def test_chemical_environments_matches_OE(self):
"""Test Topology.chemical_environment_matches"""
from simtk.openmm import app
toolkit_wrapper = OpenEyeToolkitWrapper()
pdbfile = app.PDBFile(
get_data_file_path(
"systems/packmol_boxes/cyclohexane_ethanol_0.4_0.6.pdb"))
# toolkit_wrapper = RDKitToolkitWrapper()
molecules = [
Molecule.from_file(get_data_file_path(name))
for name in ("molecules/ethanol.mol2",
"molecules/cyclohexane.mol2")
]
topology = Topology.from_openmm(pdbfile.topology,
unique_molecules=molecules)
# Test for substructure match
matches = topology.chemical_environment_matches(
"[C:1]-[C:2]-[O:3]", toolkit_registry=toolkit_wrapper)
assert len(matches) == 143
assert matches[0].topology_atom_indices == (1728, 1729, 1730)
# Test for whole-molecule match
matches = topology.chemical_environment_matches(
"[H][C:1]([H])([H])-[C:2]([H])([H])-[O:3][H]",
toolkit_registry=toolkit_wrapper,
)
assert (len(matches) == 1716
) # 143 * 12 (there are 12 possible hydrogen mappings)
assert matches[0].topology_atom_indices == (1728, 1729, 1730)
# Search for a substructure that isn't there
matches = topology.chemical_environment_matches(
"[C][C:1]-[C:2]-[O:3]", toolkit_registry=toolkit_wrapper)
assert len(matches) == 0
def setUp(self):
self.empty_molecule = Molecule()
self.ethane_from_smiles = Molecule.from_smiles("CC")
self.ethene_from_smiles = Molecule.from_smiles("C=C")
self.propane_from_smiles = Molecule.from_smiles("CCC")
filename = get_data_file_path("molecules/toluene.sdf")
self.toluene_from_sdf = Molecule.from_file(filename)
if OpenEyeToolkitWrapper.is_available():
filename = get_data_file_path("molecules/toluene_charged.mol2")
# TODO: This will require openeye to load
self.toluene_from_charged_mol2 = Molecule.from_file(filename)
self.charged_methylamine_from_smiles = Molecule.from_smiles(
"[H]C([H])([H])[N+]([H])([H])[H]")
molecule = Molecule.from_smiles("CC")
carbons = [atom for atom in molecule.atoms if atom.atomic_number == 6]
c0_hydrogens = [
atom for atom in carbons[0].bonded_atoms if atom.atomic_number == 1
]
molecule.add_bond_charge_virtual_site(
(carbons[0], carbons[1]),
0.1 * unit.angstrom,
charge_increments=[0.1, 0.05] * unit.elementary_charge,
)
molecule.add_monovalent_lone_pair_virtual_site(
(c0_hydrogens[0], carbons[0], carbons[1]),
0.2 * unit.angstrom,
20 * unit.degree,
25 * unit.degree,
charge_increments=[0.01, 0.02, 0.03] * unit.elementary_charge,
)
self.ethane_from_smiles_w_vsites = Molecule(molecule)
# Make a propane with virtual sites
molecule = Molecule.from_smiles("CCC")
carbons = [atom for atom in molecule.atoms if atom.atomic_number == 6]
c0_hydrogens = [
atom for atom in carbons[0].bonded_atoms if atom.atomic_number == 1
]
molecule.add_bond_charge_virtual_site(
(carbons[0], carbons[1]),
0.1 * unit.angstrom,
charge_increments=[0.1, 0.05] * unit.elementary_charge,
)
molecule.add_monovalent_lone_pair_virtual_site(
(c0_hydrogens[0], carbons[0], carbons[1]),
0.2 * unit.angstrom,
20 * unit.degree,
25 * unit.degree,
charge_increments=[0.01, 0.02, 0.03] * unit.elementary_charge,
)
self.propane_from_smiles_w_vsites = Molecule(molecule)
def test_from_openmm_duplicate_unique_mol(self):
"""Check that a DuplicateUniqueMoleculeError is raised if we try to pass in two indistinguishably unique mols"""
from simtk.openmm import app
pdbfile = app.PDBFile(
get_data_file_path(
'systems/packmol_boxes/cyclohexane_ethanol_0.4_0.6.pdb'))
molecules = [
Molecule.from_file(get_data_file_path(name))
for name in ('molecules/ethanol.mol2',
'molecules/ethanol_reordered.mol2',
'molecules/cyclohexane.mol2')
]
with self.assertRaises(DuplicateUniqueMoleculeError) as context:
topology = Topology.from_openmm(pdbfile.topology,
unique_molecules=molecules)
def test_to_file_vsites(self):
"""
Checks that Topology.to_file() doesn't write vsites
"""
from tempfile import NamedTemporaryFile
from openforcefield.topology import Molecule, Topology
mol = Molecule.from_pdb_and_smiles(
get_data_file_path("systems/test_systems/1_ethanol.pdb"), "CCO")
carbons = [atom for atom in mol.atoms if atom.atomic_number == 6]
positions = mol.conformers[0]
mol.add_bond_charge_virtual_site(
(carbons[0], carbons[1]),
0.1 * unit.angstrom,
charge_increments=[0.1, 0.05] * unit.elementary_charge,
)
topology = Topology()
topology.add_molecule(mol)
count = 0
# The file should be printed out with 9 atoms and 0 virtualsites, so we check to ensure that thtere are only 9 HETATM entries
with NamedTemporaryFile(suffix=".pdb") as iofile:
topology.to_file(iofile.name, positions)
data = open(iofile.name).readlines()
for line in data:
if line.startswith("HETATM"):
count = count + 1
assert count == 9
def test_chemical_environments_matches_RDK(self):
"""Test Topology.chemical_environment_matches"""
from simtk.openmm import app
toolkit_wrapper = RDKitToolkitWrapper()
pdbfile = app.PDBFile(
get_data_file_path(
'systems/packmol_boxes/cyclohexane_ethanol_0.4_0.6.pdb'))
# toolkit_wrapper = RDKitToolkitWrapper()
#molecules = [Molecule.from_file(get_data_file_path(name)) for name in ('molecules/ethanol.mol2',
# 'molecules/cyclohexane.mol2')]
molecules = []
molecules.append(Molecule.from_smiles('CCO'))
molecules.append(Molecule.from_smiles('C1CCCCC1'))
topology = Topology.from_openmm(pdbfile.topology,
unique_molecules=molecules)
# Count CCO matches
matches = topology.chemical_environment_matches(
"[C:1]-[C:2]-[O:3]", toolkit_registry=toolkit_wrapper)
assert len(matches) == 143
assert matches[0].topology_atom_indices == (1728, 1729, 1730)
matches = topology.chemical_environment_matches(
"[H][C:1]([H])([H])-[C:2]([H])([H])-[O:3][H]",
toolkit_registry=toolkit_wrapper)
assert len(
matches
) == 1716 # 143 * 12 (there are 12 possible hydrogen mappings)
assert matches[0].topology_atom_indices == (1728, 1729, 1730)
# Search for a substructure that isn't there
matches = topology.chemical_environment_matches(
"[C][C:1]-[C:2]-[O:3]", toolkit_registry=toolkit_wrapper)
assert len(matches) == 0
def test_to_file_units_check(self):
"""
Checks whether writing pdb with unitless positions, Angstrom positions,
nanometer positions, result in the same output
"""
import filecmp
from tempfile import NamedTemporaryFile
from simtk.unit import nanometer
from openforcefield.tests.test_forcefield import create_ethanol
from openforcefield.topology import Molecule, Topology
topology = Topology()
mol = Molecule.from_pdb_and_smiles(
get_data_file_path("systems/test_systems/1_ethanol.pdb"), "CCO")
topology.add_molecule(mol)
positions_angstrom = mol.conformers[0]
count = 1
# Write the molecule to PDB and ensure that the X coordinate of the first atom is 10.172
with NamedTemporaryFile(suffix=".pdb") as iofile:
topology.to_file(iofile.name, positions_angstrom)
data = open(iofile.name).readlines()
for line in data:
if line.startswith("HETATM") and count == 1:
count = count + 1
coord = line.split()[-6]
assert coord == "10.172"
# Do the same check, but feed in equivalent positions measured in nanometers and ensure the PDB is still the same
count = 1
coord = None
with NamedTemporaryFile(suffix=".pdb") as iofile:
positions_nanometer = positions_angstrom.in_units_of(nanometer)
topology.to_file(iofile.name, positions_nanometer)
data = open(iofile.name).readlines()
for line in data:
if line.startswith("HETATM") and count == 1:
count = count + 1
coord = line.split()[-6]
assert coord == "10.172"
count = 1
coord = "abc"
with NamedTemporaryFile(suffix=".pdb") as iofile:
positions_unitless = positions_angstrom._value
topology.to_file(iofile.name, positions_unitless)
data = open(iofile.name).readlines()
for line in data:
if line.startswith("HETATM") and count == 1:
count = count + 1
coord = line.split()[-6]
assert coord == "10.172"
def test_from_openmm_missing_reference(self):
"""Test creation of an openforcefield Topology object from an OpenMM Topology when missing a unique molecule"""
from simtk.openmm import app
pdbfile = app.PDBFile(
get_data_file_path(
'systems/packmol_boxes/cyclohexane_ethanol_0.4_0.6.pdb'))
molecules = [create_ethanol()]
with pytest.raises(
ValueError,
match='No match found for molecule C6H12') as excinfo:
topology = Topology.from_openmm(pdbfile.topology,
unique_molecules=molecules)
def test_from_openmm(self):
"""Test creation of an openforcefield Topology object from an OpenMM Topology and component molecules"""
from simtk.openmm import app
pdbfile = app.PDBFile(
get_data_file_path(
'systems/packmol_boxes/cyclohexane_ethanol_0.4_0.6.pdb'))
molecules = [create_ethanol(), create_cyclohexane()]
topology = Topology.from_openmm(pdbfile.topology,
unique_molecules=molecules)
assert topology.n_reference_molecules == 2
assert topology.n_topology_molecules == 239
def test_to_file_multi_molecule_different_order(self):
"""
Checks for the following if Topology.to_write maintains the order of atoms
for the same molecule with different indexing
"""
from tempfile import NamedTemporaryFile
from openforcefield.tests.test_forcefield import (
create_ethanol,
create_reversed_ethanol,
)
from openforcefield.topology import Molecule, Topology
topology = Topology()
topology.add_molecule(create_ethanol())
topology.add_molecule(create_reversed_ethanol())
mol = Molecule.from_pdb_and_smiles(
get_data_file_path("systems/test_systems/1_ethanol.pdb"), "CCO")
positions = mol.conformers[0]
# Make up coordinates for the second ethanol by translating the first by 10 angstroms
# (note that this will still be a gibberish conformation, since the atom order in the second molecule is different)
positions = np.concatenate(
[positions, positions + 10.0 * unit.angstrom])
element_order = []
with NamedTemporaryFile(suffix=".pdb") as iofile:
topology.to_file(iofile.name, positions)
data = open(iofile.name).readlines()
for line in data:
if line.startswith("HETATM"):
element_order.append(line.strip()[-1])
assert element_order == [
"C",
"C",
"O",
"H",
"H",
"H",
"H",
"H",
"H",
"H",
"H",
"H",
"H",
"H",
"H",
"O",
"C",
"C",
]
def test_to_file_fileformat_invalid(self):
"""
Checks for invalid file format
"""
from openforcefield.tests.test_forcefield import create_ethanol
from openforcefield.topology import Molecule, Topology
topology = Topology()
mol = Molecule.from_pdb_and_smiles(
get_data_file_path("systems/test_systems/1_ethanol.pdb"), "CCO")
topology.add_molecule(mol)
positions = mol.conformers[0]
fname = "ethanol_file.pdb"
with pytest.raises(NotImplementedError):
topology.to_file(fname, positions, file_format="AbC")
def test_from_openmm_missing_conect(self):
"""
Test creation of an openforcefield Topology object from an OpenMM Topology
when the origin PDB lacks CONECT records
"""
from simtk.openmm import app
pdbfile = app.PDBFile(
get_data_file_path('systems/test_systems/1_ethanol_no_conect.pdb'))
molecules = []
molecules.append(Molecule.from_smiles('CCO'))
with pytest.raises(
ValueError,
match='No match found for molecule C. This would be a '
'very unusual molecule to try and parameterize, '
'and it is likely that the data source it was '
'read from does not contain connectivity '
'information. If this molecule is coming from '
'PDB, please ensure that the file contains CONECT '
'records.') as excinfo:
topology = Topology.from_openmm(pdbfile.topology,
unique_molecules=molecules)
def test_to_file_fileformat_lettercase(self):
"""
Checks if fileformat specifier is indpendent of upper/lowercase
"""
import os
from tempfile import NamedTemporaryFile
from openforcefield.tests.test_forcefield import create_ethanol
from openforcefield.topology import Molecule, Topology
topology = Topology()
mol = Molecule.from_pdb_and_smiles(
get_data_file_path("systems/test_systems/1_ethanol.pdb"), "CCO")
topology.add_molecule(mol)
positions = mol.conformers[0]
count = 1
with NamedTemporaryFile(suffix=".pdb") as iofile:
topology.to_file(iofile.name, positions, file_format="pDb")
data = open(iofile.name).readlines()
for line in data:
if line.startswith("HETATM") and count == 1:
count = count + 1
coord = line.split()[-6]
assert coord == "10.172"
# datapath = './AlkEthOH_tripos/AlkEthOH_chain_filt1'
# datapath = './AlkEthOH_tripos/AlkEthOH_rings_filt1'
datapath = './AlkEthOH_tripos/AlkEthOH_test_filt1'
molname = 'AlkEthOH_r22'
mol_filepath = os.path.join(datapath, molname + '_tripos.mol2')
prmtop_filepath = os.path.join(datapath, molname + '.top')
inpcrd_filepath = os.path.join(datapath, molname + '.crd')
# Check if we have this data file; if not we have to extract the archive.
if not os.path.isdir(datapath):
print("Extracting archived molecule files.")
# Extract the AlkEthOH dataset shipped with the toolkit in data/molecules/ in the working directory.
from openforcefield.tests.utils import get_data_file_path
tarfile_path = os.path.join(get_data_file_path('molecules'),
'AlkEthOH_tripos.tar.gz')
import tarfile
with tarfile.open(tarfile_path, 'r:gz') as tar:
tar.extractall()
# Load molecule
from openforcefield.topology import Molecule
molecule = Molecule.from_file(mol_filepath)
# Load forcefield
from openforcefield.typing.engines.smirnoff import ForceField
forcefield = ForceField('Frosst_AlkEthOH_parmAtFrosst.offxml')
versus energies from AMBER .prmtop and .crd files (parm@frosst params).
"""
import os
import glob
# datapath = './AlkEthOH_tripos/AlkEthOH_chain_filt1'
# datapath = './AlkEthOH_tripos/AlkEthOH_rings_filt1'
datapath = './AlkEthOH_tripos/AlkEthOH_test_filt1'
# Check if we have this data file; if not we have to extract the archive.
if not os.path.isdir(datapath):
print("Extracting archived molecule files.")
# Extract the AlkEthOH dataset shipped with the toolkit in data/molecules/ in the working directory.
from openforcefield.tests.utils import get_data_file_path
tarfile_path = os.path.join(get_data_file_path('molecules'), 'AlkEthOH_tripos.tar.gz')
import tarfile
with tarfile.open(tarfile_path, 'r:gz') as tar:
tar.extractall()
#Obtain list of molecules
mol_filepaths = glob.glob(datapath+'/*tripos.mol2')
mol_filepaths = [fnm for fnm in mol_filepaths if not 'c1302' in fnm] # Skip water.
print('Found {} files to test'.format(len(mol_filepaths)))
# Load forcefield
from openforcefield.typing.engines.smirnoff import ForceField
forcefield = ForceField('test_forcefields/Frosst_AlkEthOH_parmAtFrosst.offxml')
from openforcefield.topology import Molecule
