def add_missing_heavy_atoms(molecular_system,
selection='all',
missing_heavy_atoms=None,
engine='PDBFixer',
syntaxis='MolSysMT'):
engine = digest_engine(engine)
output = None
if engine == "PDBFixer":
from molsysmt.basic import convert, get_form, select
output_form = get_form(molecular_system)
if missing_heavy_atoms is None:
from molsysmt.build import get_missing_heavy_atoms
missing_heavy_atoms = get_missing_heavy_atoms(molecular_system,
selection=selection,
syntaxis=syntaxis)
tmp_molecular_system = convert(molecular_system,
to_form="pdbfixer.PDBFixer")
tmp_molecular_system.missingResidues = {}
tmp_molecular_system.findMissingAtoms()
tmp_molecular_system.missingTerminals = {}
aux_dict = {}
for group, atoms in tmp_molecular_system.missingAtoms.items():
if group.index in missing_heavy_atoms:
aux_dict[group] = []
for atom in atoms:
if atom.name in missing_heavy_atoms[group.index]:
aux_dict[group].append(atom)
tmp_molecular_system.missingAtoms = aux_dict
tmp_molecular_system.addMissingAtoms()
output = convert(tmp_molecular_system, to_form=output_form)
else:
raise NotImplementedError
return output
def potential_energy (molecular_system, selection='all', syntaxis='MolSysMT', engine='OpenMM'):
from molsysmt._private.engines import digest_engine
from molsysmt._private._digestion import digest_molecular_system
from molsysmt.basic import convert
engine=digest_engine(engine)
if engine=='OpenMM':
molecular_system = digest_molecular_system(molecular_system)
if molecular_system.simulation_item is None:
from molsysmt.native.simulation import simulation_to_potential_energy_minimization
molecular_system = molecular_system.combine_with_items(simulation_to_potential_energy_minimization)
context = convert(molecular_system, selection=selection, syntaxis=syntaxis, to_form='openmm.Context')
state = context.getState(getEnergy=True)
output = state.getPotentialEnergy()
else:
raise NotImplementedError()
output = puw.standardize(output)
return output
def mutate(molecular_system,
residue_indices=None,
to_residue_names=None,
engine='PDBFixer',
verbose=False):
if engine == "PDBFixer":
from molsysmt.basic import get, convert, get_form
if not hasattr(residue_indices, '__iter__'):
residue_indices = [residue_indices]
if not hasattr(to_residue_names, '__iter__'):
to_residue_names = [to_residue_names]
to_residue_names = [name.upper() for name in to_residue_names]
form_in = get_form(molecular_system)
tmp_molecular_system = convert(molecular_system,
to_form="pdbfixer.PDBFixer")
from_residue_names, residue_ids, in_chain_ids = get(
tmp_molecular_system,
target='group',
indices=residue_indices,
group_name=True,
group_id=True,
chain_id=True)
for residue_id, from_residue_name, to_residue_name, in_chain_id in zip(
residue_ids, from_residue_names, to_residue_names,
in_chain_ids):
mutation_string = "-".join(
[from_residue_name,
str(residue_id), to_residue_name])
if verbose: print(mutation_string)
tmp_molecular_system.applyMutations([mutation_string], in_chain_id)
tmp_molecular_system = convert(tmp_molecular_system, to_form=form_in)
return tmp_molecular_system
else:
raise NotImplementedError
def to_molsysmt_MolSys(item, selection='all', structure_indices='all', syntaxis='MolSysMT'):
from molsysmt.tools.file_trjpk import is_file_trjpk
from molsysmt.basic import convert
if not is_file_trjpk(item):
raise ValueError
tmp_item = convert(item, 'molsysmt.MolSys', selection=selection, structure_indices=structure_indices, syntaxis=syntaxis)
return tmp_item
def to_molsysmt_MolSys(item, selection='all', structure_indices='all', syntaxis='MolSysMT'):
from molsysmt.tools.string_smiles import is_string_smiles
from molsysmt.basic import convert
if not is_string_smiles(item):
raise ValueError
tmp_item = convert(item, to_form='molsysmt.MolSys', selection=selection, structure_indices=structure_indices, syntaxis=syntaxis)
return tmp_item
def to_openmm_Simulation(item,
molecular_system=None,
atom_indices='all',
structure_indices='all'):
from molsysmt.basic import convert, get
from openmm.app import Simulation
topology = convert(molecular_system,
to_form='openmm.Topology',
selection=atom_indices)
positions = get(molecular_system,
target='atom',
selection=atom_indices,
structure_indices=structure_indices,
coordinates=True)
positions = puw.convert(positions[0], to_unit='nm', to_form='openmm.unit')
simulation = convert(molecular_system, to_form='molsysmt.Simulation')
integrator = simulation.to_openmm_Integrator()
platform = simulation.to_openmm_Platform()
properties = simulation.get_openmm_Simulation_parameters()
tmp_item = Simulation(topology, item, integrator, platform, properties)
tmp_item.context.setPositions(positions)
if simulation.initial_velocities_to_temperature:
temperature = puw.convert(simulation.temperature,
to_unit='K',
to_form='openmm.unit')
tmp_item.context.setVelocitiesToTemperature(temperature)
if molecular_system is not None:
tmp_molecular_system = molecular_system.combine_with_items(
tmp_item,
atom_indices=atom_indices,
structure_indices=structure_indices)
else:
tmp_molecular_system = None
return tmp_item, tmp_molecular_system
def to_nglview_NGLWidget(item, selection='all', structure_indices='all', syntaxis='MolSysMT'):
from molsysmt.tools.aminoacids3 import is_string_aminoacids3
from molsysmt.basic import convert
if not is_string_aminoacids3(item):
raise ValueError
tmp_item = convert(item, to_form='nglview.NGLWidget', selection=selection,
structure_indices=structure_indices, syntaxis=syntaxis)
return tmp_item
def to_molsysmt_Structures(item, selection='all', structure_indices='all', syntaxis='MolSysMT'):
from molsysmt.tools.rdkit_Mol import is_rdkit_Mol
from molsysmt.basic import convert
if not is_rdkit_Mol(item):
raise ValueError
tmp_item = convert(item, to_form='molsysmt.Trajectory', selection=selection,
structure_indices=structure_indices, syntaxis=syntaxis)
return tmp_item
def to_mdtraj_Topology(item, selection='all', structure_indices='all', syntaxis='MolSysMT'):
from molsysmt.tools.parmed_GromacsTopologyFile import is_parmed_GromacsTopologyFile
from molsysmt.basic import convert
if not is_parmed_GromacsTopologyFile(item):
raise ValueError
tmp_item = convert(item, to_form='mdtraj_Topology', selection=selection,
structure_indices=structure_indices, syntaxis=syntaxis)
return tmp_item
def to_file_top(item, selection='all', structure_indices='all', output_filename=None, syntaxis='MolSysMT'):
from molsysmt.tools.molsysmt_MolSys import is_molsymst_MolSys
from molsysmt.basic import convert
if not is_molsysmt_MolSys(item):
raise ValueError
if output_filename is None:
raise ValueError
tmp_item = convert(item, to_form=output_filename, selection=selection,
structure_indices=structure_indices, syntaxis=syntaxis)
return tmp_item
def to_file_fasta(item, selection='all', structure_indices='all', output_filename=None, syntaxis='MolSysMT'):
from molsysmt.tools.string_aminoacids1 import is_string_aminoacids1
from molsysmt.basic import convert
if not is_string_aminoacids1(item):
raise ValueError
if output_filename is None:
raise ValueError
tmp_item = convert(item, to_form=output_filename, selection=selection,
structure_indices=structure_indices, syntaxis=syntaxis)
return tmp_item
def to_biopython_SeqRecord(item,
selection='all',
structure_indices='all',
syntaxis='MolSysMT'):
from molsysmt.tools.file_fasta import is_file_fasta
from molsysmt.basic import convert
if not is_file_fasta(item):
raise ValueError
tmp_item = convert(item,
'biopython.SeqRecord',
selection=selection,
structure_indices=structure_indices,
syntaxis=syntaxis)
return tmp_item
def to_openmm_Topology(item,
selection='all',
structure_indices='all',
syntaxis='MolSysMT'):
from molsysmt.tools.file_top import is_file_top
from molsysmt.basic import convert
if not is_file_top(item):
raise ValueError
tmp_item = convert(item,
'openmm.Topology',
selection=selection,
structure_indices=structure_indices,
syntaxis=syntaxis)
return tmp_item
def to_molsysmt_Topology(item,
selection='all',
structure_indices='all',
syntaxis='MolSysMT'):
from molsysmt.tools.openff_Molecule import is_openff_Molecule
from molsysmt.basic import convert
if not is_openff_Molecule(item):
raise ValueError
tmp_item = convert(item,
to_form='molsysmt.Topology',
selection=selection,
structure_indices=structure_indices,
syntaxis=syntaxis)
return tmp_item
def to_molsysmt_Simulation(item,
selection='all',
structure_indices='all',
syntaxis='MolSysMT'):
from molsysmt.tools.molsysmt_SimulationDict import is_molsysmt_SimulationDict
from molsysmt.basic import convert
if not is_molsysmt_SimulationDict(item):
raise ValueError
tmp_item = convert(item,
to_form='molsysmt.Simulation',
selection=selection,
structure_indices=structure_indices,
syntaxis=syntaxis)
return tmp_item
def to_XYZ(item,
selection='all',
structure_indices='all',
syntaxis='MolSysMT'):
from molsysmt.tools.file_xyznpy import is_file_xyznpy
from molsysmt.basic import convert
if not is_file_xyznpy(item):
raise ValueError
tmp_item = convert(item,
'XYZ',
selection=selection,
structure_indices=structure_indices,
syntaxis=syntaxis)
return tmp_item
def to_molsysmt_Structures(item,
selection='all',
structure_indices='all',
syntaxis='MolSysMT'):
from molsysmt.tools.file_mdcrd import is_file_mdcrd
from molsysmt.basic import convert
if not is_file_mdcrd(item):
raise ValueError
tmp_item = convert(item,
'molsysmt.Trajectory',
selection=selection,
structure_indices=structure_indices,
syntaxis=syntaxis)
return tmp_item
def to_biopython_Seq(item,
selection='all',
structure_indices='all',
syntaxis='MolSysMT'):
from molsysmt.tools.aminoacids3 import is_string_aminoacids3
from molsysmt.basic import convert
if not is_string_aminoacids3(item):
raise ValueError
tmp_item = convert(item,
to_form='biopython.Seq',
selection=selection,
structure_indices=structure_indices,
syntaxis=syntaxis)
return tmp_item
def to_openmm_Context(item,
selection='all',
structure_indices='all',
syntaxis='MolSysMT'):
from molsysmt.tools.openmm_Simulation import is_openmm_Simulation
from molsysmt.basic import convert
if not is_openmm_Simulation(item):
raise ValueError
tmp_item = convert(item,
to_form='openmm.Context',
selection=selection,
structure_indices=structure_indices,
syntaxis=syntaxis)
return tmp_item
def to_parmed_Structure(item,
selection='all',
structure_indices='all',
syntaxis='MolSysMT'):
from molsysmt.tools.file_top import is_file_top
from molsysmt.basic import convert
if not is_file_top(item):
raise ValueError
tmp_item = convert(item,
'parmed.Structure',
selection=selection,
structure_indices=structure_indices,
syntaxis=syntaxis)
return tmp_item
def get_missing_heavy_atoms(molecular_system,
selection='all',
engine='PDBFixer',
syntaxis='MolSysMT'):
engine = digest_engine(engine)
output = {}
if engine == "PDBFixer":
from molsysmt.basic import convert, get_form, select
correction_group_indices = False
if selection is not 'all':
group_indices_in_selection = select(molecular_system,
target='group',
selection=selection)
correction_group_indices = True
tmp_item = convert(molecular_system,
selection=selection,
to_form="pdbfixer.PDBFixer",
syntaxis=syntaxis)
tmp_item.findMissingResidues()
tmp_item.findMissingAtoms()
missingAtoms = tmp_item.missingAtoms
for group, atoms in missingAtoms.items():
if correction_group_indices:
group_index = group_indices_in_selection[group.index]
else:
group_index = group.index
output[group_index] = []
for atom in atoms:
output[group_index].append(atom.name)
else:
raise NotImplementedError
return output
def to_openmm_System(self,
molecular_system=None,
selection='all',
structure_indices='all'):
from molsysmt.basic import convert
if molecular_system is None:
molecular_system = self._molecular_system
else:
molecular_system = digest_molecular_system(molecular_system)
if molecular_system is None:
raise NoMolecularSystemError()
system = convert([molecular_system, self],
selection=selection,
to_form='openmm.System')
return system
def get_sasa (molecular_system, target='atom', selection='all', structure_indices='all', syntaxis='MolSysMT',
engine='MDTraj'):
engine = digest_engine(engine)
target = digest_target(target)
if engine == 'MDTraj':
from mdtraj import shrake_rupley
tmp_item = convert(molecular_system, structure_indices=structure_indices, to_form='mdtraj.Trajectory')
sasa_array = shrake_rupley(tmp_item, mode='atom') # tiene probe_radius y n_sphere_points
if target=='atom':
if selection is not 'all':
atom_indices = select(molecular_system, selection=selection, syntaxis=syntaxis)
sasa_array = sasa_array[:,atom_indices]
else:
sets_atoms = get(molecular_system, target=target, selection=selection, syntaxis=syntaxis, atom_index=True)
n_sets = len(sets_atoms)
n_structures = sasa_array.shape[0]
new_sasa_array = np.empty([n_structures, n_sets], dtype='float')
for ii in range(n_sets):
new_sasa_array[:,ii] = sasa_array[:,sets_atoms[ii].astype(int)].sum(axis=1)
sasa_array = new_sasa_array
sasa_array = puw.quantity(sasa_array, 'nm**2')
sasa_array = puw.standardize(sasa_array)
else:
raise NotImplementedError("Engine not implemented yet")
return sasa_array
def to_openmm_Context(self,
molecular_system=None,
selection='all',
structure_indices='all'):
from molsysmt.basic import convert
if molecular_system is None:
molecular_system = self._molecular_system
else:
molecular_system = digest_molecular_system(molecular_system)
if molecular_system is None:
raise NoMolecularSystemError()
context = convert(molecular_system,
selection=selection,
simulation=self,
to_form='openmm.Context')
return context
def to_openmm_Simulation(item,
molecular_system,
atom_indices='all',
structure_indices='all'):
from molsysmt.form.openmm_Topology import to_openmm_Simulation as openmm_Topology_to_openmm_Simulation
from molsysmt.basic import convert
molecular_mechanics = convert(molecular_system,
to_form='molsysmt.MolecularMechanics')
forcefield = molecular_mechanics.to_openmm_ForceField()
system_parameters = molecular_mechanics.get_openmm_System_parameters()
tmp_item = openmm_Topology_to_openmm_Context(item,
atom_indices=atom_indices,
forcefield=forcefield,
parameters=parameters,
check=False)
return tmp_item
def one_system(molecular_system=None,
selection=None,
structure_indices=None,
form=None,
syntaxis='MolSysMT'):
from molsysmt.basic import convert, select
atom_indices = None
if form is not None:
tmp_molecular_system = convert(molecular_system, form)
else:
tmp_molecular_system = item
if selection is not None:
atom_indices = select(molecular_system, selection, syntaxis=syntaxis)
structure_indices = frameslist(tmp_molecular_system, structure_indices)
return tmp_molecular_system, atom_indices, structure_indices
def to_file_pir(item,
selection='all',
structure_indices='all',
output_filename=None,
syntaxis='MolSysMT'):
from molsysmt.tools.biopython_SeqRecord import is_biopython_SeqRecord
from molsysmt.basic import convert
if not is_biopython_SeqRecord(item):
raise ValueError
if output_filename is None:
raise ValueError
tmp_item = convert(item,
to_form=output_filename,
selection=selection,
structure_indices=structure_indices,
syntaxis=syntaxis)
return tmp_item
def to_file_pdb(item,
selection='all',
structure_indices='all',
output_filename=None,
syntaxis='MolSysMT'):
from molsysmt.tools.openmm_Simulation import is_openmm_Simulation
from molsysmt.basic import convert
if not is_openmm_Simulation(item):
raise ValueError
if output_filename is None:
raise ValueError
tmp_item = convert(item,
to_form=output_filename,
selection=selection,
structure_indices=structure_indices,
syntaxis=syntaxis)
return tmp_item
def add_terminal_cappings(molecular_system,
N_terminal=None,
C_terminal=None,
selection='all',
syntaxis='MolSysMT',
engine='PDBFixer'):
from molsysmt.basic import get_form, convert, get, select
form_in = get_form(molecular_system)
if engine is 'PDBFixer':
from pdbfixer.pdbfixer import Sequence
tmp_molecular_system = convert(molecular_system,
to_form='pdbfixer.PDBFixer')
atom_indices_in_selection = select(tmp_molecular_system,
selection=selection,
syntaxis=syntaxis)
atom_indices_in_components = get(
tmp_molecular_system,
target='component',
selection='component_type in ["peptide", "protein"] \
and atom_index in @atom_indices_in_selection',
atom_index=True)
for atom_indices_in_component in atom_indices_in_components:
chain_id = get(
tmp_molecular_system,
target='chain',
selection='atom_index in @atom_indices_in_component',
chain_id=True)
groups_sequence = get(
tmp_molecular_system,
target='group',
selection='atom_index in @atom_indices_in_component',
group_name=True)
groups_sequence = list(groups_sequence)
if N_terminal is not None:
groups_sequence = [N_terminal] + groups_sequence
if C_terminal is not None:
groups_sequence = groups_sequence + [C_terminal]
tmp_molecular_system.sequences.append(
Sequence(chain_id, groups_sequence))
tmp_molecular_system.findMissingResidues()
tmp_molecular_system.findMissingAtoms()
tmp_molecular_system.addMissingAtoms()
n_hs = get(tmp_molecular_system,
target='atom',
selection='atom_type=="H"',
n_atoms=True)
if n_hs > 0:
tmp_molecular_system.addMissingHydrogens(pH=7.4)
tmp_molecular_system = convert(tmp_molecular_system, to_form=form_in)
else:
raise NotImplementedError
return tmp_molecular_system
def get_sequence_alignment(molecular_system,
selection='all',
reference_molecular_system=None,
reference_selection=None,
engine='biopython',
syntaxis='MolSysMT',
prettyprint=False,
alignment_index=0):
if engine == 'biopython':
# from ensembler.modeling.align_target_template
# (https://github.com/choderalab/ensembler/blob/master/ensembler/modeling.py)
# See: https://biopython.org/docs/1.75/api/Bio.Align.html#Bio.Align.PairwiseAligner
from Bio import Align
tmp_ref_seq = convert(reference_molecular_system,
selection=reference_selection,
syntaxis=syntaxis,
to_form='biopython.Seq')
tmp_seq = convert(molecular_system,
selection=selection,
syntaxis=syntaxis,
to_form='biopython.Seq')
aligner = Align.PairwiseAligner()
aligner.mode = 'global'
aligner.match_score = 1.0
aligner.mismatch_score = 0.0
aligner.open_gap_score = -0.5
aligner.extend_gap_score = -0.1
aligner.target_end_gap_score = 0.0
aligner.query_end_gap_score = 0.0
alignment = aligner.align(tmp_ref_seq, tmp_seq)
del (aligner, Align, tmp_ref_seq, tmp_seq)
txt_aln = alignment[alignment_index].format().split('\n')
seq_ref = txt_aln[0]
seq = txt_aln[2]
elif engine == 'modeller':
raise NotImplementedError
else:
raise NotImplementedError
if prettyprint:
textredbold = '\033[1;31;48m' # Red bold text
textbluebold = '\033[1;34;48m' # Green bold text
endcolor = '\033[m' # reset color
# Color guide in: http://ozzmaker.com/add-colour-to-text-in-python/
pptxt = ''
pptxt_ref = ''
for res, res_ref in zip(seq, seq_ref):
if res == res_ref:
pptxt += res
pptxt_ref += res_ref
elif (res == '-' and res_ref != '-'):
pptxt += res
pptxt_ref += textbluebold + res_ref + endcolor
elif (res_ref == '-' and res != '-'):
pptxt += textbluebold + res + endcolor
pptxt_ref += res_ref
else:
pptxt += textredbold + res + endcolor
pptxt_ref += textredbold + res_ref + endcolor
print(pptxt)
print()
print(pptxt_ref)
pass
else:
return seq, seq_ref