def evaluate_(self, crdin, force=False):
"""
Utility function for computing energy and forces using AMBER.
Inputs:
crdin: AMBER .mdcrd file name.
force: Switch for parsing the force. (Currently it always calculates the forces.)
Outputs:
Result: Dictionary containing energies (and optionally) forces.
"""
force_mdin = """Loop over conformations and compute energy and force (use ioutfnm=1 for netcdf, ntb=0 for no box)
&cntrl
imin = 5, ntb = 0, cut=9, nstlim = 0, nsnb = 0
/
&debugf
do_debugf = 1, dumpfrc = 1
/
"""
with wopen("%s-force.mdin" % self.name) as f:
print >> f, force_mdin
## This line actually runs AMBER.
self.leap(delcheck=True)
self.callamber(
"sander -i %s-force.mdin -o %s-force.mdout -p %s.prmtop -c %s.inpcrd -y %s -O"
% (self.name, self.name, self.name, self.name, crdin))
ParseMode = 0
Result = {}
Energies = []
Forces = []
Force = []
for line in open('forcedump.dat'):
line = line.strip()
sline = line.split()
if ParseMode == 1:
if len(sline) == 1 and isfloat(sline[0]):
Energies.append(float(sline[0]) * 4.184)
ParseMode = 0
if ParseMode == 2:
if len(sline) == 3 and all(
isfloat(sline[i]) for i in range(3)):
Force += [float(sline[i]) * 4.184 * 10 for i in range(3)]
if len(Force) == 3 * self.qmatoms:
Forces.append(np.array(Force))
Force = []
ParseMode = 0
if line == '0 START of Energies':
ParseMode = 1
elif line == '1 Total Force':
ParseMode = 2
Result["Energy"] = np.array(Energies[1:])
Result["Force"] = np.array(Forces[1:])
return Result
def evaluate_(self, crdin, force=False):
"""
Utility function for computing energy and forces using AMBER.
Inputs:
crdin: AMBER .mdcrd file name.
force: Switch for parsing the force. (Currently it always calculates the forces.)
Outputs:
Result: Dictionary containing energies (and optionally) forces.
"""
force_mdin="""Loop over conformations and compute energy and force (use ioutfnm=1 for netcdf, ntb=0 for no box)
&cntrl
imin = 5, ntb = 0, cut=9, nstlim = 0, nsnb = 0
/
&debugf
do_debugf = 1, dumpfrc = 1
/
"""
with wopen("%s-force.mdin" % self.name) as f:
print >> f, force_mdin
## This line actually runs AMBER.
self.leap(delcheck=True)
self.callamber("sander -i %s-force.mdin -o %s-force.mdout -p %s.prmtop -c %s.inpcrd -y %s -O" %
(self.name, self.name, self.name, self.name, crdin))
ParseMode = 0
Result = {}
Energies = []
Forces = []
Force = []
for line in open('forcedump.dat'):
line = line.strip()
sline = line.split()
if ParseMode == 1:
if len(sline) == 1 and isfloat(sline[0]):
Energies.append(float(sline[0]) * 4.184)
ParseMode = 0
if ParseMode == 2:
if len(sline) == 3 and all(isfloat(sline[i]) for i in range(3)):
Force += [float(sline[i]) * 4.184 * 10 for i in range(3)]
if len(Force) == 3*self.qmatoms:
Forces.append(np.array(Force))
Force = []
ParseMode = 0
if line == '0 START of Energies':
ParseMode = 1
elif line == '1 Total Force':
ParseMode = 2
Result["Energy"] = np.array(Energies[1:])
Result["Force"] = np.array(Forces[1:])
return Result
def is_mol2_atom(line):
s = line.split()
if len(s) < 9:
return False
return all([
isint(s[0]),
isfloat(s[2]),
isfloat(s[3]),
isfloat(s[4]),
isfloat(s[8])
])
def __init__(self, options, tgt_opts, forcefield):
super(THCDF_Psi4, self).__init__(options, tgt_opts, forcefield)
# Parse the input.dat file to figure out the elements and molecules
MolSection = False
ElemList = []
self.Molecules = []
self.throw_outs = []
for line in open(os.path.join(self.root, self.tgtdir,
"input.dat")).readlines():
line = line.strip()
s = line.split()
if len(s) >= 3 and s[0].lower() == 'molecule' and s[2] == '{':
MolSection = True
self.Molecules.append(s[1])
elif len(s) >= 1 and s[0] == '}':
MolSection = False
elif MolSection and len(s) >= 4 and match(
"^[A-Za-z]+$", s[0]) and isfloat(s[1]) and isfloat(
s[2]) and isfloat(s[3]):
ElemList.append(s[0].capitalize())
self.Elements = set(ElemList)
xgrad = []
for p in self.pgrad:
Pelem = []
for pid in self.FF.plist[p].split():
# Extract the chemical element.
Pelem.append(pid.split(':')[1].split(',')[0].split('=')[1])
Pelem = set(Pelem)
if len(self.Elements.intersection(Pelem)) == 0:
xgrad.append(p)
for p in xgrad:
self.pgrad.remove(p)
## Psi4 basis set file
gbslist = [i for i in self.FF.fnms if os.path.splitext(i)[1] == '.gbs']
if len(gbslist) != 1:
warn_press_key(
"In %s, you should only have exactly one .gbs file in the list of force field files!"
% __file__)
self.GBSfnm = gbslist[0]
## Psi4 input file for calculation of linear dependencies
## This is actually a file in 'forcefield' until we can figure out a better system
if CheckBasis():
datlist = [
i for i in self.FF.fnms if os.path.splitext(i)[1] == '.dat'
]
if len(datlist) != 1:
warn_press_key(
"In %s, you should only have exactly one .dat file in the list of force field files!"
% __file__)
self.DATfnm = datlist[0]
## Prepare the temporary directory
self.prepare_temp_directory(options, tgt_opts)
def __init__(self, options, tgt_opts, forcefield):
super(RDVR3_Psi4, self).__init__(options, tgt_opts, forcefield)
#======================================#
# Variables which are set here #
#======================================#
## Which parameters are differentiated?
self.objfiles = OrderedDict()
self.objvals = OrderedDict()
self.elements = OrderedDict()
self.molecules = OrderedDict()
self.callderivs = OrderedDict()
self.factor = 1e6
self.bidirect = False
for d in sorted(os.listdir(self.tgtdir)):
if os.path.isdir(os.path.join(self.tgtdir, d)) and os.path.exists(
os.path.join(self.tgtdir, d, 'objective.dat')):
self.callderivs[d] = [True for i in range(forcefield.np)]
self.objfiles[d] = open(
os.path.join(self.tgtdir, d, 'objective.dat')).readlines()
ElemList = []
Molecules = []
for line in self.objfiles[d]:
line = line.strip()
s = line.split()
if len(s) >= 3 and s[0].lower(
) == 'molecule' and s[2] == '{':
MolSection = True
Molecules.append(s[1])
elif len(s) >= 1 and s[0] == '}':
MolSection = False
elif MolSection and len(s) >= 4 and match(
"^[A-Za-z]+$", s[0]) and isfloat(s[1]) and isfloat(
s[2]) and isfloat(s[3]):
ElemList.append(s[0].capitalize())
self.elements[d] = set(ElemList)
self.molecules[d] = Molecules
for p in range(self.FF.np):
Pelem = []
for pid in self.FF.plist[p].split():
# Extract the chemical element.
Pelem.append(
pid.split(':')[1].split(',')[0].split('=')[1])
Pelem = set(Pelem)
if len(self.elements[d].intersection(Pelem)) == 0:
self.callderivs[d][p] = False
def normal_modes(self, shot=0, optimize=True):
logger.error('Normal modes are not yet implemented in AMBER interface')
raise NotImplementedError
# Copied from tinkerio.py
if optimize:
self.optimize(shot, crit=1e-6)
o = self.calltinker("vibrate %s.xyz_2 a" % (self.name))
else:
warn_once("Asking for normal modes without geometry optimization?")
self.mol[shot].write('%s.xyz' % self.name, ftype="tinker")
o = self.calltinker("vibrate %s.xyz a" % (self.name))
# Read the TINKER output. The vibrational frequencies are ordered.
# The six modes with frequencies closest to zero are ignored
readev = False
calc_eigvals = []
calc_eigvecs = []
for line in o:
s = line.split()
if "Vibrational Normal Mode" in line:
freq = float(s[-2])
readev = False
calc_eigvals.append(freq)
calc_eigvecs.append([])
elif "Atom" in line and "Delta X" in line:
readev = True
elif readev and len(s) == 4 and all(
[isint(s[0]),
isfloat(s[1]),
isfloat(s[2]),
isfloat(s[3])]):
calc_eigvecs[-1].append([float(i) for i in s[1:]])
calc_eigvals = np.array(calc_eigvals)
calc_eigvecs = np.array(calc_eigvecs)
# Sort by frequency absolute value and discard the six that are closest to zero
calc_eigvecs = calc_eigvecs[np.argsort(np.abs(calc_eigvals))][6:]
calc_eigvals = calc_eigvals[np.argsort(np.abs(calc_eigvals))][6:]
# Sort again by frequency
calc_eigvecs = calc_eigvecs[np.argsort(calc_eigvals)]
calc_eigvals = calc_eigvals[np.argsort(calc_eigvals)]
os.system("rm -rf *.xyz_* *.[0-9][0-9][0-9]")
return calc_eigvals, calc_eigvecs
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 feed(self, line, linindep=False):
""" Feed in a line.
@param[in] line The line of data
"""
if linindep:
if match('^ *!', line):
self.destroy = True
else:
self.destroy = False
line = sub('^ *!', '', line)
line = line.split('!')[0].strip()
s = line.split()
self.ln += 1
# No sense in doing anything for an empty line or a comment line.
if len(s) == 0 or match('^ *!', line): return None, None
# Now go through all the cases.
if match('^[A-Za-z][A-Za-z]? +[0-9]$', line):
# This is supposed to match the element line. For example 'Li 0'
self.element = s[0].capitalize()
self.isdata = False
self.destroy = False
elif len(s) == 3 and match('[SPDFGH]+', s[0]) and isint(
s[1]) and isfloat(s[2]):
self.amom = s[0]
if self.amom == self.last_amom:
self.basis_number[self.element] += 1
else:
self.basis_number[self.element] = 0
self.last_amom = self.amom
self.contraction_number = -1
self.isdata = True
# This is supposed to match a line like 'P 1 1.00'
elif len(s) == 2 and isfloat(s[0]) and isfloat(s[1]):
self.contraction_number += 1
self.isdata = True
else:
self.isdata = False
self.destroy = False
def feed(self, line, linindep=False):
""" Feed in a line.
@param[in] line The line of data
"""
if linindep:
if match('^ *!',line):
self.destroy = True
else:
self.destroy = False
line = sub('^ *!','',line)
line = line.split('!')[0].strip()
s = line.split()
self.ln += 1
# No sense in doing anything for an empty line or a comment line.
if len(s) == 0 or match('^ *!',line): return None, None
# Now go through all the cases.
if match('^[A-Za-z][A-Za-z]? +[0-9]$',line):
# This is supposed to match the element line. For example 'Li 0'
self.element = capitalize(s[0])
self.isdata = False
self.destroy = False
elif len(s) == 3 and match('[SPDFGH]+',s[0]) and isint(s[1]) and isfloat(s[2]):
self.amom = s[0]
if self.amom == self.last_amom:
self.basis_number[self.element] += 1
else:
self.basis_number[self.element] = 0
self.last_amom = self.amom
self.contraction_number = -1
self.isdata = True
# This is supposed to match a line like 'P 1 1.00'
elif len(s) == 2 and isfloat(s[0]) and isfloat(s[1]):
self.contraction_number += 1
self.isdata = True
else:
self.isdata = False
self.destroy = False
def normal_modes(self, shot=0, optimize=True):
logger.error('Normal modes are not yet implemented in AMBER interface')
raise NotImplementedError
# Copied from tinkerio.py
if optimize:
self.optimize(shot, crit=1e-6)
o = self.calltinker("vibrate %s.xyz_2 a" % (self.name))
else:
warn_once("Asking for normal modes without geometry optimization?")
self.mol[shot].write('%s.xyz' % self.name, ftype="tinker")
o = self.calltinker("vibrate %s.xyz a" % (self.name))
# Read the TINKER output. The vibrational frequencies are ordered.
# The six modes with frequencies closest to zero are ignored
readev = False
calc_eigvals = []
calc_eigvecs = []
for line in o:
s = line.split()
if "Vibrational Normal Mode" in line:
freq = float(s[-2])
readev = False
calc_eigvals.append(freq)
calc_eigvecs.append([])
elif "Atom" in line and "Delta X" in line:
readev = True
elif readev and len(s) == 4 and all([isint(s[0]), isfloat(s[1]), isfloat(s[2]), isfloat(s[3])]):
calc_eigvecs[-1].append([float(i) for i in s[1:]])
calc_eigvals = np.array(calc_eigvals)
calc_eigvecs = np.array(calc_eigvecs)
# Sort by frequency absolute value and discard the six that are closest to zero
calc_eigvecs = calc_eigvecs[np.argsort(np.abs(calc_eigvals))][6:]
calc_eigvals = calc_eigvals[np.argsort(np.abs(calc_eigvals))][6:]
# Sort again by frequency
calc_eigvecs = calc_eigvecs[np.argsort(calc_eigvals)]
calc_eigvals = calc_eigvals[np.argsort(calc_eigvals)]
os.system("rm -rf *.xyz_* *.[0-9][0-9][0-9]")
return calc_eigvals, calc_eigvecs
def energy_force_driver_all_external_(self):
## Create the run input files (inpcrd, prmtop) from the force field file.
## Note that the frcmod and mol2 files are required.
## This is like 'grompp' in GROMACS.
_exec("tleap -f stage.leap", print_to_screen=False, print_command=False)
## This line actually runs AMBER.
_exec("sander -i force.mdin -o force.mdout -p prmtop -c inpcrd -y all.mdcrd -O", print_to_screen=False, print_command=False)
## Simple parser for
ParseMode = 0
Energies = []
Forces = []
Force = []
for line in open('forcedump.dat'):
line = line.strip()
sline = line.split()
if ParseMode == 1:
if len(sline) == 1 and isfloat(sline[0]):
Energies.append(float(sline[0]) * 4.184)
ParseMode = 0
if ParseMode == 2:
if len(sline) == 3 and all(isfloat(sline[i]) for i in range(3)):
Force += [float(sline[i]) * 4.184 * 10 for i in range(3)]
if len(Force) == 3*self.qmatoms:
Forces.append(np.array(Force))
Force = []
ParseMode = 0
if line == '0 START of Energies':
ParseMode = 1
elif line == '1 Total Force':
ParseMode = 2
Energies = np.array(Energies[1:])
Forces = np.array(Forces[1:])
M = np.hstack((Energies.reshape(-1,1), Forces))
return M
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 __init__(self,options,tgt_opts,forcefield):
super(THCDF_Psi4,self).__init__(options,tgt_opts,forcefield)
# Parse the input.dat file to figure out the elements and molecules
MolSection = False
ElemList = []
self.Molecules = []
self.throw_outs = []
for line in open(os.path.join(self.root,self.tgtdir,"input.dat")).readlines():
line = line.strip()
s = line.split()
if len(s) >= 3 and s[0].lower() == 'molecule' and s[2] == '{':
MolSection = True
self.Molecules.append(s[1])
elif len(s) >= 1 and s[0] == '}':
MolSection = False
elif MolSection and len(s) >= 4 and match("^[A-Za-z]+$",s[0]) and isfloat(s[1]) and isfloat(s[2]) and isfloat(s[3]):
ElemList.append(capitalize(s[0]))
self.Elements = set(ElemList)
xgrad = []
for p in self.pgrad:
Pelem = []
for pid in self.FF.plist[p].split():
# Extract the chemical element.
Pelem.append(pid.split(':')[1].split(',')[0].split('=')[1])
Pelem = set(Pelem)
if len(self.Elements.intersection(Pelem)) == 0:
xgrad.append(p)
for p in xgrad:
self.pgrad.remove(p)
## Psi4 basis set file
gbslist = [i for i in self.FF.fnms if os.path.splitext(i)[1] == '.gbs']
if len(gbslist) != 1:
warn_press_key("In %s, you should only have exactly one .gbs file in the list of force field files!" % __file__)
self.GBSfnm = gbslist[0]
## Psi4 input file for calculation of linear dependencies
## This is actually a file in 'forcefield' until we can figure out a better system
if CheckBasis():
datlist = [i for i in self.FF.fnms if os.path.splitext(i)[1] == '.dat']
if len(datlist) != 1:
warn_press_key("In %s, you should only have exactly one .dat file in the list of force field files!" % __file__)
self.DATfnm = datlist[0]
## Prepare the temporary directory
self.prepare_temp_directory(options,tgt_opts)
def feed(self, line, linindep=False):
""" Feed in a line.
@param[in] line The line of data
"""
line = line.split('!')[0].strip()
s = line.split()
self.ln += 1
# No sense in doing anything for an empty line or a comment line.
if len(s) == 0 or match('^ *!',line): return None, None
# Now go through all the cases.
if match('^[A-Za-z][A-Za-z]? +[0-9]$',line):
# This is supposed to match the element line. For example 'Li 0'
self.element = capitalize(s[0])
self.radii[self.element] = float(s[1])
self.isdata = False
self.point = 0
elif len(s) >= 2 and isint(s[0]) and isfloat(s[1]):
self.point += 1
self.isdata = True
else:
self.isdata = False
def feed(self, line, linindep=False):
""" Feed in a line.
@param[in] line The line of data
"""
line = line.split('!')[0].strip()
s = line.split()
self.ln += 1
# No sense in doing anything for an empty line or a comment line.
if len(s) == 0 or match('^ *!', line): return None, None
# Now go through all the cases.
if match('^[A-Za-z][A-Za-z]? +[0-9]$', line):
# This is supposed to match the element line. For example 'Li 0'
self.element = s[0].capitalize()
self.radii[self.element] = float(s[1])
self.isdata = False
self.point = 0
elif len(s) >= 2 and isint(s[0]) and isfloat(s[1]):
self.point += 1
self.isdata = True
else:
self.isdata = False
def read_psi_xyzesp(psiout):
# Read Psi4 ESP output file for geometries, ESP values and grid points.
XMode = 0
EMode = 0
ESPMode = 0
xyzs = []
xyz = []
elem = []
espxyz = []
espval = []
for line in open(psiout):
s = line.split()
if XMode == 1:
if len(s) == 4 and isfloat(s[1]) and isfloat(s[2]) and isfloat(
s[3]):
e = s[0]
xyz.append([float(i) for i in s[1:4]])
if EMode == 1:
elem.append(e)
elif len(xyz) > 0:
xyzs.append(np.array(xyz))
xyz = []
XMode = 0
if ESPMode == 1:
if len(s) == 4 and isfloat(s[0]) and isfloat(s[1]) and isfloat(
s[2]) and isfloat(s[3]):
espxyz.append([float(i) for i in s[:3]])
espval.append(float(s[3]))
elif len(espxyz) > 0:
# After reading in a block of ESPs, don't read any more.
ESPMode = -1
if line.strip().startswith("Geometry (in Angstrom)"):
XMode = 1
EMode = len(elem) == 0
if 'Electrostatic Potential' in line.strip() and ESPMode == 0:
ESPMode = 1
if len(xyzs) == 0:
raise Exception('%s has length zero' % psiout)
return xyzs, elem, espxyz, espval
def read_psi_xyzesp(psiout):
# Read Psi4 ESP output file for geometries, ESP values and grid points.
XMode = 0
EMode = 0
ESPMode = 0
xyzs = []
xyz = []
elem = []
espxyz = []
espval = []
for line in open(psiout):
s = line.split()
if XMode == 1:
if len(s) == 4 and isfloat(s[1]) and isfloat(s[2]) and isfloat(s[3]):
e = s[0]
xyz.append([float(i) for i in s[1:4]])
if EMode == 1:
elem.append(e)
elif len(xyz) > 0:
xyzs.append(np.array(xyz))
xyz = []
XMode = 0
if ESPMode == 1:
if len(s) == 4 and isfloat(s[0]) and isfloat(s[1]) and isfloat(s[2]) and isfloat(s[3]):
espxyz.append([float(i) for i in s[:3]])
espval.append(float(s[3]))
elif len(espxyz) > 0:
# After reading in a block of ESPs, don't read any more.
ESPMode = -1
if line.strip().startswith("Geometry (in Angstrom)"):
XMode = 1
EMode = len(elem) == 0
if 'Electrostatic Potential' in line.strip() and ESPMode == 0:
ESPMode = 1
if len(xyzs) == 0:
raise Exception('%s has length zero' % psiout)
return xyzs, elem, espxyz, espval
def get_monomer_properties(print_stuff=0):
# Multiply a quantity in nm to convert to a0
nm_to_a0 = 1./0.05291772108
# Multiply a quantity in e*a0 to convert to Debye
ea0_to_debye = 0.393430307
os.system("rm -rf *.log \#*")
_exec(["./grompp"], print_command=False)
_exec(["./mdrun"], outfnm="mdrun.txt", print_command=False)
_exec("./trjconv -f traj.trr -o confout.gro -ndec 6".split(), stdin="0\n", print_command=False)
x = []
q = []
for line in open("confout.gro").readlines():
sline = line.split()
if len(sline) >= 6 and isfloat(sline[3]) and isfloat(sline[4]) and isfloat(sline[5]):
x.append([float(i) for i in sline[3:6]])
for line in open("charges.log").readlines():
sline = line.split()
if 'AtomNr' in line:
q.append(float(sline[5]))
mode = 0
a = []
for line in open("mdrun.txt").readlines():
if mode == 1:
sline = line.split()
if len(sline) == 3:
if isfloat(sline[0]) and isfloat(sline[1]) and isfloat(sline[2]):
a.append([float(i) for i in sline])
elif any(["nan" in s for s in sline[:3]]):
a.append([1e10,1e10,1e10])
if "Computing the polarizability tensor" in line:
mode = 1
x = Np.array(x)
q = Np.array(q)
a = Np.array(a)
Dip = Np.zeros(3,dtype=float)
QuadXX = 0.0
QuadYY = 0.0
QuadZZ = 0.0
OctXXZ = 0.0
OctYYZ = 0.0
OctZZZ = 0.0
for i in range(q.shape[0]):
Dip += x[i]*q[i]*nm_to_a0/ea0_to_debye
xx = x[i,0]*x[i,0]
yy = x[i,1]*x[i,1]
zz = x[i,2]*x[i,2]
z = x[i,2]
r2 = Np.dot(x[i,:],x[i,:])
QuadXX += 0.5*q[i]*(2*xx - yy - zz) * 10 * nm_to_a0 / ea0_to_debye
QuadYY += 0.5*q[i]*(2*yy - xx - zz) * 10 * nm_to_a0 / ea0_to_debye
QuadZZ += 0.5*q[i]*(2*zz - xx - yy) * 10 * nm_to_a0 / ea0_to_debye
OctXXZ += 0.5*q[i]*z*(5*xx-r2) * 100 * nm_to_a0 / ea0_to_debye
OctYYZ += 0.5*q[i]*z*(5*yy-r2) * 100 * nm_to_a0 / ea0_to_debye
OctZZZ += 0.5*q[i]*z*(5*zz-3*r2) * 100 * nm_to_a0 / ea0_to_debye
DipZ = Dip[2]
AlphaXX = a[0,0]
AlphaYY = a[1,1]
AlphaZZ = a[2,2]
# Quantities taken from Niu (2001) and Berne (1994)
DipZ0 = 1.855
QuadXX0 = 2.51
QuadYY0 = -2.63
QuadZZ0 = 0.11
Quad0 = Np.sqrt((QuadXX0**2 + QuadYY0**2 + QuadZZ0**2)/3)
OctXXZ0 = 2.58
OctYYZ0 = -1.24
OctZZZ0 = -1.35
Oct0 = Np.sqrt((OctXXZ0**2 + OctYYZ0**2 + OctZZZ0**2)/3)
AlphaXX0 = 10.32
AlphaYY0 = 9.56
AlphaZZ0 = 9.91
Alpha0 = Np.sqrt((AlphaXX0**2 + AlphaYY0**2 + AlphaZZ0**2)/3)
Err_DipZ = ((DipZ-DipZ0)/DipZ0)**2
Err_QuadXX = ((QuadXX-QuadXX0)/Quad0)**2
Err_QuadYY = ((QuadYY-QuadYY0)/Quad0)**2
Err_QuadZZ = ((QuadZZ-QuadZZ0)/Quad0)**2
Err_OctXXZ = ((OctXXZ-OctXXZ0)/Oct0)**2
Err_OctYYZ = ((OctYYZ-OctYYZ0)/Oct0)**2
Err_OctZZZ = ((OctZZZ-OctZZZ0)/Oct0)**2
Err_AlphaXX = ((AlphaXX-AlphaXX0)/Alpha0)**2
Err_AlphaYY = ((AlphaYY-AlphaYY0)/Alpha0)**2
Err_AlphaZZ = ((AlphaZZ-AlphaZZ0)/Alpha0)**2
Objective = Err_DipZ + (Err_QuadXX + Err_QuadYY + Err_QuadZZ)/3 + (Err_AlphaXX + Err_AlphaYY + Err_AlphaZZ)/3
if print_stuff:
#print "\rvalues (errors): mu_z = % .3f (%.3f) q_xx = % .3f (%.3f) q_yy = % .3f (%.3f) q_zz = % .3f (%.3f) o_xxz = % .3f (%.3f) o_yyz = % .3f (%.3f) o_zzz = % .3f (%.3f) a_xx = % .3f (%.3f) a_yy = % .3f (%.3f) a_zz = % .3f (%.3f)" % (DipZ,Err_DipZ,QuadXX,Err_QuadXX,QuadYY,Err_QuadYY,QuadZZ,Err_QuadZZ,OctXXZ,Err_OctXXZ,OctYYZ,Err_OctYYZ,OctZZZ,Err_OctZZZ,AlphaXX,Err_AlphaXX,AlphaYY,Err_AlphaYY,AlphaZZ,Err_AlphaZZ)
logger.info("\rvalues (errors): mu_z = % .3f (%.3f) q = % .3f % .3f % .3f (% .3f % .3f % .3f) o = % .3f % .3f % .3f (% .3f % .3f % .3f) a = %.3f %.3f %.3f (%.3f %.3f %.3f) x2 = % .4f\n" % (DipZ,Err_DipZ,QuadXX,QuadYY,QuadZZ,Err_QuadXX,Err_QuadYY,Err_QuadZZ,OctXXZ,OctYYZ,OctZZZ,Err_OctXXZ,Err_OctYYZ,Err_OctZZZ,AlphaXX,AlphaYY,AlphaZZ,Err_AlphaXX,Err_AlphaYY,Err_AlphaZZ,Objective))
#Objective = Err_DipZ + (Err_QuadXX + Err_QuadYY + Err_QuadZZ)/3 + (Err_OctXXZ + Err_OctYYZ + Err_OctZZZ)/3 + (Err_AlphaXX + Err_AlphaYY + Err_AlphaZZ)/3
Properties = OrderedDict()
Properties['DipZ'] = DipZ
Properties['QuadXX'] = QuadXX
Properties['QuadYY'] = QuadYY
Properties['QuadZZ'] = QuadZZ
Properties['OctXXZ'] = OctXXZ
Properties['OctYYZ'] = OctYYZ
Properties['OctZZZ'] = OctZZZ
Properties['AlphaXX'] = AlphaXX
Properties['AlphaYY'] = AlphaYY
Properties['AlphaZZ'] = AlphaZZ
return Properties
def molecular_dynamics(self,
nsteps,
timestep,
temperature=None,
pressure=None,
nequil=0,
nsave=1000,
minimize=True,
anisotropic=False,
threads=1,
verbose=False,
**kwargs):
"""
Method for running a molecular dynamics simulation.
Required arguments:
nsteps = (int) Number of total time steps
timestep = (float) Time step in FEMTOSECONDS
temperature = (float) Temperature control (Kelvin)
pressure = (float) Pressure control (atmospheres)
nequil = (int) Number of additional time steps at the beginning for equilibration
nsave = (int) Step interval for saving and printing data
minimize = (bool) Perform an energy minimization prior to dynamics
threads = (int) Specify how many OpenMP threads to use
Returns simulation data:
Rhos = (array) Density in kilogram m^-3
Potentials = (array) Potential energies
Kinetics = (array) Kinetic energies
Volumes = (array) Box volumes
Dips = (3xN array) Dipole moments
EComps = (dict) Energy components
"""
logger.error(
'Molecular dynamics not yet implemented in AMBER interface')
raise NotImplementedError
md_defs = OrderedDict()
md_opts = OrderedDict()
# Print out averages only at the end.
md_opts["printout"] = nsave
md_opts["openmp-threads"] = threads
# Langevin dynamics for temperature control.
if temperature != None:
md_defs["integrator"] = "stochastic"
else:
md_defs["integrator"] = "beeman"
md_opts["thermostat"] = None
# Periodic boundary conditions.
if self.pbc:
md_opts["vdw-correction"] = ''
if temperature != None and pressure != None:
md_defs["integrator"] = "beeman"
md_defs["thermostat"] = "bussi"
md_defs["barostat"] = "montecarlo"
if anisotropic:
md_opts["aniso-pressure"] = ''
elif pressure != None:
warn_once(
"Pressure is ignored because temperature is turned off.")
else:
if pressure != None:
warn_once("Pressure is ignored because pbc is set to False.")
# Use stochastic dynamics for the gas phase molecule.
# If we use the regular integrators it may miss
# six degrees of freedom in calculating the kinetic energy.
md_opts["barostat"] = None
eq_opts = deepcopy(md_opts)
if self.pbc and temperature != None and pressure != None:
eq_opts["integrator"] = "beeman"
eq_opts["thermostat"] = "bussi"
eq_opts["barostat"] = "berendsen"
if minimize:
if verbose: logger.info("Minimizing the energy...")
self.optimize(method="bfgs", crit=1)
os.system("mv %s.xyz_2 %s.xyz" % (self.name, self.name))
if verbose: logger.info("Done\n")
# Run equilibration.
if nequil > 0:
write_key("%s-eq.key" % self.name, eq_opts, "%s.key" % self.name,
md_defs)
if verbose: printcool("Running equilibration dynamics", color=0)
if self.pbc and pressure != None:
self.calltinker(
"dynamic %s -k %s-eq %i %f %f 4 %f %f" %
(self.name, self.name, nequil, timestep,
float(nsave * timestep) / 1000, temperature, pressure),
print_to_screen=verbose)
else:
self.calltinker("dynamic %s -k %s-eq %i %f %f 2 %f" %
(self.name, self.name, nequil, timestep,
float(nsave * timestep) / 1000, temperature),
print_to_screen=verbose)
os.system("rm -f %s.arc" % (self.name))
# Run production.
if verbose: printcool("Running production dynamics", color=0)
write_key("%s-md.key" % self.name, md_opts, "%s.key" % self.name,
md_defs)
if self.pbc and pressure != None:
odyn = self.calltinker(
"dynamic %s -k %s-md %i %f %f 4 %f %f" %
(self.name, self.name, nsteps, timestep,
float(nsave * timestep / 1000), temperature, pressure),
print_to_screen=verbose)
else:
odyn = self.calltinker(
"dynamic %s -k %s-md %i %f %f 2 %f" %
(self.name, self.name, nsteps, timestep,
float(nsave * timestep / 1000), temperature),
print_to_screen=verbose)
# Gather information.
os.system("mv %s.arc %s-md.arc" % (self.name, self.name))
self.md_trajectory = "%s-md.arc" % self.name
edyn = []
kdyn = []
temps = []
for line in odyn:
s = line.split()
if 'Current Potential' in line:
edyn.append(float(s[2]))
if 'Current Kinetic' in line:
kdyn.append(float(s[2]))
if len(s) > 0 and s[0] == 'Temperature' and s[2] == 'Kelvin':
temps.append(float(s[1]))
# Potential and kinetic energies converted to kJ/mol.
edyn = np.array(edyn) * 4.184
kdyn = np.array(kdyn) * 4.184
temps = np.array(temps)
if verbose: logger.info("Post-processing to get the dipole moments\n")
oanl = self.calltinker("analyze %s-md.arc" % self.name,
stdin="G,E,M",
print_to_screen=False)
# Read potential energy and dipole from file.
eanl = []
dip = []
mass = 0.0
ecomp = OrderedDict()
havekeys = set()
first_shot = True
for ln, line in enumerate(oanl):
strip = line.strip()
s = line.split()
if 'Total System Mass' in line:
mass = float(s[-1])
if 'Total Potential Energy : ' in line:
eanl.append(float(s[4]))
if 'Dipole X,Y,Z-Components :' in line:
dip.append([float(s[i]) for i in range(-3, 0)])
if first_shot:
for key in eckeys:
if strip.startswith(key):
if key in ecomp:
ecomp[key].append(float(s[-2]) * 4.184)
else:
ecomp[key] = [float(s[-2]) * 4.184]
if key in havekeys:
first_shot = False
havekeys.add(key)
else:
for key in havekeys:
if strip.startswith(key):
if key in ecomp:
ecomp[key].append(float(s[-2]) * 4.184)
else:
ecomp[key] = [float(s[-2]) * 4.184]
for key in ecomp:
ecomp[key] = np.array(ecomp[key])
ecomp["Potential Energy"] = edyn
ecomp["Kinetic Energy"] = kdyn
ecomp["Temperature"] = temps
ecomp["Total Energy"] = edyn + kdyn
# Energies in kilojoules per mole
eanl = np.array(eanl) * 4.184
# Dipole moments in debye
dip = np.array(dip)
# Volume of simulation boxes in cubic nanometers
# Conversion factor derived from the following:
# In [22]: 1.0 * gram / mole / (1.0 * nanometer)**3 / AVOGADRO_CONSTANT_NA / (kilogram/meter**3)
# Out[22]: 1.6605387831627252
conv = 1.6605387831627252
if self.pbc:
vol = np.array([BuildLatticeFromLengthsAngles(*[float(j) for j in line.split()]).V \
for line in open("%s-md.arc" % self.name).readlines() \
if (len(line.split()) == 6 and isfloat(line.split()[1]) \
and all([isfloat(i) for i in line.split()[:6]]))]) / 1000
rho = conv * mass / vol
else:
vol = None
rho = None
prop_return = OrderedDict()
prop_return.update({
'Rhos': rho,
'Potentials': edyn,
'Kinetics': kdyn,
'Volumes': vol,
'Dips': dip,
'Ecomps': ecomp
})
return prop_return
def __init__(self,options,tgt_opts,forcefield):
super(RDVR3_Psi4,self).__init__(options,tgt_opts,forcefield)
#======================================#
# Variables which are set here #
#======================================#
## Which parameters are differentiated?
self.objfiles = OrderedDict()
self.objvals = OrderedDict()
self.elements = OrderedDict()
self.molecules = OrderedDict()
self.callderivs = OrderedDict()
self.factor = 1e6
self.bidirect = False
for d in sorted(os.listdir(self.tgtdir)):
if os.path.isdir(os.path.join(self.tgtdir,d)) and os.path.exists(os.path.join(self.tgtdir,d,'objective.dat')):
self.callderivs[d] = [True for i in range(forcefield.np)]
self.objfiles[d] = open(os.path.join(self.tgtdir,d,'objective.dat')).readlines()
ElemList = []
Molecules = []
for line in self.objfiles[d]:
line = line.strip()
s = line.split()
if len(s) >= 3 and s[0].lower() == 'molecule' and s[2] == '{':
MolSection = True
Molecules.append(s[1])
elif len(s) >= 1 and s[0] == '}':
MolSection = False
elif MolSection and len(s) >= 4 and match("^[A-Za-z]+$",s[0]) and isfloat(s[1]) and isfloat(s[2]) and isfloat(s[3]):
ElemList.append(capitalize(s[0]))
self.elements[d] = set(ElemList)
self.molecules[d] = Molecules
for p in range(self.FF.np):
Pelem = []
for pid in self.FF.plist[p].split():
# Extract the chemical element.
Pelem.append(pid.split(':')[1].split(',')[0].split('=')[1])
Pelem = set(Pelem)
if len(self.elements[d].intersection(Pelem)) == 0:
self.callderivs[d][p] = False
def molecular_dynamics(self, nsteps, timestep, temperature=None, pressure=None, nequil=0, nsave=1000, minimize=True, anisotropic=False, threads=1, verbose=False, **kwargs):
"""
Method for running a molecular dynamics simulation.
Required arguments:
nsteps = (int) Number of total time steps
timestep = (float) Time step in FEMTOSECONDS
temperature = (float) Temperature control (Kelvin)
pressure = (float) Pressure control (atmospheres)
nequil = (int) Number of additional time steps at the beginning for equilibration
nsave = (int) Step interval for saving and printing data
minimize = (bool) Perform an energy minimization prior to dynamics
threads = (int) Specify how many OpenMP threads to use
Returns simulation data:
Rhos = (array) Density in kilogram m^-3
Potentials = (array) Potential energies
Kinetics = (array) Kinetic energies
Volumes = (array) Box volumes
Dips = (3xN array) Dipole moments
EComps = (dict) Energy components
"""
logger.error('Molecular dynamics not yet implemented in AMBER interface')
raise NotImplementedError
md_defs = OrderedDict()
md_opts = OrderedDict()
# Print out averages only at the end.
md_opts["printout"] = nsave
md_opts["openmp-threads"] = threads
# Langevin dynamics for temperature control.
if temperature != None:
md_defs["integrator"] = "stochastic"
else:
md_defs["integrator"] = "beeman"
md_opts["thermostat"] = None
# Periodic boundary conditions.
if self.pbc:
md_opts["vdw-correction"] = ''
if temperature != None and pressure != None:
md_defs["integrator"] = "beeman"
md_defs["thermostat"] = "bussi"
md_defs["barostat"] = "montecarlo"
if anisotropic:
md_opts["aniso-pressure"] = ''
elif pressure != None:
warn_once("Pressure is ignored because temperature is turned off.")
else:
if pressure != None:
warn_once("Pressure is ignored because pbc is set to False.")
# Use stochastic dynamics for the gas phase molecule.
# If we use the regular integrators it may miss
# six degrees of freedom in calculating the kinetic energy.
md_opts["barostat"] = None
eq_opts = deepcopy(md_opts)
if self.pbc and temperature != None and pressure != None:
eq_opts["integrator"] = "beeman"
eq_opts["thermostat"] = "bussi"
eq_opts["barostat"] = "berendsen"
if minimize:
if verbose: logger.info("Minimizing the energy...")
self.optimize(method="bfgs", crit=1)
os.system("mv %s.xyz_2 %s.xyz" % (self.name, self.name))
if verbose: logger.info("Done\n")
# Run equilibration.
if nequil > 0:
write_key("%s-eq.key" % self.name, eq_opts, "%s.key" % self.name, md_defs)
if verbose: printcool("Running equilibration dynamics", color=0)
if self.pbc and pressure != None:
self.calltinker("dynamic %s -k %s-eq %i %f %f 4 %f %f" % (self.name, self.name, nequil, timestep, float(nsave*timestep)/1000,
temperature, pressure), print_to_screen=verbose)
else:
self.calltinker("dynamic %s -k %s-eq %i %f %f 2 %f" % (self.name, self.name, nequil, timestep, float(nsave*timestep)/1000,
temperature), print_to_screen=verbose)
os.system("rm -f %s.arc" % (self.name))
# Run production.
if verbose: printcool("Running production dynamics", color=0)
write_key("%s-md.key" % self.name, md_opts, "%s.key" % self.name, md_defs)
if self.pbc and pressure != None:
odyn = self.calltinker("dynamic %s -k %s-md %i %f %f 4 %f %f" % (self.name, self.name, nsteps, timestep, float(nsave*timestep/1000),
temperature, pressure), print_to_screen=verbose)
else:
odyn = self.calltinker("dynamic %s -k %s-md %i %f %f 2 %f" % (self.name, self.name, nsteps, timestep, float(nsave*timestep/1000),
temperature), print_to_screen=verbose)
# Gather information.
os.system("mv %s.arc %s-md.arc" % (self.name, self.name))
self.md_trajectory = "%s-md.arc" % self.name
edyn = []
kdyn = []
temps = []
for line in odyn:
s = line.split()
if 'Current Potential' in line:
edyn.append(float(s[2]))
if 'Current Kinetic' in line:
kdyn.append(float(s[2]))
if len(s) > 0 and s[0] == 'Temperature' and s[2] == 'Kelvin':
temps.append(float(s[1]))
# Potential and kinetic energies converted to kJ/mol.
edyn = np.array(edyn) * 4.184
kdyn = np.array(kdyn) * 4.184
temps = np.array(temps)
if verbose: logger.info("Post-processing to get the dipole moments\n")
oanl = self.calltinker("analyze %s-md.arc" % self.name, stdin="G,E,M", print_to_screen=False)
# Read potential energy and dipole from file.
eanl = []
dip = []
mass = 0.0
ecomp = OrderedDict()
havekeys = set()
first_shot = True
for ln, line in enumerate(oanl):
strip = line.strip()
s = line.split()
if 'Total System Mass' in line:
mass = float(s[-1])
if 'Total Potential Energy : ' in line:
eanl.append(float(s[4]))
if 'Dipole X,Y,Z-Components :' in line:
dip.append([float(s[i]) for i in range(-3,0)])
if first_shot:
for key in eckeys:
if strip.startswith(key):
if key in ecomp:
ecomp[key].append(float(s[-2])*4.184)
else:
ecomp[key] = [float(s[-2])*4.184]
if key in havekeys:
first_shot = False
havekeys.add(key)
else:
for key in havekeys:
if strip.startswith(key):
if key in ecomp:
ecomp[key].append(float(s[-2])*4.184)
else:
ecomp[key] = [float(s[-2])*4.184]
for key in ecomp:
ecomp[key] = np.array(ecomp[key])
ecomp["Potential Energy"] = edyn
ecomp["Kinetic Energy"] = kdyn
ecomp["Temperature"] = temps
ecomp["Total Energy"] = edyn+kdyn
# Energies in kilojoules per mole
eanl = np.array(eanl) * 4.184
# Dipole moments in debye
dip = np.array(dip)
# Volume of simulation boxes in cubic nanometers
# Conversion factor derived from the following:
# In [22]: 1.0 * gram / mole / (1.0 * nanometer)**3 / AVOGADRO_CONSTANT_NA / (kilogram/meter**3)
# Out[22]: 1.6605387831627252
conv = 1.6605387831627252
if self.pbc:
vol = np.array([BuildLatticeFromLengthsAngles(*[float(j) for j in line.split()]).V \
for line in open("%s-md.arc" % self.name).readlines() \
if (len(line.split()) == 6 and isfloat(line.split()[1]) \
and all([isfloat(i) for i in line.split()[:6]]))]) / 1000
rho = conv * mass / vol
else:
vol = None
rho = None
prop_return = OrderedDict()
prop_return.update({'Rhos': rho, 'Potentials': edyn, 'Kinetics': kdyn, 'Volumes': vol, 'Dips': dip, 'Ecomps': ecomp})
return prop_return
def is_mol2_atom(line):
s = line.split()
if len(s) < 9:
return False
return all([isint(s[0]), isfloat(s[2]), isfloat(s[3]), isfloat(s[4]), isfloat(s[8])])
