def test_init(self):
mol = Molecule(["C", "H", "H", "H", "H"], self.coords)
gau = GaussianInput(mol,
charge=1,
route_parameters={
"SP": "",
"SCF": "Tight"
})
self.assertEqual(gau.spin_multiplicity, 2)
mol = Molecule(["C", "H", "H", "H", "H"], self.coords, charge=-1)
gau = GaussianInput(mol, route_parameters={"SP": "", "SCF": "Tight"})
self.assertEqual(gau.spin_multiplicity, 2)
self.assertRaises(ValueError, GaussianInput, mol, spin_multiplicity=1)
def setUpClass(cls):
# head molecule
cls.peo_head = Molecule.from_file(
os.path.join(test_dir, "peo_head.xyz"))
charges = [
-0.1187, 0.0861, 0.0861, 0.0861, -0.2792, -0.0326, 0.0861, 0.0861
]
cls.peo_head.add_site_property("charge", charges)
s_head = 0
s_tail = 5
# chain molecule
cls.peo_bulk = Molecule.from_file(
os.path.join(test_dir, "peo_bulk.xyz"))
charges = [-0.0326, 0.0861, 0.0861, -0.2792, -0.0326, 0.0861, 0.0861]
cls.peo_bulk.add_site_property("charge", charges)
head = 0
tail = 4
# terminal molecule
cls.peo_tail = Molecule.from_file(
os.path.join(test_dir, "peo_tail.xyz"))
charges = [
-0.0326, 0.0861, 0.0861, -0.2792, -0.1187, 0.0861, 0.0861, 0.0861
]
cls.peo_tail.add_site_property("charge", charges)
e_head = 0
e_tail = 4
cls.n_units = 25
link_distance = 1.5075
# create the polymer
cls.peo_polymer = Polymer(cls.peo_head, s_head, s_tail, cls.peo_bulk,
head, tail, cls.peo_tail, e_head, e_tail,
cls.n_units, link_distance)
# linear chain
cls.peo_polymer_linear = Polymer(cls.peo_head,
s_head,
s_tail,
cls.peo_bulk,
head,
tail,
cls.peo_tail,
e_head,
e_tail,
cls.n_units,
link_distance,
linear_chain=True)
def convert_obatoms_to_molecule(self,
atoms,
residue_name=None,
site_property="ff_map"):
"""
Convert list of openbabel atoms to MOlecule.
Args:
atoms ([OBAtom]): list of OBAtom objects
residue_name (str): the key in self.map_residue_to_mol. Usec to
restore the site properties in the final packed molecule.
site_property (str): the site property to be restored.
Returns:
Molecule object
"""
restore_site_props = True if residue_name is not None else False
if restore_site_props and not hasattr(self, "map_residue_to_mol"):
self._set_residue_map()
coords = []
zs = []
for atm in atoms:
coords.append(list(atm.coords))
zs.append(atm.atomicnum)
mol = Molecule(zs, coords)
if restore_site_props:
props = []
ref = self.map_residue_to_mol[residue_name].copy()
# sanity check
assert len(mol) == len(ref)
assert ref.formula == mol.formula
# the packed molecules have the atoms in the same order..sigh!
for i, site in enumerate(mol):
assert site.specie.symbol == ref[i].specie.symbol
props.append(getattr(ref[i], site_property))
mol.add_site_property(site_property, props)
return mol
def test_get_atoms_from_molecule(self):
m = Molecule.from_file(os.path.join(test_dir, "acetylene.xyz"))
atoms = aio.AseAtomsAdaptor.get_atoms(m)
ase_composition = Composition(atoms.get_chemical_formula())
self.assertEqual(ase_composition, m.composition)
self.assertTrue(atoms.cell is None or not atoms.cell.any())
self.assertTrue(atoms.get_pbc() is None or not atoms.get_pbc().any())
def fit(self, p: Molecule):
"""Order, rotate and transform all of the matched `p` molecule
according to the given `threshold`.
Args:
p: a `Molecule` object what will be matched with the target one.
Returns:
Array of the possible matches where the elements are:
p_prime: Rotated and translated of the `p` `Molecule` object
rmsd: Root-mean-square-deviation between `p_prime` and the `target`
"""
out = []
for inds in self.permutations(p):
p_prime = p.copy()
p_prime._sites = [p_prime[i] for i in inds]
U, V, rmsd = super().match(p_prime)
# Rotate and translate matrix `p` onto the target molecule.
# P' = P * U + V
for site in p_prime:
site.coords = np.dot(site.coords, U) + V
out.append((p_prime, rmsd))
return out
def import_Structure(type, config): if type == 'xyz': molecule = Molecule.from_file(config['filename']) lattice = Lattice([config["lattice_parameters"]["vectors"]['i'],config["lattice_parameters"]["vectors"]["j"],config["lattice_parameters"]["vectors"]["k"]]) return Structure(lattice, generate_atom_list(molecule.species), generate_coordinate_list(molecule)) else: return None
def run_task(self, fw_spec):
molecules = self["constituent_molecules"]
mols_number = self["mols_number"]
input_filename = self["input_filename"]
forcefield = self["forcefield"]
topologies = self["topologies"]
user_settings = self.get("user_settings", {})
data_filename = self.get("data_filename",
user_settings.get("data_file", "lammps.data"))
final_molecule = self["final_molecule"]
# if the final molecule was generated using packmol
if fw_spec.get("packed_mol", None):
final_molecule = fw_spec["packed_mol"]
elif isinstance(final_molecule, six.string_types):
final_molecule = Molecule.from_file(final_molecule)
#molecules, mols_number, final_molecule
lammps_ff_data = LammpsData.from_ff_and_topologies(
forcefield, topologies, self["box_size"])
lammps_input_set = LammpsInputSet.from_file(
"ff-inputset",
self["input_file"],
user_settings=user_settings,
lammps_data=lammps_ff_data,
data_filename=data_filename,
is_forcefield=True)
lammps_input_set.write_input(input_filename, data_filename)
def setUp(self):
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]]
self.mol = Molecule(["C", "H", "H", "H", "H"], coords)
def setUp(self):
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],
]
self.coords = coords
mol = Molecule(["C", "H", "H", "H", "H"], coords)
self.cellin = FiestaInput(
mol,
correlation_grid={"dE_grid": u"0.500", "n_grid": u"14"},
Exc_DFT_option={"rdVxcpsi": u"1"},
COHSEX_options={
"eigMethod": u"C",
"mix_cohsex": u"0.500",
"nc_cohsex": u"0",
"nit_cohsex": u"0",
"nv_cohsex": u"0",
"resMethod": u"V",
"scf_cohsex_wf": u"0",
},
GW_options={"nc_corr": u"10", "nit_gw": u"3", "nv_corr": u"10"},
BSE_TDDFT_options={
"do_bse": u"1",
"do_tddft": u"0",
"nc_bse": u"382",
"nit_bse": u"50",
"npsi_bse": u"1",
"nv_bse": u"21",
},
)
def test_simple_molecule_graph(self):
mol = Molecule(["C", "H", "O"], [[0, 0, 0], [1, 0, 0], [2, 0, 0]])
graph = SimpleMolGraph().convert(mol)
self.assertListEqual(to_list(graph["atom"]), [6, 1, 8])
self.assertTrue(np.allclose(graph["bond"], [1, 2, 1, 1, 2, 1]))
self.assertListEqual(to_list(graph["index1"]), [0, 0, 1, 1, 2, 2])
self.assertListEqual(to_list(graph["index2"]), [1, 2, 0, 2, 0, 1])
def get_mol_object(self, id=0):
"""
make the pymatgen molecule object
Args:
id: the index of molecules in the given site
Returns:
a molecule object
"""
coord0 = self.mol.cart_coords.dot(self.orientation.matrix.T) #
# Obtain the center in absolute coords
if id <= len(self.wp.generators):
op = self.wp.generators[id]
center_relative = op.operate(self.position)
center_relative -= np.floor(center_relative)
#print(center_relative)
center_absolute = np.dot(center_relative, self.lattice.matrix)
# Rotate the molecule (Euclidean metric)
op_m = self.wp.generators_m[id]
rot = op_m.affine_matrix[0:3][:, 0:3].T
tau = op_m.affine_matrix[0:3][:, 3]
tmp = np.dot(coord0, rot) + tau
# Add absolute center to molecule
tmp += center_absolute
return Molecule(self.symbols, tmp)
else:
raise ValueError("id is greater than the number of molecules")
def setUp(self):
pymagen_sodium = Molecule(species=['Na'],
coords=[[999.0, 999.0, 999.0]],
charge=1)
# noinspection PyProtectedMember
sodium_obmol = BabelMolAdaptor(pymagen_sodium)._obmol
acetoxyq_anion_qcout = QcOutput(
os.path.join(test_dir, "acetoxyq_anion.out"))
pymatgen_acetoxyq = acetoxyq_anion_qcout.data[0]["molecules"][-1]
acetoxyq_obmol = BabelMolAdaptor(pymatgen_acetoxyq)._obmol
tfsi_qcout = QcOutput(os.path.join(test_dir, "tfsi.qcout"))
pymatgen_tfsi = tfsi_qcout.data[0]["molecules"][-1]
# noinspection PyProtectedMember
tfsi_obmol = BabelMolAdaptor(pymatgen_tfsi)._obmol
fragments = [sodium_obmol, tfsi_obmol]
nums_fragments = [1, 1]
self.acetoxyq_natfsi_placer = IonPlacer(acetoxyq_obmol, fragments,
nums_fragments, None)
rad_util = AtomicRadiusUtils(covalent_radius_scale=3.0,
metal_radius_scale=1.5)
mol_radius = rad_util.get_radius(acetoxyq_obmol)
cation_radius = rad_util.get_radius(sodium_obmol)
anion_radius = rad_util.get_radius(tfsi_obmol)
mol_coords = IonPlacer.normalize_molecule(acetoxyq_obmol)
fragments_atom_radius = [cation_radius, anion_radius]
nums_fragments = [1, 1]
self.detector = ContactDetector(mol_coords, mol_radius,
fragments_atom_radius, nums_fragments)
def make_a_mol_entry():
r"""
Make a symmetric (fake) molecule with ring.
O(0)
/ \
/ \
H(1)--C(2)--C(3)--H(4)
| |
H(5) H(6)
"""
species = ["O", "H", "C", "C", "H", "H", "H"]
coords = [
[0.0, 1.0, 0.0],
[-1.5, 0.0, 0.0],
[-0.5, 0.0, 0.0],
[0.5, 0.0, 0.0],
[1.5, 0.0, 0.0],
[-0.5, -1.0, 0.0],
[0.5, -1.0, 0.0],
]
m = Molecule(species, coords)
entry = MoleculeEntry(m, energy=0.0)
return entry
def random_purturbation_index():
if is_pbc():
struct=readstructure(crystal=True,molecule=False)
natom=len(struct)
d=np.zeros(2,dtype=int)
while d[0]==d[1]:
d=np.random.randint(0,natom,2)
coord=struct.frac_coords
coord[[d[0], d[1]], :] = coord[[d[1], d[0]], :]
tmp_struct=Structure(struct.lattice,struct.species,coord)
fname='swap_'+str(d[0]+1)+'_'+str(d[1]+1)+'.vasp'
proc_str="Saving data to "+ fname +" File ..."
procs(proc_str,0,sp='-->>')
tmp_struct.to(filename=fname,fmt='poscar')
else:
struct=readstructure(crystal=False,molecule=True)
# print(struct)
coord=struct.cart_coords
natom=len(struct)
d=np.zeros(2,dtype=int)
while d[0]==d[1]:
d=np.random.randint(0,natom,2)
coord[[d[0], d[1]], :] = coord[[d[1], d[0]], :]
tmp_struct=Molecule(struct.species,coord)
fname='swap_'+str(d[0]+1)+'_'+str(d[1]+1)+'.xyz'
proc_str="Saving data to "+ fname +" File ..."
procs(proc_str,0,sp='-->>')
tmp_struct.to(filename=fname,fmt='xyz')
return
def generate_shell(structs,fnames,center_atom,radius,shell=None,vacuum=15):
for struct,fname in zip(structs,fnames):
center_coord=struct[center_atom].coords
if shell is None:
sites=struct.get_neighbors_in_shell(center_coord,0,radius)
file_name="sphere_"+fname+".vasp"
else:
sites=struct.get_neighbors_in_shell(center_coord,radius,shell)
file_name="shell_"+fname+".vasp"
coords=[site[0].coords for site in sites]
species=[site[0].specie for site in sites]
mol=Molecule(coords=coords,species=species)
max_dist=np.max(mol.distance_matrix)
a=b=c=max_dist+vacuum
box_struct=mol.get_boxed_structure(a,b,c)
box_struct.to(filename=file_name,fmt='poscar')
def run_task(self, fw_spec):
molecules = self["constituent_molecules"]
mols_number = self["mols_number"]
input_filename = self["input_filename"]
forcefield = self["forcefield"]
topologies = self["topologies"]
user_settings = self.get("user_settings", {})
data_filename = self.get("data_filename", user_settings.get("data_file", "lammps.data"))
final_molecule = self["final_molecule"]
# if the final molecule was generated using packmol
if fw_spec.get("packed_mol", None):
final_molecule = fw_spec["packed_mol"]
elif isinstance(final_molecule, six.string_types):
final_molecule = Molecule.from_file(final_molecule)
#molecules, mols_number, final_molecule
lammps_ff_data = LammpsData.from_ff_and_topologies(forcefield, topologies, self["box_size"])
lammps_input_set = LammpsInputSet.from_file("ff-inputset", self["input_file"],
user_settings=user_settings,
lammps_data=lammps_ff_data,
data_filename=data_filename,
is_forcefield=True)
lammps_input_set.write_input(input_filename, data_filename)
def test__str__(self):
species = ["C", "O"]
coords = [[-9.5782000000, 0.6241500000, 0.0000000000],
[-7.5827400000, 0.5127000000, -0.0000000000]]
molecule = Molecule(species=species, coords=coords)
rem = OrderedDict({
"jobtype": "opt",
"method": "wB97M-V",
"basis": "def2-QZVPPD",
"max_scf_cycles": "300",
"gen_scfman": "true"
})
str_test = QCInput(molecule=molecule, rem=rem).__str__()
str_actual = """$molecule
0 1
C -9.5782000000 0.6241500000 0.0000000000
O -7.5827400000 0.5127000000 -0.0000000000
$end
$rem
jobtype = opt
method = wB97M-V
basis = def2-QZVPPD
max_scf_cycles = 300
gen_scfman = true
$end
"""
self.assertEqual(str_actual, str_test)
def parse_symmetry(pos):
mol = Molecule(['C'] * len(pos), pos)
try:
symbol = PointGroupAnalyzer(mol, tolerance=0.1).sch_symbol
except:
symbol = 'N/A'
return symbol
def test_init(self):
inner_charge = np.random.rand(10) - 0.5
outer_charge = np.random.rand(10) - 0.5
inner_velo = np.random.rand(10, 3) - 0.5
outer_velo = np.random.rand(10, 3) - 0.5
m = Molecule(["H"] * 10,
np.random.rand(10, 3) * 100,
site_properties={
"ff_map": ["D"] * 10,
"charge": inner_charge,
"velocities": inner_velo
})
# q and v from site properties, while type from species_string
topo = Topology(sites=m)
self.assertListEqual(topo.type_by_sites, ["H"] * 10)
np.testing.assert_array_equal(topo.charges, inner_charge)
np.testing.assert_array_equal(topo.velocities, inner_velo)
# q and v from overriding, while type from site property
topo_override = Topology(sites=m,
ff_label="ff_map",
charges=outer_charge,
velocities=outer_velo)
self.assertListEqual(topo_override.type_by_sites, ["D"] * 10)
np.testing.assert_array_equal(topo_override.charges, outer_charge)
np.testing.assert_array_equal(topo_override.velocities, outer_velo)
# test using a list of sites instead of SiteCollection
topo_from_list = Topology(sites=m.sites)
self.assertListEqual(topo_from_list.type_by_sites, topo.type_by_sites)
np.testing.assert_array_equal(topo_from_list.charges, topo.charges)
np.testing.assert_array_equal(topo_from_list.velocities,
topo.velocities)
def test_coulomb_matrix(self):
# flat
cm = CoulombMatrix(flatten=True)
df = pd.DataFrame({"s": [self.diamond, self.nacl]})
with self.assertRaises(NotFittedError):
df = cm.featurize_dataframe(df, "s")
df = cm.fit_featurize_dataframe(df, "s")
labels = cm.feature_labels()
self.assertListEqual(labels,
["coulomb matrix eig 0", "coulomb matrix eig 1"])
self.assertArrayAlmostEqual(df[labels].iloc[0], [49.169453, 24.546758],
decimal=5)
self.assertArrayAlmostEqual(df[labels].iloc[1],
[153.774731, 452.894322],
decimal=5)
# matrix
species = ["C", "C", "H", "H"]
coords = [[0, 0, 0], [0, 0, 1.203], [0, 0, -1.06], [0, 0, 2.263]]
acetylene = Molecule(species, coords)
morig = CoulombMatrix(flatten=False).featurize(acetylene)
mtarget = [[36.858, 15.835391290, 2.995098235, 1.402827813], \
[15.835391290, 36.858, 1.4028278132103624, 2.9950982], \
[2.9368896127, 1.402827813, 0.5, 0.159279959], \
[1.4028278132, 2.995098235, 0.159279959, 0.5]]
self.assertAlmostEqual(int(np.linalg.norm(morig - np.array(mtarget))),
0)
m = CoulombMatrix(diag_elems=False,
flatten=False).featurize(acetylene)[0]
self.assertAlmostEqual(m[0][0], 0.0)
self.assertAlmostEqual(m[1][1], 0.0)
self.assertAlmostEqual(m[2][2], 0.0)
self.assertAlmostEqual(m[3][3], 0.0)
def test_element_stats(self):
test = ElementStats({'H': [4, 2, 3],
'O': [2, 3, 4]},
stats=['min', 'max', 'moment:1:10'])
self.assertEqual(test.transform(['H2O']).shape, (1, 36))
res = test.transform(['H2O', 'H2O'])
self.assertEqual(res.shape, (2, 36))
res2 = test.transform([Composition('H2O'), Composition('H2O')])
np.testing.assert_allclose(res.values, res2.values)
dummy_h2o = Molecule(['H', 'H', 'O'], [[-0.5, 0, 0], [0.5, 0, 0], [0, 0, 0]])
res3 = test.transform([dummy_h2o, dummy_h2o])
np.testing.assert_allclose(res.values, res3.values)
stats = ['min', 'max', *['moment:%d:None' % i for i in range(1, 11)]]
p0_names = ['p0_%s' % i for i in stats]
p1_names = ['p1_%s' % i for i in stats]
p2_names = ['p2_%s' % i for i in stats]
all_names = []
for i, j, k in zip(p0_names, p1_names, p2_names):
all_names.extend([i, j, k])
self.assertListEqual(list(res.columns), all_names)
def test_element_stats(self):
test = ElementStats({
"H": [4, 2, 3],
"O": [2, 3, 4]
},
stats=["min", "max", "moment:1:10"])
self.assertEqual(test.transform(["H2O"]).shape, (1, 36))
res = test.transform(["H2O", "H2O"])
self.assertEqual(res.shape, (2, 36))
res2 = test.transform([Composition("H2O"), Composition("H2O")])
np.testing.assert_allclose(res.values, res2.values)
dummy_h2o = Molecule(["H", "H", "O"],
[[-0.5, 0, 0], [0.5, 0, 0], [0, 0, 0]])
res3 = test.transform([dummy_h2o, dummy_h2o])
np.testing.assert_allclose(res.values, res3.values)
stats = ["min", "max", *["moment:%d:None" % i for i in range(1, 11)]]
p0_names = ["p0_%s" % i for i in stats]
p1_names = ["p1_%s" % i for i in stats]
p2_names = ["p2_%s" % i for i in stats]
all_names = []
for i, j, k in zip(p0_names, p1_names, p2_names):
all_names.extend([i, j, k])
self.assertListEqual(list(res.columns), all_names)
def run_task(self, fw_spec):
molecules = self["constituent_molecules"]
mols_number = self["mols_number"]
input_filename = self["input_filename"]
forcefield = self["forcefield"]
topologies = self["topologies"]
user_settings = self.get("user_settings", {})
data_filename = user_settings.get("data_file", "lammps.data")
final_molecule = self["final_molecule"]
if isinstance(final_molecule, six.string_types):
final_molecule = Molecule.from_file(final_molecule)
lammps_ff_data = LammpsForceFieldData.from_forcefield_and_topology(
molecules, mols_number, self["box_size"], final_molecule,
forcefield, topologies)
lammps_input_set = LammpsInputSet.from_file(
"forcefield",
self["input_file"],
user_settings=user_settings,
lammps_data=lammps_ff_data,
data_filename=data_filename,
is_forcefield=True)
lammps_input_set.write_input(input_filename, data_filename)
def create_LiEC_pymatgen_mol():
"""
O(3) -- Li(6)
||
C(1)
/ \
O(0) O(4)
| |
C(2) --- C(5)
"""
atoms = ["O", "C", "C", "O", "O", "C", "Li", "H", "H", "H", "H"]
coords = [
[0.3103, -1.1776, -0.3722],
[-0.6822, -0.5086, 0.3490],
[1.5289, -0.4938, -0.0925],
[-1.9018, -0.6327, -0.0141],
[-0.2475, 0.9112, 0.3711],
[1.1084, 0.9722, -0.0814],
[-2.0519, 1.1814, -0.2310],
[2.2514, -0.7288, -0.8736],
[1.9228, -0.8043, 0.8819],
[1.1406, 1.4103, -1.0835],
[1.7022, 1.5801, 0.6038],
]
charge = 0
m = Molecule(atoms, coords, charge)
return m
def test__str__(self):
species = ["C", "O"]
coords = [
[-9.5782000000, 0.6241500000, 0.0000000000],
[-7.5827400000, 0.5127000000, -0.0000000000],
]
molecule = Molecule(species=species, coords=coords)
rem = {
"jobtype": "opt",
"method": "wb97m-v",
"basis": "def2-qzvppd",
"max_scf_cycles": "300",
"gen_scfman": "true",
}
str_test = QCInput(molecule=molecule, rem=rem).__str__().split("\n")
str_actual_list = [
"$molecule",
" 0 1",
" C -9.5782000000 0.6241500000 0.0000000000",
" O -7.5827400000 0.5127000000 -0.0000000000",
"$end",
"$rem",
" job_type = opt",
" method = wb97m-v",
" basis = def2-qzvppd",
" max_scf_cycles = 300",
" gen_scfman = true",
"$end",
]
for i_str in str_actual_list:
self.assertIn(i_str, str_test)
def test_simple_molecule_graph(self):
mol = Molecule(['C', 'H', 'O'], [[0, 0, 0], [1, 0, 0], [2, 0, 0]])
graph = SimpleMolGraph().convert(mol)
self.assertListEqual(graph['atom'], [6, 1, 8])
self.assertTrue(np.allclose(graph['bond'], [1, 2, 1, 1, 2, 1]))
self.assertListEqual(graph['index1'], [0, 0, 1, 1, 2, 2])
self.assertListEqual(graph['index2'], [1, 2, 0, 2, 0, 1])
def setUpClass(cls):
cls.structure = Structure.from_file(
os.path.join(MODULE_DIR, "cifs", "BaTiO3_mp-2998_computed.cif"))
cls.molecule = Molecule(["C", "O", "O"],
[[0, 0, 0], [-1, 0, 0], [1, 0, 0]])
cls.mall = MinimumDistanceNNAll(4)
cls.aapair = AllAtomPairs()
def get_snap_site_features(d):
feature = []
data_filename = "lammps_snap.data"
input_template = "lammps_snap_template.in"
input_filename = "lammps_snap.in"
dump_filename = "dump.sna"
log_filename = "log.lammps"
sbp.check_call(["rm", "-f", input_filename])
sbp.check_call(["rm", "-f", data_filename])
sbp.check_call(["rm", "-f", dump_filename])
sbp.check_call(["rm", "-f", log_filename])
structure = Structure.from_dict(d["structure"])
feature.append(structure[d["absorbing_atom"]].specie.number)
try:
mol = Molecule.from_dict(d["cluster"])
except TypeError:
atoms = Atoms(structure, d["absorbing_atom"], 10.0)
mol = atoms.cluster
logger.info(mol.formula)
lmp_data = LammpsData.from_structure(mol, [[0,25], [0,25],[0,25]], translate=False)
lmp_data.write_file(data_filename)
el_sorted = sorted(mol.composition, key=lambda x:x.atomic_mass)
cutoff = ""
weight = ""
for i, e in enumerate(el_sorted):
cutoff += " {}".format(float(e.atomic_radius))
weight += " {}".format(1.0)
settings = {
'data_file': data_filename,
'rcutfac': 1.4,
'rfac0': 0.993630,
'twojmax': 6.0,
'cutoff': cutoff,
'weight': weight,
'dump_file': dump_filename
}
lmp_in = LammpsInput.from_file(input_template, settings)
lmp_in.write_file(input_filename)
#try:
logger.info("Running LAMMPS ... ")
exit_code = sbp.check_call(["./lmp_serial", "-in", input_filename])
if exit_code != 0:
logger.error("lammps run failed")
raise RuntimeError("lammps run failed")
logger.info("Processing LAMMPS outputs ... ")
lmp_run = LammpsRun(data_filename, dump_filename, log_filename)
t = list(lmp_run.trajectory[0])
try:
assert np.linalg.norm(t[2:5]) <= 1e-6
except AssertionError:
logger.info("xyz: {}".format(t[2:5]))
logger.error("assertion failed: first one not at origin")
raise
logger.info("# bispectrum coeffs: {}".format(len(t[5:])))
feature.extend(t[5:])
return feature
def test_adsorb_both_surfaces(self):
o = Molecule("O", [[0, 0, 0]])
adslabs = self.asf_100.adsorb_both_surfaces(o)
for adslab in adslabs:
sg = SpacegroupAnalyzer(adslab)
sites = sorted(adslab, key=lambda site: site.frac_coords[2])
self.assertTrue(sites[0].species_string == "O")
self.assertTrue(sites[-1].species_string == "O")
def test_adsorb_both_surfaces(self):
o = Molecule("O", [[0, 0, 0]])
adslabs = adsorb_both_surfaces(self.slab_dict["111"], o)
for adslab in adslabs:
sites = sorted(adslab, key=lambda site: site.frac_coords[2])
self.assertTrue(sites[0].species_string == "O")
self.assertTrue(sites[-1].species_string == "O")
self.assertTrue(adslab.is_symmetric())
def test_apply_transformation(self):
co = Molecule(["C", "O"], [[0, 0, 0], [0, 0, 1.23]])
trans = AddAdsorbateTransformation(co)
pt = Structure(Lattice.cubic(5), ["Pt"], [[0, 0, 0]]) # fictitious
slab = SlabTransformation([0, 0, 1], 20, 10).apply_transformation(pt)
out = trans.apply_transformation(slab)
self.assertEqual(out.composition.reduced_formula, "Pt4CO")
def test_from_multi_jobs_file(self):
job_list_test = QCInput.from_multi_jobs_file(
os.path.join(test_dir, "pt_n2_wb97mv_0.0.in"))
species = [
"S", "C", "H", "C", "H", "C", "H", "C", "C", "C", "H", "C", "H",
"C", "H", "S"
]
coords = [[-0.00250959, -0.05817469, -0.02921636],
[1.70755408, -0.03033788, -0.01382912],
[2.24317221, -0.05215019, 0.92026728],
[2.21976393, 0.01718014, -1.27293235],
[3.27786220, 0.04082146, -1.48539646],
[1.20867399, 0.04478540, -2.27007793],
[1.40292257, 0.10591684, -3.33110912],
[-0.05341046, 0.01577217, -1.74839343],
[-1.32843436, 0.03545064, -2.45531187],
[-1.55195156, 0.08743920, -3.80184635],
[-0.75245172, 0.10267657, -4.52817967],
[-2.93293778, 0.08408786, -4.13352169],
[-3.31125108, 0.11340328, -5.14405819],
[-3.73173288, 0.02741365, -3.03412864],
[-4.80776535, 0.00535688, -2.99564645],
[-2.81590978, -0.00516172, -1.58990580]]
molecule_1_actual = Molecule(species, coords)
rem_1_actual = {
"job_type": "opt",
"method": "wb97m-v",
"basis": "def2-tzvppd",
"gen_scfman": "true",
"geom_opt_max_cycles": "75",
"max_scf_cycles": "300",
"scf_algorithm": "diis",
"scf_guess": "sad",
"sym_ignore": "true",
"symmetry": "false",
"thresh": "14"
}
opt_1_actual = {"CONSTRAINT": ["tors 6 8 9 10 0.0"]}
self.assertEqual(molecule_1_actual, job_list_test[0].molecule)
self.assertEqual(rem_1_actual, job_list_test[0].rem)
self.assertEqual(opt_1_actual, job_list_test[0].opt)
molecule_2_actual = "read"
rem_2_actual = {
"job_type": "sp",
"method": "wb97m-v",
"basis": "def2-tzvppd",
"gen_scfman": "true",
"geom_opt_max_cycles": "75",
"max_scf_cycles": "300",
"scf_algorithm": "diis",
"scf_guess": "read",
"sym_ignore": "true",
"symmetry": "false",
"thresh": "14"
}
self.assertEqual(molecule_2_actual, job_list_test[1].molecule)
self.assertEqual(rem_2_actual, job_list_test[1].rem)
def convert_obatoms_to_molecule(self, atoms, residue_name=None, site_property="ff_map"):
"""
Convert list of openbabel atoms to MOlecule.
Args:
atoms ([OBAtom]): list of OBAtom objects
residue_name (str): the key in self.map_residue_to_mol. Usec to
restore the site properties in the final packed molecule.
site_property (str): the site property to be restored.
Returns:
Molecule object
"""
restore_site_props = True if residue_name is not None else False
if restore_site_props and not hasattr(self, "map_residue_to_mol"):
self._set_residue_map()
coords = []
zs = []
for atm in atoms:
coords.append(list(atm.coords))
zs.append(atm.atomicnum)
mol = Molecule(zs, coords)
if restore_site_props:
props = []
ref = self.map_residue_to_mol[residue_name].copy()
# sanity check
assert len(mol) == len(ref)
assert ref.formula == mol.formula
# the packed molecules have the atoms in the same order..sigh!
for i, site in enumerate(mol):
assert site.specie.symbol == ref[i].specie.symbol
props.append(getattr(ref[i], site_property))
mol.add_site_property(site_property, props)
return mol
def from_dict(cls, d):
return GaussianInput(mol=Molecule.from_dict(d["molecule"]),
functional=d["functional"],
basis_set=d["basis_set"],
route_parameters=d["route_parameters"],
title=d["title"],
charge=d["charge"],
spin_multiplicity=d["spin_multiplicity"],
input_parameters=d["input_parameters"],
link0_parameters=d["link0_parameters"])
def __init__(self, start_monomer, s_head, s_tail,
monomer, head, tail,
end_monomer, e_head, e_tail,
n_units, link_distance=1.0, linear_chain=False):
"""
Args:
start_monomer (Molecule): Starting molecule
s_head (int): starting atom index of the start_monomer molecule
s_tail (int): tail atom index of the start_monomer
monomer (Molecule): The monomer
head (int): index of the atom in the monomer that forms the head
tail (int): tail atom index. monomers will be connected from
tail to head
end_monomer (Molecule): Terminal molecule
e_head (int): starting atom index of the end_monomer molecule
e_tail (int): tail atom index of the end_monomer
n_units (int): number of monomer units excluding the start and
terminal molecules
link_distance (float): distance between consecutive monomers
linear_chain (bool): linear or random walk polymer chain
"""
self.start = s_head
self.end = s_tail
self.monomer = monomer
self.n_units = n_units
self.link_distance = link_distance
self.linear_chain = linear_chain
# translate monomers so that head atom is at the origin
start_monomer.translate_sites(range(len(start_monomer)),
- monomer.cart_coords[s_head])
monomer.translate_sites(range(len(monomer)),
- monomer.cart_coords[head])
end_monomer.translate_sites(range(len(end_monomer)),
- monomer.cart_coords[e_head])
self.mon_vector = monomer.cart_coords[tail] - monomer.cart_coords[head]
self.moves = {1: [1, 0, 0],
2: [0, 1, 0],
3: [0, 0, 1],
4: [-1, 0, 0],
5: [0, -1, 0],
6: [0, 0, -1]}
self.prev_move = 1
# places the start monomer at the beginning of the chain
self.molecule = start_monomer.copy()
self.length = 1
# create the chain
self._create(self.monomer, self.mon_vector)
# terminate the chain with the end_monomer
self.n_units += 1
end_mon_vector = end_monomer.cart_coords[e_tail] - \
end_monomer.cart_coords[e_head]
self._create(end_monomer, end_mon_vector)
self.molecule = Molecule.from_sites(self.molecule.sites)
def setUpClass(cls):
# head molecule
cls.peo_head = Molecule.from_file(os.path.join(test_dir, "peo_head.xyz"))
charges = [-0.1187, 0.0861, 0.0861, 0.0861, -0.2792, -0.0326, 0.0861, 0.0861]
cls.peo_head.add_site_property("charge", charges)
s_head = 0
s_tail = 5
# chain molecule
cls.peo_bulk = Molecule.from_file(os.path.join(test_dir, "peo_bulk.xyz"))
charges = [-0.0326, 0.0861, 0.0861, -0.2792, -0.0326, 0.0861, 0.0861]
cls.peo_bulk.add_site_property("charge", charges)
head = 0
tail = 4
# terminal molecule
cls.peo_tail = Molecule.from_file(os.path.join(test_dir, "peo_tail.xyz"))
charges = [-0.0326, 0.0861, 0.0861, -0.2792, -0.1187, 0.0861, 0.0861, 0.0861]
cls.peo_tail.add_site_property("charge", charges)
e_head = 0
e_tail = 4
cls.n_units = 25
link_distance = 1.5075
# create the polymer
cls.peo_polymer = Polymer(cls.peo_head, s_head, s_tail,
cls.peo_bulk, head, tail,
cls.peo_tail, e_head, e_tail,
cls.n_units, link_distance)
# linear chain
cls.peo_polymer_linear = Polymer(cls.peo_head, s_head, s_tail,
cls.peo_bulk, head, tail,
cls.peo_tail, e_head, e_tail,
cls.n_units, link_distance, linear_chain=True)
def from_dict(d):
a = d["about"]
dec = MontyDecoder()
created_at = dec.process_decoded(a["created_at"]) if "created_at" in a \
else None
data = {k: v for k, v in d["about"].items()
if k.startswith("_")}
data = dec.process_decoded(data)
structure = Structure.from_dict(d) if "lattice" in d \
else Molecule.from_dict(d)
return MPStructureNL(structure, a["authors"],
projects=a.get("projects", None),
references=a.get("references", ""),
remarks=a.get("remarks", None), data=data,
history=a.get("history", None),
created_at=created_at)
def setUpClass(cls):
ethanol_coords = [[0.00720, -0.56870, 0.00000],
[-1.28540, 0.24990, 0.00000],
[1.13040, 0.31470, 0.00000],
[0.03920, -1.19720, 0.89000],
[0.03920, -1.19720, -0.89000],
[-1.31750, 0.87840, 0.89000],
[-1.31750, 0.87840, -0.89000],
[-2.14220, -0.42390, -0.00000],
[1.98570, -0.13650, -0.00000]]
water_coords = [[9.626, 6.787, 12.673],
[9.626, 8.420, 12.673],
[10.203, 7.604, 12.673]]
cls.ethanol_atoms = ["C", "C", "O", "H", "H", "H", "H", "H", "H"]
cls.water_atoms = ["H", "H", "O"]
ethanol = Molecule(cls.ethanol_atoms, ethanol_coords)
water = Molecule(cls.water_atoms, water_coords)
cls.mols = [ethanol, water]
cls.cocktail = Molecule.from_file(
os.path.join(test_dir, "cocktail.xyz"))
cls.packmol_config = [{"number": 1}, {"number": 15}]
def __init__(self, sites, ff_label=None, charges=None, velocities=None,
topologies=None):
"""
Args:
sites ([Site] or SiteCollection): A group of sites in a
list or as a Molecule/Structure.
ff_label (str): Site property key for labeling atoms of
different types. Default to None, i.e., use
site.species_string.
charges ([q, ...]): Charge of each site in a (n,)
array/list, where n is the No. of sites. Default to
None, i.e., search site property for charges.
velocities ([[vx, vy, vz], ...]): Velocity of each site in
a (n, 3) array/list, where n is the No. of sites.
Default to None, i.e., search site property for
velocities.
topologies (dict): Bonds, angles, dihedrals and improper
dihedrals defined by site indices. Default to None,
i.e., no additional topology. All four valid keys
listed below are optional.
{
"Bonds": [[i, j], ...],
"Angles": [[i, j, k], ...],
"Dihedrals": [[i, j, k, l], ...],
"Impropers": [[i, j, k, l], ...]
}
"""
if not isinstance(sites, (Molecule, Structure)):
sites = Molecule.from_sites(sites)
if ff_label:
type_by_sites = sites.site_properties.get(ff_label)
else:
type_by_sites = [site.specie.symbol for site in sites]
# search for site property if not override
if charges is None:
charges = sites.site_properties.get("charge")
if velocities is None:
velocities = sites.site_properties.get("velocities")
# validate shape
if charges is not None:
charge_arr = np.array(charges)
assert charge_arr.shape == (len(sites),),\
"Wrong format for charges"
charges = charge_arr.tolist()
if velocities is not None:
velocities_arr = np.array(velocities)
assert velocities_arr.shape == (len(sites), 3), \
"Wrong format for velocities"
velocities = velocities_arr.tolist()
if topologies:
topologies = {k: v for k, v in topologies.items()
if k in SECTION_KEYWORDS["topology"]}
self.sites = sites
self.ff_label = ff_label
self.charges = charges
self.velocities = velocities
self.topologies = topologies
self.type_by_sites = type_by_sites
self.species = set(type_by_sites)
def setUp(self):
self.benzene = Molecule.from_file(os.path.join(test_dir, "benzene.xyz"))
self.acetylene = Molecule.from_file(os.path.join(test_dir, "acetylene.xyz"))