# ) # import_prop_blast(mdb.db, name, "hit_in_deg", # "/data/organismos/" + name + "/annotation/offtarget/degaa-p.tbl", # "table", "Hit in DEG database", # value_fn=lambda x: x.identity > 70, # default_value=True, # no_hit_value=False, choices=["True", "False"], type="value", defaultOperation="equal") # # import_prop_blast(mdb.db, name, "human_offtarget", # "/data/organismos/" + name + "/annotation/offtarget/gencode.tbl", # "table", "Human offtarget score (1 - best hit identity)", # value_fn=lambda x: 1 - (x.identity * 1.0 / 100), # default_value=0.4, # no_hit_value=1) # import_prop_blast(mdb.db, name, "gut_microbiota_offtarget", # "/data/organismos/" + name + "/annotation/offtarget/gut_microbiota.tbl", # "table", "Gut microbiota offtarget score (1 - best hit identity)", # value_fn=lambda x: 1 - (x.identity * 1.0 / 100), # default_value=0.4, # no_hit_value=1) # index_seq_collection(mdb.db,name,pathways=False,go=False,keywords=False,ec=False,organism_idx=False,structure=True) # load_pathways(name, "/data/organismos/Ainsu/annotation/pwtools/small_molecule.sbml", mdb.db, # "/data/organismos/Ainsu/annotation/pathways", # gregexp="\(([\-\w\.]+)\)", filter_file="allfilters_con_c.dat") # index_seq_collection(mdb.db,name,pathways=False,go=False,keywords=True,ec=False,organism_idx=True,structure=False) # build_statistics(mdb.db,name) dst_db = pymongo.MongoClient(port=27018).tdr mdb.copy_genome(name,name,dst_db)
keywords=True,
ec=True,
organism_idx=True,
structure=False)
build_statistics(mdb.db, name)
import subprocess as sp
for xx in orgs:
x = xx[0]
for y in tqdm(
glob("/data/organismos/" + x +
"/estructura/sndg/modelos/*.pocket.json")):
sp.call("ln %s %s" %
(y, ("/data/organismos/%s/estructura/sndg/pockets/" % x) +
y.split("/")[-1].replace(".pdb.pocket", "")),
shell=True)
# rsync -avzh /data/organismos/Mbovis/estructura/sndg/pockets/* marvin:/data/organismos/Mbovis/estructura/sndg/pockets/
# rsync -avzh /data/organismos/Mbovis/estructura/sndg/modelos/*.pdb marvin:/data/organismos/Mbovis/estructura/sndg/modelos/
# ssh -L 27018:localhost:27017 marvin
pdbdb = dbdst = MongoClient(port=27017).pdb
dbdst = MongoClient(port=27018).pdb
for xx in orgs:
x = xx[0]
mdb.copy_genome(x, dst_db=MongoClient(port=27018).tdr)
for s in tqdm(pdbdb.structures.find({"organism": x}),
total=pdbdb.structures.count({"organism": x})):
dbdst.structures.insert(s)
# value_fn=lambda x: 1 - (x.identity * 1.0 / 100),
# default_value=0.4,
# no_hit_value=1)
#add column names
# mdb.load_metadata( name,"/mnt/data/data/organismos/Aaye/annotation/gut_microbiome.tbl")
# from pymongo import MongoClient
# db = MongoClient().pdb
# sa = StructureAnotator(basepath, struct_path=lambda wd, modeldoc: glob("/".join(
# [wd, modeldoc.templates[0].aln_query.name, modeldoc.templates[0].aln_query.name, modeldoc.name, "*.pdb"]))[0])
# total = sa.total(db, organism, {})
#
# with tqdm(sa.iterator(db, organism, {}), total=total) as pbar:
# for model in pbar:
# pbar.set_description(model.name)
#
# template = model. templates[0]
# protein = Protein.objects(organism=organism, alias=template.aln_query.name).get()
# sa.annotate_model(model, protein.domains())
# model.save()
# index_seq_collection(mdb.db,name,pathways=False,go=False,keywords=False,ec=False,organism_idx=False,structure=True)
# load_pathways(name, "/data/organismos/Aaye/annotation/pathways/small.sbml", mdb.db,
# "/data/organismos/Aaye/annotation/pathways_data/",
# gregexp="\(([\-\w\.]+)\)", filter_file="allfilters_con_c.dat")
# index_seq_collection(mdb.db,name,pathways=True,go=True,keywords=True,ec=True,organism_idx=True,structure=False)
# build_statistics(mdb.db,name)
mdb.copy_genome("Aaye", dst_db=pymongo.MongoClient(port=27018).tdr)