def test_get_rmsd(self):
mm = MoleculeMatcher()
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir,
"t3.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir,
"t4.xyz")).pymatgen_mol
self.assertEqual('{0:7.3}'.format(mm.get_rmsd(mol1, mol2)), "0.00488")
def test_from_file(self):
if not babelio.babel_loaded:
raise SkipTest("OpenBabel not present. Skipping...")
adaptor = BabelMolAdaptor.from_file(os.path.join(test_dir,
"Ethane_e.pdb"),
"pdb")
mol = adaptor.pymatgen_mol
self.assertEqual(mol.formula, "H6 C2")
def test_group_molecules(self):
mm = MoleculeMatcher(tolerance=0.001)
filename_list = None
with open(os.path.join(test_dir, "mol_list.txt")) as f:
filename_list = [line.strip() for line in f.readlines()]
mol_list = [BabelMolAdaptor.from_file(os.path.join(test_dir, f)).pymatgen_mol\
for f in filename_list]
mol_groups = mm.group_molecules(mol_list)
filename_groups = [[filename_list[mol_list.index(m)] for m in g] for g \
in mol_groups]
grouped_text = None
with open(os.path.join(test_dir, "grouped_mol_list.txt")) as f:
grouped_text = f.read().strip()
self.assertEqual(str(filename_groups), grouped_text)
def test_group_molecules(self):
mm = MoleculeMatcher(tolerance=0.001)
filename_list = None
with open(os.path.join(test_dir, "mol_list.txt")) as f:
filename_list = [line.strip() for line in f.readlines()]
mol_list = [BabelMolAdaptor.from_file(os.path.join(test_dir, f)).pymatgen_mol\
for f in filename_list]
mol_groups = mm.group_molecules(mol_list)
filename_groups = [[filename_list[mol_list.index(m)] for m in g] for g \
in mol_groups]
grouped_text = None
with open(os.path.join(test_dir, "grouped_mol_list.txt")) as f:
grouped_text = f.read().strip()
self.assertEqual(str(filename_groups), grouped_text)
def read_mol(filename):
"""
Reads a molecule based on file extension. For example, anything ending in
a "xyz" is assumed to be a XYZ file. Supported formats include xyz,
gaussian input (gjf|g03|g09|com|inp), Gaussian output (.out|and
pymatgen's JSON serialized molecules. Using openbabel,
many more extensions are supported but requires openbabel to be installed.
Args:
filename:
A filename to read from.
Returns:
A Molecule object.
"""
fname = os.path.basename(filename)
if fnmatch(fname.lower(), "*.xyz*"):
return XYZ.from_file(filename).molecule
elif any([
fnmatch(fname.lower(), "*.{}*".format(r))
for r in ["gjf", "g03", "g09", "com", "inp"]
]):
return GaussianInput.from_file(filename).molecule
elif any([
fnmatch(fname.lower(), "*.{}*".format(r))
for r in ["out", "lis", "log"]
]):
return GaussianOutput(filename).final_structure
elif fnmatch(fname, "*.json*") or fnmatch(fname, "*.mson*"):
with zopen(filename) as f:
s = json.load(f, cls=PMGJSONDecoder)
if type(s) != Molecule:
raise IOError("File does not contain a valid serialized "
"molecule")
return s
else:
m = re.search("\.(pdb|mol|mdl|sdf|sd|ml2|sy2|mol2|cml|mrv)",
filename.lower())
if m:
return BabelMolAdaptor.from_file(filename, m.group(1)).pymatgen_mol
raise ValueError("Unrecognized file extension!")
def read_mol(filename):
"""
Reads a molecule based on file extension. For example, anything ending in
a "xyz" is assumed to be a XYZ file. Supported formats include xyz,
gaussian input (gjf|g03|g09|com|inp), Gaussian output (.out|and
pymatgen's JSON serialized molecules. Using openbabel,
many more extensions are supported but requires openbabel to be installed.
Args:
filename:
A filename to read from.
Returns:
A Molecule object.
"""
fname = os.path.basename(filename)
if fnmatch(fname.lower(), "*.xyz*"):
return XYZ.from_file(filename).molecule
elif any([fnmatch(fname.lower(), "*.{}*".format(r))
for r in ["gjf", "g03", "g09", "com", "inp"]]):
return GaussianInput.from_file(filename).molecule
elif any([fnmatch(fname.lower(), "*.{}*".format(r))
for r in ["out", "lis", "log"]]):
return GaussianOutput(filename).final_structure
elif fnmatch(fname, "*.json*") or fnmatch(fname, "*.mson*"):
with zopen(filename) as f:
s = json.load(f, cls=PMGJSONDecoder)
if type(s) != Molecule:
raise IOError("File does not contain a valid serialized "
"molecule")
return s
else:
m = re.search("\.(pdb|mol|mdl|sdf|sd|ml2|sy2|mol2|cml|mrv)",
filename.lower())
if m:
return BabelMolAdaptor.from_file(filename,
m.group(1)).pymatgen_mol
raise ValueError("Unrecognized file extension!")
def test_from_file(self):
adaptor = BabelMolAdaptor.from_file(
os.path.join(test_dir, "Ethane_e.pdb"), "pdb")
mol = adaptor.pymatgen_mol
self.assertEqual(mol.formula, "H6 C2")
def test_from_file(self):
adaptor = BabelMolAdaptor.from_file(
os.path.join(test_dir, "Ethane_e.pdb"), "pdb")
mol = adaptor.pymatgen_mol
self.assertEqual(mol.formula, "H6 C2")
def test_fit_with_mapper(self, mapper):
coords = [[0.000000, 0.000000, 0.000000],
[0.000000, 0.000000, 1.089000],
[1.026719, 0.000000, -0.363000],
[-0.513360, -0.889165, -0.363000],
[-0.513360, 0.889165, -0.363000]]
mol1 = Molecule(["C", "H", "H", "H", "H"], coords)
op = SymmOp.from_origin_axis_angle([0, 0, 0], [0.1, 0.2, 0.3], 60)
rotcoords = [op.operate(c) for c in coords]
mol2 = Molecule(["C", "H", "H", "H", "H"], rotcoords)
mm = MoleculeMatcher(mapper=mapper)
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir, "benzene1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir, "benzene2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir, "benzene1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir, "t2.xyz")).pymatgen_mol
self.assertFalse(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir, "c1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir, "c2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir, "t3.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir, "t4.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir, "j1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir, "j2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir, "ethene1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir, "ethene2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir, "toluene1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir, "toluene2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir, "cyclohexane1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir, "cyclohexane2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir, "oxygen1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir, "oxygen2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mm = MoleculeMatcher(tolerance=0.001, mapper=mapper)
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir, "t3.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir, "t4.xyz")).pymatgen_mol
self.assertFalse(mm.fit(mol1, mol2))
def test_get_rmsd(self):
mm = MoleculeMatcher()
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir, "t3.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir, "t4.xyz")).pymatgen_mol
self.assertEqual('{0:7.3}'.format(mm.get_rmsd(mol1, mol2)), "0.00488")
def fit_with_mapper(self, mapper):
coords = [[0.000000, 0.000000, 0.000000],
[0.000000, 0.000000, 1.089000],
[1.026719, 0.000000, -0.363000],
[-0.513360, -0.889165, -0.363000],
[-0.513360, 0.889165, -0.363000]]
mol1 = Molecule(["C", "H", "H", "H", "H"], coords)
op = SymmOp.from_origin_axis_angle([0, 0, 0], [0.1, 0.2, 0.3], 60)
rotcoords = [op.operate(c) for c in coords]
mol2 = Molecule(["C", "H", "H", "H", "H"], rotcoords)
mm = MoleculeMatcher(mapper=mapper)
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(
test_dir, "benzene1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(
test_dir, "benzene2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(
test_dir, "benzene1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir,
"t2.xyz")).pymatgen_mol
self.assertFalse(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir,
"c1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir,
"c2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir,
"t3.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir,
"t4.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir,
"j1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir,
"j2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(
test_dir, "ethene1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(
test_dir, "ethene2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(
test_dir, "toluene1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(
test_dir, "toluene2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(
os.path.join(test_dir, "cyclohexane1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(
os.path.join(test_dir, "cyclohexane2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mol1 = BabelMolAdaptor.from_file(os.path.join(
test_dir, "oxygen1.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(
test_dir, "oxygen2.xyz")).pymatgen_mol
self.assertTrue(mm.fit(mol1, mol2))
mm = MoleculeMatcher(tolerance=0.001, mapper=mapper)
mol1 = BabelMolAdaptor.from_file(os.path.join(test_dir,
"t3.xyz")).pymatgen_mol
mol2 = BabelMolAdaptor.from_file(os.path.join(test_dir,
"t4.xyz")).pymatgen_mol
self.assertFalse(mm.fit(mol1, mol2))
