def read_reference_data(self):
""" Read the reference hydrational data from a file. """
# Read the HFE data file. This is a very simple file format:
self.IDs = []
self.expval = OrderedDict()
self.experr = OrderedDict()
self.nicknames = OrderedDict()
# We don't need every single line to be the same. This
# indicates whether *any* molecule has a nickname for printing
# out the nickname column.
self.have_nicks = False
# Again for experimental errors. Note that we're NOT using them in the optimization at this time.
self.have_experr = False
for line in open(self.datafile).readlines():
s = line.expandtabs().strip().split('#')[0].split()
if len(s) == 0: continue
ID = s[0]
self.IDs.append(ID)
# Dynamic field number for the experimental data.
nxt = 1
# If the next field is a string, then it's the "nickname"
if not isfloat(s[1]):
self.have_nicks = True
self.nicknames[ID] = s[1]
nxt += 1
else:
# We don't need nicknames on every single line.
self.nicknames[ID] = ID
# Read the experimental value.
self.expval[ID] = float(s[nxt])
# Read the experimental error bar, or use a default value of 0.6 (from Mobley).
if len(s) > (nxt + 1):
self.have_experr = True
self.experr[ID] = float(s[nxt + 1])
else:
self.experr[ID] = 0.6
self.molecules = OrderedDict([
(i,
os.path.abspath(
os.path.join(self.root, self.tgtdir, 'molecules',
i + self.crdsfx))) for i in self.IDs
])
for fnm, path in self.molecules.items():
if not os.path.isfile(path):
logger.error(
'Coordinate file %s does not exist!\nMake sure coordinate files are in the right place\n'
% path)
raise RuntimeError
if self.subset is not None:
subset = uncommadash(self.subset)
self.whfe = np.array(
[1 if i in subset else 0 for i in range(len(self.IDs))])
else:
self.whfe = np.ones(len(self.IDs))
def read_reference_data(self):
""" Read the reference hydrational data from a file. """
self.refdata = OrderedDict([(l.split()[0], float(l.split()[1])) for l in open(self.datafile).readlines()])
self.molecules = OrderedDict([(i, os.path.abspath(os.path.join(self.root, self.tgtdir, 'molecules', i+self.crdsfx))) for i in self.refdata.keys()])
for fnm, path in self.molecules.items():
if not os.path.isfile(path):
logger.error('Coordinate file %s does not exist!\nMake sure coordinate files are in the right place\n' % path)
raise RuntimeError
if self.subset != None:
subset = uncommadash(self.subset)
self.whfe = np.array([1 if i in subset else 0 for i in range(len(self.refdata.keys()))])
else:
self.whfe = np.ones(len(self.refdata.keys()))
def read_reference_data(self):
""" Read the reference hydrational data from a file. """
# Read the HFE data file. This is a very simple file format:
self.IDs = []
self.expval = OrderedDict()
self.experr = OrderedDict()
self.nicknames = OrderedDict()
# We don't need every single line to be the same. This
# indicates whether *any* molecule has a nickname for printing
# out the nickname column.
self.have_nicks = False
# Again for experimental errors. Note that we're NOT using them in the optimization at this time.
self.have_experr = False
for line in open(self.datafile).readlines():
s = line.expandtabs().strip().split('#')[0].split()
if len(s) == 0: continue
ID = s[0]
self.IDs.append(ID)
# Dynamic field number for the experimental data.
nxt = 1
# If the next field is a string, then it's the "nickname"
if not isfloat(s[1]):
self.have_nicks = True
self.nicknames[ID] = s[1]
nxt += 1
else:
# We don't need nicknames on every single line.
self.nicknames[ID] = ID
# Read the experimental value.
self.expval[ID] = float(s[nxt])
# Read the experimental error bar, or use a default value of 0.6 (from Mobley).
if len(s) > (nxt+1):
self.have_experr = True
self.experr[ID] = float(s[nxt+1])
else:
self.experr[ID] = 0.6
self.molecules = OrderedDict([(i, os.path.abspath(os.path.join(self.root, self.tgtdir, 'molecules', i+self.crdsfx))) for i in self.IDs])
for fnm, path in self.molecules.items():
if not os.path.isfile(path):
logger.error('Coordinate file %s does not exist!\nMake sure coordinate files are in the right place\n' % path)
raise RuntimeError
if self.subset != None:
subset = uncommadash(self.subset)
self.whfe = np.array([1 if i in subset else 0 for i in range(len(self.IDs))])
else:
self.whfe = np.ones(len(self.IDs))
def read_reference_data(self):
""" Read the reference hydrational data from a file. """
self.refdata = OrderedDict([(l.split()[0], float(l.split()[1]))
for l in open(self.datafile).readlines()])
self.molecules = OrderedDict([
(i,
os.path.abspath(
os.path.join(self.root, self.tgtdir, 'molecules',
i + self.crdsfx))) for i in self.refdata.keys()
])
for fnm, path in self.molecules.items():
if not os.path.isfile(path):
logger.error(
'Coordinate file %s does not exist!\nMake sure coordinate files are in the right place\n'
% path)
raise RuntimeError
if self.subset != None:
subset = uncommadash(self.subset)
self.whfe = np.array([
1 if i in subset else 0
for i in range(len(self.refdata.keys()))
])
else:
self.whfe = np.ones(len(self.refdata.keys()))
def __init__(self,options,tgt_opts,forcefield):
# Initialize the SuperClass!
super(Interaction,self).__init__(options,tgt_opts,forcefield)
#======================================#
# Options that are given by the parser #
#======================================#
## Number of snapshots
self.set_option(tgt_opts,'shots','ns')
## Do we call Q-Chem for dielectric energies? (Currently needs to be fixed)
self.set_option(tgt_opts,'do_cosmo','do_cosmo')
## Do we put the reference energy into the denominator?
self.set_option(tgt_opts,'cauchy','cauchy')
## Do we put the reference energy into the denominator?
self.set_option(tgt_opts,'attenuate','attenuate')
## Divide by the number of snapshots?
self.set_option(tgt_opts, 'normalize')
## What is the energy denominator?
self.set_option(tgt_opts,'energy_denom','energy_denom')
## Set fragment 1
self.set_option(tgt_opts,'fragment1','fragment1')
if len(self.fragment1) == 0:
logger.error('You need to define the first fragment using the fragment1 keyword\n')
raise RuntimeError
self.select1 = np.array(uncommadash(self.fragment1))
## Set fragment 2
self.set_option(tgt_opts,'fragment2','fragment2')
if len(self.fragment2) != 0:
self.select2 = np.array(uncommadash(self.fragment2))
else:
self.select2 = None
## Set upper cutoff energy
self.set_option(tgt_opts,'energy_upper','energy_upper')
#======================================#
# Variables which are set here #
#======================================#
## Reference (QM) interaction energies
self.eqm = []
## Snapshot label, useful for graphing
self.label = []
## The qdata.txt file that contains the QM energies and forces
self.qfnm = os.path.join(self.tgtdir,"qdata.txt")
self.e_err = 0.0
self.e_err_pct = None
## Read in the trajectory file
self.mol = Molecule(os.path.join(self.root,self.tgtdir,self.coords),
top=(os.path.join(self.root,self.tgtdir,self.pdb) if hasattr(self, 'pdb') else None))
if self.ns != -1:
self.mol = self.mol[:self.ns]
self.ns = len(self.mol)
if self.select2 is None:
self.select2 = [i for i in range(self.mol.na) if i not in self.select1]
logger.info('Fragment 2 is the complement of fragment 1 : %s\n' % (commadash(self.select2)))
## Build keyword dictionaries to pass to engine.
engine_args = OrderedDict(self.OptionDict.items() + options.items())
del engine_args['name']
self.engine = self.engine_(target=self, mol=self.mol, **engine_args)
## Read in the reference data
self.read_reference_data()
logger.info("The energy denominator is: %s kcal/mol\n" % str(self.energy_denom))
denom = self.energy_denom
# Create the denominator.
if self.cauchy:
self.divisor = np.sqrt(self.eqm**2 + denom**2)
if self.attenuate:
logger.error('attenuate and cauchy are mutually exclusive\n')
raise RuntimeError
elif self.attenuate:
# Attenuate only large repulsions.
self.divisor = np.zeros(len(self.eqm))
for i in range(len(self.eqm)):
if self.eqm[i] < denom:
self.divisor[i] = denom
else:
self.divisor[i] = np.sqrt(denom**2 + (self.eqm[i]-denom)**2)
else:
self.divisor = np.ones(len(self.eqm)) * denom
if self.cauchy:
logger.info("Each contribution to the interaction energy objective function will be scaled by 1.0 / ( energy_denom**2 + reference**2 )\n")
if self.energy_upper > 0:
ecut = self.energy_upper
self.prefactor = 1.0 * (self.eqm < ecut)
logger.info("Interactions more repulsive than %s will not be fitted (%i/%i excluded) \n" % (str(self.energy_upper), sum(self.eqm > ecut), len(self.eqm)))
else:
self.prefactor = np.ones(len(self.eqm))
if self.normalize:
self.prefactor /= len(self.prefactor)
def __init__(self, options, tgt_opts, forcefield):
# Initialize the SuperClass!
super(Interaction, self).__init__(options, tgt_opts, forcefield)
#======================================#
# Options that are given by the parser #
#======================================#
## Number of snapshots
self.set_option(tgt_opts, 'shots', 'ns')
## Do we call Q-Chem for dielectric energies? (Currently needs to be fixed)
self.set_option(tgt_opts, 'do_cosmo', 'do_cosmo')
## Do we put the reference energy into the denominator?
self.set_option(tgt_opts, 'cauchy', 'cauchy')
## Do we put the reference energy into the denominator?
self.set_option(tgt_opts, 'attenuate', 'attenuate')
## Divide by the number of snapshots?
self.set_option(tgt_opts, 'normalize')
## What is the energy denominator?
self.set_option(tgt_opts, 'energy_denom', 'energy_denom')
## Set fragment 1
self.set_option(tgt_opts, 'fragment1', 'fragment1')
if len(self.fragment1) == 0:
logger.error(
'You need to define the first fragment using the fragment1 keyword\n'
)
raise RuntimeError
self.select1 = np.array(uncommadash(self.fragment1))
## Set fragment 2
self.set_option(tgt_opts, 'fragment2', 'fragment2')
if len(self.fragment2) != 0:
self.select2 = np.array(uncommadash(self.fragment2))
else:
self.select2 = None
## Set upper cutoff energy
self.set_option(tgt_opts, 'energy_upper', 'energy_upper')
#======================================#
# Variables which are set here #
#======================================#
## Reference (QM) interaction energies
self.eqm = []
## Snapshot label, useful for graphing
self.label = []
## The qdata.txt file that contains the QM energies and forces
self.qfnm = os.path.join(self.tgtdir, "qdata.txt")
self.e_err = 0.0
self.e_err_pct = None
## Read in the trajectory file
if self.ns == -1:
self.mol = Molecule(
os.path.join(self.root, self.tgtdir, self.coords))
self.ns = len(self.mol)
else:
self.mol = Molecule(
os.path.join(self.root, self.tgtdir, self.coords))[:self.ns]
if self.select2 == None:
self.select2 = [
i for i in range(self.mol.na) if i not in self.select1
]
logger.info('Fragment 2 is the complement of fragment 1 : %s\n' %
(commadash(self.select2)))
## Build keyword dictionaries to pass to engine.
engine_args = OrderedDict(self.OptionDict.items() + options.items())
del engine_args['name']
self.engine = self.engine_(target=self, mol=self.mol, **engine_args)
## Read in the reference data
self.read_reference_data()
logger.info("The energy denominator is: %s kcal/mol\n" %
str(self.energy_denom))
denom = self.energy_denom
# Create the denominator.
if self.cauchy:
self.divisor = np.sqrt(self.eqm**2 + denom**2)
if self.attenuate:
logger.error('attenuate and cauchy are mutually exclusive\n')
raise RuntimeError
elif self.attenuate:
# Attenuate only large repulsions.
self.divisor = np.zeros(len(self.eqm))
for i in range(len(self.eqm)):
if self.eqm[i] < denom:
self.divisor[i] = denom
else:
self.divisor[i] = np.sqrt(denom**2 +
(self.eqm[i] - denom)**2)
else:
self.divisor = np.ones(len(self.eqm)) * denom
if self.cauchy:
logger.info(
"Each contribution to the interaction energy objective function will be scaled by 1.0 / ( energy_denom**2 + reference**2 )\n"
)
if self.energy_upper > 0:
ecut = self.energy_upper
self.prefactor = 1.0 * (self.eqm < ecut)
logger.info(
"Interactions more repulsive than %s will not be fitted (%i/%i excluded) \n"
%
(str(self.energy_upper), sum(self.eqm > ecut), len(self.eqm)))
else:
self.prefactor = np.ones(len(self.eqm))
if self.normalize:
self.prefactor /= len(self.prefactor)
def __init__(self,options,tgt_opts,forcefield):
# Initialize the SuperClass!
super(Interaction,self).__init__(options,tgt_opts,forcefield)
#======================================#
# Options that are given by the parser #
#======================================#
## Number of snapshots
self.set_option(tgt_opts,'shots','ns')
## Do we call Q-Chem for dielectric energies? (Currently needs to be fixed)
self.set_option(tgt_opts,'do_cosmo','do_cosmo')
## Do we put the reference energy into the denominator?
self.set_option(tgt_opts,'cauchy','cauchy')
## Do we put the reference energy into the denominator?
self.set_option(tgt_opts,'attenuate','attenuate')
## What is the energy denominator?
self.set_option(tgt_opts,'energy_denom','energy_denom')
## Set fragment 1
self.set_option(tgt_opts,'fragment1','fragment1')
if len(self.fragment1) == 0:
raise Exception('You need to define the first fragment using the fragment1 keyword')
self.select1 = array(uncommadash(self.fragment1))
## Set fragment 2
self.set_option(tgt_opts,'fragment2','fragment2')
if len(self.fragment2) == 0:
raise Exception('You need to define the second fragment using the fragment2 keyword')
self.select2 = array(uncommadash(self.fragment2))
## Set upper cutoff energy
self.set_option(tgt_opts,'energy_upper','energy_upper')
#======================================#
# Variables which are set here #
#======================================#
## Reference (QM) interaction energies
self.eqm = []
## Snapshot label, useful for graphing
self.label = []
## The qdata.txt file that contains the QM energies and forces
self.qfnm = os.path.join(self.tgtdir,"qdata.txt")
## Qualitative Indicator: average energy error (in kJ/mol)
self.e_err = 0.0
self.e_err_pct = None
## Read in the trajectory file
if self.ns == -1:
self.traj = Molecule(os.path.join(self.root,self.tgtdir,self.trajfnm))
self.ns = len(self.traj)
else:
self.traj = Molecule(os.path.join(self.root,self.tgtdir,self.trajfnm))[:self.ns]
## Read in the reference data
self.read_reference_data()
## Prepare the temporary directory
self.prepare_temp_directory(options,tgt_opts)
logger.info("The energy denominator is: %s kcal/mol\n" % str(self.energy_denom))
# Internally things are handled in kJ/mol.
denom = self.energy_denom * 4.184
# Create the denominator.
if self.cauchy:
self.divisor = sqrt(self.eqm**2 + denom**2)
if self.attenuate:
raise Exception('attenuate and cauchy are mutually exclusive')
elif self.attenuate:
# Attenuate only large repulsions.
self.divisor = zeros(len(self.eqm))
for i in range(len(self.eqm)):
if self.eqm[i] < denom:
self.divisor[i] = denom
else:
self.divisor[i] = sqrt(denom**2 + (self.eqm[i]-denom)**2)
else:
self.divisor = ones(len(self.eqm)) * denom
if self.cauchy:
logger.info("Each contribution to the interaction energy objective function will be scaled by 1.0 / ( energy_denom**2 + reference**2 )\n")
if self.energy_upper > 0:
logger.info("Interactions more repulsive than %s will not be fitted\n" % str(self.energy_upper))
ecut = self.energy_upper * 4.184
self.prefactor = 1.0 * (self.eqm < ecut)
else:
self.prefactor = ones(len(self.eqm))
def __init__(self, options, tgt_opts, forcefield):
# Initialize the SuperClass!
super(Interaction, self).__init__(options, tgt_opts, forcefield)
#======================================#
# Options that are given by the parser #
#======================================#
## Number of snapshots
self.set_option(tgt_opts, 'shots', 'ns')
## Do we call Q-Chem for dielectric energies? (Currently needs to be fixed)
self.set_option(tgt_opts, 'do_cosmo', 'do_cosmo')
## Attenuate weights for positive interaction energies
self.set_option(tgt_opts, 'attenuate', 'attenuate')
## Divide by the number of snapshots?
self.set_option(tgt_opts, 'normalize')
## What is the energy denominator?
self.set_option(tgt_opts, 'energy_denom', 'energy_denom')
## Set fragment 1
self.set_option(tgt_opts, 'fragment1', 'fragment1')
if len(self.fragment1) == 0:
logger.error(
'You need to define the first fragment using the fragment1 keyword\n'
)
raise RuntimeError
self.select1 = np.array(uncommadash(self.fragment1))
## Set fragment 2
self.set_option(tgt_opts, 'fragment2', 'fragment2')
if len(self.fragment2) != 0:
self.select2 = np.array(uncommadash(self.fragment2))
else:
self.select2 = None
## Set upper cutoff energy
self.set_option(tgt_opts, 'energy_upper', 'energy_upper')
## Option for how much data to write to disk.
self.set_option(tgt_opts, 'writelevel', 'writelevel')
#======================================#
# Variables which are set here #
#======================================#
## LPW 2018-02-11: This is set to True if the target calculates
## a single-point property over several existing snapshots.
self.loop_over_snapshots = True
## Reference (QM) interaction energies
self.eqm = []
## Snapshot label, useful for graphing
self.label = []
## The qdata.txt file that contains the QM energies and forces
self.qfnm = os.path.join(self.tgtdir, "qdata.txt")
self.e_err = 0.0
self.e_err_pct = None
## Read in the trajectory file
self.mol = Molecule(
os.path.join(self.root, self.tgtdir, self.coords),
top=(os.path.join(self.root, self.tgtdir, self.pdb) if hasattr(
self, 'pdb') else None),
build_topology=False if self.coords.endswith('.pdb') else True)
if self.ns != -1:
self.mol = self.mol[:self.ns]
self.ns = len(self.mol)
if self.select2 is None:
self.select2 = [
i for i in range(self.mol.na) if i not in self.select1
]
logger.info('Fragment 2 is the complement of fragment 1 : %s\n' %
(commadash(self.select2)))
## Build keyword dictionaries to pass to engine.
engine_args = OrderedDict(
list(self.OptionDict.items()) + list(options.items()))
engine_args.pop('name', None)
self.engine = self.engine_(target=self, mol=self.mol, **engine_args)
## Read in the reference data
self.read_reference_data()
logger.info("The energy denominator is: %s kcal/mol\n" %
str(self.energy_denom))
denom = self.energy_denom
if self.attenuate:
# The attenuation function for weights is constant for energies up to energy_denom, then falls off smoothly in the shape of a "mesa".
self.divisor = np.zeros(len(self.eqm))
for i in range(len(self.eqm)):
if self.eqm[i] < denom:
self.divisor[i] = denom
else:
self.divisor[i] = np.sqrt(denom**2 +
(self.eqm[i] - denom)**2)
logger.info(
"Interaction energies more positive than %.1f will have reduced weight going as: 1.0 / (%.1f^2 + (energy-%.1f)^2)\n"
% (denom, denom, denom))
else:
self.divisor = np.ones(len(self.eqm)) * denom
if self.energy_upper > 0:
ecut = self.energy_upper
self.prefactor = 1.0 * (self.eqm < ecut)
logger.info(
"Interactions more repulsive than %s will not be fitted (%i/%i excluded) \n"
%
(str(self.energy_upper), sum(self.eqm > ecut), len(self.eqm)))
else:
self.prefactor = np.ones(len(self.eqm))
if self.normalize:
self.prefactor /= len(self.prefactor)
