def test_cut_rgroup_filename(self):
filename = create_test_filename(self, "rgroups.txt")
with open(filename, "w") as f:
f.write("*O\n" "*N\n")
reader, records = fragment(SPACE_SMI, "--cut-rgroup-file", filename)
record = records[0]
self.assertEqual(record.normalized_smiles, "Oc1ccccc1O")
self.assertEqual(len(record.fragments), 3)
variable_smiles_set = set(frag.variable_smiles
for frag in record.fragments)
self.assertEqual(variable_smiles_set,
set(("*O", "*c1ccccc1O", "*c1ccccc1*")))
record = records[1]
self.assertEqual(record.normalized_smiles, "Cc1ccccc1N")
self.assertEqual(len(record.fragments), 2)
variable_smiles_set = set(frag.variable_smiles
for frag in record.fragments)
self.assertEqual(variable_smiles_set, set(("*N", "*c1ccccc1C")))
record = records[2]
self.assertEqual(record.normalized_smiles, "Cc1ccc(S)cc1N")
self.assertEqual(len(record.fragments), 2)
variable_smiles_set = set(frag.variable_smiles
for frag in record.fragments)
self.assertEqual(variable_smiles_set, set(("*N", "*c1cc(S)ccc1C")))
def test_different_whitespace(self):
filename = support.create_test_filename(self, "rgroups.txt")
with open(filename, "w") as outfile:
outfile.write("*Cl\tchlorine\n" "*Br bromine\n" "*F and more\n")
stdout, stderr = run(["rgroup2smarts", filename])
self.assertEqual(stderr, "")
self.assertEqual(stdout, "*-!@[$([ClH0v1]),$([BrH0v1]),$([FH0v1])]\n")
def test_output_gz(self):
filename = create_test_filename(self, "transform.out.gz")
transform("--smiles", "c1cccnc1O", "--output", filename)
with gzip.open(filename) as infile:
table = parse_table(infile.read().decode("ascii"))
self.assertEqual(len(table), 4)
self.assertIn("MP_count", table[0])
self.assertIn("MW_count", table[0])
def test_file_does_not_exist(self):
filename = support.create_test_filename(self, "rgroups.dat")
stdout, stderr = run_failure(["rgroup2smarts", filename])
stderr = fix_stderr(self, stderr, filename)
self.assertEqual(
stderr,
"Cannot open input file: [Errno 2] No such file or directory: frags.smi\n"
)
def test_empty_file_not_allowed(self):
filename = support.create_test_filename(self, "rgroups.dat")
with open(filename, "w") as f:
f.close()
stdout, stderr = run_failure(["rgroup2smarts", filename])
stderr = fix_stderr(self, stderr, filename)
self.assertEqual(
stderr,
"Cannot make a SMARTS: no SMILES strings found in frags.smi\n")
def test_blank_line_not_allowed(self):
filename = support.create_test_filename(self, "rgroups.dat")
with open(filename, "w") as f:
f.write("*C\n\n*N\n")
stdout, stderr = run_failure(["rgroup2smarts", filename])
stderr = fix_stderr(self, stderr, filename)
self.assertEqual(
stderr,
"Cannot parse input file: no SMILES found at frags.smi, line 2\n")
def test_initial_whitespace_not_allowed(self):
filename = support.create_test_filename(self, "rgroups.dat")
with open(filename, "w") as f:
f.write("*C\n *N\n")
stdout, stderr = run_failure(["rgroup2smarts", filename])
stderr = fix_stderr(self, stderr, filename)
self.assertEqual(
stderr,
"Cannot parse input file: expected SMILES at start of line at frags.smi, line 2\n"
)
def _test_merged(self, check):
filename = support.create_test_filename(self, "groups.txt")
for inputs, output in merged_test_cases:
with open(filename, "w") as f:
for smiles in inputs:
f.write(smiles + "\n")
args = ["rgroup2smarts", filename]
if check:
args.append("--check")
stdout, stderr = run(args)
self.assertEqual(stdout, output + "\n", repr(inputs))
def test_bad_smiles(self):
filename = support.create_test_filename(self, "rgroups.dat")
args = ["rgroup2smarts", filename]
for smiles_list, errmsg in _bad_smiles_inputs:
with open(filename, "w") as outfile:
for smiles in smiles_list.split():
outfile.write(smiles + "\n")
stdout, stderr = run_failure(args)
stderr = fix_stderr(self, stderr, filename)
errmsg = errmsg.replace("--cut-rgroup SMILES #",
"frags.smi, line ")
self.assertEqual(stderr, errmsg)
def _test_explain(self, check):
filename = support.create_test_filename(self, "fra\tgs.smi")
with open(filename, "w") as f:
f.write("c1ccccc1*\nO*\n")
args = ["rgroup2smarts", "--explain", filename]
if check:
args.append("--check")
stdout, stderr = run(args, True)
self.assertEqual(
stdout,
"*-!@[$([cH0v4]1:[cHv4]:[cHv4]:[cHv4]:[cHv4]:[cHv4]:1),$([OHv2])]\n"
)
return fix_stderr(self, stderr, filename)
def _test_single(self, check):
filename = support.create_test_filename(self, "rgroups.txt")
for inputs, _ in merged_test_cases:
expected_output_lines = []
with open(filename, "w") as f:
for smiles in inputs:
f.write(smiles + "\n")
output = simple_test_cases[smiles]
expected_output_lines.append(output + "\n")
expected_output = "".join(expected_output_lines)
args = ["rgroup2smarts", "--single", filename]
if check:
args.append("--check")
stdout, stderr = run(args)
self.assertEqual(stdout, expected_output, repr(inputs))
def test_save_details(self):
prefix = create_test_filename(self, "predict_details")
result = predict("--smiles", "c1cccnc1O", "--reference", "Clc1ccccn1",
"--property", "MW", "--save-details", "--prefix",
prefix)
self.assertEqual(result, ("-18.5", None))
rules_table, pairs_table = read_details(prefix)
self.assertEqual(rules_table.get_column("from_smiles"),
["[*:1]Cl", "[*:1]Cl"])
self.assertEqual(rules_table.get_column("to_smiles"),
["[*:1]O", "[*:1]O"])
self.assertEqual(pairs_table.get_column("radius"), ["0", "1"])
self.assertEqual(pairs_table.get_column("lhs_public_id"),
["2-chlorophenol", "2-chlorophenol"])
self.assertEqual(pairs_table.get_column("rhs_public_id"),
["catechol", "catechol"])
def test_cut_rgroup_filename(self):
filename = create_test_filename(self, "rgroups.txt")
with open(filename, "w") as f:
f.write("*O\n" "*N\n")
result = smifrag("Cc1cc(O)ccc1N", "--cut-rgroup-file", filename)
self.assertEqual(
result,
[[
'1', 'N', '1', '1', '*O', '0', '8', '1', '*c1ccc(N)c(C)c1',
'Cc1ccccc1N'
],
['1', 'N', '8', '1', '*c1ccc(N)c(C)c1', '0', '1', '1', '*O', 'O'],
[
'2', 'N', '7', '12', '*c1ccc(*)c(C)c1', '10', '2', '12',
'*N.*O', '-'
],
[
'1', 'N', '1', '1', '*N', '0', '8', '1', '*c1ccc(O)cc1C',
'Cc1cccc(O)c1'
],
['1', 'N', '8', '1', '*c1ccc(O)cc1C', '0', '1', '1', '*N', 'N']])
def _get_options(self, *args):
mmpdb_filename = create_test_filename(self, "default.mmpdb")
index(mmpdb_filename, *args)
db = dbutils.open_database(mmpdb_filename)
dataset = db.get_dataset()
return dataset, json.loads(dataset.index_options_str)
def test_missing_rgroup_filename(self):
filename = create_test_filename(self, "rgroups.txt")
stderr = smifrag_fail("Nc1ccccc1O", "--cut-rgroup-file", filename)
self.assertIn("Cannot use --cut-rgroup-file", stderr)
self.assertIn(repr(filename), stderr)
self.assertIn("No such file or directory", stderr)