone/urls.py b/drugstone/urls.py
index eb547c75c0b82fa759778cc5820f1924e261a9e0..fff8b1a3e191ce2e3f300a3f9dc97893fa250fa4 100755
--- a/drugstone/urls.py
+++ b/drugstone/urls.py
@@ -16,34 +16,54 @@ Including another URLconf
from django.contrib import admin
from django.urls import path
-from drugstone.views import map_nodes, tasks_view, result_view, \
- graph_export, TissueView, TissueExpressionView, query_tissue_proteins, TaskView, \
- adjacent_drugs, adjacent_disorders, fetch_edges, create_network, load_network, get_license, get_datasets, \
- get_max_tissue_expression, convert_compact_ids, get_default_params, send_bugreport, save_selection, get_view, get_view_infos
+from drugstone.views import (
+ map_nodes,
+ tasks_view,
+ result_view,
+ graph_export,
+ TissueView,
+ TissueExpressionView,
+ query_tissue_proteins,
+ TaskView,
+ adjacent_drugs,
+ adjacent_disorders,
+ fetch_edges,
+ create_network,
+ load_network,
+ get_license,
+ get_datasets,
+ get_max_tissue_expression,
+ convert_compact_ids,
+ get_default_params,
+ send_bugreport,
+ save_selection,
+ get_view,
+ get_view_infos,
+)
# cache time is 6 hours
urlpatterns = [
- path('get_datasets/', get_datasets),
- path('map_nodes/', map_nodes),
- path('convert_compact_node_list/', convert_compact_ids),
- path('fetch_edges/', fetch_edges),
- path('task/', TaskView.as_view()),
- path('tasks/', tasks_view),
- path('task_result/', result_view),
- path('graph_export/', graph_export),
- path('query_tissue_proteins/', query_tissue_proteins),
- path('adjacent_drugs/', adjacent_drugs),
- path('adjacent_disorders/', adjacent_disorders),
- path('tissue_expression/', TissueExpressionView.as_view()),
- path('tissue_max_expression/', get_max_tissue_expression),
- path('tissues/', TissueView.as_view()),
- path('admin/', admin.site.urls),
- path('create_network', create_network),
- path('load_network', load_network),
- path('get_default_params', get_default_params),
- path('get_license', get_license),
- path('send_bugreport/', send_bugreport),
- path('save_selection', save_selection),
- path('view/', get_view),
- path('view_infos', get_view_infos)
+ path("get_datasets/", get_datasets),
+ path("map_nodes/", map_nodes),
+ path("convert_compact_node_list/", convert_compact_ids),
+ path("fetch_edges/", fetch_edges),
+ path("task/", TaskView.as_view()),
+ path("tasks/", tasks_view),
+ path("task_result/", result_view),
+ path("graph_export/", graph_export),
+ path("query_tissue_proteins/", query_tissue_proteins),
+ path("adjacent_drugs/", adjacent_drugs),
+ path("adjacent_disorders/", adjacent_disorders),
+ path("tissue_expression/", TissueExpressionView.as_view()),
+ path("tissue_max_expression/", get_max_tissue_expression),
+ path("tissues/", TissueView.as_view()),
+ path("admin/", admin.site.urls),
+ path("create_network", create_network),
+ path("load_network", load_network),
+ path("get_default_params", get_default_params),
+ path("get_license", get_license),
+ path("send_bugreport/", send_bugreport),
+ path("save_selection", save_selection),
+ path("view/", get_view),
+ path("view_infos", get_view_infos),
]
diff --git a/drugstone/views.py b/drugstone/views.py
index 366af9f3335fa34e1ee9f56b84fbd02b7159c323..7e9f32f6e42609ab2c4c0cbc003268e5dd254fef 100755
--- a/drugstone/views.py
+++ b/drugstone/views.py
@@ -4,25 +4,30 @@ import string
import time
import uuid
from collections import defaultdict
-from functools import reduce
-
import pandas as pd
-
import networkx as nx
from django.http import HttpResponse
from django.db.models import Q, Max
from django.db import IntegrityError
-from rest_framework import status
from rest_framework.decorators import api_view
from rest_framework.response import Response
from rest_framework.views import APIView
from drugstone.util.mailer import bugreport
-from drugstone.util.query_db import query_proteins_by_identifier, clean_proteins_from_compact_notation
+from drugstone.util.query_db import (
+ query_proteins_by_identifier,
+ clean_proteins_from_compact_notation,
+)
from drugstone.models import *
from drugstone.serializers import *
-from drugstone.backend_tasks import start_task, refresh_from_redis, task_stats, task_result, task_parameters
+from drugstone.backend_tasks import (
+ start_task,
+ refresh_from_redis,
+ task_stats,
+ task_result,
+ task_parameters,
+)
from drugstone.settings import DEFAULTS
@@ -42,87 +47,109 @@ def get_pdi_ds(source, licenced):
def get_pdis_ds(source, licenced):
- ds = models.PDisDataset.objects.filter(name__iexact=source, licenced=licenced).last()
+ ds = models.PDisDataset.objects.filter(
+ name__iexact=source, licenced=licenced
+ ).last()
if ds is None and licenced:
return get_pdis_ds(source, False)
return ds
def get_drdis_ds(source, licenced):
- ds = models.DrDiDataset.objects.filter(name__iexact=source, licenced=licenced).last()
+ ds = models.DrDiDataset.objects.filter(
+ name__iexact=source, licenced=licenced
+ ).last()
if ds is None and licenced:
return get_drdis_ds(source, False)
return ds
class TaskView(APIView):
-
def post(self, request) -> Response:
chars = string.ascii_lowercase + string.ascii_uppercase + string.digits
- token_str = ''.join(random.choice(chars) for _ in range(32))
- parameters = request.data['parameters']
- licenced = parameters.get('licenced', False)
- algorithm = request.data['algorithm']
+ token_str = "".join(random.choice(chars) for _ in range(32))
+ parameters = request.data["parameters"]
+ licenced = parameters.get("licenced", False)
+ algorithm = request.data["algorithm"]
# find databases based on parameter strings
- parameters['ppi_dataset'] = PPIDatasetSerializer().to_representation(
- get_ppi_ds(parameters.get('ppi_dataset', DEFAULTS['ppi']), licenced))
+ parameters["ppi_dataset"] = PPIDatasetSerializer().to_representation(
+ get_ppi_ds(parameters.get("ppi_dataset", DEFAULTS["ppi"]), licenced)
+ )
- parameters['pdi_dataset'] = PDIDatasetSerializer().to_representation(
- get_pdi_ds(parameters.get('pdi_dataset', DEFAULTS['pdi']), licenced))
+ parameters["pdi_dataset"] = PDIDatasetSerializer().to_representation(
+ get_pdi_ds(parameters.get("pdi_dataset", DEFAULTS["pdi"]), licenced)
+ )
# if algorithm in ['connect', 'connectSelected', 'quick', 'super']:
# parameters["num_trees"] = 5
# parameters["tolerance"] = 5
# parameters["hub_penalty"] = 0.5
- task = Task.objects.create(token=token_str,
- target=request.data['target'],
- algorithm=algorithm,
- parameters=json.dumps(parameters))
+ task = Task.objects.create(
+ token=token_str,
+ target=request.data["target"],
+ algorithm=algorithm,
+ parameters=json.dumps(parameters),
+ )
start_task(task)
task.save()
- return Response({
- 'token': token_str,
- })
+ return Response(
+ {
+ "token": token_str,
+ }
+ )
def get(self, request) -> Response:
- token_str = request.query_params['token']
+ token_str = request.query_params["token"]
task = Task.objects.get(token=token_str)
if not task.done and not task.failed:
refresh_from_redis(task)
task.save()
- return Response({
- 'token': task.token,
- 'info': TaskSerializer().to_representation(task),
- 'stats': task_stats(task),
- })
+ return Response(
+ {
+ "token": task.token,
+ "info": TaskSerializer().to_representation(task),
+ "stats": task_stats(task),
+ }
+ )
-@api_view(['GET'])
+@api_view(["GET"])
def get_license(request) -> Response:
from drugstone.management.includes.DatasetLoader import import_license
- return Response({'license': import_license()})
+ return Response({"license": import_license()})
-@api_view(['GET'])
+
+@api_view(["GET"])
def get_default_params(request) -> Response:
- algorithm = request.GET.get('algorithm')
- connect = {'algorithm': 'multisteiner', 'numTrees': 5, 'tolerance': 5, 'hubPenalty': 0.5}
- quick = {'algorithm': 'closeness', 'result_size': 50, 'hub_penalty': 0, 'include_non_approved_drugs': False,
- 'include_indirect_drugs': False}
+ algorithm = request.GET.get("algorithm")
+ connect = {
+ "algorithm": "multisteiner",
+ "numTrees": 5,
+ "tolerance": 5,
+ "hubPenalty": 0.5,
+ }
+ quick = {
+ "algorithm": "closeness",
+ "result_size": 50,
+ "hub_penalty": 0,
+ "include_non_approved_drugs": False,
+ "include_indirect_drugs": False,
+ }
resp = {}
- if algorithm in ['quick', 'super', 'connect', 'connectSelected']:
- resp['protein'] = connect
- if algorithm in ['quick', 'super']:
- resp['drug'] = quick
+ if algorithm in ["quick", "super", "connect", "connectSelected"]:
+ resp["protein"] = connect
+ if algorithm in ["quick", "super"]:
+ resp["drug"] = quick
return Response(resp)
-@api_view(['POST'])
+@api_view(["POST"])
def fetch_edges(request) -> Response:
"""Retrieves interactions between nodes given as a list of drugstone IDs.
@@ -133,32 +160,39 @@ def fetch_edges(request) -> Response:
Returns:
Response: List of edges which are objects with 'from' and to ' attribtues'
"""
- dataset = request.data.get('dataset', DEFAULTS['ppi'])
+ dataset = request.data.get("dataset", DEFAULTS["ppi"])
drugstone_ids = set()
- for node in request.data.get('nodes', '[]'):
- if 'drugstone_id' in node:
- if isinstance(node['drugstone_id'], list):
- for id in node['drugstone_id']:
+ for node in request.data.get("nodes", "[]"):
+ if "drugstone_id" in node:
+ if isinstance(node["drugstone_id"], list):
+ for id in node["drugstone_id"]:
drugstone_ids.add(id[1:])
else:
- drugstone_ids.add(node['drugstone_id'])
- licenced = request.data.get('licenced', False)
+ drugstone_ids.add(node["drugstone_id"])
+ licenced = request.data.get("licenced", False)
dataset_object = get_ppi_ds(dataset, licenced)
interaction_objects = models.ProteinProteinInteraction.objects.filter(
- Q(ppi_dataset=dataset_object) & Q(from_protein__in=drugstone_ids) & Q(to_protein__in=drugstone_ids))
+ Q(ppi_dataset=dataset_object)
+ & Q(from_protein__in=drugstone_ids)
+ & Q(to_protein__in=drugstone_ids)
+ )
- return Response(ProteinProteinInteractionSerializer(many=True).to_representation(interaction_objects))
+ return Response(
+ ProteinProteinInteractionSerializer(many=True).to_representation(
+ interaction_objects
+ )
+ )
-@api_view(['POST'])
+@api_view(["POST"])
def convert_compact_ids(request) -> Response:
- nodes = request.data.get('nodes', '[]')
- identifier = request.data.get('identifier', '')
+ nodes = request.data.get("nodes", "[]")
+ identifier = request.data.get("identifier", "")
cleaned = clean_proteins_from_compact_notation(nodes, identifier)
return Response(cleaned)
-@api_view(['POST'])
+@api_view(["POST"])
def map_nodes(request) -> Response:
"""Maps user given input nodes to Proteins in the django database.
Further updates the node list given by the user by extending the matching proteins with information
@@ -174,23 +208,23 @@ def map_nodes(request) -> Response:
Response: Updates node list.
"""
# load data from request
- nodes = request.data.get('nodes', '[]')
+ nodes = request.data.get("nodes", "[]")
id_map = {}
nodes_clean = []
for node in nodes:
- if not node['id']:
+ if not node["id"]:
# skip empty node id ''
continue
- upper = node['id'].upper()
- id_map[upper] = node['id']
- node['id'] = upper
+ upper = node["id"].upper()
+ id_map[upper] = node["id"]
+ node["id"] = upper
nodes_clean.append(node)
nodes = nodes_clean
- identifier = request.data.get('identifier', '')
+ identifier = request.data.get("identifier", "")
# extract ids for filtering
- node_ids = set([node['id'] for node in nodes])
+ node_ids = set([node["id"] for node in nodes])
# query protein table
nodes_mapped, id_key = query_proteins_by_identifier(node_ids, identifier)
@@ -207,55 +241,61 @@ def map_nodes(request) -> Response:
# merge fetched data with given data to avoid data loss
for node in nodes:
- node['drugstoneType'] = 'other'
- if node['id'] in nodes_mapped_dict:
- node.update(nodes_mapped_dict[node['id']])
- node['drugstoneType'] = 'protein'
- node['id'] = id_map[node['id']]
+ node["drugstoneType"] = "other"
+ if node["id"] in nodes_mapped_dict:
+ node.update(nodes_mapped_dict[node["id"]])
+ node["drugstoneType"] = "protein"
+ node["id"] = id_map[node["id"]]
# set label to node identifier if label is unset, otherwise
# return list of nodes updated nodes
return Response(nodes)
-@api_view(['POST'])
+@api_view(["POST"])
def tasks_view(request) -> Response:
- tokens = json.loads(request.data.get('tokens', '[]'))
- tasks = Task.objects.filter(token__in=tokens).order_by('-created_at').all()
+ tokens = json.loads(request.data.get("tokens", "[]"))
+ tasks = Task.objects.filter(token__in=tokens).order_by("-created_at").all()
tasks_info = []
for task in tasks:
if not task.done and not task.failed:
refresh_from_redis(task)
task.save()
- tasks_info.append({
- 'token': task.token,
- 'info': TaskStatusSerializer().to_representation(task),
- 'stats': task_stats(task),
- })
+ tasks_info.append(
+ {
+ "token": task.token,
+ "info": TaskStatusSerializer().to_representation(task),
+ "stats": task_stats(task),
+ }
+ )
return Response(tasks_info)
-@api_view(['POST'])
+@api_view(["POST"])
def create_network(request) -> Response:
- if 'network' not in request.data:
+ if "network" not in request.data:
return Response(None)
else:
- if 'nodes' not in request.data['network']:
- request.data['network']['nodes'] = []
- if 'edges' not in request.data['network']:
- request.data['network']['edges'] = []
- if 'config' not in request.data:
- request.data['config'] = {}
- if 'groups' not in request.data:
- request.data['groups'] = {}
+ if "nodes" not in request.data["network"]:
+ request.data["network"]["nodes"] = []
+ if "edges" not in request.data["network"]:
+ request.data["network"]["edges"] = []
+ if "config" not in request.data:
+ request.data["config"] = {}
+ if "groups" not in request.data:
+ request.data["groups"] = {}
id = uuid.uuid4().hex
while True:
try:
- Network.objects.create(id=id, nodes=request.data['network']['nodes'],
- edges=request.data['network']['edges'], config=request.data['config'],
- groups=request.data['groups'])
+ Network.objects.create(
+ id=id,
+ nodes=request.data["network"]["nodes"],
+ edges=request.data["network"]["edges"],
+ config=request.data["config"],
+ groups=request.data["groups"],
+ )
break
except IntegrityError:
id = uuid.uuid4().hex
@@ -274,75 +314,93 @@ def latest_datasets(ds):
return dataset_dict.values()
-@api_view(['GET'])
+@api_view(["GET"])
def get_datasets(request) -> Response:
datasets = {}
- 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()))
+ 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)
-@api_view(['GET'])
+@api_view(["GET"])
def load_network(request) -> Response:
- network = NetworkSerializer().to_representation(Network.objects.get(id=request.query_params.get('id')))
- result = {'network': {'nodes': json.loads(network['nodes'].replace("'", '"')),
- 'edges': json.loads(network['edges'].replace("'", '"'))},
- 'config': json.loads(
- network['config'].replace("'", '"').replace('True', 'true').replace('False', 'false')),
- 'groups': json.loads(
- network['groups'].replace("'", '"').replace('True', 'true').replace('False', 'false'))}
+ network = NetworkSerializer().to_representation(
+ Network.objects.get(id=request.query_params.get("id"))
+ )
+ result = {
+ "network": {
+ "nodes": json.loads(network["nodes"].replace("'", '"')),
+ "edges": json.loads(network["edges"].replace("'", '"')),
+ },
+ "config": json.loads(
+ network["config"]
+ .replace("'", '"')
+ .replace("True", "true")
+ .replace("False", "false")
+ ),
+ "groups": json.loads(
+ network["groups"]
+ .replace("'", '"')
+ .replace("True", "true")
+ .replace("False", "false")
+ ),
+ }
return Response(result)
@api_view()
def result_view(request) -> Response:
- node_name_attribute = 'drugstone_id'
+ node_name_attribute = "drugstone_id"
- view = request.query_params.get('view')
- fmt = request.query_params.get('fmt')
- token_str = request.query_params['token']
+ view = request.query_params.get("view")
+ fmt = request.query_params.get("fmt")
+ token_str = request.query_params["token"]
task = Task.objects.get(token=token_str)
result = task_result(task)
- node_attributes = result.get('node_attributes')
+ node_attributes = result.get("node_attributes")
if not node_attributes:
node_attributes = {}
- result['node_attributes'] = node_attributes
+ result["node_attributes"] = node_attributes
proteins = []
drugs = []
- network = result['network']
- node_types = node_attributes.get('node_types')
+ network = result["network"]
+ node_types = node_attributes.get("node_types")
if not node_types:
node_types = {}
- node_attributes['node_types'] = node_types
+ node_attributes["node_types"] = node_types
- is_seed = node_attributes.get('is_seed')
+ is_seed = node_attributes.get("is_seed")
if not is_seed:
is_seed = {}
- node_attributes['is_seed'] = is_seed
- scores = node_attributes.get('scores', {})
+ node_attributes["is_seed"] = is_seed
+ scores = node_attributes.get("scores", {})
node_details = {}
protein_id_map = defaultdict(set)
- node_attributes['details'] = node_details
+ node_attributes["details"] = node_details
parameters = json.loads(task.parameters)
- seeds = parameters['seeds']
- nodes = network['nodes']
+ seeds = parameters["seeds"]
+ nodes = network["nodes"]
parameters = task_parameters(task)
# attach input parameters to output
- result['parameters'] = parameters
+ result["parameters"] = parameters
identifier_nodes = set()
- identifier = parameters['config']['identifier']
+ identifier = parameters["config"]["identifier"]
# merge input network with result network
- for node in parameters['input_network']['nodes']:
+ for node in parameters["input_network"]["nodes"]:
# if node was already mapped, add user defined values to result of analysis
if identifier in node:
node_name = node[identifier][0]
@@ -356,30 +414,32 @@ def result_view(request) -> Response:
# append mapped input node to analysis result
nodes.append(node_name)
# manually add node to node types
- result['node_attributes']['node_types'][node_name] = 'protein'
+ result["node_attributes"]["node_types"][node_name] = "protein"
else:
# node is custom node from user, not mapped to drugstone but will be displayed with all custom attributes
- node_id = node['id']
+ node_id = node["id"]
identifier_nodes.add(node_id)
node_details[node_id] = node
is_seed[node_id] = False
# append custom node to analysis result later on
# manually add node to node types
- result['node_attributes']['node_types'][node_id] = 'custom'
+ result["node_attributes"]["node_types"][node_id] = "custom"
# extend the analysis network by the input netword nodes
# map edge endpoints to database proteins if possible and add edges to analysis network
protein_nodes = set()
# mapping all new protein and drug nodes by drugstoneIDs + adding scores
for node_id in nodes:
- if node_id[:2] == 'dr':
- node_data = DrugSerializer().to_representation(Drug.objects.get(id=int(node_id[2:])))
- node_data['drugstoneType'] = 'drug'
+ if node_id[:2] == "dr":
+ node_data = DrugSerializer().to_representation(
+ Drug.objects.get(id=int(node_id[2:]))
+ )
+ node_data["drugstoneType"] = "drug"
drugs.append(node_data)
if node_id in scores:
- node_data['score'] = scores.get(node_id, None)
- node_types[node_id] = 'drug'
+ node_data["score"] = scores.get(node_id, None)
+ node_types[node_id] = "drug"
node_details[node_id] = node_data
- elif node_id[:2] != 'di':
+ elif node_id[:2] != "di":
protein_nodes.add(node_id)
else:
continue
@@ -393,109 +453,143 @@ def result_view(request) -> Response:
if node_id in nodes_mapped_dict:
# node.update(nodes_mapped_dict[node['id']])
node_data = nodes_mapped_dict[node_id]
- node_data['drugstoneType'] = 'protein'
+ node_data["drugstoneType"] = "protein"
# proteins.append(node_data)
node_ident = node_data[identifier][0]
# node_data[identifier] = [node_ident]
protein_id_map[node_ident].add(node_id)
identifier_nodes.add(node_ident)
- is_seed[node_ident] = node_id in seeds or (is_seed[node_ident] if node_ident in is_seed else False)
- node_types[node_ident] = 'protein'
+ is_seed[node_ident] = node_id in seeds or (
+ is_seed[node_ident] if node_ident in is_seed else False
+ )
+ node_types[node_ident] = "protein"
score = scores.get(node_id, None)
if node_ident in node_details:
data = node_details[node_ident]
- data['score'] = [score] if score else None
+ data["score"] = [score] if score else None
else:
- node_data['score'] = score if score else None
- node_data['drugstoneType'] = 'protein'
- node_data['id'] = node_ident
- node_data['label'] = node_ident
+ node_data["score"] = score if score else None
+ node_data["drugstoneType"] = "protein"
+ node_data["id"] = node_ident
+ node_data["label"] = node_ident
node_details[node_ident] = node_data
for node_id, detail in node_details.items():
- if 'drugstoneType' in detail and detail['drugstoneType'] == 'protein':
- 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 []
+ if "drugstoneType" in detail and detail["drugstoneType"] == "protein":
+ 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']
+ edges = parameters["input_network"]["edges"]
edge_endpoint_ids = set()
# TODO check for custom edges when working again with ensemble gene ids
for edge in edges:
- edge_endpoint_ids.add(edge['from'])
- edge_endpoint_ids.add(edge['to'])
+ edge_endpoint_ids.add(edge["from"])
+ edge_endpoint_ids.add(edge["to"])
nodes_mapped, id_key = query_proteins_by_identifier(edge_endpoint_ids, identifier)
- if 'autofill_edges' in parameters['config'] and parameters['config']['autofill_edges']:
- prots = list(filter(lambda n: n['drugstone_type'] == 'protein',
- filter(lambda n: 'drugstone_type' in n and node_name_attribute in n,
- parameters['input_network']['nodes'])))
-
- proteins = {node_name[1:] for node in prots for node_name in node[node_name_attribute]}
- dataset = DEFAULTS['ppi'] if 'interaction_protein_protein' not in parameters['config'] else \
- parameters['config'][
- 'interaction_protein_protein']
+ if (
+ "autofill_edges" in parameters["config"]
+ and parameters["config"]["autofill_edges"]
+ ):
+ prots = list(
+ filter(
+ lambda n: n["drugstone_type"] == "protein",
+ filter(
+ lambda n: "drugstone_type" in n and node_name_attribute in n,
+ parameters["input_network"]["nodes"],
+ ),
+ )
+ )
+
+ proteins = {
+ node_name[1:] for node in prots for node_name in node[node_name_attribute]
+ }
+ dataset = (
+ DEFAULTS["ppi"]
+ if "interaction_protein_protein" not in parameters["config"]
+ else parameters["config"]["interaction_protein_protein"]
+ )
dataset_object = models.PPIDataset.objects.filter(name__iexact=dataset).last()
interaction_objects = models.ProteinProteinInteraction.objects.filter(
- Q(ppi_dataset=dataset_object) & Q(from_protein__in=proteins) & Q(to_protein__in=proteins))
- auto_edges = list(map(lambda n: {"from": f'p{n.from_protein_id}', "to": f'p{n.to_protein_id}'},
- interaction_objects))
+ Q(ppi_dataset=dataset_object)
+ & Q(from_protein__in=proteins)
+ & Q(to_protein__in=proteins)
+ )
+ auto_edges = list(
+ map(
+ lambda n: {
+ "from": f"p{n.from_protein_id}",
+ "to": f"p{n.to_protein_id}",
+ },
+ interaction_objects,
+ )
+ )
edges.extend(auto_edges)
- result['network']['edges'].extend(edges)
+ result["network"]["edges"].extend(edges)
uniq_edges = dict()
- for edge in result['network']['edges']:
- hash = edge['from'] + edge['to']
+ for edge in result["network"]["edges"]:
+ hash = edge["from"] + edge["to"]
uniq_edges[hash] = edge
- result['network']['edges'] = list(uniq_edges.values())
+ result["network"]["edges"] = list(uniq_edges.values())
- if 'scores' in result['node_attributes']:
- del result['node_attributes']['scores']
+ if "scores" in result["node_attributes"]:
+ del result["node_attributes"]["scores"]
if not view:
return Response(result)
else:
- if view == 'proteins':
+ if view == "proteins":
proteins = list(
- filter(lambda n: 'drugstone_type' in n and n['drugstone_type'] == 'protein', node_details.values()))
- if fmt == 'csv':
+ filter(
+ lambda n: "drugstone_type" in n
+ and n["drugstone_type"] == "protein",
+ node_details.values(),
+ )
+ )
+ if fmt == "csv":
items = []
for i in proteins:
new_i = {
- 'id': i['id'],
- '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 [],
- 'entrez': i['entrez'] if 'entrez' in i else [],
- 'seed': is_seed[i['id']],
+ "id": i["id"],
+ "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 [],
+ "entrez": i["entrez"] if "entrez" in i else [],
+ "seed": is_seed[i["id"]],
}
- if 'score' in i:
- new_i['score'] = i['score']
+ if "score" in i:
+ new_i["score"] = i["score"]
items.append(new_i)
else:
items = proteins
- elif view == 'drugs':
- if fmt == 'csv':
+ elif view == "drugs":
+ if fmt == "csv":
items = [i for i in drugs]
else:
items = drugs
else:
return Response({})
- if not fmt or fmt == 'json':
+ if not fmt or fmt == "json":
return Response(items)
- elif fmt == 'csv':
+ elif fmt == "csv":
if len(items) != 0:
keys = items[0].keys()
else:
keys = []
- response = HttpResponse(content_type='text/csv')
- response['Content-Disposition'] = f'attachment; filename="{task.token}_{view}.csv"'
+ response = HttpResponse(content_type="text/csv")
+ response[
+ "Content-Disposition"
+ ] = f'attachment; filename="{task.token}_{view}.csv"'
dict_writer = csv.DictWriter(response, keys)
dict_writer.writeheader()
dict_writer.writerows(items)
@@ -504,20 +598,32 @@ def result_view(request) -> Response:
return Response({})
-@api_view(['POST'])
+@api_view(["POST"])
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', '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')
+ 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")
G = nx.Graph()
node_map = dict()
for node in nodes:
@@ -534,15 +640,15 @@ def graph_export(request) -> Response:
node[key] = json.dumps(node[key])
elif node[key] is None:
# networkx has difficulties with None when writing graphml
- node[key] = ''
+ node[key] = ""
try:
- node_name = node['label']
- if 'drugstone_id' in node:
- node_map[node['drugstone_id']] = node['label']
- elif 'id' in node:
- node_map[node['id']] = node['label']
+ node_name = node["label"]
+ if "drugstone_id" in node:
+ node_map[node["drugstone_id"]] = node["label"]
+ elif "id" in node:
+ node_map[node["id"]] = node["label"]
except KeyError:
- node_name = node['drugstone_id']
+ node_name = node["drugstone_id"]
G.add_node(node_name, **node)
for e in edges:
@@ -558,20 +664,20 @@ def graph_export(request) -> Response:
if isinstance(e[key], list) or isinstance(e[key], dict):
e[key] = json.dumps(e[key])
elif e[key] is None:
- e[key] = ''
- u_of_edge = e.pop('from')
+ e[key] = ""
+ u_of_edge = e.pop("from")
u_of_edge = u_of_edge if u_of_edge not in node_map else node_map[u_of_edge]
- v_of_edge = e.pop('to')
+ v_of_edge = e.pop("to")
v_of_edge = node_map[v_of_edge] if v_of_edge in node_map else v_of_edge
G.add_edge(u_of_edge, v_of_edge, **e)
- if fmt == 'graphml':
+ if fmt == "graphml":
data = nx.generate_graphml(G)
- response = HttpResponse(data, content_type='application/xml')
- elif fmt == 'json':
+ response = HttpResponse(data, content_type="application/xml")
+ elif fmt == "json":
data = nx.readwrite.json_graph.node_link_data(G)
- del data['graph']
- del data['multigraph']
+ del data["graph"]
+ del data["multigraph"]
# for node in data['nodes']:
# for prop in remove_node_properties:
@@ -583,56 +689,78 @@ def graph_export(request) -> Response:
# del edge[prop]
data["edges"] = data.pop("links")
data = json.dumps(data)
- data = data.replace('"{', '{').replace('}"', '}').replace('"[', '[').replace(']"', ']').replace('\\"', '"')
- response = HttpResponse(data, content_type='application/json')
- elif fmt == 'csv':
- data = pd.DataFrame(nx.to_numpy_array(G), columns=G.nodes(), index=G.nodes(), dtype=int)
- response = HttpResponse(data.to_csv(), content_type='text/csv')
-
- response['content-disposition'] = f'attachment; filename="{int(time.time())}_network.{fmt}"'
+ data = (
+ data.replace('"{', "{")
+ .replace('}"', "}")
+ .replace('"[', "[")
+ .replace(']"', "]")
+ .replace('\\"', '"')
+ )
+ response = HttpResponse(data, content_type="application/json")
+ elif fmt == "csv":
+ data = pd.DataFrame(
+ nx.to_numpy_array(G), columns=G.nodes(), index=G.nodes(), dtype=int
+ )
+ response = HttpResponse(data.to_csv(), content_type="text/csv")
+
+ response[
+ "content-disposition"
+ ] = f'attachment; filename="{int(time.time())}_network.{fmt}"'
return response
-@api_view(['POST'])
+@api_view(["POST"])
def adjacent_disorders(request) -> Response:
"""Find all adjacent disorders to a list of proteins.
- Args:
- request (django.request): Request object with keys "proteins" and "pdi_dataset"
+ Args:
+ request (django.request): Request object with keys "proteins" and "pdi_dataset"
- Returns:
- Response: With lists "pdis" (protein-drug-intersions) and "disorders"
- """
+ Returns:
+ Response: With lists "pdis" (protein-drug-intersions) and "disorders"
+ """
data = request.data
- if 'proteins' in data:
- drugstone_ids = data.get('proteins', [])
- pdis_dataset = get_pdis_ds(data.get('dataset', DEFAULTS['pdis']), data.get('licenced', False))
+ if "proteins" in data:
+ drugstone_ids = data.get("proteins", [])
+ pdis_dataset = get_pdis_ds(
+ data.get("dataset", DEFAULTS["pdis"]), data.get("licenced", False)
+ )
# find adjacent drugs by looking at drug-protein edges
- pdis_objects = ProteinDisorderAssociation.objects.filter(protein__id__in=drugstone_ids,
- pdis_dataset_id=pdis_dataset.id)
+ pdis_objects = ProteinDisorderAssociation.objects.filter(
+ protein__id__in=drugstone_ids, pdis_dataset_id=pdis_dataset.id
+ )
disorders = {e.disorder for e in pdis_objects}
# serialize
- edges = ProteinDisorderAssociationSerializer(many=True).to_representation(pdis_objects)
+ edges = ProteinDisorderAssociationSerializer(many=True).to_representation(
+ pdis_objects
+ )
disorders = DisorderSerializer(many=True).to_representation(disorders)
- elif 'drugs' in data:
- drugstone_ids = data.get('drugs', [])
- drdi_dataset = get_drdis_ds(data.get('dataset', DEFAULTS['drdi']), data.get('licenced', False))
+ elif "drugs" in data:
+ drugstone_ids = data.get("drugs", [])
+ drdi_dataset = get_drdis_ds(
+ data.get("dataset", DEFAULTS["drdi"]), data.get("licenced", False)
+ )
# find adjacent drugs by looking at drug-protein edges
- drdi_objects = DrugDisorderIndication.objects.filter(drug__id__in=drugstone_ids,
- drdi_dataset_id=drdi_dataset.id)
+ drdi_objects = DrugDisorderIndication.objects.filter(
+ drug__id__in=drugstone_ids, drdi_dataset_id=drdi_dataset.id
+ )
disorders = {e.disorder for e in drdi_objects}
# serialize
- edges = DrugDisorderIndicationSerializer(many=True).to_representation(drdi_objects)
+ edges = DrugDisorderIndicationSerializer(many=True).to_representation(
+ drdi_objects
+ )
disorders = DisorderSerializer(many=True).to_representation(disorders)
for d in disorders:
- d['drugstone_type'] = 'disorder'
- return Response({
- 'edges': edges,
- 'disorders': disorders,
- })
+ d["drugstone_type"] = "disorder"
+ return Response(
+ {
+ "edges": edges,
+ "disorders": disorders,
+ }
+ )
-@api_view(['POST'])
+@api_view(["POST"])
def adjacent_drugs(request) -> Response:
"""Find all adjacent drugs to a list of proteins.
@@ -643,24 +771,30 @@ def adjacent_drugs(request) -> Response:
Response: With lists "pdis" (protein-drug-intersions) and "drugs"
"""
data = request.data
- drugstone_ids = data.get('proteins', [])
- pdi_dataset = get_pdi_ds(data.get('pdi_dataset', DEFAULTS['pdi']), data.get('licenced', False))
+ drugstone_ids = data.get("proteins", [])
+ pdi_dataset = get_pdi_ds(
+ data.get("pdi_dataset", DEFAULTS["pdi"]), data.get("licenced", False)
+ )
# find adjacent drugs by looking at drug-protein edges
- pdi_objects = ProteinDrugInteraction.objects.filter(protein__id__in=drugstone_ids, pdi_dataset_id=pdi_dataset.id)
+ pdi_objects = ProteinDrugInteraction.objects.filter(
+ protein__id__in=drugstone_ids, pdi_dataset_id=pdi_dataset.id
+ )
drugs = {e.drug for e in pdi_objects}
# serialize
pdis = ProteinDrugInteractionSerializer(many=True).to_representation(pdi_objects)
drugs = DrugSerializer(many=True).to_representation(drugs)
for drug in drugs:
- drug['drugstone_type'] = 'drug'
+ drug["drugstone_type"] = "drug"
- return Response({
- 'pdis': pdis,
- 'drugs': drugs,
- })
+ return Response(
+ {
+ "pdis": pdis,
+ "drugs": drugs,
+ }
+ )
-@api_view(['POST'])
+@api_view(["POST"])
def query_proteins(request) -> Response:
proteins = request.data
@@ -682,13 +816,15 @@ def query_proteins(request) -> Response:
not_found.append(p)
- return Response({
- 'details': details,
- 'notFound': not_found,
- })
+ return Response(
+ {
+ "details": details,
+ "notFound": not_found,
+ }
+ )
-@api_view(['POST'])
+@api_view(["POST"])
def send_bugreport(request) -> Response:
data = request.data
title = data.get("title")
@@ -703,54 +839,74 @@ def send_bugreport(request) -> Response:
return Response({"status": 200})
-@api_view(['POST'])
+@api_view(["POST"])
def save_selection(request) -> Response:
chars = string.ascii_lowercase + string.ascii_uppercase + string.digits
- token_str = ''.join(random.choice(chars) for _ in range(32))
+ token_str = "".join(random.choice(chars) for _ in range(32))
config = request.data.get("config")
network = request.data.get("network")
- Network.objects.create(id=token_str, config=json.dumps(config), nodes=json.dumps(network["nodes"]), edges=json.dumps(network["edges"]))
- return Response({
- 'token': token_str,
- })
+ Network.objects.create(
+ id=token_str,
+ config=json.dumps(config),
+ nodes=json.dumps(network["nodes"]),
+ edges=json.dumps(network["edges"]),
+ )
+ return Response(
+ {
+ "token": token_str,
+ }
+ )
+
-@api_view(['GET'])
+@api_view(["GET"])
def get_view(request) -> Response:
- token = request.query_params.get('token')
+ token = request.query_params.get("token")
network = Network.objects.get(id=token)
- return Response({
- 'config': json.loads(network.config),
- 'created_at': network.created_at,
- 'network': {
- 'nodes': json.loads(network.nodes),
- 'edges': json.loads(network.edges),
+ return Response(
+ {
+ "config": json.loads(network.config),
+ "created_at": network.created_at,
+ "network": {
+ "nodes": json.loads(network.nodes),
+ "edges": json.loads(network.edges),
+ },
}
- })
+ )
-@api_view(['POST'])
+@api_view(["POST"])
def get_view_infos(request) -> Response:
- tokens = request.data.get('tokens')
- networks = Network.objects.filter(id__in = tokens)
- return Response([{
- 'token': n.id,
- 'created_at': n.created_at,
- } for n in networks])
-
-
-@api_view(['GET'])
+ tokens = request.data.get("tokens")
+ networks = Network.objects.filter(id__in=tokens)
+ return Response(
+ [
+ {
+ "token": n.id,
+ "created_at": n.created_at,
+ }
+ for n in networks
+ ]
+ )
+
+
+@api_view(["GET"])
def get_max_tissue_expression(request) -> Response:
- tissue = Tissue.objects.get(id=request.query_params.get('tissue'))
- return Response({'max': ExpressionLevel.objects.filter(tissue=tissue).aggregate(Max('expression_level'))[
- 'expression_level__max']})
+ tissue = Tissue.objects.get(id=request.query_params.get("tissue"))
+ return Response(
+ {
+ "max": ExpressionLevel.objects.filter(tissue=tissue).aggregate(
+ Max("expression_level")
+ )["expression_level__max"]
+ }
+ )
-@api_view(['POST'])
+@api_view(["POST"])
def query_tissue_proteins(request) -> Response:
- threshold = request.data['threshold']
- tissue_id = request.data['tissue_id']
+ threshold = request.data["threshold"]
+ tissue_id = request.data["tissue_id"]
tissue = Tissue.objects.get(id=tissue_id)
proteins = []
@@ -761,7 +917,6 @@ def query_tissue_proteins(request) -> Response:
class TissueView(APIView):
-
def get(self, request) -> Response:
tissues = Tissue.objects.all()
return Response(TissueSerializer(many=True).to_representation(tissues))
@@ -773,15 +928,15 @@ class TissueExpressionView(APIView):
"""
def get(self, request) -> Response:
- tissue = Tissue.objects.get(id=request.query_params.get('tissue'))
- proteins = request.query_params.get('proteins')
- token = request.query_params.get('token')
+ tissue = Tissue.objects.get(id=request.query_params.get("tissue"))
+ proteins = request.query_params.get("proteins")
+ token = request.query_params.get("token")
return self.get_tissue_expression(tissue, proteins, token)
def post(self, request) -> Response:
- tissue = Tissue.objects.get(id=request.data.get('tissue'))
- proteins = request.data.get('proteins')
- token = request.data.get('token')
+ tissue = Tissue.objects.get(id=request.data.get("tissue"))
+ proteins = request.data.get("proteins")
+ token = request.data.get("token")
return self.get_tissue_expression(tissue, proteins, token)
def get_tissue_expression(self, tissue, proteins, token):
@@ -792,20 +947,20 @@ class TissueExpressionView(APIView):
proteins = []
task = Task.objects.get(token=token)
result = task_result(task)
- network = result['network']
- node_attributes = result.get('node_attributes')
+ network = result["network"]
+ node_attributes = result.get("node_attributes")
if not node_attributes:
node_attributes = {}
- node_types = node_attributes.get('node_types')
+ node_types = node_attributes.get("node_types")
if not node_types:
node_types = {}
parameters = json.loads(task.parameters)
- seeds = parameters['seeds']
- nodes = network['nodes']
+ seeds = parameters["seeds"]
+ nodes = network["nodes"]
for node in nodes + seeds:
node_type = node_types.get(node)
details = None
- if node_type == 'protein':
+ if node_type == "protein":
if details:
proteins.append(details)
else:
@@ -820,10 +975,15 @@ class TissueExpressionView(APIView):
for protein in proteins:
try:
- expression_level = ExpressionLevel.objects.get(protein=protein, tissue=tissue)
+ expression_level = ExpressionLevel.objects.get(
+ protein=protein, tissue=tissue
+ )
pt_expressions[
- ProteinSerializer().to_representation(protein)['drugstone_id']] = expression_level.expression_level
+ ProteinSerializer().to_representation(protein)["drugstone_id"]
+ ] = expression_level.expression_level
except ExpressionLevel.DoesNotExist:
- pt_expressions[ProteinSerializer().to_representation(protein)['drugstone_id']] = None
+ pt_expressions[
+ ProteinSerializer().to_representation(protein)["drugstone_id"]
+ ] = None
return Response(pt_expressions)
diff --git a/setup.cfg b/setup.cfg
index 9f22bc39c62d7081d1d47c879611057c787a7ac8..901b49587207463596e188c31f506969e6be29f8 100755
--- a/setup.cfg
+++ b/setup.cfg
@@ -1,8 +1,10 @@
[pycodestyle]
exclude = */migrations/*,.env,venv,test_*,manage.py,tasks/*,*/commands/*
max-line-length = 120
+ignore = E203,W503
[flake8]
exclude = */migrations/*,.env,venv,test_*,manage.py,tasks/*,*/commands/*,*/__init__.py,*/settings.py
max-line-length = 120
+ignore = E203,W503,F405,F403
inline-quotes = '