def test_explicit_hydrogens(self):
"""
It checks initialization of a Molecule with the explicit hydrogens
flag.
"""
# Load ethane from SMILES with implicit hydrogen atoms
molecule = Molecule(smiles='CC')
atom_names = molecule.get_pdb_atom_names()
for atom_name in atom_names:
assert 'H' not in atom_name, 'Unexpected H in molecule without ' \
+ 'explicit hydrogen atoms and hydrogens_are_explicit ' \
+ 'set to True'
# Load ethane from SMILES without explicit hydrogen atoms
molecule = Molecule(smiles='CC', hydrogens_are_explicit=False)
atom_names = molecule.get_pdb_atom_names()
found_hydrogen = False
for atom_name in atom_names:
if 'H' in atom_name:
found_hydrogen = True
break
assert found_hydrogen, 'Hydrogen not found regardless of setting ' \
+ 'hydrogens_are_explicit to False'
# Load ethane from SMILES with explicit hydrogen atoms
molecule = Molecule(smiles='[H]C([H])([H])C([H])([H])([H])',
hydrogens_are_explicit=True)
atom_names = molecule.get_pdb_atom_names()
found_hydrogen = False
for atom_name in atom_names:
if 'H' in atom_name:
found_hydrogen = True
break
assert found_hydrogen, 'Hydrogen not found regardless of being ' \
+ 'explicitly defined in the SMILES tag'
# Load ethane from PDB with implicit hydrogen atoms
pdb_path = get_data_file_path('tests/ethane_noH.pdb')
molecule = Molecule(pdb_path,
hydrogens_are_explicit=True)
atom_names = molecule.get_pdb_atom_names()
for atom_name in atom_names:
assert 'H' not in atom_name, 'Unexpected H in molecule without ' \
+ 'explicit hydrogen atoms and hydrogens_are_explicit ' \
+ 'set to True'
# Load ethane from PDB without explicit hydrogen atoms
pdb_path = get_data_file_path('tests/ethane_noH.pdb')
molecule = Molecule(pdb_path,
hydrogens_are_explicit=False)
atom_names = molecule.get_pdb_atom_names()
found_hydrogen = False
for atom_name in atom_names:
if 'H' in atom_name:
found_hydrogen = True
break
assert found_hydrogen, 'Hydrogen not found regardless of setting ' \
+ 'hydrogens_are_explicit to False'
def test_datalocal_paths_for_offopls(self):
"""
It tests the datalocal paths assignment for OpenFF-OPLS2005
force field.
"""
from peleffy.utils import OutputPathHandler
from peleffy.forcefield import OpenFFOPLS2005ForceField
# Load benzene molecule
molecule = Molecule(smiles='c1ccccc1', name='benzene', tag='BNZ',
hydrogens_are_explicit=False)
molecule._forcefield = OpenFFOPLS2005ForceField('OPLS2005')
# Load force field
hybridff = OpenFFOPLS2005ForceField(
'openff_unconstrained-1.2.1.offxml')
# Molecule's tag
tag = molecule.tag
# Initialize output handler without output_path
output_handler = OutputPathHandler(molecule, hybridff,
as_datalocal=True)
# Validate output paths
assert output_handler.get_rotamer_library_path(
create_missing_folders=False) == \
'./DataLocal/LigandRotamerLibs/' \
+ '{}.rot.assign'.format(tag.upper()), \
'Unexpected default rotamer library path'
assert output_handler.get_impact_template_path(
create_missing_folders=False) == \
'./DataLocal/Templates/OpenFF/Parsley/' \
+ '{}z'.format(tag.lower()), \
'Unexpected default Impact template path'
assert output_handler.get_solvent_template_path(
create_missing_folders=False) == \
'./DataLocal/OBC/ligandParams.txt', \
'Unexpected default solvent parameters path'
assert output_handler.get_conformation_library_path(
create_missing_folders=False) == \
'./DataLocal/Conformations/' \
+ '{}.conformation'.format(tag.upper()), \
'Unexpected default conformation library path'
# Initialize output handler with an output_path set
with tempfile.TemporaryDirectory() as tmpdir:
output_handler = OutputPathHandler(
molecule, hybridff, as_datalocal=True,
output_path=os.path.join(tmpdir, 'output'))
assert output_handler.get_rotamer_library_path(
create_missing_folders=False) == \
os.path.join(tmpdir, 'output', 'DataLocal/LigandRotamerLibs/'
+ '{}.rot.assign'.format(tag.upper())), \
'Unexpected default rotamer library path'
assert output_handler.get_impact_template_path(
create_missing_folders=False) == \
os.path.join(tmpdir, 'output', 'DataLocal/Templates/'
+ 'OpenFF/Parsley/{}z'.format(tag.lower())), \
'Unexpected default Impact template path'
assert output_handler.get_solvent_template_path(
create_missing_folders=False) == \
os.path.join(tmpdir, 'output',
'DataLocal/OBC/ligandParams.txt'), \
'Unexpected default solvent parameters path'
assert output_handler.get_conformation_library_path(
create_missing_folders=False) == \
os.path.join(tmpdir, 'output/DataLocal/Conformations/' \
+ '{}.conformation'.format(tag.upper())), \
'Unexpected default conformation library path'
# Initialize output handler without output_path
output_handler = OutputPathHandler(molecule, hybridff,
as_datalocal=True)
# Set force field source for nonbonding parameters
hybridff.set_nonbonding_parameters('opls2005')
# Validate output paths
assert output_handler.get_rotamer_library_path(
create_missing_folders=False) == \
'./DataLocal/LigandRotamerLibs/' \
+ '{}.rot.assign'.format(tag.upper()), \
'Unexpected default rotamer library path'
assert output_handler.get_impact_template_path(
create_missing_folders=False) == \
'./DataLocal/Templates/OPLS2005/HeteroAtoms/' \
+ '{}z'.format(tag.lower()), \
'Unexpected default Impact template path'
assert output_handler.get_solvent_template_path(
create_missing_folders=False) == \
'./DataLocal/OBC/ligandParams.txt', \
'Unexpected default solvent parameters path'
assert output_handler.get_conformation_library_path(
create_missing_folders=False) == \
'./DataLocal/Conformations/' \
+ '{}.conformation'.format(tag.upper()), \
'Unexpected default conformation library path'
# Initialize output handler with an output_path set
with tempfile.TemporaryDirectory() as tmpdir:
output_handler = OutputPathHandler(
molecule, hybridff, as_datalocal=True,
output_path=os.path.join(tmpdir, 'output'))
assert output_handler.get_rotamer_library_path(
create_missing_folders=False) == \
os.path.join(tmpdir, 'output', 'DataLocal/LigandRotamerLibs/'
+ '{}.rot.assign'.format(tag.upper())), \
'Unexpected default rotamer library path'
assert output_handler.get_impact_template_path(
create_missing_folders=False) == \
os.path.join(tmpdir, 'output', 'DataLocal/Templates/OPLS2005/'
+ 'HeteroAtoms/{}z'.format(tag.lower())), \
'Unexpected default Impact template path'
assert output_handler.get_solvent_template_path(
create_missing_folders=False) == \
os.path.join(tmpdir, 'output',
'DataLocal/OBC/ligandParams.txt'), \
'Unexpected default solvent parameters path'
assert output_handler.get_conformation_library_path(
create_missing_folders=False) == \
os.path.join(tmpdir, 'output',
'DataLocal/Conformations/',
'{}.conformation'.format(tag.upper())), \
'Unexpected default conformation library path'
def test_PDB_connectivity_template(self):
"""
It tests the initialization of an peleffy's Molecule representation
from a PDB file without connectivity and a connectivity template.
"""
# Initialize an empty Molecule object
molecule = Molecule()
assert molecule.connectivity_template is None, \
'Unexpected connectivity template'
# Initialize a Molecule from a PDB without connectivity and
# without a connectivity template
ligand_path = get_data_file_path(
'ligands/benzene_without_connectivity.pdb')
molecule = Molecule(ligand_path)
expected_bond_ids = [(1, 0, False), (2, 1, False), (3, 2, False),
(4, 3, False), (5, 4, False), (5, 0, False),
(6, 0, False), (7, 1, False), (8, 2, False),
(9, 3, False), (10, 4, False), (11, 5, False)]
for bond in molecule.rdkit_molecule.GetBonds():
bond_id = (bond.GetBeginAtomIdx(), bond.GetEndAtomIdx(),
bond.GetIsAromatic())
assert bond_id in expected_bond_ids, 'Unexpected bond id ' \
+ '{}'.format(bond_id)
# Initialize a Molecule from a PDB without connectivity but with
# a connectivity template
template_path = get_data_file_path(
'ligands/benzene.pdb')
template = Molecule(template_path)
ligand_path = get_data_file_path(
'ligands/benzene_without_connectivity.pdb')
molecule = Molecule(ligand_path,
connectivity_template=template.rdkit_molecule)
expected_bond_ids = [(1, 0, True), (2, 1, True), (3, 2, True),
(4, 3, True), (5, 4, True), (5, 0, True),
(6, 0, False), (7, 1, False), (8, 2, False),
(9, 3, False), (10, 4, False), (11, 5, False)]
for bond in molecule.rdkit_molecule.GetBonds():
bond_id = (bond.GetBeginAtomIdx(), bond.GetEndAtomIdx(),
bond.GetIsAromatic())
assert bond_id in expected_bond_ids, 'Unexpected bond id ' \
+ '{}'.format(bond_id)
# Initialize a Molecule from a PDB with connectivity and with
# a connectivity template
template_path = get_data_file_path(
'ligands/benzene.pdb')
template = Molecule(template_path)
ligand_path = get_data_file_path(
'ligands/benzene.pdb')
molecule = Molecule(ligand_path,
connectivity_template=template.rdkit_molecule)
expected_bond_ids = [(0, 1, True), (1, 2, True), (2, 3, True),
(3, 4, True), (4, 5, True), (0, 5, True),
(0, 6, False), (1, 7, False), (2, 8, False),
(3, 9, False), (4, 10, False), (5, 11, False)]
for bond in molecule.rdkit_molecule.GetBonds():
bond_id = (bond.GetBeginAtomIdx(), bond.GetEndAtomIdx(),
bond.GetIsAromatic())
assert bond_id in expected_bond_ids, 'Unexpected bond id ' \
+ '{}'.format(bond_id)
def test_PDB_residue_name(self):
"""
It tests the PDB residue name and checks for consistency with
Molecule tag.
"""
def check_residue_name(name):
"""Check if residue names are valid in the output PDB file"""
with open('molecule.pdb') as f:
for line in f:
if line.startswith('HETATM'):
assert line[17:20] == name, 'Unexpected residue name'
ligand_path = get_data_file_path('ligands/benzene.pdb')
# Checking tag assignation from PDB
molecule = Molecule(ligand_path)
with tempfile.TemporaryDirectory() as tmpdir:
with temporary_cd(tmpdir):
assert molecule.tag == 'BNZ', 'Unexpected molecule tag'
molecule.to_pdb_file('molecule.pdb')
check_residue_name('BNZ')
# Checking set_tag() function
molecule = Molecule(ligand_path)
with tempfile.TemporaryDirectory() as tmpdir:
with temporary_cd(tmpdir):
molecule.set_tag('TAG')
assert molecule.tag == 'TAG', 'Unexpected molecule tag'
molecule.to_pdb_file('molecule.pdb')
check_residue_name('TAG')
# Checking default tag assignment from SMILES
molecule = Molecule(smiles='c1ccccc1', hydrogens_are_explicit=False)
with tempfile.TemporaryDirectory() as tmpdir:
with temporary_cd(tmpdir):
assert molecule.tag == 'UNK', 'Unexpected molecule tag'
molecule.to_pdb_file('molecule.pdb')
check_residue_name('UNK')
# Checking custom tag assignment from SMILES
molecule = Molecule(smiles='c1ccccc1', tag='BEN',
hydrogens_are_explicit=False)
with tempfile.TemporaryDirectory() as tmpdir:
with temporary_cd(tmpdir):
assert molecule.tag == 'BEN', 'Unexpected molecule tag'
molecule.to_pdb_file('molecule.pdb')
check_residue_name('BEN')
# Checking second custom tag assignment from SMILES
molecule = Molecule(smiles='c1ccccc1', hydrogens_are_explicit=False)
with tempfile.TemporaryDirectory() as tmpdir:
with temporary_cd(tmpdir):
molecule.set_tag('BNZ')
assert molecule.tag == 'BNZ', 'Unexpected molecule tag'
molecule.to_pdb_file('molecule.pdb')
check_residue_name('BNZ')
def test_terminal_rotamer_filtering(self):
"""
It tests the rotamer library builder when the terminal rotatable bonds
are ignored.
"""
LIGAND_PATH = 'ligands/oleic_acid.pdb'
ligand_path = get_data_file_path(LIGAND_PATH)
molecule = Molecule(ligand_path, exclude_terminal_rotamers=True)
rotamers_per_branch = molecule.rotamers
assert len(rotamers_per_branch) == 2, "Found an invalid number " + \
"of branches: {}".format(len(rotamers_per_branch))
atom_list_1 = list()
atom_list_2 = list()
rotamers = rotamers_per_branch[0]
for rotamer in rotamers:
atom_list_1.append(set([rotamer.index1, rotamer.index2]))
rotamers = rotamers_per_branch[1]
for rotamer in rotamers:
atom_list_2.append(set([rotamer.index1, rotamer.index2]))
EXPECTED_INDICES_1 = [
set([9, 10]),
set([8, 9]),
set([7, 8]),
set([6, 7]),
set([5, 6]),
set([2, 5]),
set([0, 2]),
set([0, 1])
]
EXPECTED_INDICES_2 = [
set([12, 11]),
set([12, 13]),
set([13, 14]),
set([14, 15]),
set([15, 16]),
set([16, 17]),
set([17, 18])
]
where_1 = list()
for atom_pair in atom_list_1:
if atom_pair in EXPECTED_INDICES_1:
where_1.append(1)
elif atom_pair in EXPECTED_INDICES_2:
where_1.append(2)
else:
where_1.append(0)
where_2 = list()
for atom_pair in atom_list_2:
if atom_pair in EXPECTED_INDICES_1:
where_2.append(1)
elif atom_pair in EXPECTED_INDICES_2:
where_2.append(2)
else:
where_2.append(0)
assert (all(i == 1 for i in where_1)
and all(i == 2 for i in where_2)) or \
(all(i == 2 for i in where_1)
and all(i == 1 for i in where_2)), "Invalid rotamer library " + \
"{}, {}".format(where_1, where_2)
assert (all(i == 1 for i in where_1)
and all(i == 2 for i in where_2)
and len(where_1) == len(EXPECTED_INDICES_1)
and len(where_2) == len(EXPECTED_INDICES_2)) or \
(all(i == 2 for i in where_1)
and all(i == 1 for i in where_2)
and len(where_1) == len(EXPECTED_INDICES_2)
and len(where_2) == len(EXPECTED_INDICES_1)), "Unexpected " + \
"number of rotamers"
def test_rotamer_core_constraint(self):
"""
It tests the rotamer library builder when constraining its core
to contain a specific atom.
"""
LIGAND_PATH = 'ligands/oleic_acid.pdb'
ligand_path = get_data_file_path(LIGAND_PATH)
# Test atom index constraint
molecule = Molecule(ligand_path,
core_constraints=[
19,
],
exclude_terminal_rotamers=False)
rotamers_per_branch = molecule.rotamers
assert len(rotamers_per_branch) == 1, "Found an invalid number " + \
"of branches: {}".format(len(rotamers_per_branch))
atom_list = list()
for rotamer in rotamers_per_branch[0]:
atom_list.append(set([rotamer.index1, rotamer.index2]))
EXPECTED_INDICES = [
set([18, 19]),
set([17, 18]),
set([16, 17]),
set([15, 16]),
set([14, 15]),
set([13, 14]),
set([12, 13]),
set([11, 12]),
set([9, 10]),
set([8, 9]),
set([7, 8]),
set([6, 7]),
set([5, 6]),
set([2, 5]),
set([0, 2]),
set([0, 1])
]
assert len(atom_list) == len(EXPECTED_INDICES), "Unexpected " + \
"number of rotamers"
assert all(atom_pair in EXPECTED_INDICES for atom_pair in atom_list), \
"Invalid rotamer library"
# Test PDB atom name constraint
molecule = Molecule(ligand_path,
core_constraints=[
' C18',
],
exclude_terminal_rotamers=False)
rotamers_per_branch = molecule.rotamers
assert len(rotamers_per_branch) == 1, "Found an invalid number " + \
"of branches: {}".format(len(rotamers_per_branch))
atom_list = list()
for rotamer in rotamers_per_branch[0]:
atom_list.append(set([rotamer.index1, rotamer.index2]))
EXPECTED_INDICES = [
set([18, 19]),
set([17, 18]),
set([16, 17]),
set([15, 16]),
set([14, 15]),
set([13, 14]),
set([12, 13]),
set([11, 12]),
set([9, 10]),
set([8, 9]),
set([7, 8]),
set([6, 7]),
set([5, 6]),
set([2, 5]),
set([0, 2]),
set([0, 1])
]
assert len(atom_list) == len(EXPECTED_INDICES), "Unexpected " + \
"number of rotamers"
assert all(atom_pair in EXPECTED_INDICES for atom_pair in atom_list), \
"Invalid rotamer library"
# Test core constraint with terminal exclusion
molecule = Molecule(ligand_path,
core_constraints=[
' C18',
],
exclude_terminal_rotamers=True)
rotamers_per_branch = molecule.rotamers
assert len(rotamers_per_branch) == 1, "Found an invalid number " + \
"of branches: {}".format(len(rotamers_per_branch))
atom_list = list()
for rotamer in rotamers_per_branch[0]:
atom_list.append(set([rotamer.index1, rotamer.index2]))
EXPECTED_INDICES = [
set([17, 18]),
set([16, 17]),
set([15, 16]),
set([14, 15]),
set([13, 14]),
set([12, 13]),
set([11, 12]),
set([9, 10]),
set([8, 9]),
set([7, 8]),
set([6, 7]),
set([5, 6]),
set([2, 5]),
set([0, 2]),
set([0, 1])
]
assert len(atom_list) == len(EXPECTED_INDICES), "Unexpected " + \
"number of rotamers"
assert all(atom_pair in EXPECTED_INDICES for atom_pair in atom_list), \
"Invalid rotamer library"
# Test core constraint with a central core
molecule = Molecule(ligand_path,
core_constraints=[
' C9 ',
],
exclude_terminal_rotamers=True)
rotamers_per_branch = molecule.rotamers
assert len(rotamers_per_branch) == 2, "Found an invalid number " + \
"of branches: {}".format(len(rotamers_per_branch))
atom_list_1 = list()
atom_list_2 = list()
rotamers = rotamers_per_branch[0]
for rotamer in rotamers:
atom_list_1.append(set([rotamer.index1, rotamer.index2]))
rotamers = rotamers_per_branch[1]
for rotamer in rotamers:
atom_list_2.append(set([rotamer.index1, rotamer.index2]))
EXPECTED_INDICES_1 = [
set([9, 10]),
set([8, 9]),
set([7, 8]),
set([6, 7]),
set([5, 6]),
set([2, 5]),
set([0, 2]),
set([0, 1])
]
EXPECTED_INDICES_2 = [
set([12, 11]),
set([12, 13]),
set([13, 14]),
set([14, 15]),
set([15, 16]),
set([16, 17]),
set([17, 18])
]
where_1 = list()
for atom_pair in atom_list_1:
if atom_pair in EXPECTED_INDICES_1:
where_1.append(1)
elif atom_pair in EXPECTED_INDICES_2:
where_1.append(2)
else:
where_1.append(0)
where_2 = list()
for atom_pair in atom_list_2:
if atom_pair in EXPECTED_INDICES_1:
where_2.append(1)
elif atom_pair in EXPECTED_INDICES_2:
where_2.append(2)
else:
where_2.append(0)
assert (all(i == 1 for i in where_1)
and all(i == 2 for i in where_2)) or \
(all(i == 2 for i in where_1)
and all(i == 1 for i in where_2)), "Invalid rotamer library " + \
"{}, {}".format(where_1, where_2)
assert (all(i == 1 for i in where_1)
and all(i == 2 for i in where_2)
and len(where_1) == len(EXPECTED_INDICES_1)
and len(where_2) == len(EXPECTED_INDICES_2)) or \
(all(i == 2 for i in where_1)
and all(i == 1 for i in where_2)
and len(where_1) == len(EXPECTED_INDICES_2)
and len(where_2) == len(EXPECTED_INDICES_1)), "Unexpected " + \
"number of rotamers"
# Test core constraint with a multiple central core
molecule = Molecule(ligand_path,
core_constraints=[' C8 ', ' C9 ', ' C10'],
exclude_terminal_rotamers=True)
rotamers_per_branch = molecule.rotamers
assert len(rotamers_per_branch) == 2, "Found an invalid number " + \
"of branches: {}".format(len(rotamers_per_branch))
atom_list_1 = list()
atom_list_2 = list()
rotamers = rotamers_per_branch[0]
for rotamer in rotamers:
atom_list_1.append(set([rotamer.index1, rotamer.index2]))
rotamers = rotamers_per_branch[1]
for rotamer in rotamers:
atom_list_2.append(set([rotamer.index1, rotamer.index2]))
EXPECTED_INDICES_1 = [
set([8, 9]),
set([7, 8]),
set([6, 7]),
set([5, 6]),
set([2, 5]),
set([0, 2]),
set([0, 1])
]
EXPECTED_INDICES_2 = [
set([12, 11]),
set([12, 13]),
set([13, 14]),
set([14, 15]),
set([15, 16]),
set([16, 17]),
set([17, 18])
]
where_1 = list()
for atom_pair in atom_list_1:
if atom_pair in EXPECTED_INDICES_1:
where_1.append(1)
elif atom_pair in EXPECTED_INDICES_2:
where_1.append(2)
else:
where_1.append(0)
where_2 = list()
for atom_pair in atom_list_2:
if atom_pair in EXPECTED_INDICES_1:
where_2.append(1)
elif atom_pair in EXPECTED_INDICES_2:
where_2.append(2)
else:
where_2.append(0)
assert (all(i == 1 for i in where_1)
and all(i == 2 for i in where_2)) or \
(all(i == 2 for i in where_1)
and all(i == 1 for i in where_2)), "Invalid rotamer library " + \
"{}, {}".format(where_1, where_2)
assert (all(i == 1 for i in where_1)
and all(i == 2 for i in where_2)
and len(where_1) == len(EXPECTED_INDICES_1)
and len(where_2) == len(EXPECTED_INDICES_2)) or \
(all(i == 2 for i in where_1)
and all(i == 1 for i in where_2)
and len(where_1) == len(EXPECTED_INDICES_2)
and len(where_2) == len(EXPECTED_INDICES_1)), "Unexpected " + \
"number of rotamers"
def run_peleffy(pdb_file,
forcefield_name=DEFAULT_OFF_FORCEFIELD,
resolution=DEFAULT_RESOLUTION,
charge_method=DEFAULT_CHARGE_METHOD,
charges_from_file=None,
chain=None,
exclude_terminal_rotamers=True,
output=None,
with_solvent=False,
as_datalocal=False,
conformation_path=None):
"""
It runs peleffy.
Parameters
----------
pdb_file : str
The path to the pdb_file to parameterize with peleffy
forcefield_name : str
The name of an OpenForceField's forcefield
resolution : float
The resolution in degrees for the rotamer library. Default is 30
charge_method : str
The name of the method to use to compute partial charges. Default
is 'am1bcc'
charges_from_file : str
The file containing the partial charges to assign to the
molecule. Default is None
chain : str
Chain to the molecule if the PDB contains multiple molecules.
exclude_terminal_rotamers : bool
Whether to exclude terminal rotamers or not
output : str
Path where output files will be saved
with_solvent : bool
Whether to generate and save the solvent parameters for the input
molecule or not
as_datalocal : bool
Whether to save output files following PELE's DataLocal hierarchy or
not
conformation_path: str
Path to the BCE server outupt to use to extract dihedral angles
dihedral_mode: str
Select what kind of dihedrals to extract (all or only flexible)
"""
if charges_from_file is not None:
charge_method_str = 'file\n' \
+ ' - Charge file: {}'.format(charges_from_file)
charge_method = 'dummy'
else:
charge_method_str = charge_method
log = Logger()
log.info('-' * 60)
log.info('Open Force Field parameterizer for PELE', peleffy.__version__)
log.info('-' * 60)
log.info(' - General:')
log.info(' - Input PDB:', pdb_file)
log.info(' - Output path:', output)
log.info(' - Write solvent parameters:', with_solvent)
log.info(' - DataLocal-like output:', as_datalocal)
log.info(' - Parameterization:')
log.info(' - Force field:', forcefield_name)
log.info(' - Charge method:', charge_method_str)
log.info(' - Rotamer library:')
log.info(' - Resolution:', resolution)
log.info(' - Exclude terminal rotamers:', exclude_terminal_rotamers)
log.info('-' * 60)
from peleffy.topology import Molecule, BCEConformations
from peleffy.template import Impact
from peleffy.solvent import OBC2
from peleffy.forcefield import ForceFieldSelector
from peleffy.topology import Topology
from peleffy.utils import parse_charges_from_mae
from peleffy.utils.input import PDBFile
if not output:
output = os.getcwd()
# Initialize molecule
if chain is not None:
PDBreader = PDBFile(pdb_file)
molecule = PDBreader.get_molecules_from_chain(
selected_chain=chain,
rotamer_resolution=resolution,
exclude_terminal_rotamers=exclude_terminal_rotamers)
else:
molecule = Molecule(
pdb_file,
rotamer_resolution=resolution,
exclude_terminal_rotamers=exclude_terminal_rotamers)
# Initialize force field
ff_selector = ForceFieldSelector()
forcefield = ff_selector.get_by_name(forcefield_name)
output_handler = OutputPathHandler(molecule,
forcefield,
output_path=output,
as_datalocal=as_datalocal)
# if conformation_path is set, we don't want a rotamer library
if conformation_path is None:
rotamer_library = peleffy.topology.RotamerLibrary(molecule)
rotamer_library.to_file(output_handler.get_rotamer_library_path())
# Parameterize molecule with the selected force field
log.info(' - Parameterizing molecule')
parameters = forcefield.parameterize(molecule, charge_method=charge_method)
# Update charge parameters from the MAE file
if charges_from_file is not None:
parameters = parse_charges_from_mae(charges_from_file, parameters)
# Generate the molecular topology
topology = Topology(molecule, parameters)
log.info(' - Parameters were built successfully:')
log.info(' - {} atoms'.format(len(topology.atoms)))
log.info(' - {} bonds'.format(len(topology.bonds)))
log.info(' - {} torsions'.format(len(topology.angles)))
log.info(' - {} propers'.format(len(topology.propers)))
log.info(' - {} impropers'.format(len(topology.impropers)))
# Generate the impact template
impact = Impact(topology)
impact.to_file(output_handler.get_impact_template_path())
# Generate the solvent template
if with_solvent:
solvent = OBC2(topology)
solvent.to_file(output_handler.get_solvent_template_path())
if conformation_path is not None:
conformations = BCEConformations(topology, conformation_path)
conformations.calculate()
conformations.save(output_handler.get_conformation_library_path())
log.info(' - All files were generated successfully:')
if conformation_path is None:
log.info(' - {}'.format(output_handler.get_rotamer_library_path()))
log.info(' - {}'.format(output_handler.get_impact_template_path()))
if conformation_path is not None:
log.info(' - {}'.format(
output_handler.get_conformation_library_path()))
if with_solvent:
log.info(' - {}'.format(output_handler.get_solvent_template_path()))
log.info('-' * 60)
def test_parameterizer(self):
"""It checks the parameterized method."""
def check(hybridff, molecule, ffld_file, reference_file):
"""
It checks the parameters obtained by the force field.
Parameters
----------
hybridff : an OpenFFOPLS2005ForceField object
The hybrid force field to employ in the parameterization
along with the ffld_file
molecule : a peleffy.topology.Molecule
The peleffy's Molecule object to parameterize with the
ffld file
ffld_file : str
The path to the precomputed ffld file from where the
parameters will be extracted
reference_file : str
The path to the file containing the reference parameters
"""
parameters = parameterize_openffopls2005(hybridff, molecule,
ffld_file)
writable_parameters = convert_all_quantities_to_string(parameters)
with open(reference_file) as f:
compare_dicts(writable_parameters, json.load(f))
from peleffy.topology import Molecule
from peleffy.forcefield import OpenFFOPLS2005ForceField
from peleffy.utils import (get_data_file_path,
convert_all_quantities_to_string)
from .utils import compare_dicts, parameterize_openffopls2005
import json
# Load molecule 1
molecule = Molecule(get_data_file_path('ligands/methane.pdb'))
hybridff = OpenFFOPLS2005ForceField(self.FORCE_FIELD_NAME)
ffld_file = get_data_file_path('tests/MET_ffld_output.txt')
# 1st check
check(
hybridff, molecule, ffld_file,
get_data_file_path(
'tests/MET_openff-1.2.1_opls2005_parameters1.json'))
# 2nd check
hybridff.set_nonbonding_parameters('OPLS2005')
check(
hybridff, molecule, ffld_file,
get_data_file_path(
'tests/MET_openff-1.2.1_opls2005_parameters2.json'))
# 3rd check
hybridff.set_nonbonding_parameters('OpenFF')
hybridff.set_bond_parameters('OPLS2005')
check(
hybridff, molecule, ffld_file,
get_data_file_path(
'tests/MET_openff-1.2.1_opls2005_parameters3.json'))
# 4th check
hybridff.set_nonbonding_parameters('OpenFF')
hybridff.set_bond_parameters('OpenFF')
hybridff.set_angle_parameters('OPLS2005')
check(
hybridff, molecule, ffld_file,
get_data_file_path(
'tests/MET_openff-1.2.1_opls2005_parameters4.json'))
# 5th check
hybridff.set_nonbonding_parameters('OPLS2005')
hybridff.set_bond_parameters('OPLS2005')
hybridff.set_angle_parameters('OPLS2005')
check(
hybridff, molecule, ffld_file,
get_data_file_path(
'tests/MET_openff-1.2.1_opls2005_parameters5.json'))
# Load molecule 2
molecule = Molecule(get_data_file_path('ligands/ethylene.pdb'))
hybridff = OpenFFOPLS2005ForceField(self.FORCE_FIELD_NAME)
ffld_file = get_data_file_path('tests/ETL_ffld_output.txt')
# 1st check
check(
hybridff, molecule, ffld_file,
get_data_file_path(
'tests/ETL_openff-1.2.1_opls2005_parameters1.json'))
# 2nd check
hybridff.set_nonbonding_parameters('OpenFF')
hybridff.set_dihedral_parameters('OPLS2005')
check(
hybridff, molecule, ffld_file,
get_data_file_path(
'tests/ETL_openff-1.2.1_opls2005_parameters2.json'))
def test_atom_degrees(self):
"""It checks that the atom degree getter works well."""
from peleffy.topology import Molecule
from peleffy.utils.toolkits import RDKitToolkitWrapper
from peleffy.utils import get_data_file_path
wrapper = RDKitToolkitWrapper()
pdb_path = get_data_file_path('ligands/methane.pdb')
m = Molecule(pdb_path)
degree_by_name = dict(zip(wrapper.get_atom_names(m),
wrapper.get_atom_degrees(m)))
assert degree_by_name == {' C1 ': 4, ' H1 ': 1, ' H2 ': 1,
' H3 ': 1, ' H4 ': 1}, \
'Unexpected pairing between atom names and degrees'
pdb_path = get_data_file_path('ligands/ethylene.pdb')
m = Molecule(pdb_path)
degree_by_name = dict(zip(wrapper.get_atom_names(m),
wrapper.get_atom_degrees(m)))
assert degree_by_name == {' C1 ': 3, ' C2 ': 3, ' H1 ': 1,
' H2 ': 1, ' H3 ': 1, ' H4 ': 1}, \
'Unexpected pairing between atom names and degrees'
pdb_path = get_data_file_path('ligands/acetylene.pdb')
m = Molecule(pdb_path)
degree_by_name = dict(zip(wrapper.get_atom_names(m),
wrapper.get_atom_degrees(m)))
assert degree_by_name == {' C1 ': 2, ' C2 ': 2, ' H1 ': 1,
' H2 ': 1}, \
'Unexpected pairing between atom names and degrees'
pdb_path = get_data_file_path('ligands/propionic_acid.pdb')
m = Molecule(pdb_path)
degree_by_name = dict(zip(wrapper.get_atom_names(m),
wrapper.get_atom_degrees(m)))
assert degree_by_name == {' C1 ': 4, ' C2 ': 4, ' C3 ': 3,
' O1 ': 1, ' O2 ': 2, ' H1 ': 1,
' H2 ': 1, ' H3 ': 1, ' H4 ': 1,
' H5 ': 1, ' H6 ': 1}, \
'Unexpected pairing between atom names and degrees'
pdb_path = get_data_file_path('ligands/trimethylglycine.pdb')
m = Molecule(pdb_path)
degree_by_name = dict(zip(wrapper.get_atom_names(m),
wrapper.get_atom_degrees(m)))
assert degree_by_name == {' C1 ': 4, ' N1 ': 4, ' C2 ': 4,
' C3 ': 4, ' C4 ': 4, ' C5 ': 3,
' O1 ': 1, ' O2 ': 1, ' H1 ': 1,
' H2 ': 1, ' H3 ': 1, ' H4 ': 1,
' H5 ': 1, ' H6 ': 1, ' H7 ': 1,
' H8 ': 1, ' H9 ': 1, ' H10': 1,
' H11': 1}, \
'Unexpected pairing between atom names and degrees'
pdb_path = get_data_file_path('ligands/malonate.pdb')
m = Molecule(pdb_path)
degree_by_name = dict(zip(wrapper.get_atom_names(m),
wrapper.get_atom_degrees(m)))
assert degree_by_name == {' O1 ': 1, ' C1 ': 3, ' O2 ': 1,
' C2 ': 4, ' C3 ': 3, ' O3 ': 2,
' O4 ': 1, ' H1 ': 1, ' H2 ': 1,
' H3 ': 1}, \
'Unexpected pairing between atom names and degrees'
