def __init__(self, config_vep_version: float, file_vep_version: float,
config_grch_build: int, file_grch_build: int):
"""
Class to check the given VEP config argument and
the header of the VEP file match.
:param config_vep_version: float,
config argument for the used VEP version
:param file_vep_version: flaot,
config argument for the used GRCh build
"""
self.config_vep_version = config_vep_version
self.file_vep_version = file_vep_version
self.config_grch_build = config_grch_build
self.file_grch_build = file_grch_build
self.manager = CapiceManager()
self.export_vep_version = None
self.export_grch_build = None
self.check_match = []
self.unable_check = []
self.check_overrule = False
self.log = Logger().logger
self._check_all_present()
if self.check_overrule:
self._check_overrule()
self._check_version_match()
self._set_global_vep_version()
self._set_global_grch_build()
def __init__(self, name, usable, vep_version, grch_build):
self.log = Logger().logger
self.property_checker = PropertyCheckerLogger()
self.name = name
self.usable = usable
self.supported_vep_version = vep_version
self.supported_grch_build = grch_build
self.impute_data = self._get_impute_data()
def __init__(self):
self.log = Logger().logger
self.vep_annotators = []
self.location = os.path.join(get_project_root_dir(),
'src',
'main',
'python',
'resources',
'annotaters',
'vep')
self._load_vep_annotators()
def __init__(self, is_train: bool = False):
self.manager = CapiceManager()
self.log = Logger().logger
self.log.info('Preprocessor started.')
self.overrule = self.manager.overwrite_model
self.vep_version = self.manager.vep_version
self.grch_build = self.manager.grch_build
self.train = is_train
self.preprocessors = []
self.preprocessor = None
self._prepare_preprocessor()
def __init__(self, file_path):
self.log = Logger().logger
self.force = CapiceManager().force
self.now = CapiceManager().now
self.capice_filename = CapiceManager().output_filename
self.file_path = file_path
self.export_cols = [
Column.chr_pos_ref_alt.value, Column.GeneName.value,
Column.FeatureID.value, Column.Consequence.value,
Column.probabilities.value
]
def setUpClass(cls):
print('Setting up.')
cls.manager = CapiceManager()
cls.output_loc = os.path.join(get_project_root_dir(), '.test_output')
if not os.path.exists(cls.output_loc):
os.makedirs(cls.output_loc)
cls.manager.now = datetime.now()
cls.manager.log_loc = cls.output_loc
cls.manager.critical_logging_only = False
cls.manager.enable_logfile = True
cls.log = Logger().logger
def __init__(self, name, usable, vep_version, grch_build):
self.log = Logger().logger
self.property_checker = PropertyCheckerLogger()
self.name = name
self.usable = usable
self.supported_vep_version = vep_version
self.supported_grch_build = grch_build
self.annotation_features = CapiceManager().annotation_features
self.train = False
self.model = None
self.annotation_object = []
self.model_features = None
def __init__(self):
self.manager = CapiceManager()
self.vep_version = self.manager.vep_version
self.grch_build = self.manager.grch_build
self.log = Logger().logger
self.log.info('Imputer started.')
self.overrule = self.manager.overwrite_impute
self.modules = []
self.module = None
self._load_modules()
self._is_correct_datafile_present()
self._check_if_imputer_is_applied()
self.columns = []
self.annotation_columns_present = []
self.impute_values = {}
self.pre_dtypes = {}
self.dtypes = {}
def __init__(self, is_gzipped: bool, input_file_loc: str):
self.log = Logger().logger
self.manager = CapiceManager()
self.log.info('Starting to parse input file header.')
self.is_gzipped = is_gzipped
self.input_file_loc = input_file_loc
self.header = ''
self.header_build = False
self.header_version = False
self.header_present = False
self.file_type = None
self.skip_rows = 0
self._parse_header()
if self.header_present:
self.log.info(
"Input file header successfully identified: {}".format(
self.header.strip()))
self._get_file_type()
else:
self.log.warning(
'Unable to parse input file header, header not located. '
'Does the header start with "##"?')
def __init__(self, dataset: pd.DataFrame):
self.dataset = dataset
self.log = Logger().logger
def __init__(self):
self.sep = '\t'
self.log = Logger().logger
def __init__(self):
self.log = Logger().logger
self.manager = CapiceManager()
self.fasta_loc = self.manager.reference_genome
self.fasta = None
self._load_fasta()
def __init__(self, dataset: pd.DataFrame):
self.log = Logger().logger
self.manager = CapiceManager()
self.fasta_lookup = FastaLookupAnnotator()
self.manual_annotater = ManualAnnotator()
self.dataset = dataset
def __init__(self):
super().__init__()
self.log = Logger().logger
def __init__(self):
self.log = Logger().logger
def setUp(self):
print('Testing case:')
self.log = Logger()