def delete_database(args):
from elaspic import elaspic_database
db = elaspic_database.MyDatabase()
if db.engine == "sqlite":
os.remove(db.engine.database)
else:
db.delete_database_tables(drop_schema=True, drop_uniprot_sequence=True)
logger.info("Done!")
def load_data_to_database(args, tables):
if not args.url:
raise Exception("URL argument was not provided; don't know where to load the data from!")
from elaspic import elaspic_database
db = elaspic_database.MyDatabase()
for table_name in tables:
load_table_to_database(table_name, args.url, db.engine)
def __init__(
self,
uniprot_id,
mutations,
configurations=None,
run_type="5",
number_of_tries=[],
uniprot_domain_pair_ids=[],
):
"""Run the main function of the program and parse errors.
Parameters
----------
uniprot_domain_pair_ids : list of integers
List of uniprot_domain_pair_ids specifying which uniprot domain pairs to analyse.
run_type : str
1 / sequence: Calculate provean supporting set.
2 / model: Calculate all homology models.
3 / mutations: Calculate mutations using precalculated provean and models
(not working)
4 : Calculate mutations using precalculated provean (calculating mutations on the fly)
(not working)
5 : Calculate mutations, calculating provean and homology models as required.
"""
super().__init__(configurations)
if isinstance(run_type, (int, float)):
run_type = str(int(run_type))
self.uniprot_id = uniprot_id
self.mutations = self._split_mutations(mutations)
self.calculated_mutations = []
self.run_type = self._validate_run_type(run_type)
self.number_of_tries = number_of_tries
self.uniprot_domain_pair_ids = uniprot_domain_pair_ids
logger.info("=" * 80)
logger.info("## Input parameters")
logger.info("uniprot_id: {}".format(uniprot_id))
logger.info("mutations: {}".format(mutations))
logger.info("run_type: {}".format(run_type))
logger.info(
"uniprot_domain_pair_ids: {}".format(uniprot_domain_pair_ids))
logger.info("unique_temp_dir: {}".format(
conf.CONFIGS["unique_temp_dir"]))
logger.info("db_schema: {}".format(conf.CONFIGS.get("db_schema")))
logger.info("temp_dir: {temp_dir}".format(**conf.CONFIGS))
logger.info("=" * 80)
logger.info("")
# Switch to the root of the unique tmp directory
os.chdir(conf.CONFIGS["unique_temp_dir"])
# Initialise the sql database for accessing all information
self.db = elaspic_database.MyDatabase()
# Obtain all domains and interactions for a given uniprot
logger.info("Obtaining protein domain information...")
self.uniprot_domains = self.db.get_uniprot_domain(
self.uniprot_id, True)
self._update_path_to_data(self.uniprot_domains)
logger.info("Found {} domains.".format(len(self.uniprot_domains)))
# Mutations results
self.uniprot_mutations = []
def create_database(args):
from elaspic import elaspic_database
db = elaspic_database.MyDatabase()
db.create_database_tables(drop_schema=True)
logger.info("Done!")
if hasattr(pytest, "config"):
QUICK = pytest.config.getoption("--quick")
CONFIG_FILE = pytest.config.getoption("--config-file") or CONFIG_FILE
conf.read_configuration_file(CONFIG_FILE)
assert conf.CONFIGS["db_type"]
logger.debug("Running quick: {}".format(QUICK))
logger.debug("Config file: {}".format(CONFIG_FILE))
# Imports that require a parsed config file
import helper_fns # noqa
from elaspic import elaspic_database # noqa
db = elaspic_database.MyDatabase()
conf.CONFIGS["engine"] = db.get_engine()
conf.CONFIGS["engine"].execute("SET sql_mode = ''")
test_cases = []
def append_test_cases(df, num=3, num_mutations=3):
""".
Parameters
----------
df : DataFrame
Contains the following columns:
- `uniprot_id`
- `uniprot_sequence`