def t_write_format():
record_parser = GenBank.RecordParser(debug_level=0)
for file in write_format_files:
print("Testing GenBank writing for %s..." % os.path.basename(file))
cur_handle = open(os.path.join("GenBank", file), "r")
compare_handle = open(os.path.join("GenBank", file), "r")
iterator = GenBank.Iterator(cur_handle, record_parser)
compare_iterator = GenBank.Iterator(compare_handle)
while True:
cur_record = next(iterator)
compare_record = next(compare_iterator)
if cur_record is None or compare_record is None:
break
print("\tTesting for %s" % cur_record.version)
output_record = str(cur_record) + "\n"
do_comparison(compare_record, output_record)
cur_handle.close()
compare_handle.close()
def write_format(file):
"""Write a GenBank record from a Genbank file and compare them."""
record_parser = GenBank.RecordParser(debug_level=2)
print("Testing GenBank writing for %s..." % os.path.basename(file))
# be able to handle gzipped files
if ".gz" in file:
cur_handle = gzip.open(file, "r")
compare_handle = gzip.open(file, "r")
else:
cur_handle = open(file, "r")
compare_handle = open(file, "r")
iterator = GenBank.Iterator(cur_handle, record_parser)
compare_iterator = GenBank.Iterator(compare_handle)
while True:
cur_record = next(iterator)
compare_record = next(compare_iterator)
if cur_record is None or compare_record is None:
break
# print("\tTesting for %s" % cur_record.version)
output_record = str(cur_record) + "\n"
try:
do_comparison(compare_record, output_record)
except AssertionError as msg:
print("\tTesting for %s" % cur_record.version)
print(msg)
cur_handle.close()
compare_handle.close()
def write_format(file):
record_parser = GenBank.RecordParser(debug_level = 2)
print "Testing GenBank writing for %s..." % os.path.basename(file)
# be able to handle gzipped files
if '.gz' in file:
cur_handle = gzip.open(file, "r")
compare_handle = gzip.open(file, "r")
else:
cur_handle = open(file, "r")
compare_handle = open(file, "r")
iterator = GenBank.Iterator(cur_handle, record_parser)
compare_iterator = GenBank.Iterator(compare_handle)
while 1:
cur_record = iterator.next()
compare_record = compare_iterator.next()
if cur_record is None or compare_record is None:
break
# print "\tTesting for %s" % cur_record.version
output_record = str(cur_record) + "\n"
try:
do_comparison(compare_record, output_record)
except AssertionError, msg:
print "\tTesting for %s" % cur_record.version
print msg
def setUp(self):
# create TESTDB
create_database()
# load the database
db_name = "biosql-test"
server = BioSeqDatabase.open_database(driver=DBDRIVER,
user=DBUSER,
passwd=DBPASSWD,
host=DBHOST,
db=TESTDB)
# remove the database if it already exists
try:
server[db_name]
server.remove_database(db_name)
except KeyError:
pass
self.db = server.new_database(db_name)
# get the GenBank file we are going to put into it
input_file = os.path.join(os.getcwd(), "GenBank", "cor6_6.gb")
handle = open(input_file, "r")
parser = GenBank.FeatureParser()
self.iterator = GenBank.Iterator(handle, parser)
def loadData(self, data, dbtype):
if (dbtype == "GenBank"):
# get the GenBank file we are going to put into it
parser = GenBank.FeatureParser()
iterator = GenBank.Iterator(data, parser)
# finally put it in the database
try:
self.getDatabase().load(iterator)
except:
self.getBioSQLRoot().getDBServer().adaptor.conn.rollback()
return traceback.format_exc()
self.getBioSQLRoot().getDBServer().adaptor.conn.commit()
return ""
else:
raise "Unknown dbtype: %r" % (dbtype)
def t_cleaning_features():
"""Test the ability to clean up feature values."""
gb_parser = GenBank.FeatureParser(
feature_cleaner=utils.FeatureValueCleaner())
handle = open(os.path.join("GenBank", "arab1.gb"))
iterator = GenBank.Iterator(handle, gb_parser)
first_record = next(iterator)
# test for cleaning of translation
translation_feature = first_record.features[1]
test_trans = translation_feature.qualifiers["translation"][0]
assert " " not in test_trans, "Did not clean spaces out of the translation"
assert "\012" not in test_trans, "Did not clean newlines out of the translation"
handle.close()
def t_cleaning_features():
"""Test the ability to clean up feature values.
"""
parser = GenBank.FeatureParser(feature_cleaner = \
utils.FeatureValueCleaner())
handle = open(os.path.join("GenBank", "arab1.gb"))
iterator = GenBank.Iterator(handle, parser)
first_record = iterator.next()
# test for cleaning of translation
translation_feature = first_record.features[1]
test_trans = translation_feature.qualifiers["translation"][0]
assert test_trans.find(" ") == -1, \
"Did not clean spaces out of the translation"
assert test_trans.find("\012") == -1, \
"Did not clean newlines out of the translation"
def load_database(gb_handle):
"""Load a GenBank file into a BioSQL database.
This is useful for running tests against a newly created database.
"""
create_database()
# now open a connection to load the database
db_name = "biosql-test"
server = BioSeqDatabase.open_database(driver=DBDRIVER,
user=DBUSER,
passwd=DBPASSWD,
host=DBHOST,
db=TESTDB)
db = server.new_database(db_name)
# get the GenBank file we are going to put into it
parser = GenBank.FeatureParser()
iterator = GenBank.Iterator(gb_handle, parser)
# finally put it in the database
db.load(iterator)
server.adaptor.conn.commit()
server.adaptor.conn.close()
# files_to_parse += [os.path.join(os.getcwd(), 'GenBank', 'biojava_test.gb')]
# test the parsers
feature_parser = GenBank.FeatureParser(debug_level=0)
record_parser = GenBank.RecordParser(debug_level=0)
all_parsers = [feature_parser, record_parser]
print("Testing parsers...")
for parser in all_parsers:
for filename in files_to_parse:
if not os.path.isfile(filename):
print("Missing test input file: %s" % filename)
continue
handle = open(filename, 'r')
iterator = GenBank.Iterator(handle, parser)
while True:
with warnings.catch_warnings():
warnings.simplefilter("ignore", BiopythonParserWarning)
# e.g. BiopythonParserWarning: Premature end of file in sequence data
cur_record = next(iterator)
if cur_record is None:
break
if isinstance(parser, GenBank.FeatureParser):
print("***Record from %s with the FeatureParser" %
filename.split(os.path.sep)[-1])
print("Seq: %r" % cur_record.seq)
print("Id: %s" % cur_record.id)
import sys
# GenBank
from Bio import GenBank
verbose = 0
if len(sys.argv) != 2:
print("Usage ./find_parser_problems <GenBank file to parse>")
sys.exit()
feature_parser = GenBank.FeatureParser(debug_level=0)
parser = GenBank.ErrorParser(feature_parser)
handle = open(sys.argv[1], 'r')
iterator = GenBank.Iterator(handle, parser, has_header=1)
while 1:
have_record = 0
while have_record == 0:
try:
cur_record = iterator.next()
have_record = 1
except GenBank.ParserFailureError as msg:
print "Parsing Problem:", msg
sys.exit()
if cur_record is None:
break
#!/usr/bin/env python
from Bio import GenBank
from Bio import Entrez
from BioSQL import BioSeqDatabase
import sys
# Should read these from settings at some point
dbpath = 'biosql.sqlite3'
dbname = 'local_db'
Entrez.email = '*****@*****.**'
server = BioSeqDatabase.open_database(driver='sqlite3', db=dbpath)
db = server[dbname]
parser = GenBank.FeatureParser()
loadgb = lambda _id: db.load(
GenBank.Iterator(
Entrez.efetch(db='nucleotide', id=_id, rettype='gb', retmode='text'),
parser))
ACCESSIONS_FILE = 'accession.lst' if len(sys.argv) < 2 else sys.argv[1]
for id in open(ACCESSIONS_FILE):
print "Loading %s" % id
loadgb(id)
server.adaptor.commit()
"Leptocephalus sp. 'type II larva' (Smith, 1989)":
"Leptocephalus sp. 'type II larva'",
"Humphaplotropis culaishanensis":
"Humphaplotropis culaishanensis (nomen nudum)",
"Paraglypturus tonganus": "Paraglypturus tonganus (nomen nudum)",
"Hoploplana elisabelloi": "Hoploplana elisabelloi (nomen nudum)",
"Palpitomonas bilix Eukaryota.": "Palpitomonas bilix",
"Eukaryota sp. BB2 Eukaryota.": "Eukaryota sp. BB2",
"Ancoracysta twista Eukaryota.": "Ancoracysta twista"
}
# --- load a parser and iterator for our GenBank file
gb_handle = gzip.open(sys.argv[1], "r")
# -- a parser that will give you back SeqFeature objects
feature_parser = GenBank.FeatureParser()
iterator = GenBank.Iterator(gb_handle, feature_parser)
# load taxonomy for taxids
ncbi = NCBITaxa()
# output using prefix
out_1 = open("%s.cdna.fasta" % sys.argv[2], "w")
out_2 = open("%s.codons.tab" % sys.argv[2], "w")
strands = []
stop_codons = []
prot_ids = []
excluded = []
missing_id = []
# begin iterating through the file and getting GenBank records
def loadDB(catalog):
from BioSQL import BioSeqDatabase
import sys
username = raw_input("Please enter user name: ")
password = raw_input("and password: "******"dbpg-ifi-utv.uio.no"
db_name = "rnammer"
server = BioSeqDatabase.open_database(driver="psycopg2", user=username,passwd=password,
host=host, db=db_name)
biodb_name = "empty" # genebank problem ? se staving
db = "nodb"
gi_rep = 1
for gbff in catalog:
#server.remove_database(source)
print gi_rep
print gbff
parser = GenBank.FeatureParser()
#record = parser.parse(open(gbff))
#records = SeqIO.parse(open(gbff),'genbank')
records = GenBank.Iterator(open(gbff), parser)
for x in records:
if re.search("plasmid",x.description, re.IGNORECASE):
continue
print "Record name:"
print x.id
#print dir(x)
if "Proteobacteria" == x.annotations["taxonomy"][1]:
print x.annotations["taxonomy"][1]
print x.annotations["taxonomy"][2]
biodb_name = x.annotations["taxonomy"][2]
else :
print x.annotations["taxonomy"][1]
biodb_name = x.annotations["taxonomy"][1]
while True :
try :
db = server[biodb_name]
#print "here"
break
except KeyError :
#print ("Cannot find biodatabase with name %r making it" % source)
server.new_database(biodb_name)
server.commit()
db.load([x])
#record.annotations["gi"] = gi_rep
#print type(records)
#print record.id
gi_rep = gi_rep + 1
#db.load([records])
server.adaptor.commit()
# -*- coding: utf-8 -*-
"""
Created on Wed Aug 17 15:02:37 2016
@author: rgilmore
"""
import sqlite3
from BioSQL import BioSeqDatabase
from Bio import GenBank
import os
server = BioSeqDatabase.open_database(driver="sqlite3", db="biosql.db")
db = server.new_database("HTR1A")
dir_list1 = os.listdir()
print(dir_list1)
#for files in dir_list1:
parser = GenBank.FeatureParser()
iterator = GenBank.Iterator(open("HTR1A_Ailuropoda melanoleuca.gbk"), parser)
db.load(iterator)
db.adaptor.commit()
#input("%s loaded into HTR1A database. Proceed?")
server.commit()
server.close()
