def __init__(self, system, ai, settings, ffrefs=[]): ''' **Arguments** system a Yaff `System` instance defining the system ai a `Reference` instance corresponding to the ab initio input data settings a `Settings` instance defining all QuickFF settings **Optional Arguments** ffrefs a list of `Reference` instances defining the a-priori force field contributions. ''' with log.section('INIT', 1, timer='Initializing'): log.dump('Initializing program') self.settings = settings self.system = system self.ai = ai self.ffrefs = ffrefs self.valence = ValenceFF(system, settings) self.perturbation = RelaxedStrain(system, self.valence, settings) self.trajectories = None self.print_system()
def __init__(self, system, ai, **kwargs): ''' **Arguments** system a Yaff `System` object defining the system ai a `Reference` instance corresponding to the ab initio input data **Keyword Arguments** ffrefs a list of `Reference` objects corresponding to a priori determined contributions to the force field (such as eg. electrostatics or van der Waals contributions) fn_yaff the name of the file to write the final parameters to in Yaff format. The default is `pars.txt`. fn_sys the name of the file to write the system to. The default is `system.chk`. fn_traj a cPickle filename to read/write the perturbation trajectories from/to. If the file exists, the trajectories are read from the file. If the file does not exist, the trajectories are written to the file. only_traj specifier to determine for which terms a perturbation trajectory needs to be constructed. If ONLY_TRAJ is a single string, it is interpreted as a task (only terms that have this task in their tasks attribute will get a trajectory). If ONLY_TRAJ is a list of strings, each string is interpreted as the basename of the term for which a trajectory will be constructed. plot_traj if set to True, all energy contributions along each perturbation trajectory will be plotted using the final force field. xyz_traj if set to True, each perturbation trajectory will be written to an XYZ file. ''' with log.section('PROG', 2, timer='Initializing'): log.dump('Initializing program') self.system = system self.ai = ai self.kwargs = kwargs self.valence = ValenceFF(system) self.perturbation = RelaxedStrain(system, self.valence) self.trajectories = None
def __init__(self, system, ai, settings, ffrefs=[]): ''' **Arguments** system a Yaff `System` instance defining the system ai a `Reference` instance corresponding to the ab initio input data settings a `Settings` instance defining all QuickFF settings **Optional Arguments** ffrefs a list of `Reference` instances defining the a-priori force field contributions. ''' with log.section('INIT', 1, timer='Initializing'): log.dump('Initializing program') self.settings = settings self.system = system self.ai = ai self.ffrefs = ffrefs self.valence = ValenceFF(system, settings) self.perturbation = RelaxedStrain(system, self.valence, settings) self.trajectories = None self.print_system()
class BaseProgram(object): ''' Base program which implements all possible steps of a force field fitting program. The actual sequence of the steps are defined in the deriving classes. ''' def __init__(self, system, ai, **kwargs): ''' **Arguments** system a Yaff `System` object defining the system ai a `Reference` instance corresponding to the ab initio input data **Keyword Arguments** ffrefs a list of `Reference` objects corresponding to a priori determined contributions to the force field (such as eg. electrostatics or van der Waals contributions) fn_yaff the name of the file to write the final parameters to in Yaff format. The default is `pars.txt`. fn_charmm22_prm the name of a CHARMM parameter file. If not given, the file is not written fn_charmm22_psf the name of a CHARMM topology file. If not given, the file is not written fn_sys the name of the file to write the system to. The default is `system.chk`. fn_traj a cPickle filename to read/write the perturbation trajectories from/to. If the file exists, the trajectories are read from the file. If the file does not exist, the trajectories are written to the file. only_traj specifier to determine for which terms a perturbation trajectory needs to be constructed. If ONLY_TRAJ is a single string, it is interpreted as a task (only terms that have this task in their tasks attribute will get a trajectory). If ONLY_TRAJ is a list of strings, each string is interpreted as the basename of the term for which a trajectory will be constructed. plot_traj if set to True, all energy contributions along each perturbation trajectory will be plotted using the final force field. xyz_traj if set to True, each perturbation trajectory will be written to an XYZ file. ''' with log.section('PROG', 2, timer='Initializing'): log.dump('Initializing program') self.system = system self.ai = ai self.kwargs = kwargs self.valence = ValenceFF(system) self.perturbation = RelaxedStrain(system, self.valence) self.trajectories = None def reset_system(self): ''' routine to reset the system coords to the ai equilbrium ''' log.dump('Resetting system coordinates to ab initio ref') self.system.pos = self.ai.coords0.copy() self.valence.dlist.forward() self.valence.iclist.forward() def update_trajectory_terms(self): ''' Routine to make ``self.valence.terms`` and the term attribute of each trajectory in ``self.trajectories`` consistent again. This is usefull if the trajectory were read from a file and the ``valenceFF`` instance was modified. ''' log.dump('Updating terms of trajectories to current valenceFF terms') with log.section('PTUPD', 3): #update the terms in the trajectories to match the terms in #self.valence for traj in self.trajectories: found = False for term in self.valence.iter_terms(): if traj.term.get_atoms() == term.get_atoms(): if found: raise ValueError( 'Found two terms for trajectory %s with atom indices %s' % (traj.term.basename, str(traj.term.get_atoms()))) traj.term = term if 'PT_ALL' not in term.tasks: log.dump( 'PT_ALL not in tasks of %s-%i, deactivated PT' % (term.basename, term.index)) traj.active = False found = True if not found: log.warning( 'No term found for trajectory %s with atom indices %s' % (traj.term.basename, str(traj.term.get_atoms()))) #check if every term with task PT_ALL has a trajectory associated #with it. It a trajectory is missing, generate it. for term in self.valence.iter_terms(): if 'PT_ALL' not in term.tasks: continue found = False for traj in self.trajectories: if term.get_atoms() == traj.term.get_atoms(): if found: raise ValueError( 'Found two trajectories for term %s with atom indices %s' % (term.basename, str(term.get_atoms()))) found = True if not found: log.warning( 'No trajectory found for term %s with atom indices %s. Generating it now.' % (term.basename, str(term.get_atoms()))) trajectory = self.perturbation.prepare([term])[term.index] self.perturbation.generate(trajectory) self.trajectories.append(trajectory) def average_pars(self): ''' Average force field parameters over master and slaves. ''' log.dump('Averaging force field parameters over master and slaves') for master in self.valence.iter_masters(): npars = len(self.valence.get_params(master.index)) pars = np.zeros([len(master.slaves) + 1, npars], float) pars[0, :] = np.array(self.valence.get_params(master.index)) for i, islave in enumerate(master.slaves): pars[1 + i, :] = np.array(self.valence.get_params(islave)) if master.kind == 0: #harmonic fc, rv = pars.mean(axis=0) self.valence.set_params(master.index, fc=fc, rv0=rv) for islave in master.slaves: self.valence.set_params(islave, fc=fc, rv0=rv) elif master.kind == 1: a0, a1, a2, a3 = pars.mean(axis=0) self.valence.set_params(master.index, a0=a0, a1=a1, a2=a2, a3=a3) for islave in master.slaves: self.valence.set_params(islave, a0=a0, a1=a1, a2=a2, a3=a3) elif master.kind == 3: #cross fc, rv0, rv1 = pars.mean(axis=0) self.valence.set_params(master.index, fc=fc, rv0=rv0, rv1=rv1) for islave in master.slaves: self.valence.set_params(islave, fc=fc, rv0=rv0, rv1=rv1) elif master.kind == 4: #cosine assert pars[:, 0].std() < 1e-6, 'dihedral multiplicity not unique' m, fc, rv = pars.mean(axis=0) self.valence.set_params(master.index, fc=fc, rv0=rv, m=m) for islave in master.slaves: self.valence.set_params(islave, fc=fc, rv0=rv, m=m) else: raise NotImplementedError def make_output(self): ''' Dump Yaff parameters, Yaff system, plot energy contributions along perturbation trajectories and dump perturbation trajectories to XYZ files. ''' fn_yaff = self.kwargs.get('fn_yaff', None) if fn_yaff is None: fn_yaff = 'pars_cov%s.txt' % (self.kwargs.get('suffix', '')) self.valence.dump_yaff(fn_yaff) fn_charmm22_prm = self.kwargs.get('fn_charmm22_prm') if fn_charmm22_prm is not None: dump_charmm22_prm(self.valence, fn_charmm22_prm) fn_charmm22_psf = self.kwargs.get('fn_charmm22_psf') if fn_charmm22_psf is not None: dump_charmm22_psf(self.system, self.valence, fn_charmm22_psf) fn_sys = self.kwargs.get('fn_sys', None) if fn_sys is None: fn_sys = 'system%s.chk' % (self.kwargs.get('suffix', '')) self.system.to_file(fn_sys) self.plot_trajectories(do_valence=True) def plot_trajectories(self, do_valence=False): ''' Plot energy contributions along perturbation trajectories and dump perturbation trajectories to XYZ files. ''' only = self.kwargs.get('only_traj', 'PT_ALL') if not isinstance(only, list): only = [only] with log.section('PLOT', 3, timer='PT plot energy'): if self.kwargs.get('plot_traj', False): ffrefs = self.kwargs.get('ffrefs', []) valence = None if do_valence: valence = self.valence for trajectory in self.trajectories: if trajectory is None: continue for pattern in only: if pattern == 'PT_ALL' or pattern in trajectory.term.basename: trajectory.plot(self.ai, ffrefs=ffrefs, valence=valence) with log.section('XYZ', 3, timer='PT dump XYZ'): if self.kwargs.get('xyz_traj', False): for trajectory in self.trajectories: if trajectory is None: continue for pattern in only: if pattern == 'PT_ALL' or pattern in trajectory.term.basename: trajectory.to_xyz() def do_pt_generate(self): 'Generate perturbation trajectories.' with log.section('PTGEN', 2, timer='PT Generate'): #read if an existing file was specified through fn_traj fn_traj = self.kwargs.get('fn_traj', None) if fn_traj is not None and os.path.isfile(fn_traj): self.trajectories = cPickle.load(open(fn_traj, 'r')) log.dump('Trajectories read from file %s' % fn_traj) self.update_trajectory_terms() newname = 'updated_' + fn_traj.split('/')[-1] cPickle.dump(self.trajectories, open(newname, 'w')) return #configure self.reset_system() only = self.kwargs.get('only_traj', 'PT_ALL') if isinstance(only, str): do_terms = [ term for term in self.valence.terms if only in term.tasks ] else: do_terms = [] for pattern in only: for term in self.valence.iter_terms(pattern): do_terms.append(term) trajectories = self.perturbation.prepare(do_terms) #compute log.dump('Constructing trajectories') self.trajectories = paracontext.map( self.perturbation.generate, [traj for traj in trajectories if traj.active]) #write the trajectories to the non-existing file fn_traj if fn_traj is not None: assert not os.path.isfile(fn_traj) cPickle.dump(self.trajectories, open(fn_traj, 'w')) log.dump('Trajectories stored to file %s' % fn_traj) def do_pt_estimate(self, do_valence=False, logger_level=3): ''' Estimate force constants and rest values from the perturbation trajectories **Optional Arguments** do_valence if set to True, the current valence force field will be used to estimate the contribution of all other valence terms. ''' with log.section('PTEST', 2, timer='PT Estimate'): self.reset_system() message = 'Estimating FF parameters from perturbation trajectories' if do_valence: message += ' with valence reference' log.dump(message) ffrefs = self.kwargs.get('ffrefs', []) #compute fc and rv from trajectory for traj in self.trajectories: if traj is None: continue self.perturbation.estimate(traj, self.ai, ffrefs=ffrefs, do_valence=do_valence) #set force field parameters to computed fc and rv for traj in self.trajectories: if traj is None: continue self.valence.set_params(traj.term.index, fc=traj.fc, rv0=traj.rv) #output self.valence.dump_logger(print_level=logger_level) #do not add average here since the fluctuation on the parameters is #required for do_pt_postprocess. Average will be done at the end of #do_pt_postprocess def do_pt_postprocess(self): ''' Do some first post processing of the ff parameters estimated from the perturbation trajectories including: * detecting bend patterns with rest values of 90 and 180 deg * detecting bend patterns with rest values only close to 180 deg * averaging parameters ''' with log.section('PTPOST', 2, timer='PT Post process'): self.do_squarebend() self.do_bendcharm() #self.do_sqoopdist_to_oopdist() self.average_pars() def do_eq_setrv(self, tasks, logger_level=3): ''' Set the rest values to their respective AI equilibrium values. ''' with log.section('EQSET', 2, timer='Equil Set RV'): self.reset_system() log.dump( 'Setting rest values to AI equilibrium values for tasks %s' % ' '.join(tasks)) for term in self.valence.terms: vterm = self.valence.vlist.vtab[term.index] if np.array([task in term.tasks for task in tasks]).any(): if term.kind == 3: #cross term ic0 = self.valence.iclist.ictab[vterm['ic0']] ic1 = self.valence.iclist.ictab[vterm['ic1']] self.valence.set_params(term.index, rv0=ic0['value'], rv1=ic1['value']) elif term.kind == 4 and term.ics[ 0].kind == 4: #Cosine of DihedAngle ic = self.valence.iclist.ictab[vterm['ic0']] m = self.valence.get_params(term.index, only='m') rv = ic['value'] % (360.0 * deg / m) with log.section('EQSET', 4, timer='Equil Set RV'): log.dump( 'Set rest value of %s(%s) (eq=%.3f deg) to %.3f deg' % (term.basename, '.'.join([ str(at) for at in term.get_atoms() ]), ic['value'] / deg, rv / deg)) self.valence.set_params(term.index, rv0=rv) else: rv = self.valence.iclist.ictab[vterm['ic0']]['value'] self.valence.set_params(term.index, rv0=rv) self.valence.dump_logger(print_level=logger_level) self.average_pars() def do_hc_estimatefc(self, tasks, logger_level=3): ''' Refine force constants using Hessian Cost function. **Arguments** tasks A list of strings identifying which terms should have their force constant estimated from the hessian cost function. Using such a flag, one can distinguish between for example force constant refinement (flag=HC_FC_DIAG) of the diagonal terms and force constant estimation of the cross terms (flag=HC_FC_CROSS). If the string 'all' is present in tasks, all fc's will be estimated. **Optional Arguments** logger_level print level at which the resulting parameters should be dumped to the logger. By default, the parameters will only be dumped at the highest log level. ''' with log.section('HCEST', 2, timer='HC Estimate FC'): self.reset_system() log.dump( 'Estimating force constants from Hessian cost for tasks %s' % ' '.join(tasks)) ffrefs = self.kwargs.get('ffrefs', []) term_indices = [] for index in xrange(self.valence.vlist.nv): term = self.valence.terms[index] flagged = False for flag in tasks: if flag in term.tasks: flagged = True break if flagged: #first check if all rest values and multiplicities have been defined if term.kind == 0: self.valence.check_params(term, ['rv']) if term.kind == 1: self.valence.check_params(term, ['a0', 'a1', 'a2', 'a3']) if term.kind == 3: self.valence.check_params(term, ['rv0', 'rv1']) if term.kind == 4: self.valence.check_params(term, ['rv', 'm']) if term.is_master(): term_indices.append(index) else: #first check if all pars have been defined if term.kind == 0: self.valence.check_params(term, ['fc', 'rv']) if term.kind == 1: self.valence.check_params(term, ['a0', 'a1', 'a2', 'a3']) if term.kind == 3: self.valence.check_params(term, ['fc', 'rv0', 'rv1']) if term.kind == 4: self.valence.check_params(term, ['fc', 'rv', 'm']) cost = HessianFCCost(self.system, self.ai, self.valence, term_indices, ffrefs=ffrefs) fcs = cost.estimate() for index, fc in zip(term_indices, fcs): master = self.valence.terms[index] assert master.is_master() self.valence.set_params(index, fc=fc) for islave in master.slaves: self.valence.set_params(islave, fc=fc) self.valence.dump_logger(print_level=logger_level) def do_cross_init(self): ''' Set the rest values of cross terms to the rest values of the corresponding diagonal terms. The force constants are initialized to zero. ''' with log.section('VAL', 2, 'Initializing'): self.reset_system() self.valence.init_cross_terms() for index in xrange(self.valence.vlist.nv): term = self.valence.vlist.vtab[index] if term['kind'] != 3: continue rv0, rv1 = None, None for index2 in xrange(self.valence.vlist.nv): term2 = self.valence.vlist.vtab[index2] if term2['kind'] == 3: continue if term['ic0'] == term2['ic0']: assert rv0 is None rv0 = self.valence.get_params(index2, only='rv') if term['ic1'] == term2['ic0']: assert rv1 is None rv1 = self.valence.get_params(index2, only='rv') if rv0 is None or rv1 is None: raise ValueError('No rest values found for %s' % self.valence.terms[index].basename) self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) def do_squarebend(self, thresshold=10 * deg): ''' Identify bend patterns in which 4 atoms of type A surround a central atom of type B with A-B-A angles of 90/180 degrees. A simple harmonic pattern will not be adequate since a rest value of 90 and 180 degrees is possible for the same A-B-A term. Therefore, a cosine term with multiplicity of 4 is used: V = K/2*[1-cos(4*theta)] To identify the patterns, it is assumed that the rest values have already been estimated from the perturbation trajectories. For each master and slave of a BENDAHARM term, its rest value is computed and checked if it lies either the interval [90-thresshold,90+thresshold] or [180-thresshold,180]. If this is the case, the new cosine term is used. **Optional arguments** thresshold the (half) the width of the interval around 180 deg (90 degrees) to check if a square BA4 ''' for master in self.valence.iter_masters(label='BendAHarm'): rvs = np.zeros([len(master.slaves) + 1], float) rvs[0] = self.valence.get_params(master.index, only='rv') for i, islave in enumerate(master.slaves): rvs[1 + i] = self.valence.get_params(islave, only='rv') n90 = 0 n180 = 0 nother = 0 for i, rv in enumerate(rvs): if 90 * deg - thresshold <= rv and rv <= 90 * deg + thresshold: n90 += 1 elif 180 * deg - thresshold <= rv and rv <= 180 * deg + thresshold: n180 += 1 else: nother += 1 if n90 > 0 and n180 > 0: log.dump( '%s has rest values around 90 deg and 180 deg, converted to BendCos with m=4' % master.basename) #modify master and slaves indices = [master.index] for slave in master.slaves: indices.append(slave) for index in indices: term = self.valence.terms[index] self.valence.modify_term( index, Cosine, [BendAngle(*term.get_atoms())], term.basename.replace('BendAHarm', 'BendCos'), ['HC_FC_DIAG'], ['au', 'kjmol', 'deg']) self.valence.set_params(index, rv0=0.0, m=4) for traj in self.trajectories: if traj.term.index == index: traj.active = False traj.fc = None traj.rv = None def do_bendcharm(self, thresshold=2 * deg): ''' No Harmonic bend can have a rest value equal to are large than 180 deg - thresshold. If a master (or its slaves) has such a rest value, convert master and all slaves to BendCharm with cos(phis0)=-1. ''' for master in self.valence.iter_masters(label='BendAHarm'): indices = [master.index] for slave in master.slaves: indices.append(slave) found = False for index in indices: rv = self.valence.get_params(index, only='rv') if rv >= 180.0 * deg - thresshold: found = True break if found: log.dump( '%s has rest value > 180-%.0f deg, converted to BendCHarm with cos(phi0)=-1' % (master.basename, thresshold / deg)) for index in indices: term = self.valence.terms[index] self.valence.modify_term( index, Harmonic, [BendCos(*term.get_atoms())], term.basename.replace('BendAHarm', 'BendCHarm'), ['HC_FC_DIAG'], ['kjmol', 'au']) self.valence.set_params(index, fc=0.0, rv0=-1.0) for traj in self.trajectories: if traj.term.index == index: traj.rv = None traj.fc = None traj.active = False def do_sqoopdist_to_oopdist(self, thresshold=1e-4 * angstrom): ''' Transform a SqOopdist term with a rest value that has been set to zero, to a term Oopdist (harmonic in Oopdist instead of square of Oopdist) with a rest value of 0.0 A. ''' for master in self.valence.iter_masters(label='SqOopdist'): indices = [master.index] for slave in master.slaves: indices.append(slave) found = False for index in indices: rv = self.valence.get_params(index, only='rv') if rv <= thresshold: found = True break if found: log.dump( '%s has rest value <= %.0f A^2, converted to Oopdist with d0=0' % (master.basename, thresshold / angstrom)) for index in indices: term = self.valence.terms[index] self.valence.modify_term( index, Harmonic, [OopDist(*term.get_atoms())], term.basename.replace('SqOopdist', 'Oopdist'), ['HC_FC_DIAG'], ['kjmol/A**2', 'A']) self.valence.set_params(index, fc=0.0, rv0=0.0) def run(self): ''' Sequence of instructions, should be implemented in the inheriting classes. The various inheriting classes distinguish themselves by means of the instructions implemented in this routine. ''' raise NotImplementedError
class BaseProgram(object): ''' Base program which implements all possible steps of a force field fitting program. The actual sequence of the steps are defined in the deriving classes. ''' def __init__(self, system, ai, settings, ffrefs=[]): ''' **Arguments** system a Yaff `System` instance defining the system ai a `Reference` instance corresponding to the ab initio input data settings a `Settings` instance defining all QuickFF settings **Optional Arguments** ffrefs a list of `Reference` instances defining the a-priori force field contributions. ''' with log.section('INIT', 1, timer='Initializing'): log.dump('Initializing program') self.settings = settings self.system = system self.ai = ai self.ffrefs = ffrefs self.valence = ValenceFF(system, settings) self.perturbation = RelaxedStrain(system, self.valence, settings) self.trajectories = None self.print_system() def print_system(self): ''' dump overview of atoms (and associated parameters) in the system ''' with log.section('SYS', 3, timer='Initializing'): log.dump('Atomic configuration of the system:') log.dump('') log.dump( ' index | x [A] | y [A] | z [A] | ffatype | q | R [A] ' ) log.dump( '---------------------------------------------------------------------' ) for i in range(len(self.system.numbers)): x, y, z = self.system.pos[i, 0], self.system.pos[ i, 1], self.system.pos[i, 2] if self.system.charges is not None: q = self.system.charges[i] else: q = np.nan if self.system.radii is not None: R = self.system.radii[i] else: R = np.nan log.dump( ' %4i | % 7.3f | % 7.3f | % 7.3f | %6s | % 7.3f | % 7.3f ' % (i, x / angstrom, y / angstrom, z / angstrom, self.system.ffatypes[self.system.ffatype_ids[i]], q, R / angstrom)) def reset_system(self): ''' routine to reset the system coords to the ai equilbrium ''' log.dump('Resetting system coordinates to ab initio ref') self.system.pos = self.ai.coords0.copy() self.valence.dlist.forward() self.valence.iclist.forward() def update_trajectory_terms(self): ''' Routine to make ``self.valence.terms`` and the term attribute of each trajectory in ``self.trajectories`` consistent again. This is usefull if the trajectory were read from a file and the ``valenceFF`` instance was modified. ''' log.dump('Updating terms of trajectories to current valenceFF terms') with log.section('PTUPD', 3): #update the terms in the trajectories to match the terms in #self.valence for traj in self.trajectories: found = False for term in self.valence.iter_terms(): if traj.term.get_atoms() == term.get_atoms(): if found: raise ValueError( 'Found two terms for trajectory %s with atom indices %s' % (traj.term.basename, str(traj.term.get_atoms()))) traj.term = term if 'PT_ALL' not in term.tasks: log.dump( 'PT_ALL not in tasks of %s-%i, deactivated PT' % (term.basename, term.index)) traj.active = False found = True if not found: log.warning( 'No term found for trajectory %s with atom indices %s, deactivating trajectory' % (traj.term.basename, str(traj.term.get_atoms()))) traj.active = False #check if every term with task PT_ALL has a trajectory associated #with it. It a trajectory is missing, generate it. for term in self.valence.iter_terms(): if 'PT_ALL' not in term.tasks: continue found = False for traj in self.trajectories: if term.get_atoms() == traj.term.get_atoms(): if found: raise ValueError( 'Found two trajectories for term %s with atom indices %s' % (term.basename, str(term.get_atoms()))) found = True if not found: log.warning( 'No trajectory found for term %s with atom indices %s. Generating it now.' % (term.basename, str(term.get_atoms()))) trajectory = self.perturbation.prepare([term])[0] self.perturbation.generate(trajectory) self.trajectories.append(trajectory) def average_pars(self): ''' Average force field parameters over master and slaves. ''' log.dump('Averaging force field parameters over master and slaves') for master in self.valence.iter_masters(): npars = len(self.valence.get_params(master.index)) pars = np.zeros([len(master.slaves) + 1, npars], float) pars[0, :] = np.array(self.valence.get_params(master.index)) for i, islave in enumerate(master.slaves): pars[1 + i, :] = np.array(self.valence.get_params(islave)) if master.kind in [0, 2, 11, 12]: #harmonic,fues,MM3Quartic,MM3Bend fc, rv = pars.mean(axis=0) self.valence.set_params(master.index, fc=fc, rv0=rv) for islave in master.slaves: self.valence.set_params(islave, fc=fc, rv0=rv) elif master.kind == 1: a0, a1, a2, a3 = pars.mean(axis=0) self.valence.set_params(master.index, a0=a0, a1=a1, a2=a2, a3=a3) for islave in master.slaves: self.valence.set_params(islave, a0=a0, a1=a1, a2=a2, a3=a3) elif master.kind == 3: #cross fc, rv0, rv1 = pars.mean(axis=0) self.valence.set_params(master.index, fc=fc, rv0=rv0, rv1=rv1) for islave in master.slaves: self.valence.set_params(islave, fc=fc, rv0=rv0, rv1=rv1) elif master.kind == 4: #cosine assert pars[:, 0].std() < 1e-6, 'dihedral multiplicity not unique' m, fc, rv = pars.mean(axis=0) self.valence.set_params(master.index, fc=fc, rv0=rv, m=m) for islave in master.slaves: self.valence.set_params(islave, fc=fc, rv0=rv, m=m) elif master.kind in [5, 6, 7, 8, 9]: #chebychev assert pars.shape[1] == 2 fc = pars[:, 0].mean() self.valence.set_params(master.index, fc=fc) for islave in master.slaves: self.valence.set_params(islave, fc=fc) else: raise NotImplementedError def make_output(self): ''' Dump Yaff parameters, Yaff system, plot energy contributions along perturbation trajectories and dump perturbation trajectories to XYZ files. ''' if self.settings.fn_yaff is not None: dump_yaff(self.valence, self.settings.fn_yaff) if self.settings.fn_charmm22_prm is not None: dump_charmm22_prm(self.valence, self.settings.fn_charmm22_prm) if self.settings.fn_charmm22_psf is not None: dump_charmm22_psf(self.system, self.valence, self.settings.fn_charmm22_psf) if self.settings.fn_sys is not None: self.system.to_file(self.settings.fn_sys) if self.settings.plot_traj is not None and self.settings.plot_traj.lower( ) in ['Ehc3', 'final', 'all']: self.plot_trajectories(do_valence=True, suffix='_Ehc3') if self.settings.xyz_traj: self.write_trajectories() def plot_trajectories(self, do_valence=False, suffix=''): ''' Plot energy contributions along perturbation trajectories and ''' only = self.settings.only_traj if not isinstance(only, list): only = [only] with log.section('PLOT', 3, timer='PT plot energy'): valence = None if do_valence: valence = self.valence for trajectory in self.trajectories: if trajectory is None: continue for pattern in only: if pattern in ['PT_ALL', 'pt_all', None ] or pattern in trajectory.term.basename: log.dump('Plotting trajectory for %s' % trajectory.term.basename) trajectory.plot(self.ai, ffrefs=self.ffrefs, valence=valence, suffix=suffix) def write_trajectories(self): ''' Write perturbation trajectories to XYZ files. ''' only = self.settings.only_traj if not isinstance(only, list): only = [only] with log.section('XYZ', 3, timer='PT dump XYZ'): for trajectory in self.trajectories: if trajectory is None: continue for pattern in only: if pattern in ['PT_ALL', 'pt_all', None ] or pattern in trajectory.term.basename: log.dump('Writing XYZ trajectory for %s' % trajectory.term.basename) trajectory.to_xyz() def do_pt_generate(self): ''' Generate perturbation trajectories. ''' with log.section('PTGEN', 2, timer='PT Generate'): #read if an existing file was specified through fn_traj fn_traj = self.settings.fn_traj if fn_traj is not None and os.path.isfile(fn_traj): self.trajectories = pickle.load(open(fn_traj, 'rb')) log.dump('Trajectories read from file %s' % fn_traj) self.update_trajectory_terms() newname = 'updated_' + fn_traj.split('/')[-1] pickle.dump(self.trajectories, open(newname, 'wb')) return #configure self.reset_system() only = self.settings.only_traj dont_traj = self.settings.dont_traj if sum([only is None, dont_traj is None]) == 0: raise AssertionError( 'The settings only_traj and dont_traj cannot be specified both' ) if (only is None or only == 'PT_ALL' or only == 'pt_all' ) and dont_traj is None: # only=None is equivalent to PT_ALL do_terms = [ term for term in self.valence.terms if term.kind in [0, 2, 11, 12] ] elif only is None and dont_traj is not None: kind2string = { 0: 'bond', 2: 'bend', 11: 'oopdist', 12: 'dihedral' } ffatypes = [ self.system.ffatypes[fid] for fid in self.system.ffatype_ids ] dont_patterns = dont_traj.split(',') # split patterns dont_terms = [] for term in self.valence.terms: if term.kind in [0, 2, 11, 12]: types = term.basename.split('/')[1].split('.') option1 = '.'.join(types) option2 = '.'.join(types[::-1]) for dp in dont_patterns: pattern = re.compile(dp, re.IGNORECASE) if pattern.match(option1) or pattern.match( option2): dont_terms.append(term) do_terms = [ term for term in self.valence.terms if term.kind in [0, 2, 11, 12] and term not in dont_terms ] with log.section('PTNOT', 3): for term in dont_terms: log.dump( 'Taking AI equilibrium rest value instead of generating perturbation trajectory for %s' % term.basename) vterm = self.valence.vlist.vtab[term.index] self.valence.set_params(term.index, fc=0, rv0=self.valence.iclist.ictab[ vterm['ic0']]['value']) else: if isinstance(only, str): only = [only] do_terms = [] for pattern in only: for term in self.valence.iter_terms(pattern): if term.kind in [0, 2, 11, 12]: do_terms.append(term) trajectories = self.perturbation.prepare(do_terms) #compute log.dump('Constructing trajectories') self.trajectories = paracontext.map( self.perturbation.generate, [traj for traj in trajectories if traj.active]) #write the trajectories to the non-existing file fn_traj if fn_traj is not None: assert not os.path.isfile(fn_traj) pickle.dump(self.trajectories, open(fn_traj, 'wb')) log.dump('Trajectories stored to file %s' % fn_traj) def do_pt_estimate(self, do_valence=False, energy_noise=None, logger_level=3): ''' Estimate force constants and rest values from the perturbation trajectories **Optional Arguments** do_valence if set to True, the current valence force field will be used to estimate the contribution of all other valence terms. ''' with log.section('PTEST', 2, timer='PT Estimate'): self.reset_system() message = 'Estimating FF parameters from perturbation trajectories' if do_valence: message += ' with valence reference' log.dump(message) #compute fc and rv from trajectory only = self.settings.only_traj for traj in self.trajectories: if traj is None: continue if not (only is None or only == 'PT_ALL' or only == 'pt_all'): if isinstance(only, str): only = [only] basename = self.valence.terms[traj.term.master].basename if basename not in only: continue self.perturbation.estimate(traj, self.ai, ffrefs=self.ffrefs, do_valence=do_valence, energy_noise=energy_noise) #set force field parameters to computed fc and rv for traj in self.trajectories: if traj is None: continue if not (only is None or only == 'PT_ALL' or only == 'pt_all'): if isinstance(only, str): only = [only] basename = self.valence.terms[traj.term.master].basename if basename not in only: continue self.valence.set_params(traj.term.index, fc=traj.fc, rv0=traj.rv) #output self.valence.dump_logger(print_level=logger_level) #do not add average here since the fluctuation on the parameters is #required for do_pt_postprocess. Average will be done at the end of #do_pt_postprocess def do_pt_postprocess(self): ''' Do some first post processing of the ff parameters estimated from the perturbation trajectories including: * detecting bend patterns with rest values of 90 and 180 deg * detecting bend patterns with rest values only close to 180 deg * transforming SqOopDist with rv=0.0 to OopDist * averaging parameters ''' with log.section('PTPOST', 2, timer='PT Post process'): if self.settings.do_squarebend: self.do_squarebend() if self.settings.do_bendclin: self.do_bendclin() if self.settings.do_sqoopdist_to_oopdist: self.do_sqoopdist_to_oopdist() self.average_pars() def do_eq_setrv(self, tasks, logger_level=3): ''' Set the rest values to their respective AI equilibrium values. ''' with log.section('EQSET', 2, timer='Equil Set RV'): self.reset_system() log.dump( 'Setting rest values to AI equilibrium values for tasks %s' % ' '.join(tasks)) for term in self.valence.terms: vterm = self.valence.vlist.vtab[term.index] if np.array([task in term.tasks for task in tasks]).any(): if term.kind == 3: #cross term ic0 = self.valence.iclist.ictab[vterm['ic0']] ic1 = self.valence.iclist.ictab[vterm['ic1']] self.valence.set_params(term.index, rv0=ic0['value'], rv1=ic1['value']) elif term.kind == 4 and term.ics[ 0].kind == 4: #Cosine of DihedAngle ic = self.valence.iclist.ictab[vterm['ic0']] m = self.valence.get_params(term.index, only='m') rv = ic['value'] % (360.0 * deg / m) with log.section('EQSET', 4, timer='Equil Set RV'): log.dump( 'Set rest value of %s(%s) (eq=%.3f deg) to %.3f deg' % (term.basename, '.'.join([ str(at) for at in term.get_atoms() ]), ic['value'] / deg, rv / deg)) self.valence.set_params(term.index, rv0=rv) else: rv = self.valence.iclist.ictab[vterm['ic0']]['value'] self.valence.set_params(term.index, rv0=rv) self.valence.dump_logger(print_level=logger_level) self.average_pars() def do_hc_estimatefc(self, tasks, logger_level=3, do_svd=False, svd_rcond=0.0, do_mass_weighting=True): ''' Refine force constants using Hessian Cost function. **Arguments** tasks A list of strings identifying which terms should have their force constant estimated from the hessian cost function. Using such a flag, one can distinguish between for example force constant refinement (flag=HC_FC_DIAG) of the diagonal terms and force constant estimation of the cross terms (flag=HC_FC_CROSS). If the string 'all' is present in tasks, all fc's will be estimated. **Optional Arguments** logger_level print level at which the resulting parameters should be dumped to the logger. By default, the parameters will only be dumped at the highest log level. do_svd whether or not to do an SVD decomposition before solving the set of equations and explicitly throw out the degrees of freedom that correspond to the lowest singular values. do_mass_weighting whether or not to apply mass weighing to the ab initio hessian and the force field contributions before doing the fitting. ''' with log.section('HCEST', 2, timer='HC Estimate FC'): self.reset_system() log.dump( 'Estimating force constants from Hessian cost for tasks %s' % ' '.join(tasks)) term_indices = [] for index in range(self.valence.vlist.nv): term = self.valence.terms[index] flagged = False for flag in tasks: if flag in term.tasks: flagged = True break if flagged: #first check if all rest values and multiplicities have been defined if term.kind == 0: self.valence.check_params(term, ['rv']) if term.kind == 1: self.valence.check_params(term, ['a0', 'a1', 'a2', 'a3']) if term.kind == 3: self.valence.check_params(term, ['rv0', 'rv1']) if term.kind == 4: self.valence.check_params(term, ['rv', 'm']) if term.is_master(): term_indices.append(index) else: #first check if all pars have been defined if term.kind == 0: self.valence.check_params(term, ['fc', 'rv']) if term.kind == 1: self.valence.check_params(term, ['a0', 'a1', 'a2', 'a3']) if term.kind == 3: self.valence.check_params(term, ['fc', 'rv0', 'rv1']) if term.kind == 4: self.valence.check_params(term, ['fc', 'rv', 'm']) if len(term_indices) == 0: log.dump( 'No terms (with task in %s) found to estimate FC from HC' % (str(tasks))) return # Try to estimate force constants; if the remove_dysfunctional_cross # keyword is True, a loop is performed which checks whether there # are cross terms for which corresponding diagonal terms have zero # force constants. If this is the case, those cross terms are removed # from the fit and we try again until such cases do no longer occur max_iter = 100 niter = 0 while niter < max_iter: cost = HessianFCCost(self.system, self.ai, self.valence, term_indices, ffrefs=self.ffrefs, do_mass_weighting=do_mass_weighting) fcs = cost.estimate(do_svd=do_svd, svd_rcond=svd_rcond) # No need to continue, if cross terms with corresponding diagonal # terms with negative force constants are allowed if self.settings.remove_dysfunctional_cross is False: break to_remove = [] for index, fc in zip(term_indices, fcs): term = self.valence.terms[index] if term.basename.startswith('Cross'): # Find force constants of corresponding diagonal terms diag_fcs = np.zeros((2)) for idiag in range(2): diag_index = term.diag_term_indexes[idiag] if diag_index in term_indices: fc_diag = fcs[term_indices.index(diag_index)] else: fc_diag = self.valence.get_params(diag_index, only='fc') diag_fcs[idiag] = fc_diag # If a force constant from any corresponding diagonal term is negative, # we remove the cross term for the next iteration if np.any(diag_fcs <= 0.0): to_remove.append(index) self.valence.set_params(index, fc=0.0) log.dump( 'WARNING! Dysfunctional cross term %s detected, removing from the hessian fit.' % term.basename) if len(to_remove) == 0: break else: for index in to_remove: term_indices.remove(index) niter += 1 assert niter < max_iter, "Could not remove all dysfunctional cross terms in %d iterations, something is seriously wrong" % max_iter for index, fc in zip(term_indices, fcs): master = self.valence.terms[index] assert master.is_master() self.valence.set_params(index, fc=fc) for islave in master.slaves: self.valence.set_params(islave, fc=fc) self.valence.dump_logger(print_level=logger_level) def do_cross_init(self): ''' Add cross terms to the valence list and initialize parameters. ''' with log.section('VAL', 2, 'Initializing'): self.reset_system() self.valence.init_cross_angle_terms() if self.settings.do_cross_DSS or self.settings.do_cross_DSD or self.settings.do_cross_DAD or self.settings.do_cross_DAA: self.valence.init_cross_dihed_terms() self.update_cross_pars() def update_cross_pars(self): ''' Set the rest values of cross terms to the rest values of the corresponding diagonal terms. Set the force constants to zero. ''' with log.section('VAL', 2, 'Initializing'): def find_rest_value(iterm): term = self.valence.terms[iterm] if term.basename.startswith( 'TorsCheby') or term.basename.startswith('BendCheby'): return -self.valence.get_params(iterm, only='sign') else: return self.valence.get_params(iterm, only='rv') # Bond-Bond Cross terms cases = [('Cross', 'bb', 3), ('Cross', 'b0a', 3), ('Cross', 'b1a', 3)] # Bond-Dihedral Cross terms for m in [1, 2, 3, 4, 6]: for suffix in ['bb', 'b0d', 'b1d', 'b2d']: case = ('CrossBondDih%i' % m, suffix, 4) cases.append(case) # Angle-Dihedral Cross terms for m in [1, 2, 3, 4, 6]: for suffix in ['aa', 'a0d', 'a1d']: case = ('CrossBendDih%i' % m, suffix, 4) cases.append(case) for suffix in ['a0d', 'a1d']: case = ('CrossCBendDih%i' % m, suffix, 4) cases.append(case)
class BaseProgram(object): ''' Base program which implements all possible steps of a force field fitting program. The actual sequence of the steps are defined in the deriving classes. ''' def __init__(self, system, ai, settings, ffrefs=[]): ''' **Arguments** system a Yaff `System` instance defining the system ai a `Reference` instance corresponding to the ab initio input data settings a `Settings` instance defining all QuickFF settings **Optional Arguments** ffrefs a list of `Reference` instances defining the a-priori force field contributions. ''' with log.section('INIT', 1, timer='Initializing'): log.dump('Initializing program') self.settings = settings self.system = system self.ai = ai self.ffrefs = ffrefs self.valence = ValenceFF(system, settings) self.perturbation = RelaxedStrain(system, self.valence, settings) self.trajectories = None self.print_system() def print_system(self): ''' dump overview of atoms (and associated parameters) in the system ''' with log.section('SYS', 3, timer='Initializing'): log.dump('Atomic configuration of the system:') log.dump('') log.dump(' index | x [A] | y [A] | z [A] | ffatype | q | R [A] ') log.dump('---------------------------------------------------------------------') for i in range(len(self.system.numbers)): x, y, z = self.system.pos[i,0], self.system.pos[i,1], self.system.pos[i,2] if self.system.charges is not None: q = self.system.charges[i] else: q = np.nan if self.system.radii is not None: R = self.system.radii[i] else: R = np.nan log.dump(' %4i | % 7.3f | % 7.3f | % 7.3f | %6s | % 7.3f | % 7.3f ' %( i, x/angstrom, y/angstrom, z/angstrom, self.system.ffatypes[self.system.ffatype_ids[i]], q, R/angstrom )) def reset_system(self): ''' routine to reset the system coords to the ai equilbrium ''' log.dump('Resetting system coordinates to ab initio ref') self.system.pos = self.ai.coords0.copy() self.valence.dlist.forward() self.valence.iclist.forward() def update_trajectory_terms(self): ''' Routine to make ``self.valence.terms`` and the term attribute of each trajectory in ``self.trajectories`` consistent again. This is usefull if the trajectory were read from a file and the ``valenceFF`` instance was modified. ''' log.dump('Updating terms of trajectories to current valenceFF terms') with log.section('PTUPD', 3): #update the terms in the trajectories to match the terms in #self.valence for traj in self.trajectories: found = False for term in self.valence.iter_terms(): if traj.term.get_atoms()==term.get_atoms(): if found: raise ValueError('Found two terms for trajectory %s with atom indices %s' %(traj.term.basename, str(traj.term.get_atoms()))) traj.term = term if 'PT_ALL' not in term.tasks: log.dump('PT_ALL not in tasks of %s-%i, deactivated PT' %(term.basename, term.index)) traj.active = False found = True if not found: log.warning('No term found for trajectory %s with atom indices %s, deactivating trajectory' %(traj.term.basename, str(traj.term.get_atoms()))) traj.active = False #check if every term with task PT_ALL has a trajectory associated #with it. It a trajectory is missing, generate it. for term in self.valence.iter_terms(): if 'PT_ALL' not in term.tasks: continue found = False for traj in self.trajectories: if term.get_atoms()==traj.term.get_atoms(): if found: raise ValueError('Found two trajectories for term %s with atom indices %s' %(term.basename, str(term.get_atoms()))) found =True if not found: log.warning('No trajectory found for term %s with atom indices %s. Generating it now.' %(term.basename, str(term.get_atoms()))) trajectory = self.perturbation.prepare([term])[term.index] self.perturbation.generate(trajectory) self.trajectories.append(trajectory) def average_pars(self): ''' Average force field parameters over master and slaves. ''' log.dump('Averaging force field parameters over master and slaves') for master in self.valence.iter_masters(): npars = len(self.valence.get_params(master.index)) pars = np.zeros([len(master.slaves)+1, npars], float) pars[0,:] = np.array(self.valence.get_params(master.index)) for i, islave in enumerate(master.slaves): pars[1+i,:] = np.array(self.valence.get_params(islave)) if master.kind in [0,2,11,12]:#harmonic,fues,MM3Quartic,MM3Bend fc, rv = pars.mean(axis=0) self.valence.set_params(master.index, fc=fc, rv0=rv) for islave in master.slaves: self.valence.set_params(islave, fc=fc, rv0=rv) elif master.kind==1: a0, a1, a2, a3 = pars.mean(axis=0) self.valence.set_params(master.index, a0=a0, a1=a1, a2=a2, a3=a3) for islave in master.slaves: self.valence.set_params(islave, a0=a0, a1=a1, a2=a2, a3=a3) elif master.kind==3:#cross fc, rv0, rv1 = pars.mean(axis=0) self.valence.set_params(master.index, fc=fc, rv0=rv0, rv1=rv1) for islave in master.slaves: self.valence.set_params(islave, fc=fc, rv0=rv0, rv1=rv1) elif master.kind==4:#cosine assert pars[:,0].std()<1e-6, 'dihedral multiplicity not unique' m, fc, rv = pars.mean(axis=0) self.valence.set_params(master.index, fc=fc, rv0=rv, m=m) for islave in master.slaves: self.valence.set_params(islave, fc=fc, rv0=rv, m=m) elif master.kind in [5, 6, 7, 8, 9]:#chebychev assert pars.shape[1]==2 fc = pars[:,0].mean() self.valence.set_params(master.index, fc=fc) for islave in master.slaves: self.valence.set_params(islave, fc=fc) else: raise NotImplementedError def make_output(self): ''' Dump Yaff parameters, Yaff system, plot energy contributions along perturbation trajectories and dump perturbation trajectories to XYZ files. ''' if self.settings.fn_yaff is not None: dump_yaff(self.valence, self.settings.fn_yaff) if self.settings.fn_charmm22_prm is not None: dump_charmm22_prm(self.valence, self.settings.fn_charmm22_prm) if self.settings.fn_charmm22_psf is not None: dump_charmm22_psf(self.system, self.valence, self.settings.fn_charmm22_psf) if self.settings.fn_sys is not None: self.system.to_file(self.settings.fn_sys) if self.settings.plot_traj is not None and self.settings.plot_traj.lower() in ['Ehc3', 'final', 'all']: self.plot_trajectories(do_valence=True, suffix='_Ehc3') if self.settings.xyz_traj: self.write_trajectories() def plot_trajectories(self, do_valence=False, suffix=''): ''' Plot energy contributions along perturbation trajectories and ''' only = self.settings.only_traj if not isinstance(only, list): only = [only] with log.section('PLOT', 3, timer='PT plot energy'): valence = None if do_valence: valence=self.valence for trajectory in self.trajectories: if trajectory is None: continue for pattern in only: if pattern=='PT_ALL' or pattern in trajectory.term.basename: log.dump('Plotting trajectory for %s' %trajectory.term.basename) trajectory.plot(self.ai, ffrefs=self.ffrefs, valence=valence, suffix=suffix) def write_trajectories(self): ''' Write perturbation trajectories to XYZ files. ''' only = self.settings.only_traj if not isinstance(only, list): only = [only] with log.section('XYZ', 3, timer='PT dump XYZ'): for trajectory in self.trajectories: if trajectory is None: continue for pattern in only: if pattern=='PT_ALL' or pattern in trajectory.term.basename: log.dump('Writing XYZ trajectory for %s' %trajectory.term.basename) trajectory.to_xyz() def do_pt_generate(self): ''' Generate perturbation trajectories. ''' with log.section('PTGEN', 2, timer='PT Generate'): #read if an existing file was specified through fn_traj fn_traj = self.settings.fn_traj if fn_traj is not None and os.path.isfile(fn_traj): self.trajectories = pickle.load(open(fn_traj, 'rb')) log.dump('Trajectories read from file %s' %fn_traj) self.update_trajectory_terms() newname = 'updated_'+fn_traj.split('/')[-1] pickle.dump(self.trajectories, open(newname, 'wb')) return #configure self.reset_system() only = self.settings.only_traj if only is None or only=='PT_ALL' or only=='pt_all': do_terms = [term for term in self.valence.terms if term.kind in [0,2,11,12]] else: if isinstance(only, str): only = [only] do_terms = [] for pattern in only: for term in self.valence.iter_terms(pattern): if term.kind in [0,2,11,12]: do_terms.append(term) trajectories = self.perturbation.prepare(do_terms) #compute log.dump('Constructing trajectories') self.trajectories = paracontext.map(self.perturbation.generate, [traj for traj in trajectories if traj.active]) #write the trajectories to the non-existing file fn_traj if fn_traj is not None: assert not os.path.isfile(fn_traj) pickle.dump(self.trajectories, open(fn_traj, 'wb')) log.dump('Trajectories stored to file %s' %fn_traj) def do_pt_estimate(self, do_valence=False, energy_noise=None, logger_level=3): ''' Estimate force constants and rest values from the perturbation trajectories **Optional Arguments** do_valence if set to True, the current valence force field will be used to estimate the contribution of all other valence terms. ''' with log.section('PTEST', 2, timer='PT Estimate'): self.reset_system() message = 'Estimating FF parameters from perturbation trajectories' if do_valence: message += ' with valence reference' log.dump(message) #compute fc and rv from trajectory only = self.settings.only_traj for traj in self.trajectories: if traj is None: continue if not (only is None or only=='PT_ALL' or only=='pt_all'): if isinstance(only, str): only = [only] basename = self.valence.terms[traj.term.master].basename if basename not in only: continue self.perturbation.estimate(traj, self.ai, ffrefs=self.ffrefs, do_valence=do_valence, energy_noise=energy_noise) #set force field parameters to computed fc and rv for traj in self.trajectories: if traj is None: continue if not (only is None or only=='PT_ALL' or only=='pt_all'): if isinstance(only, str): only = [only] basename = self.valence.terms[traj.term.master].basename if basename not in only: continue self.valence.set_params(traj.term.index, fc=traj.fc, rv0=traj.rv) #output self.valence.dump_logger(print_level=logger_level) #do not add average here since the fluctuation on the parameters is #required for do_pt_postprocess. Average will be done at the end of #do_pt_postprocess def do_pt_postprocess(self): ''' Do some first post processing of the ff parameters estimated from the perturbation trajectories including: * detecting bend patterns with rest values of 90 and 180 deg * detecting bend patterns with rest values only close to 180 deg * transforming SqOopDist with rv=0.0 to OopDist * averaging parameters ''' with log.section('PTPOST', 2, timer='PT Post process'): if self.settings.do_squarebend: self.do_squarebend() if self.settings.do_bendclin: self.do_bendclin() if self.settings.do_sqoopdist_to_oopdist: self.do_sqoopdist_to_oopdist() self.average_pars() def do_eq_setrv(self, tasks, logger_level=3): ''' Set the rest values to their respective AI equilibrium values. ''' with log.section('EQSET', 2, timer='Equil Set RV'): self.reset_system() log.dump('Setting rest values to AI equilibrium values for tasks %s' %' '.join(tasks)) for term in self.valence.terms: vterm = self.valence.vlist.vtab[term.index] if np.array([task in term.tasks for task in tasks]).any(): if term.kind==3:#cross term ic0 = self.valence.iclist.ictab[vterm['ic0']] ic1 = self.valence.iclist.ictab[vterm['ic1']] self.valence.set_params(term.index, rv0=ic0['value'], rv1=ic1['value']) elif term.kind==4 and term.ics[0].kind==4:#Cosine of DihedAngle ic = self.valence.iclist.ictab[vterm['ic0']] m = self.valence.get_params(term.index, only='m') rv = ic['value']%(360.0*deg/m) with log.section('EQSET', 4, timer='Equil Set RV'): log.dump('Set rest value of %s(%s) (eq=%.3f deg) to %.3f deg' %( term.basename, '.'.join([str(at) for at in term.get_atoms()]), ic['value']/deg, rv/deg )) self.valence.set_params(term.index, rv0=rv) else: rv = self.valence.iclist.ictab[vterm['ic0']]['value'] self.valence.set_params(term.index, rv0=rv) self.valence.dump_logger(print_level=logger_level) self.average_pars() def do_hc_estimatefc(self, tasks, logger_level=3, do_svd=False, svd_rcond=0.0, do_mass_weighting=True): ''' Refine force constants using Hessian Cost function. **Arguments** tasks A list of strings identifying which terms should have their force constant estimated from the hessian cost function. Using such a flag, one can distinguish between for example force constant refinement (flag=HC_FC_DIAG) of the diagonal terms and force constant estimation of the cross terms (flag=HC_FC_CROSS). If the string 'all' is present in tasks, all fc's will be estimated. **Optional Arguments** logger_level print level at which the resulting parameters should be dumped to the logger. By default, the parameters will only be dumped at the highest log level. do_svd whether or not to do an SVD decomposition before solving the set of equations and explicitly throw out the degrees of freedom that correspond to the lowest singular values. do_mass_weighting whether or not to apply mass weighing to the ab initio hessian and the force field contributions before doing the fitting. ''' with log.section('HCEST', 2, timer='HC Estimate FC'): self.reset_system() log.dump('Estimating force constants from Hessian cost for tasks %s' %' '.join(tasks)) term_indices = [] for index in range(self.valence.vlist.nv): term = self.valence.terms[index] flagged = False for flag in tasks: if flag in term.tasks: flagged = True break if flagged: #first check if all rest values and multiplicities have been defined if term.kind==0: self.valence.check_params(term, ['rv']) if term.kind==1: self.valence.check_params(term, ['a0', 'a1', 'a2', 'a3']) if term.kind==3: self.valence.check_params(term, ['rv0','rv1']) if term.kind==4: self.valence.check_params(term, ['rv', 'm']) if term.is_master(): term_indices.append(index) else: #first check if all pars have been defined if term.kind==0: self.valence.check_params(term, ['fc', 'rv']) if term.kind==1: self.valence.check_params(term, ['a0', 'a1', 'a2', 'a3']) if term.kind==3: self.valence.check_params(term, ['fc', 'rv0','rv1']) if term.kind==4: self.valence.check_params(term, ['fc', 'rv', 'm']) if len(term_indices)==0: log.dump('No terms (with task in %s) found to estimate FC from HC' %(str(tasks))) return # Try to estimate force constants; if the remove_dysfunctional_cross # keyword is True, a loop is performed which checks whether there # are cross terms for which corresponding diagonal terms have zero # force constants. If this is the case, those cross terms are removed # from the fit and we try again until such cases do no longer occur max_iter = 100 niter = 0 while niter<max_iter: cost = HessianFCCost(self.system, self.ai, self.valence, term_indices, ffrefs=self.ffrefs, do_mass_weighting=do_mass_weighting) fcs = cost.estimate(do_svd=do_svd, svd_rcond=svd_rcond) # No need to continue, if cross terms with corresponding diagonal # terms with negative force constants are allowed if self.settings.remove_dysfunctional_cross is False: break to_remove = [] for index, fc in zip(term_indices, fcs): term = self.valence.terms[index] if term.basename.startswith('Cross'): # Find force constants of corresponding diagonal terms diag_fcs = np.zeros((2)) for idiag in range(2): diag_index = term.diag_term_indexes[idiag] if diag_index in term_indices: fc_diag = fcs[term_indices.index(diag_index)] else: fc_diag = self.valence.get_params(diag_index, only='fc') diag_fcs[idiag] = fc_diag # If a force constant from any corresponding diagonal term is negative, # we remove the cross term for the next iteration if np.any(diag_fcs<=0.0): to_remove.append(index) self.valence.set_params(index, fc=0.0) log.dump('WARNING! Dysfunctional cross term %s detected, removing from the hessian fit.'%term.basename) if len(to_remove)==0: break else: for index in to_remove: term_indices.remove(index) niter += 1 assert niter<max_iter, "Could not remove all dysfunctional cross terms in %d iterations, something is seriously wrong"%max_iter for index, fc in zip(term_indices, fcs): master = self.valence.terms[index] assert master.is_master() self.valence.set_params(index, fc=fc) for islave in master.slaves: self.valence.set_params(islave, fc=fc) self.valence.dump_logger(print_level=logger_level) def do_cross_init(self): ''' Add cross terms to the valence list and initialize parameters. ''' with log.section('VAL', 2, 'Initializing'): self.reset_system() self.valence.init_cross_angle_terms() if self.settings.do_cross_DSS or self.settings.do_cross_DSD or self.settings.do_cross_DAD or self.settings.do_cross_DAA: self.valence.init_cross_dihed_terms() self.update_cross_pars() def update_cross_pars(self): ''' Set the rest values of cross terms to the rest values of the corresponding diagonal terms. Set the force constants to zero. ''' with log.section('VAL', 2, 'Initializing'): def find_rest_value(iterm): term = self.valence.terms[iterm] if term.basename.startswith('TorsCheby') or term.basename.startswith('BendCheby'): return -self.valence.get_params(iterm, only='sign') else: return self.valence.get_params(iterm, only='rv') # Bond-Bond Cross terms cases = [('Cross','bb',3),('Cross','b0a',3),('Cross','b1a',3)] # Bond-Dihedral Cross terms for m in [1,2,3,4,6]: for suffix in ['bb','b0d','b1d','b2d']: case = ('CrossBondDih%i'%m,suffix,4) cases.append(case) # Angle-Dihedral Cross terms for m in [1,2,3,4,6]: for suffix in ['aa','a0d','a1d']: case = ('CrossBendDih%i'%m,suffix,4) cases.append(case) for suffix in ['a0d','a1d']: case = ('CrossCBendDih%i'%m,suffix,4) cases.append(case) # Loop over all cases for prefix, suffix, ntypes in cases: # Loop over all cross terms belonging to this case for term in self.valence.iter_masters('^%s/.*/%s$'%(prefix,suffix), use_re=True): types = term.basename.split('/')[1].split('.') assert len(types)==ntypes, 'Found cross term with %d atom types, expected %d'%(len(types),ntype) rv0 = find_rest_value(term.diag_term_indexes[0]) rv1 = find_rest_value(term.diag_term_indexes[1]) self.valence.set_params(term.index, fc=0.0, rv0=rv0, rv1=rv1) for index in term.slaves: self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) def do_squarebend(self, thresshold=20*deg): ''' Identify bend patterns in which 4 atoms of type A surround a central atom of type B with A-B-A angles of 90/180 degrees. A simple harmonic pattern will not be adequate since a rest value of 90 and 180 degrees is possible for the same A-B-A term. Therefore, a cosine term with multiplicity of 4 is used (which corresponds to a chebychev4 potential with sign=-1): V = K/2*[1-cos(4*theta)] To identify the patterns, it is assumed that the rest values have already been estimated from the perturbation trajectories. For each master and slave of a BENDAHARM term, its rest value is computed and checked if it lies either the interval [90-thresshold,90+thresshold] or [180-thresshold,180]. If this is the case, the new cosine term is used. **Optional arguments** thresshold the (half) the width of the interval around 180 deg (90 degrees) to check if a square BA4 ''' for master in self.valence.iter_masters(label='BendAHarm'): rvs = np.zeros([len(master.slaves)+1], float) rvs[0] = self.valence.get_params(master.index, only='rv') for i, islave in enumerate(master.slaves): rvs[1+i] = self.valence.get_params(islave, only='rv') n90 = 0 n180 = 0 nother = 0 for i, rv in enumerate(rvs): if 90*deg-thresshold<=rv and rv<=90*deg+thresshold: n90 += 1 elif 180*deg-thresshold<=rv and rv<=180*deg+thresshold: n180 += 1 else: nother += 1 if n90>0 and n180>0: log.dump('%s has rest values around 90 deg and 180 deg, converted to BendCheby4' %master.basename) #modify master and slaves indices = [master.index] for slave in master.slaves: indices.append(slave) for index in indices: term = self.valence.terms[index] self.valence.modify_term( index, Chebychev4, [BendCos(*term.get_atoms())], term.basename.replace('BendAHarm', 'BendCheby4'), ['HC_FC_DIAG'], ['kjmol', 'au'] ) self.valence.set_params(index, sign=-1) for traj in self.trajectories: if traj.term.index==index: traj.active = False traj.fc = None traj.rv = None def do_bendclin(self, thresshold=5*deg): ''' No Harmonic bend can have a rest value equal to are large than 180 deg - thresshold. If a master (or its slaves) has such a rest value, convert master and all slaves to BendCLin (which corresponds to a chebychev1 potential with sign=+1): 0.5*K*[1+cos(theta)] ''' for master in self.valence.iter_masters(label='BendAHarm'): indices = [master.index] for slave in master.slaves: indices.append(slave) found = False for index in indices: rv = self.valence.get_params(index, only='rv') if rv>=180.0*deg-thresshold: found = True break if found: log.dump('%s has rest value > 180-%.0f deg, converted to BendCheby1' %(master.basename, thresshold/deg)) for index in indices: term = self.valence.terms[index] self.valence.modify_term( index, Chebychev1, [BendCos(*term.get_atoms())], term.basename.replace('BendAHarm', 'BendCheby1'), ['HC_FC_DIAG'], ['kjmol', 'au'] ) self.valence.set_params(index, fc=0.0, sign=1.0) for traj in self.trajectories: if traj.term.index==index: traj.rv = None traj.fc = None traj.active = False def do_sqoopdist_to_oopdist(self, thresshold=1e-4*angstrom): ''' Transform a SqOopdist term with a rest value that has been set to zero, to a term Oopdist (harmonic in Oopdist instead of square of Oopdist) with a rest value of 0.0 A. ''' for master in self.valence.iter_masters(label='SqOopdist'): indices = [master.index] for slave in master.slaves: indices.append(slave) found = False for index in indices: rv = self.valence.get_params(index, only='rv') if rv<=thresshold: found = True break if found: log.dump('%s has rest value <= %.0f A^2, converted to Oopdist with d0=0' %(master.basename, thresshold/angstrom)) for index in indices: term = self.valence.terms[index] self.valence.modify_term( index, Harmonic, [OopDist(*term.get_atoms())], term.basename.replace('SqOopdist', 'Oopdist'), ['HC_FC_DIAG'], ['kjmol/A**2', 'A'] ) self.valence.set_params(index, fc=0.0, rv0=0.0) def run(self): ''' Sequence of instructions, should be implemented in the inheriting classes. The various inheriting classes distinguish themselves by means of the instructions implemented in this routine. ''' raise NotImplementedError
class BaseProgram(object): ''' Base program which implements all possible steps of a force field fitting program. The actual sequence of the steps are defined in the deriving classes. ''' def __init__(self, system, ai, settings, ffrefs=[]): ''' **Arguments** system a Yaff `System` instance defining the system ai a `Reference` instance corresponding to the ab initio input data settings a `Settings` instance defining all QuickFF settings **Optional Arguments** ffrefs a list of `Reference` instances defining the a-priori force field contributions. ''' with log.section('PROG', 2, timer='Initializing'): log.dump('Initializing program') self.settings = settings self.system = system self.ai = ai self.ffrefs = ffrefs self.valence = ValenceFF(system, settings) self.perturbation = RelaxedStrain(system, self.valence, settings) self.trajectories = None def reset_system(self): ''' routine to reset the system coords to the ai equilbrium ''' log.dump('Resetting system coordinates to ab initio ref') self.system.pos = self.ai.coords0.copy() self.valence.dlist.forward() self.valence.iclist.forward() def update_trajectory_terms(self): ''' Routine to make ``self.valence.terms`` and the term attribute of each trajectory in ``self.trajectories`` consistent again. This is usefull if the trajectory were read from a file and the ``valenceFF`` instance was modified. ''' log.dump('Updating terms of trajectories to current valenceFF terms') with log.section('PTUPD', 3): #update the terms in the trajectories to match the terms in #self.valence for traj in self.trajectories: found = False for term in self.valence.iter_terms(): if traj.term.get_atoms() == term.get_atoms(): if found: raise ValueError( 'Found two terms for trajectory %s with atom indices %s' % (traj.term.basename, str(traj.term.get_atoms()))) traj.term = term if 'PT_ALL' not in term.tasks: log.dump( 'PT_ALL not in tasks of %s-%i, deactivated PT' % (term.basename, term.index)) traj.active = False found = True if not found: log.warning( 'No term found for trajectory %s with atom indices %s, deactivating trajectory' % (traj.term.basename, str(traj.term.get_atoms()))) traj.active = False #check if every term with task PT_ALL has a trajectory associated #with it. It a trajectory is missing, generate it. for term in self.valence.iter_terms(): if 'PT_ALL' not in term.tasks: continue found = False for traj in self.trajectories: if term.get_atoms() == traj.term.get_atoms(): if found: raise ValueError( 'Found two trajectories for term %s with atom indices %s' % (term.basename, str(term.get_atoms()))) found = True if not found: log.warning( 'No trajectory found for term %s with atom indices %s. Generating it now.' % (term.basename, str(term.get_atoms()))) trajectory = self.perturbation.prepare([term])[term.index] self.perturbation.generate(trajectory) self.trajectories.append(trajectory) def average_pars(self): ''' Average force field parameters over master and slaves. ''' log.dump('Averaging force field parameters over master and slaves') for master in self.valence.iter_masters(): npars = len(self.valence.get_params(master.index)) pars = np.zeros([len(master.slaves) + 1, npars], float) pars[0, :] = np.array(self.valence.get_params(master.index)) for i, islave in enumerate(master.slaves): pars[1 + i, :] = np.array(self.valence.get_params(islave)) if master.kind in [0, 2, 11, 12]: #harmonic,fues,MM3Quartic,MM3Bend fc, rv = pars.mean(axis=0) self.valence.set_params(master.index, fc=fc, rv0=rv) for islave in master.slaves: self.valence.set_params(islave, fc=fc, rv0=rv) elif master.kind == 1: a0, a1, a2, a3 = pars.mean(axis=0) self.valence.set_params(master.index, a0=a0, a1=a1, a2=a2, a3=a3) for islave in master.slaves: self.valence.set_params(islave, a0=a0, a1=a1, a2=a2, a3=a3) elif master.kind == 3: #cross fc, rv0, rv1 = pars.mean(axis=0) self.valence.set_params(master.index, fc=fc, rv0=rv0, rv1=rv1) for islave in master.slaves: self.valence.set_params(islave, fc=fc, rv0=rv0, rv1=rv1) elif master.kind == 4: #cosine assert pars[:, 0].std() < 1e-6, 'dihedral multiplicity not unique' m, fc, rv = pars.mean(axis=0) self.valence.set_params(master.index, fc=fc, rv0=rv, m=m) for islave in master.slaves: self.valence.set_params(islave, fc=fc, rv0=rv, m=m) elif master.kind in [5, 6, 7, 8, 9]: #chebychev assert pars.shape[1] == 2 fc = pars[:, 0].mean() self.valence.set_params(master.index, fc=fc) for islave in master.slaves: self.valence.set_params(islave, fc=fc) else: raise NotImplementedError def make_output(self): ''' Dump Yaff parameters, Yaff system, plot energy contributions along perturbation trajectories and dump perturbation trajectories to XYZ files. ''' if self.settings.fn_yaff is not None: dump_yaff(self.valence, self.settings.fn_yaff) if self.settings.fn_charmm22_prm is not None: dump_charmm22_prm(self.valence, self.settings.fn_charmm22_prm) if self.settings.fn_charmm22_psf is not None: dump_charmm22_psf(self.system, self.valence, self.settings.fn_charmm22_psf) if self.settings.fn_sys is not None: self.system.to_file(self.settings.fn_sys) if self.settings.plot_traj is not None and self.settings.plot_traj.lower( ) in ['final', 'all']: self.plot_trajectories(do_valence=True, suffix='_Ehc3') if self.settings.xyz_traj: self.write_trajectories() def plot_trajectories(self, do_valence=False, suffix=''): ''' Plot energy contributions along perturbation trajectories and ''' only = self.settings.only_traj if not isinstance(only, list): only = [only] with log.section('PLOT', 3, timer='PT plot energy'): valence = None if do_valence: valence = self.valence for trajectory in self.trajectories: if trajectory is None: continue for pattern in only: if pattern == 'PT_ALL' or pattern in trajectory.term.basename: trajectory.plot(self.ai, ffrefs=self.ffrefs, valence=valence, suffix=suffix) def write_trajectories(self): ''' Write perturbation trajectories to XYZ files. ''' only = self.settings.only_traj if not isinstance(only, list): only = [only] with log.section('XYZ', 3, timer='PT dump XYZ'): for trajectory in self.trajectories: if trajectory is None: continue for pattern in only: if pattern == 'PT_ALL' or pattern in trajectory.term.basename: trajectory.to_xyz() def do_pt_generate(self): ''' Generate perturbation trajectories. ''' with log.section('PTGEN', 2, timer='PT Generate'): #read if an existing file was specified through fn_traj fn_traj = self.settings.fn_traj if fn_traj is not None and os.path.isfile(fn_traj): self.trajectories = pickle.load(open(fn_traj, 'rb')) log.dump('Trajectories read from file %s' % fn_traj) self.update_trajectory_terms() newname = 'updated_' + fn_traj.split('/')[-1] pickle.dump(self.trajectories, open(newname, 'wb')) return #configure self.reset_system() only = self.settings.only_traj if only is None or only == 'PT_ALL' or only == 'pt_all': do_terms = [ term for term in self.valence.terms if term.kind in [0, 2, 11, 12] ] else: if isinstance(only, str): only = [only] do_terms = [] for pattern in only: for term in self.valence.iter_terms(pattern): if term.kind in [0, 2, 11, 12]: do_terms.append(term) trajectories = self.perturbation.prepare(do_terms) #compute log.dump('Constructing trajectories') self.trajectories = paracontext.map( self.perturbation.generate, [traj for traj in trajectories if traj.active]) #write the trajectories to the non-existing file fn_traj if fn_traj is not None: assert not os.path.isfile(fn_traj) pickle.dump(self.trajectories, open(fn_traj, 'wb')) log.dump('Trajectories stored to file %s' % fn_traj) def do_pt_estimate(self, do_valence=False, logger_level=3): ''' Estimate force constants and rest values from the perturbation trajectories **Optional Arguments** do_valence if set to True, the current valence force field will be used to estimate the contribution of all other valence terms. ''' with log.section('PTEST', 2, timer='PT Estimate'): self.reset_system() message = 'Estimating FF parameters from perturbation trajectories' if do_valence: message += ' with valence reference' log.dump(message) #compute fc and rv from trajectory only = self.settings.only_traj for traj in self.trajectories: if traj is None: continue if not (only is None or only == 'PT_ALL' or only == 'pt_all'): if isinstance(only, str): only = [only] basename = self.valence.terms[traj.term.master].basename if basename not in only: continue self.perturbation.estimate(traj, self.ai, ffrefs=self.ffrefs, do_valence=do_valence) #set force field parameters to computed fc and rv for traj in self.trajectories: if traj is None: continue if not (only is None or only == 'PT_ALL' or only == 'pt_all'): if isinstance(only, str): only = [only] basename = self.valence.terms[traj.term.master].basename if basename not in only: continue self.valence.set_params(traj.term.index, fc=traj.fc, rv0=traj.rv) #output self.valence.dump_logger(print_level=logger_level) #do not add average here since the fluctuation on the parameters is #required for do_pt_postprocess. Average will be done at the end of #do_pt_postprocess def do_pt_postprocess(self): ''' Do some first post processing of the ff parameters estimated from the perturbation trajectories including: * detecting bend patterns with rest values of 90 and 180 deg * detecting bend patterns with rest values only close to 180 deg * transforming SqOopDist with rv=0.0 to OopDist * averaging parameters ''' with log.section('PTPOST', 2, timer='PT Post process'): if self.settings.do_squarebend: self.do_squarebend() if self.settings.do_bendclin: self.do_bendclin() if self.settings.do_sqoopdist_to_oopdist: self.do_sqoopdist_to_oopdist() self.average_pars() def do_eq_setrv(self, tasks, logger_level=3): ''' Set the rest values to their respective AI equilibrium values. ''' with log.section('EQSET', 2, timer='Equil Set RV'): self.reset_system() log.dump( 'Setting rest values to AI equilibrium values for tasks %s' % ' '.join(tasks)) for term in self.valence.terms: vterm = self.valence.vlist.vtab[term.index] if np.array([task in term.tasks for task in tasks]).any(): if term.kind == 3: #cross term ic0 = self.valence.iclist.ictab[vterm['ic0']] ic1 = self.valence.iclist.ictab[vterm['ic1']] self.valence.set_params(term.index, rv0=ic0['value'], rv1=ic1['value']) elif term.kind == 4 and term.ics[ 0].kind == 4: #Cosine of DihedAngle ic = self.valence.iclist.ictab[vterm['ic0']] m = self.valence.get_params(term.index, only='m') rv = ic['value'] % (360.0 * deg / m) with log.section('EQSET', 4, timer='Equil Set RV'): log.dump( 'Set rest value of %s(%s) (eq=%.3f deg) to %.3f deg' % (term.basename, '.'.join([ str(at) for at in term.get_atoms() ]), ic['value'] / deg, rv / deg)) self.valence.set_params(term.index, rv0=rv) else: rv = self.valence.iclist.ictab[vterm['ic0']]['value'] self.valence.set_params(term.index, rv0=rv) self.valence.dump_logger(print_level=logger_level) self.average_pars() def do_hc_estimatefc(self, tasks, logger_level=3, do_svd=False, do_mass_weighting=True): ''' Refine force constants using Hessian Cost function. **Arguments** tasks A list of strings identifying which terms should have their force constant estimated from the hessian cost function. Using such a flag, one can distinguish between for example force constant refinement (flag=HC_FC_DIAG) of the diagonal terms and force constant estimation of the cross terms (flag=HC_FC_CROSS). If the string 'all' is present in tasks, all fc's will be estimated. **Optional Arguments** logger_level print level at which the resulting parameters should be dumped to the logger. By default, the parameters will only be dumped at the highest log level. do_svd whether or not to do an SVD decomposition before solving the set of equations and explicitly throw out the degrees of freedom that correspond to the lowest singular values. do_mass_weighting whether or not to apply mass weighing to the ab initio hessian and the force field contributions before doing the fitting. ''' with log.section('HCEST', 2, timer='HC Estimate FC'): self.reset_system() log.dump( 'Estimating force constants from Hessian cost for tasks %s' % ' '.join(tasks)) term_indices = [] for index in range(self.valence.vlist.nv): term = self.valence.terms[index] flagged = False for flag in tasks: if flag in term.tasks: flagged = True break if flagged: #first check if all rest values and multiplicities have been defined if term.kind == 0: self.valence.check_params(term, ['rv']) if term.kind == 1: self.valence.check_params(term, ['a0', 'a1', 'a2', 'a3']) if term.kind == 3: self.valence.check_params(term, ['rv0', 'rv1']) if term.kind == 4: self.valence.check_params(term, ['rv', 'm']) if term.is_master(): term_indices.append(index) else: #first check if all pars have been defined if term.kind == 0: self.valence.check_params(term, ['fc', 'rv']) if term.kind == 1: self.valence.check_params(term, ['a0', 'a1', 'a2', 'a3']) if term.kind == 3: self.valence.check_params(term, ['fc', 'rv0', 'rv1']) if term.kind == 4: self.valence.check_params(term, ['fc', 'rv', 'm']) if len(term_indices) == 0: log.dump( 'No terms (with task in %s) found to estimate FC from HC' % (str(tasks))) return cost = HessianFCCost(self.system, self.ai, self.valence, term_indices, ffrefs=self.ffrefs, do_mass_weighting=do_mass_weighting) fcs = cost.estimate(do_svd=do_svd) for index, fc in zip(term_indices, fcs): master = self.valence.terms[index] assert master.is_master() self.valence.set_params(index, fc=fc) for islave in master.slaves: self.valence.set_params(islave, fc=fc) self.valence.dump_logger(print_level=logger_level) def do_cross_init(self): ''' Set the rest values of cross terms to the rest values of the corresponding diagonal terms. The force constants are initialized to zero. ''' with log.section('VAL', 2, 'Initializing'): self.reset_system() self.valence.init_cross_angle_terms() #function to find rest value def find_rest_value(label): candidates = [ cand for cand in self.valence.iter_masters(label=label, use_re=True) ] assert len( candidates) < 2, 'Multiple masters found for %s: %s' % ( label, ','.join([cand.basename for cand in candidates])) if len(candidates) == 0: if label.startswith('^Bond') or label.startswith( '^Bend') or label.startswith('^Tors'): sublabels = label.split('|') prefix0, types0 = sublabels[0].lstrip('^').rstrip( '$').split('/') label = '^' + prefix0 + '/' + '\.'.join( types0.split('.')[::-1]) + '$' if len(sublabels) > 1: prefix1, types1 = sublabels[1].lstrip('^').rstrip( '$').split('/') label += '|' label += '^' + prefix1 + '/' + '\.'.join( types1.split('.')[::-1]) + '$' candidates = [ cand for cand in self.valence.iter_masters(label=label, use_re=True) ] assert len( candidates ) < 2, 'Multiple masters found for %s: %s' % ( label, ','.join( [cand.basename for cand in candidates])) if len(candidates) == 0: return None can = candidates[0] if can.basename.startswith( 'TorsCheby') or can.basename.startswith('BendCheby'): return -self.valence.get_params(can.index, only='sign') else: return self.valence.get_params(can.index, only='rv') #set rest values and initialize fc for bond-bond cross for term in self.valence.iter_masters('^Cross/.*/bb$', use_re=True): types = term.basename.split('/')[1].split('.') assert len( types ) == 3, 'Found angle cross terms with more/less than 3 atom types' rv0 = find_rest_value('^Bond.*/%s$' % ('.'.join(types[:2]))) rv1 = find_rest_value('^Bond.*/%s$' % ('.'.join(types[1:]))) assert rv0 is not None, 'Rest value of BondHarm/%s not found' % ( '.'.join(types[:2])) assert rv1 is not None, 'Rest value of BondHarm/%s not found' % ( '.'.join(types[1:])) self.valence.set_params(term.index, fc=0.0, rv0=rv0, rv1=rv1) for index in term.slaves: self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) #set rest values and initialize fc for bond-angle cross for term in self.valence.iter_masters('^Cross/.*/b0a$', use_re=True): types = term.basename.split('/')[1].split('.') assert len( types ) == 3, 'Found angle cross terms with more/less than 3 atom types' rv0 = find_rest_value('^Bond.*/%s$' % ('.'.join(types[:2]))) rv1 = find_rest_value('^BendAHarm/%s$|^BendMM3/%s$' % ('.'.join(types), '.'.join(types))) assert rv0 is not None, 'Rest value of BondHarm/%s not found' % ( '.'.join(types[:2])) assert rv1 is not None, 'Rest value of BendAHarm|BendMM3/%s not found' % ( '.'.join(types)) self.valence.set_params(term.index, fc=0.0, rv0=rv0, rv1=rv1) for index in term.slaves: self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) for term in self.valence.iter_masters('^Cross/.*/b1a$', use_re=True): types = term.basename.split('/')[1].split('.') assert len( types ) == 3, 'Found angle cross terms with more/less than 3 atom types' rv0 = find_rest_value('^Bond.*/%s$' % ('.'.join(types[1:]))) rv1 = find_rest_value('^BendAHarm/%s$|^BendMM3/%s$' % ('.'.join(types), '.'.join(types))) assert rv0 is not None, 'Rest value of BondHarm/%s not found' % ( '.'.join(types[1:])) assert rv1 is not None, 'Rest value of BendAHarm|BendMM3/%s not found' % ( '.'.join(types)) self.valence.set_params(term.index, fc=0.0, rv0=rv0, rv1=rv1) for index in term.slaves: self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) if self.settings.do_cross_DSS or self.settings.do_cross_DSD or self.settings.do_cross_DAD or self.settings.do_cross_DAA: self.valence.init_cross_dihed_terms() #set rest values and initialize fc for bond-bond cross for m in [1, 2, 3, 4, 6]: for term in self.valence.iter_masters( '^CrossBondDih%i/.*/bb$' % m, use_re=True): types = term.basename.split('/')[1].split('.') assert len( types ) == 4, 'Found angle cross terms with more/less than 4 atom types' rv0 = find_rest_value('^Bond.*/%s$' % ('.'.join(types[:2]))) rv1 = find_rest_value('^Bond.*/%s$' % ('.'.join(types[2:]))) self.valence.set_params(term.index, fc=0.0, rv0=rv0, rv1=rv1) for index in term.slaves: self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) #set rest values and initialize fc for bond-dihed cross for m in [1, 2, 3, 4, 6]: for term in self.valence.iter_masters( '^CrossBondDih%i/.*/b0d$' % m, use_re=True): types = term.basename.split('/')[1].split('.') assert len( types ) == 4, 'Found angle cross terms with more/less than 4 atom types' rv0 = find_rest_value('^Bond.*/%s$' % ('.'.join(types[:2]))) rv1 = find_rest_value('^TorsCheby%i/%s$' % (m, '.'.join(types))) self.valence.set_params(term.index, fc=0.0, rv0=rv0, rv1=rv1) for index in term.slaves: self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) for term in self.valence.iter_masters( '^CrossBondDih%i/.*/b1d$' % m, use_re=True): types = term.basename.split('/')[1].split('.') assert len( types ) == 4, 'Found angle cross terms with more/less than 4 atom types' rv0 = find_rest_value('^Bond.*/%s$' % ('.'.join(types[1:3]))) rv1 = find_rest_value('^TorsCheby%i/%s$' % (m, '.'.join(types))) self.valence.set_params(term.index, fc=0.0, rv0=rv0, rv1=rv1) for index in term.slaves: self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) for term in self.valence.iter_masters( '^CrossBondDih%i/.*/b2d$' % m, use_re=True): types = term.basename.split('/')[1].split('.') assert len( types ) == 4, 'Found angle cross terms with more/less than 4 atom types' rv0 = find_rest_value('^Bond.*/%s$' % ('.'.join(types[2:]))) rv1 = find_rest_value('^TorsCheby%i/%s$' % (m, '.'.join(types))) self.valence.set_params(term.index, fc=0.0, rv0=rv0, rv1=rv1) for index in term.slaves: self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) #set rest values and initialize fc for angle-angle cross for m in [1, 2, 3, 4, 6]: for term in self.valence.iter_masters( '^CrossBendDih%i/.*/aa$' % m, use_re=True): types = term.basename.split('/')[1].split('.') assert len( types ) == 4, 'Found angle cross terms with more/less than 4 atom types' rv0 = find_rest_value( '^BendAHarm/%s$|^BendMM3/%s$' % ('.'.join(types[:3]), '.'.join(types[:3]))) rv1 = find_rest_value( '^BendAHarm/%s$|^BendMM3/%s$' % ('.'.join(types[1:]), '.'.join(types[1:]))) self.valence.set_params(term.index, fc=0.0, rv0=rv0, rv1=rv1) for index in term.slaves: self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) #set rest values and initialize fc for angle-dihed cross for m in [1, 2, 3, 4, 6]: for term in self.valence.iter_masters( '^CrossBendDih%i/.*/a0d$' % m, use_re=True): types = term.basename.split('/')[1].split('.') assert len( types ) == 4, 'Found angle cross terms with more/less than 4 atom types' rv0 = find_rest_value( '^BendAHarm/%s$|^BendMM3/%s$' % ('.'.join(types[:3]), '.'.join(types[:3]))) rv1 = find_rest_value('^TorsCheby%i/%s$' % (m, '.'.join(types))) self.valence.set_params(term.index, fc=0.0, rv0=rv0, rv1=rv1) for index in term.slaves: self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) for term in self.valence.iter_masters( '^CrossBendDih%i/.*/a1d$' % m, use_re=True): types = term.basename.split('/')[1].split('.') assert len( types ) == 4, 'Found angle cross terms with more/less than 4 atom types' rv0 = find_rest_value( '^BendAHarm/%s$|^BendMM3/%s$' % ('.'.join(types[1:]), '.'.join(types[1:]))) rv1 = find_rest_value('^TorsCheby%i/%s$' % (m, '.'.join(types))) self.valence.set_params(term.index, fc=0.0, rv0=rv0, rv1=rv1) for index in term.slaves: self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) for term in self.valence.iter_masters( '^CrossCBendDih%i/.*/a0d$' % m, use_re=True): types = term.basename.split('/')[1].split('.') assert len( types ) == 4, 'Found angle cross terms with more/less than 4 atom types' rv0 = find_rest_value('^BendCLin/%s$' % ('.'.join(types[:3]))) rv1 = find_rest_value('^TorsCheby%i/%s$' % (m, '.'.join(types))) self.valence.set_params(term.index, fc=0.0, rv0=rv0, rv1=rv1) for index in term.slaves: self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) for term in self.valence.iter_masters( '^CrossCBendDih%i/.*/a1d$' % m, use_re=True): types = term.basename.split('/')[1].split('.') assert len( types ) == 4, 'Found angle cross terms with more/less than 4 atom types' rv0 = find_rest_value('^BendCLin/%s$' % ('.'.join(types[1:]))) rv1 = find_rest_value('^TorsCheby%i/%s$' % (m, '.'.join(types))) self.valence.set_params(term.index, fc=0.0, rv0=rv0, rv1=rv1) for index in term.slaves: self.valence.set_params(index, fc=0.0, rv0=rv0, rv1=rv1) def do_squarebend(self, thresshold=10 * deg): ''' Identify bend patterns in which 4 atoms of type A surround a central atom of type B with A-B-A angles of 90/180 degrees. A simple harmonic pattern will not be adequate since a rest value of 90 and 180 degrees is possible for the same A-B-A term. Therefore, a cosine term with multiplicity of 4 is used (which corresponds to a chebychev4 potential with sign=-1): V = K/2*[1-cos(4*theta)] To identify the patterns, it is assumed that the rest values have already been estimated from the perturbation trajectories. For each master and slave of a BENDAHARM term, its rest value is computed and checked if it lies either the interval [90-thresshold,90+thresshold] or [180-thresshold,180]. If this is the case, the new cosine term is used. **Optional arguments** thresshold the (half) the width of the interval around 180 deg (90 degrees) to check if a square BA4 ''' for master in self.valence.iter_masters(label='BendAHarm'): rvs = np.zeros([len(master.slaves) + 1], float) rvs[0] = self.valence.get_params(master.index, only='rv') for i, islave in enumerate(master.slaves): rvs[1 + i] = self.valence.get_params(islave, only='rv') n90 = 0 n180 = 0 nother = 0 for i, rv in enumerate(rvs): if 90 * deg - thresshold <= rv and rv <= 90 * deg + thresshold: n90 += 1 elif 180 * deg - thresshold <= rv and rv <= 180 * deg + thresshold: n180 += 1 else: nother += 1 if n90 > 0 and n180 > 0: log.dump( '%s has rest values around 90 deg and 180 deg, converted to BendCheby4' % master.basename) #modify master and slaves indices = [master.index] for slave in master.slaves: indices.append(slave) for index in indices: term = self.valence.terms[index] self.valence.modify_term( index, Chebychev4, [BendCos(*term.get_atoms())], term.basename.replace('BendAHarm', 'BendCheby4'), ['HC_FC_DIAG'], ['kjmol', 'au']) self.valence.set_params(index, sign=-1) for traj in self.trajectories: if traj.term.index == index: traj.active = False traj.fc = None traj.rv = None def do_bendclin(self, thresshold=5 * deg): ''' No Harmonic bend can have a rest value equal to are large than 180 deg - thresshold. If a master (or its slaves) has such a rest value, convert master and all slaves to BendCLin (which corresponds to a chebychev1 potential with sign=+1): 0.5*K*[1+cos(theta)] ''' for master in self.valence.iter_masters(label='BendAHarm'): indices = [master.index] for slave in master.slaves: indices.append(slave) found = False for index in indices: rv = self.valence.get_params(index, only='rv') if rv >= 180.0 * deg - thresshold: found = True break if found: log.dump( '%s has rest value > 180-%.0f deg, converted to BendCheby1' % (master.basename, thresshold / deg)) for index in indices: term = self.valence.terms[index] self.valence.modify_term( index, Chebychev1, [BendCos(*term.get_atoms())], term.basename.replace('BendAHarm', 'BendCheby1'), ['HC_FC_DIAG'], ['kjmol', 'au']) self.valence.set_params(index, fc=0.0, sign=1.0) for traj in self.trajectories: if traj.term.index == index: traj.rv = None traj.fc = None traj.active = False def do_sqoopdist_to_oopdist(self, thresshold=1e-4 * angstrom): ''' Transform a SqOopdist term with a rest value that has been set to zero, to a term Oopdist (harmonic in Oopdist instead of square of Oopdist) with a rest value of 0.0 A. ''' for master in self.valence.iter_masters(label='SqOopdist'): indices = [master.index] for slave in master.slaves: indices.append(slave) found = False for index in indices: rv = self.valence.get_params(index, only='rv') if rv <= thresshold: found = True break if found: log.dump( '%s has rest value <= %.0f A^2, converted to Oopdist with d0=0' % (master.basename, thresshold / angstrom)) for index in indices: term = self.valence.terms[index] self.valence.modify_term( index, Harmonic, [OopDist(*term.get_atoms())], term.basename.replace('SqOopdist', 'Oopdist'), ['HC_FC_DIAG'], ['kjmol/A**2', 'A']) self.valence.set_params(index, fc=0.0, rv0=0.0) def run(self): ''' Sequence of instructions, should be implemented in the inheriting classes. The various inheriting classes distinguish themselves by means of the instructions implemented in this routine. ''' raise NotImplementedError