def setUpClass(cls):
print('Setting up.')
manager, output_loc = set_up_manager_and_loc()
cls.main = set_up_main()
cls.main.infile = os.path.join(get_project_root_dir(),
'CAPICE_example',
'CAPICE_input.tsv.gz')
manager.overwrite_model = 'CAPICE using XGBoost 0.72.1,' \
' CADD 1.4 and genome build 37.'
def setUpClass(cls):
print('Setting up.')
cls.manager, output_loc = set_up_manager_and_loc()
cls.main = set_up_main()
cls.main.infile = os.path.join(get_project_root_dir(),
'CAPICE_example', 'CAPICE_input.tsv.gz')
cls.vep_version = 104.0
cls.grch_build = 37
cls.impute_overwrite = 'VEP104'
cls.model_overwrite = 'CAPICE using XGBoost 0.72.1,' \
' CADD 1.4 and genome build 37.'
def setUpClass(cls):
print('Setting up.')
cls.manager, cls.output_dir = set_up_manager_and_loc()
cls.manager.overwrite_impute = 'CADD 1.4, GRCh build 37'
train_file = os.path.join(get_project_root_dir(), 'CAPICE_example', 'train_dataset.tsv.gz')
ConfigReader().parse()
cls.main = Train(__program__=__program__,
__author__=__author__,
__version__=__version__,
input_loc=train_file,
output_loc=cls.output_dir)
def setUpClass(cls):
print('Setting up.')
manager, cls.output_loc = set_up_manager_and_loc()
cls.exporter = Exporter(file_path=cls.output_loc)
cls.prediction_output_dataframe = pd.DataFrame({
Column.chr_pos_ref_alt.value: ['1_100_A_C', '2_200_T_G'],
Column.GeneName.value: ['foo', 'bar'],
Column.FeatureID.value: ['TRANS_01', 'TRANS_02'],
Column.Consequence.value: ['Synonymous', 'Frame-shift'],
Column.probabilities.value: [0.01, 0.998]
})
cls.export_dataset = pd.DataFrame({
'chr': [1, 2],
'pos': [100, 200],
'ref': ['A', 'A'],
'alt': ['C', 'G'],
'feature_1': [0.001, 0.2],
'feature_2': [0.02, 5.5]
})
def setUpClass(cls):
print('Setting up')
cls.manager, output = set_up_manager_and_loc()
cls.vep_build = False
cls.grch_build = False
def setUpClass(cls):
print('Setting up.')
set_up_manager_and_loc()
cls.train_checker = TrainChecker()
def setUpClass(cls) -> None:
set_up_manager_and_loc()
# Creating a dataframe of data that is tailored to test the
# return N append function within lookup.py.
dataset = pd.DataFrame({
'Chr': {
0: '1',
1: '1'
},
'Pos': {
0: 1,
1: 10042538
},
'Ref': {
0: 'C',
1: 'C'
},
'Alt': {
0: 'T',
1: 'T'
},
'Consequence': {
0: 'missense_variant',
1: 'downstream_gene_variant'
},
'GeneName': {
0: 'NMNAT1',
1: 'NMNAT1'
},
'SourceID': {
0: 'HGNC',
1: 'HGNC'
},
'HGNC_ID': {
0: '17877',
1: '17877'
},
'FeatureID': {
0: 'ENST00000377205',
1: 'ENST00000403197'
},
'cDNA_position': {
0: '763/3781',
1: np.nan
},
'CDS_position': {
0: '619/840',
1: np.nan
},
'Protein_position': {
0: '207/279',
1: np.nan
},
'Amino_acids': {
0: 'R/W',
1: np.nan
},
'STRAND': {
0: 1,
1: 1
},
'SIFT': {
0: 'deleterious(0.04)',
1: np.nan
},
'PolyPhen': {
0: 'benign(0.08)',
1: np.nan
},
'DOMAINS': {
0:
'PANTHER:PTHR12039&'
'PANTHER:PTHR12039:SF3&'
'TIGRFAM:TIGR00482&'
'Gene3D:3.40.50.620&'
'Pfam:PF01467&'
'Superfamily:SSF52374',
1:
np.nan
},
'MOTIF_NAME': {
0: np.nan,
1: np.nan
},
'HIGH_INF_POS': {
0: np.nan,
1: np.nan
},
'MOTIF_SCORE_CHANGE': {
0: np.nan,
1: np.nan
},
'Exon': {
0: '5/5',
1: np.nan
},
'Intron': {
0: np.nan,
1: np.nan
}
})
cls.annotator = Annotator(dataset)
def setUpClass(cls) -> None:
print('Setting up.')
set_up_manager_and_loc()