from Bio.PDB.PDBParser import PDBParser
from mongoengine.errors import DoesNotExist
from SNDG import init_log
from SNDG.BioMongo.Model import BioProperties
from SNDG.BioMongo.Model import Cluster
from SNDG.BioMongo.Model.Structure import ExperimentalStructure, ResidueSet
from SNDG.BioMongo.Process.BioMongoDB import BioMongoDB
from SNDG.Structure.CompoundTypes import get_compound_type
from SNDG.Structure.FPocket import FPocket
from SNDG.Structure.PDBs import PDBs
# from Bia.Programs.Cluster.CDHit import CDHit
init_log()
_log = logging.getLogger(__name__)
from SNDG.Structure.CompoundTypes import compound_type
def update_clusters():
for cluster_name, seqs in CDHit().clustered_seq_iterator("/data/databases/pdb/processed/seqs_from_pdb95.fasta"):
_log.debug(cluster_name)
cristals = []
cluster = Cluster(name=cluster_name, type="PDB_Segments_95")
for seq in seqs:
seq_id, seq_start, seq_end, clust_start, clust_end = seq
pdb, chain, start, end = seq_id.split("_")
cristals.append(pdb)
#!/usr/bin/env python
import os
import time
from SNDG import mkdir, execute, execute_from, init_log
from SNDG.WebServices import download_file
from SNDG.Structure.PDBs import PDBs
init_log("/tmp/createdb.log")
def old_or_inexistent(filepath, period=30):
return not os.path.exists(filepath) or ((
(time.time() - os.path.getatime(filepath)) / 60 / 60 / 24) > period)
#os.environ["http_proxy"] = "http://proxy.fcen.uba.ar:8080"
#os.environ["ftp_proxy"] = "http://proxy.fcen.uba.ar:8080"
mkdir("/data/pdb/")
download_file("ftp://ftp.wwpdb.org/pub/pdb/derived_data/index/entries.idx",
"/data/pdb/entries.idx",
ovewrite=True)
pdbs = PDBs("/data/pdb/")
pdbs.download_pdb_seq_ses()
pdbs.update_pdb_dir()
mkdir("/data/pdb/processed/")
pdbs.pdbs_seq_for_modelling()
execute("makeblastdb -dbtype prot -in /data/pdb/processed/seqs_from_pdb.fasta")
protein_fasta = tmp_dir + "/proteins.fasta"
if not os.path.exists(protein_fasta) or (
not os.path.getsize(protein_fasta)):
with open(protein_fasta, "w") as h:
for p in Protein.objects(organism=seq_col_name).no_cache():
bpio.write(SeqRecord(id=p.gene[0], seq=Seq(p.seq)), h,
"fasta")
genome = SeqCollection.objects(name=seq_col_name).get()
genome.ncbi_assembly = seq_col_name
if not genome.statistics:
self.mdb.index_seq_collection(seq_col_name, pathways=False)
self.mdb.build_statistics(seq_col_name)
_log.info("Sequence collection %s created correctly " %
seq_col_name)
if __name__ == '__main__':
init_log("/tmp/sndg2.log")
logger = logging.getLogger('peewee')
logger.setLevel(logging.ERROR)
dep = Deployer()
connect_to_db(password="******")
import mysql.connector
dep.mdb = "saureus"
#dep.annotation_tax = "158879"
dep.init()
tax_db.initialize(MySQLDatabase('bioseq', user='******', passwd="mito"))
@author: eze
'''
import logging
from argparse import ArgumentParser, RawDescriptionHelpFormatter
import math
from Bio.PDB.PDBParser import PDBParser
from tqdm import tqdm
from SNDG import init_log
from SNDG.Structure.PDBdb import *
from SNDG.Structure.PDBs import PDBs
init_log(rootloglevel=logging.INFO)
_log = logging.getLogger(__name__)
if __name__ == "__main__":
parser = ArgumentParser(formatter_class=RawDescriptionHelpFormatter)
parser.add_argument("-p", "--dbpass", required=True)
parser.add_argument("-i", "--pdb_dir", default="/data/databases/pdb/")
parser.add_argument("-db", "--dbname", default="pdbdb")
parser.add_argument("-u", "--dbuser", default="root")
args = parser.parse_args()
from peewee import MySQLDatabase
mysql_db = MySQLDatabase(args.dbname,
import logging
import pymongo
from mongoengine.connection import connect
from pymongo.mongo_client import MongoClient
from SNDG import init_log
from SNDG.BioMongo.Model.SeqCollection import Genome, SeqColDruggabilityParam
from SNDG.BioMongo.Process.BioCyc2Mongo import BioCyc
from SNDG.BioMongo.Process.StructureAnotator import StructureAnotator
from SNDG.BioMongo.Process.StructureIndexer import StructuromeIndexer
from SNDG.BioMongo.Process.PathwaysAnnotator import PathwaysAnnotator
from SNDG.BioMongo.Process.BioMongoDB import BioMongoDB
from pprint import pprint
init_log("/tmp/validate.log")
_log = logging.getLogger(__name__)
db = MongoClient().tdr
import re
regx_go = re.compile("^go:") # , re.IGNORECASE)
regx_ec = re.compile("^ec:")
def validate_pathways_protein(g):
for dp in BioCyc.pathways_search_params:
if not g.has_druggability_param(dp[0]):
print "%s no tiene el atributo %s" % (g.name, dp[0])
count = db.proteins.count({
from SNDG import init_log
from SNDG.Structure.FPocket import FPocket
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument("-d", "--models_directory", required=True)
parser.add_argument("-l", "--log_path", default=None)
args = parser.parse_args()
assert os.path.exists(args.models_directory), "%s does not exists" % args.models_directory
if not args.log_path:
args.log_path = args.models_directory + "/pocketome.log"
init_log(args.log_path, logging.INFO)
_log = logging.getLogger("pocketome")
with tqdm(glob.glob(args.models_directory + "/*.pdb")) as pbar:
for pdb in pbar:
pbar.set_description(pdb)
try:
pocket_data = pdb + ".json"
if not os.path.exists(pocket_data):
fpo = FPocket(pdb)
result = fpo.hunt_pockets()
result.save(pocket_data)
result.delete_dir()
except Exception as e:
_log.warn(e)
["uniprot", "db", "value"])
})
except IntegrityError:
pass
if __name__ == '__main__':
from SNDG import init_log
import logging
from SNDG.BioMongo.Process.BioMongoDB import BioMongoDB
mysqldb = ProteinAnnotator.connect_to_db(database="unipmap",
user="******",
password="******")
pa = ProteinAnnotator()
# pa.connect_to_db(password="******")
# pa.create_db()
# pa.populate_sql("/data/uniprot/idmapping_filtered.dat",
# "/data/uniprot/goa/goa_uniprot_all.gpa")
tmpdir = "/tmp/lepto/Lepto-CLM-U50"
logging.getLogger("peewee").setLevel(logging.WARN)
init_log(log_file_path=tmpdir + "/ann.log")
mdb = BioMongoDB("tdr")
tax = 1958811
list(Mapping.select().where(Mapping.uniprot == "12"))
n = "Lepto-CLM-U50"
from SNDG.BioMongo.Process.Importer import update_proteins
update_proteins(tmpdir, tmpdir + "/genome.fasta", n, tax, db_init=mysqldb)
