def test_calculate_snfold_single_hard(self):
"""test the single claculation based on hard coded parameters"""
input_smiles = (
"Cc1ccc(cc1Nc2nccc(n2)c3cccnc3)NC(=O)c4ccc(cc4)CN5CCN(CC5)C" # imatinib
)
sa = ScaffoldFoldAssign(nfolds=5, secret="melloddy")
result_actual = sa.calculate_single(input_smiles)
result_expected = (
"O=C(Nc1cccc(Nc2nccc(-c3cccnc3)n2)c1)c1ccc(CN2CCNCC2)cc1",
"c1ccc(Nc2nccc(-c3cccnc3)n2)cc1",
2,
True,
None,
)
self.assertEqual(result_actual, result_expected)
def test_calculate_sn_fold_multiple(self):
infile = os.path.join(curDir, "input", "test_sn_fold_input.csv")
outfile = os.path.join(curDir, "output", "tmp", "sn_fold_output.csv")
output_columns = [
"murcko_smiles",
"sn_smiles",
"fold_id",
"success",
"error_message",
]
output_types = ["object", "object", "int", "bool", "object"]
sa = ScaffoldFoldAssign(
nfolds=self.config["scaffold_folding"]["nfolds"],
secret=self.keys["key"])
dt = DfTransformer(
sa,
input_columns={"canonical_smiles": "smiles"},
output_columns=output_columns,
output_types=output_types,
)
dt.process_file(infile, outfile)
result = filecmp.cmp(
os.path.join(curDir, "output", "test_sn_fold_output.csv"),
os.path.join(outfile),
shallow=False,
)
self.assertEqual(result, True)
def test_calculate_snfold_single_config(self):
"""test the single claculation based on config file conent"""
input_smiles = (
"Cc1ccc(cc1Nc2nccc(n2)c3cccnc3)NC(=O)c4ccc(cc4)CN5CCN(CC5)C" # imatinib
)
sa = ScaffoldFoldAssign(
nfolds=self.config["scaffold_folding"]["nfolds"],
secret=self.keys["key"])
result_actual = sa.calculate_single(input_smiles)
result_expected = (
"O=C(Nc1cccc(Nc2nccc(-c3cccnc3)n2)c1)c1ccc(CN2CCNCC2)cc1",
"c1ccc(Nc2nccc(-c3cccnc3)n2)cc1",
2,
True,
None,
)
self.assertEqual(result_actual, result_expected)
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 prepare(args):
"""
Prepare output directories and instantiate df tansformer object for scaffold based folding
Args:
args (dict): argparser arguments
Returns:
Tuple(Path, DfTransformer): Path to output directory and instatitaed DfTranfomer for sccaffold folding
"""
output_dir = make_dir(args, "results_tmp", "folding", args["non_interactive"])
mapping_table_dir = make_dir(args, "mapping_table", None, args["non_interactive"])
create_log_files(output_dir)
create_log_files(mapping_table_dir)
load_config(args)
load_key(args)
key = SecretDict.get_secrets()["key"]
method_params = ConfigDict.get_parameters()["scaffold_folding"]
sa = ScaffoldFoldAssign.from_param_dict(
secret=key, method_param_dict=method_params, verbosity=0
)
outcols = ["murcko_smiles", "sn_smiles", "fold_id", "success", "error_message"]
out_types = ["object", "object", "int", "bool", "object"]
dt = DfTransformer(
sa,
input_columns={"canonical_smiles": "smiles"},
output_columns=outcols,
output_types=out_types,
success_column="success",
nproc=args["number_cpu"],
verbosity=0,
)
return output_dir, mapping_table_dir, dt