def protein_manager(self, database="datanator"):
return query_protein.QueryProtein(username=self.username,
password=self.password,
server=self.server,
authSource=self.authDB,
readPreference=self.read_preference,
replicaSet=self.repl,
database=database)
def data_from_mongo_protein(self,
server,
db,
username,
password,
verbose=False,
readPreference='nearest',
authSource='admin',
projection={'_id': 0},
query={}):
''' Acquire documents from protein collection in datanator
Args:
server (:obj:`str`): mongodb ip address
db (:obj:`str`): database name
username (:obj:`str`): username for mongodb login
password (:obj:`str`): password for mongodb login
verbose (:obj:`bool`): display verbose messages
readPreference (:obj:`str`): mongodb readpreference
authSource (:obj:`str`): database login info is authenticating against
projection (:obj:`str`): mongodb query projection
query (:obj:`str`): mongodb query filter
Returns:
(:obj:`tuple`): tuple containing:
docs (:obj:`pymongo.Cursor`): pymongo cursor object that points to all documents in protein collection;
count (:obj:`int`): number of documents returned
'''
protein_manager = query_protein.QueryProtein(
server=server,
database=db,
verbose=verbose,
username=username,
authSource=authSource,
password=password,
readPreference=readPreference)
docs = protein_manager.collection.find(filter=query,
projection=projection)
count = protein_manager.collection.count_documents(query)
return (count, docs)
def __init__(self, server, src_db='datanator', des_db='datanator', collection_str='uniprot',
username=None, password=None, readPreference='nearest', authSource='admin', verbose=True,
max_entries=float('inf')):
super().__init__(MongoDB=server, db=des_db, verbose=verbose, max_entries=max_entries,
username=username, password=password, authSource=authSource,
readPreference=readPreference)
self.collection_str = collection_str
self.max_entries = max_entries
self.verbose = verbose
self.des_client, self.des_db, self.des_collection = self.con_db(collection_str)
self.koc_manager = query_kegg_organism_code.QueryKOC(username=username, password=password,
server=server, authSource=authSource, collection_str='kegg_organism_code', readPreference=readPreference,
database=src_db)
self.uniprot_manager = query_uniprot.QueryUniprot(username=username, password=password, server=server,
authSource=authSource, database=src_db, collection_str='uniprot', readPreference=readPreference)
self.kegg_manager = query_kegg_orthology.QueryKO(username=username, password=password, server=server,
authSource=authSource, database=src_db, max_entries=max_entries, verbose=verbose, readPreference=readPreference)
self.protein_manager = query_protein.QueryProtein(username=username, password=password, server=server,
authSource=authSource, database=src_db, max_entries=max_entries, verbose=verbose, readPreference=readPreference)
self.uniprot_nosql_manager = uniprot_nosql.UniprotNoSQL(MongoDB=server, db=des_db, max_entries=max_entries,
verbose=verbose, username=username, password=password, authSource=authSource)
self.endpoint = 'https://www.kegg.jp/ssdb-bin/ssdb_best?org_gene='
def __init__(self,
db=None,
MongoDB=None,
cache_directory=None,
verbose=False,
max_entries=float('inf'),
replicaSet=None,
username=None,
password=None,
authSource='admin'):
'''
Attributes:
cache_directory: JSON file (converted from sqlite) directory
db: mongodb database name
MongoDB: MongoDB server address and login e.g. 'mongodb://mongo:27017/'
'''
self.db = db
self.MongoDB = MongoDB
self.cache_directory = cache_directory
self.verbose = verbose
self.max_entries = max_entries
self.collection_str = 'sabio_rk_old'
super(SabioRkNoSQL, self).__init__(cache_dirname=cache_directory,
MongoDB=MongoDB,
replicaSet=replicaSet,
db=db,
verbose=verbose,
max_entries=max_entries,
username=username,
password=password,
authSource=authSource)
self.client, self.db_obj, self.collection = self.con_db(
self.collection_str)
self.sabio_reaction_entries = self.db_obj['sabio_reaction_entries']
self.kegg_collection = self.db_obj['kegg_orthology']
self.sabiork_manager = query_sabiork.QuerySabio(
MongoDB=MongoDB,
db=db,
collection_str='sabio_rk',
verbose=verbose,
max_entries=max_entries,
username=username,
password=password,
authSource=authSource)
self.protein_manager = query_protein.QueryProtein(
username=username,
password=password,
server=MongoDB,
authSource=authSource,
database=db,
max_entries=max_entries,
verbose=verbose,
collection_str='uniprot',
readPreference='nearest')
self.ec = self.db_obj['ec']
self.chem_manager = chem_util.ChemUtil()
self.tax_manager = query_taxon_tree.QueryTaxonTree(username=username,
MongoDB=MongoDB,
password=password)
self.file_manager = file_util.FileUtil()
def __init__(self,
username=None,
password=None,
server=None,
authSource='admin',
src_database='datanator',
max_entries=float('inf'),
verbose=True,
collection='protein',
destination_database='datanator',
cache_dir=None):
'''
Args:
src_database (:obj: `str`): name of database in which source collections reside
destination_database (:obj: `str`): name of database to put the aggregated collection
'''
self.max_entries = max_entries
self.verbose = verbose
self.cache_dir = cache_dir
self.mongo_manager = mongo_util.MongoUtil(MongoDB=server,
username=username,
password=password,
authSource=authSource,
db=src_database)
self.pax_manager = query_pax.QueryPax(MongoDB=server,
db=src_database,
collection_str='pax',
verbose=verbose,
max_entries=max_entries,
username=username,
password=password,
authSource=authSource)
self.kegg_manager = query_kegg_orthology.QueryKO(
server=server,
database=src_database,
verbose=verbose,
max_entries=max_entries,
username=username,
password=password,
authSource=authSource)
self.taxon_manager = query_taxon_tree.QueryTaxonTree(
collection_str='taxon_tree',
verbose=verbose,
max_entries=max_entries,
username=username,
MongoDB=server,
password=password,
db=src_database,
authSource=authSource)
self.protein_manager = query_protein.QueryProtein(
username=username,
password=password,
server=server,
collection_str='protein',
max_entries=max_entries,
database=src_database)
self.client, self.db, self.col = mongo_util.MongoUtil(
MongoDB=server,
username=username,
password=password,
authSource=authSource,
db=destination_database).con_db(collection)
self.bad_kinlawid = [
24416, 24417, 24418, 24419, 24420, 24421, 24422, 24423
]
self.collation = Collation(locale='en',
strength=CollationStrength.SECONDARY)
def setUpClass(cls):
cls.db = 'test'
conf = config.TestConfig()
username = conf.USERNAME
password = conf.PASSWORD
MongoDB = conf.SERVER
cls.MongoDB = MongoDB
cls.username = username
cls.password = password
cls.src = query_protein.QueryProtein(server=cls.MongoDB, database=cls.db,
verbose=True, max_entries=20, username = cls.username,
password = cls.password, collection_str='test_query_protein', readPreference='primary')
cls.src_1 = query_protein.QueryProtein(server=cls.MongoDB, database='datanator',
verbose=True, username = cls.username,
password = cls.password, readPreference='nearest')
cls.src_2 = query_protein.QueryProtein(server=cls.MongoDB, database='datanator-test',
verbose=True, username = cls.username,
password = cls.password, readPreference='nearest')
cls.src.db_obj.drop_collection('test_query_protein')
mock_doc_0 = {'uniprot_id': 'MOCK_0', 'ancestor_taxon_id': [105,104,103,102,101],
'ancestor_name': ['name_5', 'name_4','name_3','name_2','name_1'],
'ko_number': 'MOCK_0', 'ncbi_taxonomy_id': 100, 'abundances': 0}
mock_doc_1 = {'uniprot_id': 'MOCK_1', 'ko_number': 'MOCK_0'} # missing ancestor_taxon_id
mock_doc_2 = {'uniprot_id': 'MOCK_2', 'ancestor_taxon_id': [105,104,103],
'ancestor_name': ['name_5', 'name_4','name_3'],
'ko_number': 'MOCK_0', 'ncbi_taxonomy_id': 102, 'abundances': 2}
mock_doc_3 = {'uniprot_id': 'MOCK_3', 'ancestor_taxon_id': [105,104],
'ancestor_name': ['name_5', 'name_4'],
'ko_number': 'MOCK_1', 'ncbi_taxonomy_id': 103, 'abundances': 3} # different ko_number
mock_doc_4 = {'uniprot_id': 'MOCK_4', 'ancestor_taxon_id': [105],
'ancestor_name': ['name_5'],
'ko_number': 'MOCK_0', 'ncbi_taxonomy_id': 104, 'abundances': 4}
mock_doc_5 = {'uniprot_id': 'MOCK_5', 'ancestor_taxon_id': [105],
'ancestor_name': ['name_5'],
'ncbi_taxonomy_id': 104, 'abundances': 5}
mock_doc_6 = {'uniprot_id': 'MOCK_6', 'ancestor_taxon_id': [105],
'ancestor_name': ['name_5'],
'ko_number': 'MOCK_0', 'ncbi_taxonomy_id': 104, 'abundances': 6}
dic_0 = {'ncbi_taxonomy_id': 0, 'species_name': 's0', 'ancestor_taxon_id': [5,4,3,2,1], 'ancestor_name': ['s5', 's4', 's3', 's2', 's1'],
'ko_number': 'KO0', 'uniprot_id': 'uniprot0', "protein_name": 'special name one', 'kinetics': [{'ncbi_taxonomy_id': 100, 'kinlaw_id': 1},
{'ncbi_taxonomy_id': 101, 'kinlaw_id': 2}], 'abundances': [], 'ko_name': ['KO0 name']}
dic_1 = {'ncbi_taxonomy_id': 1, 'species_name': 's1', 'ancestor_taxon_id': [5,4,3,2], 'ancestor_name': ['s5', 's4', 's3', 's2'],
'ko_number': 'KO0', 'uniprot_id': 'uniprot1', "protein_name": 'nonspeciali name one'}
dic_2 = {'ncbi_taxonomy_id': 2, 'species_name': 's2', 'ancestor_taxon_id': [5,4,3], 'ancestor_name': ['s5', 's4', 's3'],
'ko_number': 'KO0', 'uniprot_id': 'uniprot2', "protein_name": 'nonspeciali name two'}
dic_3 = {'ncbi_taxonomy_id': 3, 'species_name': 's3', 'ancestor_taxon_id': [5,4], 'ancestor_name': ['s5', 's4'], 'ko_number': 'ko3',
'uniprot_id': 'uniprot3', "protein_name": 'your name one'}
dic_4 = {'ncbi_taxonomy_id': 4, 'species_name': 's4', 'ancestor_taxon_id': [5], 'ancestor_name': ['s5'], 'ko_number': 'KO0', 'uniprot_id': 'uniprot4'}
dic_5 = {'ncbi_taxonomy_id': 5, 'species_name': 's5', 'ancestor_taxon_id': [], 'ancestor_name': [], 'ko_number': 'KO0', 'uniprot_id': 'uniprot5'}
dic_6 = {'ncbi_taxonomy_id': 6, 'species_name': 's6', 'ancestor_taxon_id': [5,4,3,2], 'ancestor_name': ['s5', 's4', 's3', 's2'],
'ko_number': 'KO0', 'uniprot_id': 'uniprot6', "protein_name": 'your name two', 'ko_name': 'ko name 0', 'abundances': []}
dic_15 = {'ncbi_taxonomy_id': 6, 'species_name': 's6', 'ancestor_taxon_id': [5,4,3,2], 'ancestor_name': ['s5', 's4', 's3', 's2'],
'ko_number': 'KO1', 'uniprot_id': 'uniprot15', "protein_name": 'your name fifteen', 'ko_name': ['ko name 1']}
dic_14 = {'ncbi_taxonomy_id': 14, 'species_name': 's6 something', 'ancestor_taxon_id': [5,4,3,2], 'ancestor_name': ['s5', 's4', 's3', 's2'],
'ko_number': 'KO0', 'uniprot_id': 'uniprot6', "protein_name": 'your name three'}
dic_7 = {'ncbi_taxonomy_id': 7, 'species_name': 's7', 'ancestor_taxon_id': [5,4,3,2,6], 'ancestor_name': ['s5', 's4', 's3', 's2', 's6'],
'ko_number': 'KO0', 'uniprot_id': 'uniprot7', "protein_name": 'special name two'}
dic_8 = {'ncbi_taxonomy_id': 8, 'species_name': 's8', 'ancestor_taxon_id': [5,4,3,2,6,7], 'ancestor_name': ['s5', 's4', 's3', 's2', 's6', 's7'],
'ko_number': 'KO0', 'uniprot_id': 'uniprot8'}
dic_9 = {'ncbi_taxonomy_id': 9, 'species_name': 's9', 'ancestor_taxon_id': [5,4,3], 'ancestor_name': ['s5', 's4', 's3'], 'ko_number': 'KO0',
'uniprot_id': 'uniprot9'}
dic_10 = {'ncbi_taxonomy_id': 10, 'species_name': 's10', 'ancestor_taxon_id': [5,4,3,9], 'ancestor_name': ['s5', 's4', 's3', 's9'],
'ko_number': 'KO0', 'uniprot_id': 'uniprot10'}
dic_11 = {'ncbi_taxonomy_id': 11, 'species_name': 's11', 'ancestor_taxon_id': [5,4,3,2,1,0], 'ancestor_name': ['s5', 's4', 's3', 's2', 's1', 's0'],
'ko_number': 'KO0', 'uniprot_id': 'uniprot11'}
dic_12 = {'ncbi_taxonomy_id': 12, 'species_name': 's12', 'ancestor_taxon_id': [5,4,3,2,1,0], 'ancestor_name': ['s5', 's4', 's3', 's2', 's1', 's0'],
'ko_number': 'KO0', 'uniprot_id': 'uniprot12'}
dic_13 = {'ncbi_taxonomy_id': 13, 'species_name': 's13', 'ancestor_taxon_id': [5,4,3,2,1], 'ancestor_name': ['s5', 's4', 's3', 's2', 's1'],
'ko_number': 'KO0', 'uniprot_id': 'uniprot13', 'kinetics':[{'ncbi_taxonomy_id': 100, 'kinlaw_id': 1}, {'ncbi_taxonomy_id': 101, 'kinlaw_id': 2}]}
dic_16 = {'ncbi_taxonomy_id': 6, 'species_name': 's6', 'ancestor_taxon_id': [5,4,3,2], 'ancestor_name': ['s5', 's4', 's3', 's2'],
'ko_number': 'KO1', 'uniprot_id': 'uniprot16', "protein_name": 'your name fifteen'}
cls.src.collection.insert_many([mock_doc_0, mock_doc_1, mock_doc_2, mock_doc_3, mock_doc_4,mock_doc_5,mock_doc_6])
cls.src.collection.insert_many([dic_0,dic_1,dic_2,dic_3,dic_4,dic_5,dic_6,dic_7,dic_8,dic_9,dic_10,dic_11,dic_12,dic_13,dic_14,dic_15,dic_16])