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_standardizer_pipeline(self):
"""
Testing standardization of a larger set of smiles from Chembl using serial execution
Compared are resulting output files.
"""
infile = os.path.join(curDir, "input", "test_standardizer.csv")
outfile = os.path.join(curDir, "output", "sn_fold_output.OK.csv")
errfile = os.path.join(curDir, "output", "sn_fold_output.failed.csv")
outfile_tmp = os.path.join(curDir, "output", "tmp",
"sn_fold_output.OK.csv")
errfile_tmp = os.path.join(curDir, "output", "tmp",
"sn_fold_output.failed.csv")
st = Standardizer.from_param_dict(
method_param_dict=self.config["standardization"], verbosity=0)
outcols = ["canonical_smiles", "success", "error_message"]
out_types = ["object", "bool", "object"]
dt = DfTransformer(
st,
input_columns={"smiles": "smiles"},
output_columns=outcols,
output_types=out_types,
success_column="success",
nproc=2,
verbosity=0,
)
# build reference files, only run once
# dt.process_file(infile, outfile, errfile)
# run test with tmp files
dt.process_file(infile, outfile_tmp, errfile_tmp)
result = filecmp.cmp(outfile, outfile_tmp, shallow=False)
error = filecmp.cmp(errfile, errfile_tmp, shallow=False)
os.remove(outfile_tmp)
os.remove(errfile_tmp)
self.assertEqual(result, error, True)