logger = logging.getLogger('peewee')
logger.setLevel(logging.INFO)
init_log()
mdb = BioMongoDB("saureus")
tax_db.initialize(MySQLDatabase('bioseqdb', user='******', passwd="mito"))
mysql_db.initialize(MySQLDatabase('sndg', user='******', passwd="mito"))
assemblies = list(ExternalAssembly.select().where(
ExternalAssembly.sample_source.is_null(False)))
ProteinAnnotator.connect_to_db(database="unipmap",
user="******",
password="******")
with tqdm(assemblies) as pbar:
for x in pbar:
if mdb.seq_col_exists(x.assembly_accession):
continue
pbar.set_description(x.assembly_accession)
try:
dst_dir = "/data/organismos/" + x.assembly_accession + "/annotation/"
mkdir(dst_dir)
gbpath = x.download_gbk(dst_dir)
from_ref_seq(x.assembly_accession,
gbpath,
tax=x.ncbi_tax,
tmp_dir=dst_dir)
tid = int(
mdb.db.sequence_collection.find_one(
{"name": x.assembly_accession})["tax"]["tid"])
tmp_dir = "/data/organismos/" + x.assembly_accession + "/annotation/"
parser.add_argument("--cpus", default=multiprocessing.cpu_count())
parser.add_argument("-mydbunip", "--mysqldbunip", default="unipmap")
parser.add_argument("-myu", "--mysqldbuser", default="root")
args = parser.parse_args()
args.cpus = int(args.cpus)
mdb = BioMongoDB(args.mongodbname)
tax_db.initialize(
MySQLDatabase(args.mysqldbtaxname,
user=args.mysqldbuser,
passwd=args.dbpass))
ProteinAnnotator.connect_to_db(database=args.mysqldbunip,
user=args.mysqldbuser,
password=args.dbpass)
assert not mdb.seq_col_exists(
args.assemblyAccession), "assembly already exists"
Entrez.email = "*****@*****.**"
assembly_id = Entrez.read(
Entrez.esearch(db="assembly", term=args.assemblyAccession,
retmax=1))["IdList"][0]
resource = Entrez.read(
Entrez.esummary(db="assembly", id=assembly_id, validate=False))
try:
data = resource["DocumentSummarySet"]["DocumentSummary"][0]
name = data["AssemblyName"]
genome = str(data["SpeciesName"])
tax = data["Taxid"]
status = data["AssemblyStatus"]
ea = ExternalAssembly(type="assembly",