def fetch_and_assign_taxids(seq, table):
non_decimal = re.compile(r"[^\d.]+")
results = uniprot.fetch_uniprot_metadata(seq)
time.sleep(1)
connection = mdb.connect(host="localhost", db="FamilyCpolymerases", user="******")
cursor = connection.cursor()
for k, v in results.iteritems():
TaxID = non_decimal.sub("", results[k]["TaxID"])
ID = results[k]["id"]
k = repr(k)
print "IDs:{} {} {}".format(k, TaxID, ID)
# TaxID = non_decimal.sub('', results[seq[0]]['TaxID'])
# ID = results[seq[0]]['id']
# sql='select * from `{}` where `Accession_Number` like {}'
# print sql.format(table,repr(k))
# cursor.execute(sql.format(table,repr(k)))
# rows=cursor.fetchall()
# print rows
sql = "update {} set {}='{}' where Accession_Number={}"
print sql.format(table, "`OrganismID`", TaxID, k)
cursor.execute(sql.format(table, "`OrganismID`", TaxID, k))
print sql.format(table, "`Entry_Name`", ID, k)
cursor.execute(sql.format(table, "`Entry_Name`", ID, k))
connection.commit()
time.sleep(1)
connection.close()
def fetch_and_assign_taxids(seq,table):
non_decimal = re.compile(r'[^\d.]+')
results=uniprot.fetch_uniprot_metadata(seq)
time.sleep(1)
connection = mdb.connect(host='localhost',db='FamilyCpolymerases',user='******')
cursor=connection.cursor()
for k,v in results.iteritems():
TaxID = non_decimal.sub('', results[k]['TaxID'])
ID = results[k]['id']
k=repr(k)
print 'IDs:{} {} {}'.format(k,TaxID,ID)
# TaxID = non_decimal.sub('', results[seq[0]]['TaxID'])
# ID = results[seq[0]]['id']
# sql='select * from `{}` where `Accession_Number` like {}'
# print sql.format(table,repr(k))
# cursor.execute(sql.format(table,repr(k)))
# rows=cursor.fetchall()
# print rows
sql="update {} set {}='{}' where Accession_Number={}"
print sql.format(table,'`OrganismID`',TaxID,k)
cursor.execute(sql.format(table,'`OrganismID`',TaxID,k))
print sql.format(table,'`Entry_Name`',ID,k)
cursor.execute(sql.format(table,'`Entry_Name`',ID,k))
connection.commit()
time.sleep(1)
connection.close()
def fetch_and_assign_taxids(seq,table):
non_decimal = re.compile(r'[^\d.]+')
results=uniprot.fetch_uniprot_metadata(seq)
time.sleep(1)
connection = mdb.connect(host='localhost',db='FamilyCpolymerases',user='******')
cursor=connection.cursor()
for k,v in results.iteritems():
TaxID = non_decimal.sub('', results[k]['TaxID'])
ID = results[k]['id']
k=repr(k)
sql="update {} set {}='{}' where Accession_Number={}"
cursor.execute(sql.format(table,'OrganismID',TaxID,k))
# logger.debug('update TaxID sql statement for table {}:{}'.format(table,sql.format(table,'OrganismID',TaxID,k)))
cursor.execute(sql.format(table,'Entry_Name',ID,k))
# logger.debug('update ID sql statement for table {}:{}'.format(table,sql.format(table,'Entry_Name',ID,k)))
connection.commit()
time.sleep(1)
connection.close()
def fetch_and_assign_taxids(seq,table):
non_decimal = re.compile(r'[^\d.]+')
results=uniprot.fetch_uniprot_metadata(seq)
time.sleep(1)
connection = mdb.connect(host='localhost',db='FamilyCpolymerases',user='******')
cursor=connection.cursor()
for k,v in results.iteritems():
TaxID = non_decimal.sub('', results[k]['TaxID'])
ID = results[k]['id']
k=repr(k)
sql="update {} set {}='{}' where Accession_Number={}"
cursor.execute(sql.format(table,'OrganismID',TaxID,k))
# logger.debug('update TaxID sql statement for table {}:{}'.format(table,sql.format(table,'OrganismID',TaxID,k)))
cursor.execute(sql.format(table,'Entry_Name',ID,k))
# logger.debug('update ID sql statement for table {}:{}'.format(table,sql.format(table,'Entry_Name',ID,k)))
connection.commit()
time.sleep(1)
connection.close()
def fetch_uniprot_data(
self, uniprot_ids: Union[str,
List[str]]) -> List[Mapping[str, str]]:
"""
Fetches a list of dicts of UniProt metadata, one per UniProt ID.
Raises:
ValueError: If a UniProt ID wasn't found.
"""
if isinstance(uniprot_ids, str): # not a list type
uniprot_ids = [uniprot_ids]
# if we don't prevent these here, we'll get a ValueError from below, which is confusing
# That's because uniprot.fetch_uniprot_metadata will only return one per unique ID
if len(set(uniprot_ids)) != len(uniprot_ids):
raise MultipleMatchesError(
"Set of UniProt IDs cannot contain duplicates")
with silenced(no_stderr=False):
uniprot_data = uniprot.fetch_uniprot_metadata(uniprot_ids)
if uniprot_data is None or uniprot_data == {} or len(
uniprot_data) != len(uniprot_ids):
raise LookupError(
f"At least one UniProt ID not found in {uniprot_ids}")
return list(uniprot_data.values())
