aboutsummaryrefslogtreecommitdiff
path: root/wqflask/base
diff options
context:
space:
mode:
Diffstat (limited to 'wqflask/base')
-rw-r--r--wqflask/base/data_set.py113
-rw-r--r--wqflask/base/trait.py19
-rw-r--r--wqflask/base/webqtlConfig.py1
3 files changed, 100 insertions, 33 deletions
diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py
index ebf3f021..1457ba8d 100644
--- a/wqflask/base/data_set.py
+++ b/wqflask/base/data_set.py
@@ -56,7 +56,7 @@ from pprint import pformat as pf
from db.gn_server import menu_main
from db.call import fetchall,fetchone,fetch1
-from utility.tools import USE_GN_SERVER, USE_REDIS, flat_files, flat_file_exists
+from utility.tools import USE_GN_SERVER, USE_REDIS, flat_files, flat_file_exists, GN2_BASE_URL
from utility.logger import getLogger
logger = getLogger(__name__ )
@@ -64,10 +64,9 @@ logger = getLogger(__name__ )
# Each subclass will add to this
DS_NAME_MAP = {}
-def create_dataset(dataset_name, rebuild=True, dataset_type = None, get_samplelist = True, group_name = None):
+def create_dataset(dataset_name, dataset_type = None, get_samplelist = True, group_name = None):
if not dataset_type:
dataset_type = Dataset_Getter(dataset_name)
- logger.debug("dataset_type", dataset_type)
dataset_ob = DS_NAME_MAP[dataset_type]
dataset_class = globals()[dataset_ob]
@@ -78,7 +77,7 @@ def create_dataset(dataset_name, rebuild=True, dataset_type = None, get_sampleli
class Dataset_Types(object):
- def __init__(self, rebuild=False):
+ def __init__(self):
"""Create a dictionary of samples where the value is set to Geno,
Publish or ProbeSet. E.g.
@@ -94,33 +93,95 @@ Publish or ProbeSet. E.g.
"""
self.datasets = {}
- if rebuild: #ZS: May make this the only option
- data = json.loads(requests.get("http://gn2.genenetwork.org/api/v_pre1/gen_dropdown").content)
- logger.debug("THE DATA:", data)
- #data = gen_menu.gen_dropdown_json()
- else:
- file_name = "wqflask/static/new/javascript/dataset_menu_structure.json"
- with open(file_name, 'r') as fh:
- data = json.load(fh)
-
- for species in data['datasets']:
- for group in data['datasets'][species]:
- for dataset_type in data['datasets'][species][group]:
- for dataset in data['datasets'][species][group][dataset_type]:
- short_dataset_name = dataset[1]
- if dataset_type == "Phenotypes":
- new_type = "Publish"
- elif dataset_type == "Genotypes":
- new_type = "Geno"
- else:
- new_type = "ProbeSet"
- self.datasets[short_dataset_name] = new_type
+
+ data = Redis.get("dataset_structure")
+ if data:
+ self.datasets = json.loads(data)
+ else: #ZS: I don't think this should ever run unless Redis is emptied
+ try:
+ data = json.loads(requests.get(GN2_BASE_URL + "/api/v_pre1/gen_dropdown", timeout = 5).content)
+ for species in data['datasets']:
+ for group in data['datasets'][species]:
+ for dataset_type in data['datasets'][species][group]:
+ for dataset in data['datasets'][species][group][dataset_type]:
+ short_dataset_name = dataset[1]
+ if dataset_type == "Phenotypes":
+ new_type = "Publish"
+ elif dataset_type == "Genotypes":
+ new_type = "Geno"
+ else:
+ new_type = "ProbeSet"
+ self.datasets[short_dataset_name] = new_type
+ except:
+ pass
+
+ Redis.set("dataset_structure", json.dumps(self.datasets))
# Set LOG_LEVEL_DEBUG=5 to see the following:
logger.debugf(5, "datasets",self.datasets)
def __call__(self, name):
- return self.datasets[name]
+ if name not in self.datasets:
+ mrna_expr_query = """
+ SELECT
+ ProbeSetFreeze.Id
+ FROM
+ ProbeSetFreeze
+ WHERE
+ ProbeSetFreeze.Name = "{0}"
+ """.format(name)
+
+ results = g.db.execute(mrna_expr_query).fetchall()
+ if len(results):
+ self.datasets[name] = "ProbeSet"
+ Redis.set("dataset_structure", json.dumps(self.datasets))
+ return self.datasets[name]
+
+ group_name = name.replace("Publish", "")
+
+ pheno_query = """SELECT InfoFiles.GN_AccesionId
+ FROM InfoFiles, PublishFreeze, InbredSet
+ WHERE InbredSet.Name = '{0}' AND
+ PublishFreeze.InbredSetId = InbredSet.Id AND
+ InfoFiles.InfoPageName = PublishFreeze.Name""".format(group_name)
+
+ results = g.db.execute(pheno_query).fetchall()
+ if len(results):
+ self.datasets[name] = "Publish"
+ Redis.set("dataset_structure", json.dumps(self.datasets))
+ return self.datasets[name]
+
+ #ZS: For when there isn't an InfoFiles ID; not sure if this and the preceding query are both necessary
+ other_pheno_query = """SELECT PublishFreeze.Name
+ FROM PublishFreeze, InbredSet
+ WHERE InbredSet.Name = '{}' AND
+ PublishFreeze.InbredSetId = InbredSet.Id""".format(group_name)
+
+ results = g.db.execute(other_pheno_query).fetchall()
+ if len(results):
+ self.datasets[name] = "Publish"
+ Redis.set("dataset_structure", json.dumps(self.datasets))
+ return self.datasets[name]
+
+ geno_query = """
+ SELECT
+ GenoFreeze.Id
+ FROM
+ GenoFreeze
+ WHERE
+ GenoFreeze.Name = "{0}"
+ """.format(name)
+
+ results = g.db.execute(geno_query).fetchall()
+ if len(results):
+ self.datasets[name] = "Geno"
+ Redis.set("dataset_structure", json.dumps(self.datasets))
+ return self.datasets[name]
+
+ #ZS: It shouldn't ever reach this
+ return None
+ else:
+ return self.datasets[name]
# Do the intensive work at startup one time only
Dataset_Getter = Dataset_Types()
diff --git a/wqflask/base/trait.py b/wqflask/base/trait.py
index 5525472e..1b7cb23c 100644
--- a/wqflask/base/trait.py
+++ b/wqflask/base/trait.py
@@ -5,15 +5,15 @@ import resource
import codecs
import requests
-import redis
-Redis = redis.StrictRedis()
-
from base import webqtlConfig
from base.webqtlCaseData import webqtlCaseData
from base.data_set import create_dataset
from db import webqtlDatabaseFunction
from utility import webqtlUtil
from utility import hmac
+from utility.tools import GN2_BASE_URL
+from utility.redis_tools import get_redis_conn
+Redis = get_redis_conn()
from wqflask import app
@@ -135,9 +135,9 @@ class GeneralTrait(object):
alias = 'Not available'
if self.symbol:
- human_response = requests.get("http://gn2.genenetwork.org/gn3/gene/aliases/" + self.symbol.upper())
- mouse_response = requests.get("http://gn2.genenetwork.org/gn3/gene/aliases/" + self.symbol.capitalize())
- other_response = requests.get("http://gn2.genenetwork.org/gn3/gene/aliases/" + self.symbol.lower())
+ human_response = requests.get(GN2_BASE_URL + "gn3/gene/aliases/" + self.symbol.upper())
+ mouse_response = requests.get(GN2_BASE_URL + "gn3/gene/aliases/" + self.symbol.capitalize())
+ other_response = requests.get(GN2_BASE_URL + "gn3/gene/aliases/" + self.symbol.lower())
if human_response and mouse_response and other_response:
alias_list = json.loads(human_response.content) + json.loads(mouse_response.content) + json.loads(other_response.content)
@@ -348,8 +348,13 @@ def jsonable_table_row(trait, dataset_name, index):
def retrieve_trait_info(trait, dataset, get_qtl_info=False):
assert dataset, "Dataset doesn't exist"
-
+
if dataset.type == 'Publish':
+ resource_id = hmac.data_hmac("{}:{}".format(dataset.id, trait.name))
+
+ the_url = "http://localhost:8080/run_action/?resource={}&user={}&branch=data&action=view".format(resource_id, g.user_session.user_id)
+ trait_data = json.loads(requests.get("http://localhost:8080/run_action/?resource={}&user={}&branch=data&action=view".format(resource_id, g.user_session.user_id)))
+
query = """
SELECT
PublishXRef.Id, InbredSet.InbredSetCode, Publication.PubMed_ID,
diff --git a/wqflask/base/webqtlConfig.py b/wqflask/base/webqtlConfig.py
index 018d5d54..55407123 100644
--- a/wqflask/base/webqtlConfig.py
+++ b/wqflask/base/webqtlConfig.py
@@ -58,6 +58,7 @@ PROTEIN_ATLAS_URL = "http://www.proteinatlas.org/search/%s"
OPEN_TARGETS_URL = "https://genetics.opentargets.org/gene/%s"
UNIPROT_URL = "https://www.uniprot.org/uniprot/%s"
RGD_URL = "https://rgd.mcw.edu/rgdweb/elasticResults.html?term=%s&category=Gene&species=%s"
+PHENOGEN_URL = "https://phenogen.org/gene.jsp?speciesCB=Rn&auto=Y&geneTxt=%s&genomeVer=rn6&section=geneEQTL"
# Temporary storage (note that this TMPDIR can be set as an
# environment variable - use utility.tools.TEMPDIR when you
generated by cgit v1.2.3 (git 2.44.0) at 2024-11-23 09:15:06 +0000