def test_sanitizeSMILES():
"""
Test SMILES sanitization.
"""
from perses.utils.smallmolecules import sanitizeSMILES
smiles_list = [
'CC', 'CCC', '[H][C@]1(NC[C@@H](CC1CO[C@H]2CC[C@@H](CC2)O)N)[H]'
]
sanitized_smiles_list = sanitizeSMILES(smiles_list, mode='drop')
if len(sanitized_smiles_list) != 2:
raise Exception(
"Molecules with undefined stereochemistry are not being properly dropped (size=%d)."
% len(sanitized_smiles_list))
sanitized_smiles_list = sanitizeSMILES(smiles_list, mode='expand')
if len(sanitized_smiles_list) != 4:
raise Exception(
"Molecules with undefined stereochemistry are not being properly expanded (size=%d)."
% len(sanitized_smiles_list))
# Check that all molecules can be round-tripped.
from openeye.oechem import OEGraphMol, OESmilesToMol, OECreateIsoSmiString
for smiles in sanitized_smiles_list:
molecule = OEGraphMol()
OESmilesToMol(molecule, smiles)
isosmiles = OECreateIsoSmiString(molecule)
if (smiles != isosmiles):
raise Exception(
"Molecule '%s' was not properly round-tripped (result was '%s')"
% (smiles, isosmiles))
def createSystemFromSMILES(smiles,title='MOL', **system_generator_kwargs):
"""
Create an openmm system from a smiles string
Parameters
----------
smiles : str
smiles string of molecule
Returns
-------
molecule : openeye.oechem.OEMol
OEMol molecule
system : openmm.System object
OpenMM system
positions : [n,3] np.array of floats
Positions
topology : openmm.app.Topology object
Topology
"""
# clean up smiles string
from perses.utils.smallmolecules import sanitizeSMILES
smiles = sanitizeSMILES([smiles])
smiles = smiles[0]
# Create OEMol
molecule = smiles_to_oemol(smiles, title=title)
system_generator = system_generator_wrapper([molecule], **system_generator_kwargs)
# generate openmm system, positions and topology
system, positions, topology = OEMol_to_omm_ff(molecule, system_generator)
return (molecule, system, positions, topology)
def __init__(self, **kwargs):
super(Selectivity, self).__init__(**kwargs)
solvents = ['explicit'] # DEBUG
components = ['src-imatinib', 'abl-imatinib'] # TODO: Add 'ATP:kinase' complex to enable resistance design
padding = 9.0*unit.angstrom
explicit_solvent_model = 'tip3p'
setup_path = 'data/abl-src'
thermodynamic_states = dict()
temperature = 300*unit.kelvin
pressure = 1.0*unit.atmospheres
geometry_engine = geometry.FFAllAngleGeometryEngine()
# Construct list of all environments
environments = list()
for solvent in solvents:
for component in components:
environment = solvent + '-' + component
environments.append(environment)
# Read SMILES from CSV file of clinical kinase inhibitors.
from pkg_resources import resource_filename
smiles_filename = resource_filename('perses', 'data/clinical-kinase-inhibitors.csv')
import csv
molecules = list()
with open(smiles_filename, 'r') as csvfile:
csvreader = csv.reader(csvfile, delimiter=',', quotechar='"')
for row in csvreader:
name = row[0]
smiles = row[1]
molecules.append(smiles)
# Add current molecule
molecules.append('Cc1ccc(cc1Nc2nccc(n2)c3cccnc3)NC(=O)c4ccc(cc4)C[NH+]5CCN(CC5)C')
self.molecules = molecules
# Expand molecules without explicit stereochemistry and make canonical isomeric SMILES.
molecules = sanitizeSMILES(self.molecules)
# Create a system generator for desired forcefields
from perses.rjmc.topology_proposal import SystemGenerator
from pkg_resources import resource_filename
gaff_xml_filename = resource_filename('perses', 'data/gaff.xml')
system_generators = dict()
system_generators['explicit'] = SystemGenerator([gaff_xml_filename, 'amber99sbildn.xml', 'tip3p.xml'],
forcefield_kwargs={'nonbondedCutoff' : 9.0 * unit.angstrom, 'implicitSolvent' : None, 'constraints' : None },periodic_forcefield_kwargs = {'nonbondedMethod': app.CutoffPeriodic})
use_antechamber=True)
def __init__(self, **kwargs):
super(Selectivity, self).__init__(**kwargs)
solvents = ['explicit'] # DEBUG
components = ['src-imatinib', 'abl-imatinib'] # TODO: Add 'ATP:kinase' complex to enable resistance design
padding = 9.0*unit.angstrom
explicit_solvent_model = 'tip3p'
setup_path = 'data/abl-src'
thermodynamic_states = dict()
temperature = 300*unit.kelvin
pressure = 1.0*unit.atmospheres
geometry_engine = geometry.FFAllAngleGeometryEngine()
# Construct list of all environments
environments = list()
for solvent in solvents:
for component in components:
environment = solvent + '-' + component
environments.append(environment)
# Read SMILES from CSV file of clinical kinase inhibitors.
from pkg_resources import resource_filename
smiles_filename = resource_filename('perses', 'data/clinical-kinase-inhibitors.csv')
import csv
molecules = list()
with open(smiles_filename, 'r') as csvfile:
csvreader = csv.reader(csvfile, delimiter=',', quotechar='"')
for row in csvreader:
name = row[0]
smiles = row[1]
molecules.append(smiles)
# Add current molecule
molecules.append('Cc1ccc(cc1Nc2nccc(n2)c3cccnc3)NC(=O)c4ccc(cc4)C[NH+]5CCN(CC5)C')
self.molecules = molecules
# Expand molecules without explicit stereochemistry and make canonical isomeric SMILES.
molecules = sanitizeSMILES(self.molecules)
# Create a system generator for desired forcefields
from perses.rjmc.topology_proposal import SystemGenerator
from pkg_resources import resource_filename
gaff_xml_filename = resource_filename('perses', 'data/gaff.xml')
system_generators = dict()
system_generators['explicit'] = SystemGenerator([gaff_xml_filename, 'amber99sbildn.xml', 'tip3p.xml'],
forcefield_kwargs={ 'nonbondedMethod' : app.CutoffPeriodic, 'nonbondedCutoff' : 9.0 * unit.angstrom, 'implicitSolvent' : None, 'constraints' : None },
use_antechamber=True)
# NOTE implicit solvent not supported by this SystemGenerator
# system_generators['implicit'] = SystemGenerator([gaff_xml_filename, 'amber99sbildn.xml', 'amber99_obc.xml'],
# forcefield_kwargs={ 'nonbondedMethod' : app.NoCutoff, 'implicitSolvent' : app.OBC2, 'constraints' : None },
# use_antechamber=True)
system_generators['vacuum'] = SystemGenerator([gaff_xml_filename, 'amber99sbildn.xml'],
forcefield_kwargs={ 'nonbondedMethod' : app.NoCutoff, 'implicitSolvent' : None, 'constraints' : None },
use_antechamber=True)
# Copy system generators for all environments
for solvent in solvents:
for component in components:
environment = solvent + '-' + component
system_generators[environment] = system_generators[solvent]
# Load topologies and positions for all components
from simtk.openmm.app import PDBFile, Modeller
topologies = dict()
positions = dict()
for component in components:
pdb_filename = resource_filename('perses', os.path.join(setup_path, '%s.pdb' % component))
print(pdb_filename)
pdbfile = PDBFile(pdb_filename)
topologies[component] = pdbfile.topology
positions[component] = pdbfile.positions
# Construct positions and topologies for all solvent environments
for solvent in solvents:
for component in components:
environment = solvent + '-' + component
if solvent == 'explicit':
# Create MODELLER object.
modeller = app.Modeller(topologies[component], positions[component])
modeller.addSolvent(system_generators[solvent].getForceField(), model='tip3p', padding=9.0*unit.angstrom)
topologies[environment] = modeller.getTopology()
positions[environment] = modeller.getPositions()
else:
environment = solvent + '-' + component
topologies[environment] = topologies[component]
positions[environment] = positions[component]
# Set up the proposal engines.
from perses.rjmc.topology_proposal import SmallMoleculeSetProposalEngine
proposal_metadata = { }
proposal_engines = dict()
for environment in environments:
storage = None
if self.storage:
storage = NetCDFStorageView(self.storage, envname=environment)
proposal_engines[environment] = SmallMoleculeSetProposalEngine(molecules, system_generators[environment], residue_name='MOL', storage=storage)
# Generate systems
systems = dict()
for environment in environments:
systems[environment] = system_generators[environment].build_system(topologies[environment])
# Define thermodynamic state of interest.
from perses.samplers.thermodynamics import ThermodynamicState
thermodynamic_states = dict()
temperature = 300*unit.kelvin
pressure = 1.0*unit.atmospheres
for component in components:
for solvent in solvents:
environment = solvent + '-' + component
if solvent == 'explicit':
thermodynamic_states[environment] = ThermodynamicState(system=systems[environment], temperature=temperature, pressure=pressure)
else:
thermodynamic_states[environment] = ThermodynamicState(system=systems[environment], temperature=temperature)
# Create SAMS samplers
from perses.samplers.samplers import SamplerState, MCMCSampler, ExpandedEnsembleSampler, SAMSSampler
mcmc_samplers = dict()
exen_samplers = dict()
sams_samplers = dict()
for solvent in solvents:
for component in components:
environment = solvent + '-' + component
chemical_state_key = proposal_engines[environment].compute_state_key(topologies[environment])
storage = None
if self.storage:
storage = NetCDFStorageView(self.storage, envname=environment)
if solvent == 'explicit':
thermodynamic_state = ThermodynamicState(system=systems[environment], temperature=temperature, pressure=pressure)
sampler_state = SamplerState(system=systems[environment], positions=positions[environment], box_vectors=systems[environment].getDefaultPeriodicBoxVectors())
else:
thermodynamic_state = ThermodynamicState(system=systems[environment], temperature=temperature)
sampler_state = SamplerState(system=systems[environment], positions=positions[environment])
mcmc_samplers[environment] = MCMCSampler(thermodynamic_state, sampler_state, storage=storage)
mcmc_samplers[environment].nsteps = 5 # reduce number of steps for testing
mcmc_samplers[environment].verbose = True
exen_samplers[environment] = ExpandedEnsembleSampler(mcmc_samplers[environment], topologies[environment], chemical_state_key, proposal_engines[environment], options={'nsteps':10}, geometry_engine=geometry_engine, storage=storage)
exen_samplers[environment].verbose = True
sams_samplers[environment] = SAMSSampler(exen_samplers[environment], storage=storage)
sams_samplers[environment].verbose = True
thermodynamic_states[environment] = thermodynamic_state
# Create test MultiTargetDesign sampler.
from perses.samplers.samplers import MultiTargetDesign
target_samplers = {sams_samplers['explicit-src-imatinib']: 1.0, sams_samplers['explicit-abl-imatinib']: -1.0}
designer = MultiTargetDesign(target_samplers, storage=self.storage)
designer.verbose = True
# Store things.
self.molecules = molecules
self.environments = environments
self.topologies = topologies
self.positions = positions
self.system_generators = system_generators
self.systems = systems
self.proposal_engines = proposal_engines
self.thermodynamic_states = thermodynamic_states
self.mcmc_samplers = mcmc_samplers
self.exen_samplers = exen_samplers
self.sams_samplers = sams_samplers
self.designer = designer
# This system must currently be minimized.
minimize(self)