def main():
try:
app = QApplication(sys.argv)
window = MainWindow()
sys.exit(app.exec_())
except Exception as e:
logger.critical(f"{e}")
logger.critical(e, exc_info=True)
def connection(self):
if isinstance(self.db, str):
self._connectSQLite3(self.db)
elif isinstance(self.db, Dict):
self._connectMySQL()
else:
logger.critical(f"unknown databse instance passed: {type(self.db)}")
def saveWorkbook(self):
logger.critical("saving workbook")
# remove empty default sheet
try:
self.book.remove_sheet(self.book.get_sheet_by_name("Sheet"))
except Exception as e:
logger.warn(f'{e}')
self.book.save(self.fileName)
def tblastn(file, blast):
"""
parse a xml file result of a tblastn
"""
count = 0 #counter of result in blast xml
#verification if file is a xml
f = open(file, 'r')
header = f.readline()
if '<?xml version="1.0"?>' not in header:
log.critical("Make sure of your file is an xml")
return False
f.close()
#initialisation for parsing file
tree = ET.parse(file)
root = tree.getroot()
for iteration in root.findall('./BlastOutput_iterations/Iteration'):
#a iteration is a query sequence
numberQuery = int(iteration[0].text)
name = iteration[2].text
lenght = iteration[3].text
blast[numberQuery] = Query(numberQuery, name, lenght)
for hit in iteration[4]:
#a hit is a resultat of blast, a hit in xml file
id = hit[1].text
queryDef = hit[2].text
log.debug(queryDef)
for hsp in hit[5]:
#a hsp is result of blast hit, like sequence or score… ; is hit_hsps°in xml
eValue = float(hsp.find('Hsp_evalue').text)
gaps = int(hsp.find('Hsp_gaps').text)
identity = int(hsp.find('Hsp_identity').text)
positive = int(hsp.find('Hsp_positive').text)
qSeq = hsp.find('Hsp_qseq').text
mSeq = hsp.find('Hsp_midline').text
hSeq = hsp.find('Hsp_hseq').text
hSeqLen = int(hsp.find('Hsp_align-len').text)
scores = {
'eValue': eValue,
'gaps': gaps,
'identity': identity,
'positive': positive
}
blast[numberQuery][id] = Hit(id, queryDef, scores, qSeq, hSeq,
mSeq, hSeqLen)
count += 1
log.info(str(len(blast)) + ' sequences was submited')
log.info(str(count) + ' sequences in total')
def seqUniprot(self):
"""
get sequence from Uniprot database
"""
if self.accession == "":
log.info('no sequence because no accession code for ' + self.id)
return ""
queryURL = "https://www.ebi.ac.uk/proteins/api/proteins?offset=0&size=-1&accession=" + self.accession
r = requests.get(queryURL, headers={"Accept": "text/x-fasta"})
if not r.ok:
try:
r.raise_for_status()
except requests.exceptions.HTTPError as e:
log.critical(str(e) + " with id " + self.id)
log.warning("error to download the sequence from uniprot")
self.sequence = ""
else:
self.sequence = "".join(r.text.split("\n")[1:])
def getXPaths(self, url, filename):
if not self.subSystem._setupScrap():
logger.critical(f"driver setup failed")
self.subSystem.driver.get(url)
#self.subSystem.driver.mana manage().timeouts().implicitlyWait(10)
try:
WebDriverWait(self.subSystem.driver, 10).until(
EC.presence_of_all_elements_located((By.CSS_SELECTOR, '*')))
except:
print("webwait failed")
#time.sleep(5)
'''EC.element_to_be_clickable((By.CLASS_NAME, 'playButton'))
self.subSystem.driver.find_element(By.CLASS_NAME,"ule-onboarding-continue-button").click()
self.subSystem.driver.find_element(By.CLASS_NAME,"playButton").click()'''
elements = self.subSystem.driver.find_elements(By.TAG_NAME, 'html')
tags = []
self.subSystem.driver.implicitly_wait(0.00001)
self.subSystem.paths = []
#self.subSystem.index = 0
self.subSystem.paths.append('/html')
self.trigger = True
for x in elements:
#print(x.get_attribute("innerHTML"))
subElems = x.find_elements_by_xpath(".//*")
self.elemSize = len(subElems)
print(f'Final Total: {self.xPath(subElems,"/html", 1)}')
allpaths = ""
for x in self.subSystem.paths:
#print(x)
#x = x.replace('[1]', '')
#print(x)
allpaths += f"\n{x}"
file = open(filename + ".txt", 'w')
file.write(allpaths)
file.close()
return self.subSystem.paths
def accEnsembl(self):
"""
Get accession from Ensemble ID to Uniprot
"""
url = 'https://www.uniprot.org/uploadlists/'
params = {'from': 'ENSEMBL_ID', 'to': 'ACC', 'format': 'tab', 'query': self.id}
data = urllib.parse.urlencode(params)
data = data.encode('utf-8')
req = urllib.request.Request(url, data)
essai = 1
#request API Uniprot
while True:
try:
response = urllib.request.urlopen(req).read()
break
except urllib.error.HTTPError as e:
if e.code == 503 and essai < 5:
log.info('Error 503, renew in 10 secondes')
time.sleep(5)
essai += 1
pass
elif e.code == 400 and essai < 5:
log.critical('Error 400 with ' + url + str(urllib.parse.urlencode(params)))
time.sleep(5)
essai += 1
elif essai > 5:
log.warning('Error ' + str(e.code))
break
else:
log.debug(e.code)
essai += 1
accList = re.findall('[0-9A-Z]+',response.decode('utf-8'))
#Verification of good request
if len(accList[-1]) >= 5:
self.accession = accList[-1]
elif len(accList) == 2:
#maybe no have accession found
self.accession = ""
log.warning("no accession uniprot found with id " + self.id)
else:
log.critical("unknow error with id " + self.id)
from flask import Flask
from src.logger import logger
from src.connectors.redis_helper import RedisHelper
from src.thread_pool import ThreadPoolExecutorStackTraced
app = Flask(__name__)
CACHE = RedisHelper().create_client()
# ANA_CACHE = RedisHelper().create_ana_client()
DB_CONNECTION = os.environ.get("DB_CONNECTION") or "mongodb://localhost:27027/anachatdb"
MONGO_CLIENT = MongoClient(DB_CONNECTION)
MessageHandlerPool = ThreadPoolExecutorStackTraced(max_workers=20)
EventLogPool = ThreadPoolExecutorStackTraced(max_workers=2)
try:
MONGO_CLIENT.server_info()
DB = MONGO_CLIENT["anachatdb"]
logger.info("Connected to anachatdb")
except pymongo.errors.ServerSelectionTimeoutError as err:
logger.error(f"Error connecting to mongodb {err}")
raise
except:
logger.critical("Server could not start.\n Unexpected error occured")
raise