def record_processor(self, record, database):
"""
Splits the record returned by Entrez into sparate variables and returns
them.
"""
count = int(record["Count"]) # Int
webenv = record["WebEnv"] # String
query_key = record["QueryKey"] # String
IDs = []
for i in range(0, count, 10000):
iter_handle = Entrez.efetch(db=database, webenv=webenv,
query_key=query_key, retmax=10000,
rettype="acc", retstart=i)
IDs += [x.rstrip() for x in iter_handle]
iter_handle.close()
assert count == len(IDs)
if count == 0 and self.gui == 0:
sys.exit("Your serch query returned no results!")
elif count == 0:
self.no_match.emit("Your serch query returned no results!")
return None
return count, IDs, webenv, query_key
def erratum_check(PMID, comments):
""" Does this PMID have an erratum?
I can't do the erratum formatting automatically.
But I can warn user that there is an erratum.
"""
Entrez.email = app.config['EMAIL']
handle = Entrez.efetch(db="pubmed", id=PMID, rettype="gb", retmode="xml")
records = Entrez.read(handle)
erratum_count = 0
try:
corrections = records['PubmedArticle'][0]['MedlineCitation'][
'CommentsCorrectionsList']
for correction in corrections:
if correction.attributes['RefType'] == 'ErratumIn':
if erratum_count == 0:
comments.append(
"I smell an erratum: " + correction['RefSource'] +
". \nAdd it to the end of your citation: [Erratum in Journal, Issue(Volume): page. DOI: #. Accessed date.]"
)
else: # Is this the second (or later) erratum we're reporting for this article? Then shorten report.
comments.append("There's another erratum! What a mess." +
correction['RefSource'])
erratum_count += 1
except:
pass # No errata? Do nothing.
return comments
def genbank_entries_from_accession(accessions,
read_out=False,
email='*****@*****.**'):
import Entrez
entries = []
Entrez.email = email
request = Entrez.epost('nucleotide', id=','.join(map(str, accessions)))
result = Entrez.read(request)
handle = Entrez.efetch(db='nucleotide',
retmode='xml',
webenv=result['WebEnv'],
query_key=result['QueryKey'])
for r in Entrez.parse(handle):
try:
entry = [x for x in r['GBSeq_other-seqids'] if 'gi' in x][0]
gi = int(entry.split('|')[1])
entries.append(gi)
except ValueError:
gi = None
if read_out is True:
print(">GI {0} {1} {2}\n{3}".format(gi,
r['GBSeq_primary-accession'],
r['GBSeq_definition'],
r['GBSeq_sequence'][:15]))
return entries
def retrieve_abstract(PMID):
Entrez.email = app.config['EMAIL']
handle = Entrez.efetch(db="pubmed",rettype="medline", retmode="text", id=PMID)
record = Medline.read(handle)
handle.close()
try:
abstract = record['AB']
except:
abstract = ''
return abstract
def get_description(mail,ID):
"""Used by xml write for searching the definition of the hit using the accession number from NCBI
which appears in the rapsearch output"""
Entrez.email = mail
handle = Entrez.efetch(db="protein", id=ID, rettype="gb", retmode="text")
entry=(handle.read().strip())
complete=entry.split("\n")
definition=complete[1][12:]
definition2=definition.strip(".")
handle.close()
return (definition2)
def get_description(mail,ID):
"""Used by make description for searching the definition of the hit using the accession number from NCBI
which appears in the nnotation output
Adapted from the RapsearchToXml.py file"""
Entrez.email = mail
handle = Entrez.efetch(db="protein", id=ID, rettype="gb", retmode="text")
entry=(handle.read().strip())
complete=entry.split("\n")
definition=complete[1][12:] #get the definition camp
definition2=definition.split("[")#removes the species informaton
handle.close()
return (definition2[0])
def fetch_by_id(self, IDs, b_size):
"""
Fetches NCBI data based on the IDs, rather than a search query. Returns
the data handle string.
"""
id_handle = Entrez.efetch(db=self.database,
id=IDs,
rettype="fasta",
retmode="text",
retmax=b_size)
data = id_handle.read()
id_handle.close()
return data
def fetch_by_id(self, IDs, b_size):
"""
Fetches NCBI data based on the IDs, rather than a search query. Returns
the data handle string.
"""
id_handle = Entrez.efetch(db=self.database,
id=IDs,
rettype="fasta",
retmode="text",
retmax=b_size)
data = id_handle.read()
id_handle.close()
return data
def fetch_by_history(self, start, b_size, webenv, query_key):
"""
Fetches NCBI data based on the provided search query. Returns the data
handle string.
"""
hist_handle = Entrez.efetch(db=self.database,
retstart=start,
rettype="fasta",
retmode="text",
retmax=b_size,
webenv=webenv,
query_key=query_key)
data = hist_handle.read()
hist_handle.close()
return data
def fetch_by_history(self, start, b_size, webenv, query_key):
"""
Fetches NCBI data based on the provided search query. Returns the data
handle string.
"""
hist_handle = Entrez.efetch(db=self.database,
retstart=start,
rettype="fasta",
retmode="text",
retmax=b_size,
webenv=webenv,
query_key=query_key)
data = hist_handle.read()
hist_handle.close()
return data
