def prepare(args: dict, overwriting: bool):
"""Setup run by creating directories and log files.
Args:
args (dict): argparser arguments
overwriting (bool): overwriting flag
Returns:
Tuple(DataFrame, DataFrame): Path to output and mapping_table subdirectories.
"""
output_dir = make_dir(args, "results_tmp", "descriptors", overwriting)
create_log_files(output_dir)
load_config(args)
load_key(args)
method_params = ConfigDict.get_parameters()["fingerprint"]
key = SecretDict.get_secrets()["key"]
dc = DescriptorCalculator.from_param_dict(secret=key,
method_param_dict=method_params,
verbosity=0)
outcols = ["fp_feat", "fp_val", "success", "error_message"]
out_types = ["object", "object", "bool", "object"]
dt = DfTransformer(
dc,
input_columns={"canonical_smiles": "smiles"},
output_columns=outcols,
output_types=out_types,
success_column="success",
nproc=args["number_cpu"],
verbosity=0,
)
return output_dir, dt
def test_calculate_desc_multiple(self):
tempFilePath = curDir / "output/tmp/ecfp_feat_multiple.csv"
df_smiles = read_csv(curDir / "input/chembl/chembl_23_example_T2.csv",
nrows=10)
dc = DescriptorCalculator.from_param_dict(
secret=self.keys["key"],
method_param_dict=self.config["fingerprint"],
verbosity=0,
)
outcols = ["fp_feat", "fp_val", "success", "error_message"]
out_types = ["object", "object", "bool", "object"]
dt = DfTransformer(
dc,
input_columns={"smiles": "smiles"},
output_columns=outcols,
output_types=out_types,
success_column="success",
nproc=1,
verbosity=0,
)
# df_ref = dt.process_dataframe(df_smiles)[0] #calculate reference fingperprints
# df_ref.to_csv("unit_test/output/test_calculate_desc_y2.csv", index=False) #write reference fingperprints
df_test = dt.process_dataframe(df_smiles)[0]
df_test.to_csv(tempFilePath, index=False) # write test fingperprints
result = filecmp.cmp("unit_test/output/test_calculate_desc_y2.csv",
tempFilePath,
shallow=False)
self.assertEqual(result, True)
def test_scramble_desc_multiple_key(self):
"""test if scrambling is depending on the input key"""
newKey = "melloddy_2"
tempFilePathFeat = curDir / "output/tmp/ecfp_feat_scrambled_new_key.csv"
df_smiles = read_csv(curDir / "input/chembl/chembl_23_example_T2.csv",
nrows=10)
dc = DescriptorCalculator.from_param_dict(
secret=newKey,
method_param_dict=self.config["fingerprint"],
verbosity=0)
outcols = ["fp_feat", "fp_val", "success", "error_message"]
out_types = ["object", "object", "bool", "object"]
dt = DfTransformer(
dc,
input_columns={"smiles": "smiles"},
output_columns=outcols,
output_types=out_types,
success_column="success",
nproc=1,
verbosity=0,
)
df_test = dt.process_dataframe(df_smiles)[0]
df_test.to_csv(tempFilePathFeat,
index=False) # write test fingperprints
result = filecmp.cmp(
"unit_test/output/test_calculate_desc_y2.csv",
tempFilePathFeat,
shallow=False,
)
self.assertEqual(result, False)
def prepare(args):
overwriting = True
load_config(args)
load_key(args)
output_dir = make_dir(args, "reference_set", None, overwriting)
key = SecretDict.get_secrets()["key"]
method_params_standardizer = ConfigDict.get_parameters()["standardization"]
st = Standardizer.from_param_dict(
method_param_dict=method_params_standardizer, verbosity=0)
outcols_st = ["canonical_smiles", "success", "error_message"]
out_types_st = ["object", "bool", "object"]
dt_standarizer = DfTransformer(
st,
input_columns={"smiles": "smiles"},
output_columns=outcols_st,
output_types=out_types_st,
success_column="success",
nproc=1,
verbosity=0,
)
method_params_folding = ConfigDict.get_parameters()["scaffold_folding"]
sa = ScaffoldFoldAssign.from_param_dict(
secret=key, method_param_dict=method_params_folding, verbosity=0)
outcols_sa = [
"murcko_smiles", "sn_smiles", "fold_id", "success", "error_message"
]
out_types_sa = ["object", "object", "int", "bool", "object"]
dt_fold = DfTransformer(
sa,
input_columns={"canonical_smiles": "smiles"},
output_columns=outcols_sa,
output_types=out_types_sa,
success_column="success",
nproc=1,
verbosity=0,
)
method_params_descriptor = ConfigDict.get_parameters()["fingerprint"]
dc = DescriptorCalculator.from_param_dict(
secret=key, method_param_dict=method_params_descriptor, verbosity=0)
outcols_dc = ["fp_feat", "fp_val", "success", "error_message"]
out_types_dc = ["object", "object", "bool", "object"]
dt_descriptor = DfTransformer(
dc,
input_columns={"canonical_smiles": "smiles"},
output_columns=outcols_dc,
output_types=out_types_dc,
success_column="success",
nproc=1,
verbosity=0,
)
return output_dir, dt_standarizer, dt_fold, dt_descriptor
def test_calculate_desc_val_single(self):
tempFilePath = curDir / "output/tmp/ecfp_val.npy"
dc = DescriptorCalculator.from_param_dict(
secret=self.keys["key"],
method_param_dict=self.config["fingerprint"],
verbosity=0,
)
fp = dc.calculate_single(
"Cc1ccc(S(=O)(=O)Nc2ccc(-c3nc4cc(NS(=O)(=O)c5ccc(C)cc5)ccc4[nH]3)cc2)cc1"
)
fp_val = fp[1]
# np.save("unit_test/output/test_calculate_desc_val.npy",fp_val) #write reference fingperprints
np.save(tempFilePath, fp_val) # write test fingperprints
result = filecmp.cmp("unit_test/output/test_calculate_desc_val.npy",
tempFilePath,
shallow=False)
self.assertEqual(result, True)