def generate(self):
"""
Creates the input for each reaction, runs them, and tests for success.
If successful, it creates the barrier and product objects.
It also then does the conformational search, and finally, the hindered rotor scans.
To make the code the most efficient, all of these happen in parallel, in a sense that
the jobs are not waiting for each other. E.g., one reaction can still be in the stage
of TS search, while the other can be already at the hindered rotor scan. This way,
all cores are occupied efficiently.
The switching between the various stages are done via the reac_ts_done variable.
0: initiate the TS search
1: check barrier height and errors in TS, and initiates normal mode displacement test, start the irc calculations
2: submit product optimization
3: submit the frequency calculation
4: do the optimization of the ts and the products
5: follow up on the optimizations
6: finalize calculations, check for wrong number of negative frequencies
If at any times the calculation fails, reac_ts_done is set to -999.
If all steps are successful, reac_ts_done is set to -1.
"""
deleted = []
if len(self.species.reac_inst) > 0:
alldone = 1
else:
alldone = 0
# status to see of kinbot needs to wait for the product optimizations
# from another kinbot run, to avoid duplication of calculations
products_waiting_status = [[] for i in self.species.reac_inst]
count = 0
for i in self.species.reac_inst:
count = count + 1
all_unique_prod = []
frag_unique = []
nameUnique = []
stpt_inchis = []
while alldone:
for index, instance in enumerate(self.species.reac_inst):
obj = self.species.reac_obj[index]
instance_name = obj.instance_name
# START REACTION SEARCH
if self.species.reac_ts_done[
index] == 0 and self.species.reac_step[index] == 0:
#verify after restart if search has failed in previous kinbot run
status = self.qc.check_qc(instance_name)
if status == 'error' or status == 'killed':
logging.info(
'\tRxn search failed (error or killed) for {}'.
format(instance_name))
self.species.reac_ts_done[index] = -999
if self.species.reac_ts_done[
index] == 0: # ts search is ongoing
if obj.scan == 0: #don't do a scan of a bond
if self.species.reac_step[index] == obj.max_step + 1:
status = self.qc.get_qc_freq(
instance_name, self.species.natom)[0]
if status == 0:
self.species.reac_ts_done[index] = 1
elif status == -1:
logging.info(
'\tRxn search failed for {}'.format(
instance_name))
self.species.reac_ts_done[index] = -999
else:
self.species.reac_step[
index] = reac_family.carry_out_reaction(
obj, self.species.reac_step[index],
self.par.par['qc_command'])
else: # do a bond scan
if self.species.reac_step[
index] == self.par.par['scan_step'] + 1:
status = self.qc.get_qc_freq(
instance_name, self.species.natom)[0]
if status == 0:
self.species.reac_ts_done[index] = 1
elif status == -1:
logging.info(
'\tRxn search failed for {}'.format(
instance_name))
self.species.reac_ts_done[index] = -999
else:
if self.species.reac_step[index] == 0:
self.species.reac_step[
index] = reac_family.carry_out_reaction(
obj, self.species.reac_step[index],
self.par.par['qc_command'])
elif self.species.reac_step[index] > 0:
status = self.qc.check_qc(instance_name)
if status == 'error' or status == 'killed':
logging.info(
'\tRxn search failed for {}'.format(
instance_name))
self.species.reac_ts_done[index] = -999
else:
err, energy = self.qc.get_qc_energy(
instance_name)
if err == 0:
self.species.reac_scan_energy[
index].append(energy)
if len(self.species.
reac_scan_energy[index]) > 1:
if self.species.reac_scan_energy[
index][
-1] < self.species.reac_scan_energy[
index][-2]:
self.species.reac_step[
index] = self.par.par[
'scan_step']
#ts search restarted w/ next line?
self.species.reac_step[
index] = reac_family.carry_out_reaction(
obj,
self.species.reac_step[index],
self.par.par['qc_command'])
elif self.species.reac_ts_done[index] == 1:
status = self.qc.check_qc(instance_name)
if status == 'running': continue
elif status == 'error':
logging.info(
'\tRxn search failed (gaussian error) for {}'.
format(instance_name))
self.species.reac_ts_done[index] = -999
else:
#check the barrier height:
if self.species.reac_type[
index] == 'R_Addition_MultipleBond':
sp_energy = self.qc.get_qc_energy(
str(self.species.chemid) + '_well_mp2')[1]
barrier = (self.qc.get_qc_energy(instance_name)[1]
- sp_energy) * constants.AUtoKCAL
else:
sp_energy = self.qc.get_qc_energy(
str(self.species.chemid) + '_well')[1]
barrier = (self.qc.get_qc_energy(instance_name)[1]
- sp_energy) * constants.AUtoKCAL
if barrier > self.par.par['barrier_threshold']:
logging.info(
'\tRxn barrier too high ({0:.2f} kcal/mol) for {1}'
.format(barrier, instance_name))
self.species.reac_ts_done[index] = -999
else:
obj.irc = IRC(
obj, self.par
) #TODO: this doesn't seem like a good design
irc_status = obj.irc.check_irc()
if 0 in irc_status:
# No IRC started yet, start the IRC now
logging.info(
'\tStarting IRC calculations for {}'.
format(instance_name))
obj.irc.do_irc_calculations()
elif irc_status[0] == 'running' or irc_status[
1] == 'running':
continue
else:
#IRC's have successfully finished, have an error or were killed, in any case
#read the geometries and try to make products out of them
#verify which of the ircs leads back to the reactant, if any
prod = obj.irc.irc2stationary_pt()
if prod == 0:
logging.info(
'\t\tNo product found for {}'.format(
instance_name))
self.species.reac_ts_done[index] = -999
else:
obj.products = prod
obj.product_bonds = prod.bond
self.species.reac_ts_done[index] = 2
elif self.species.reac_ts_done[index] == 2:
if len(products_waiting_status[index]) == 0:
#identify bimolecular products and wells
fragments, maps = obj.products.start_multi_molecular()
obj.products = []
a = []
for frag in fragments:
a.append(frag)
if len(frag_unique) == 0:
frag_unique.append(frag)
elif len(frag_unique) > 0:
new = 1
for fragb in frag_unique:
if frag.chemid == fragb.chemid:
e, geom2 = self.qc.get_qc_geom(
str(fragb.chemid) + '_well',
fragb.natom)
if e == 0:
a.pop()
frag = fragb
a.append(frag)
new = 0
break
if new:
frag_unique.append(frag)
obj.products_final = []
for frag in a:
self.qc.qc_opt(frag, frag.geom)
e, geom2 = self.qc.get_qc_geom(
str(frag.chemid) + '_well', frag.natom)
obj.products_final.append(frag)
#check products make sure they are the same
for i, st_pt_i in enumerate(obj.products_final):
for j, st_pt_j in enumerate(obj.products_final):
if st_pt_i.chemid == st_pt_j.chemid and i < j:
obj.products_final[j] = obj.products_final[
i]
#print products generated by IRC
products = []
for i, st_pt in enumerate(obj.products_final):
products.append(st_pt.chemid)
products.extend([' ', ' ', ' '])
barrier = (self.qc.get_qc_energy(instance_name)[1] -
sp_energy) * constants.AUtoKCAL
logging.info(
'\tReaction {0} has a barrier of {1:.2f} kcal/mol and leads to products {2} {3} {4}'
.format(instance_name, barrier, products[0],
products[1], products[2]))
for i, st_pt in enumerate(obj.products_final):
chemid = st_pt.chemid
e, st_pt.geom = self.qc.get_qc_geom(
str(st_pt.chemid) + '_well', st_pt.natom)
if e < 0:
logging.info(
'\tProduct optimization failed for {}, product {}'
.format(instance_name, st_pt.chemid))
self.species.reac_ts_done[index] = -999
err = -1
elif e != 0:
err = -1
else:
e2, st_pt.energy = self.qc.get_qc_energy(
str(st_pt.chemid) + '_well')
e2, st_pt.zpe = self.qc.get_qc_zpe(
str(st_pt.chemid) + '_well')
st_pt.characterize(
dimer=0
) # not allowed to use the dimer option here
if chemid != st_pt.chemid:
obj.products_final.pop(i)
newfrags, newmaps = st_pt.start_multi_molecular(
) # newfrags is list of stpt obj
products_waiting_status[index] = [
0 for frag in newfrags
]
fragChemid = []
for i, newfr in enumerate(newfrags):
for prod in frag_unique:
if newfr.chemid == prod.chemid:
newfrags.pop(i)
newfr = prod
j = i - 1
newfrags.insert(j, newfr)
#add new frag to frag_unique somehow?
j = i - 1
obj.products_final.insert(j, newfr)
self.qc.qc_opt(newfr, newfr.geom, 0)
fragChemid.append(newfr.chemid)
if len(fragChemid) == 1:
fragChemid.append(" ")
for i, frag in enumerate(newfrags):
products_waiting_status[index][i] = 1
logging.info(
'\ta) Product optimized to other structure for {}, product {} to {} {}'
.format(instance_name, chemid,
fragChemid[0], fragChemid[1]))
obj.products = []
for prod in obj.products_final:
obj.products.append(prod)
obj.products_final = []
if all([pi == 1 for pi in products_waiting_status[index]]):
self.species.reac_ts_done[index] = 3
elif self.species.reac_ts_done[index] == 3:
# wait for the optimization to finish
# if two st_pt are the same in the products, we make them exactly identical otherwise
# the different ordering of the atoms causes the chemid of the second to be seemingly wrong
for i, st_pt_i in enumerate(obj.products):
for j, st_pt_j in enumerate(obj.products):
if st_pt_i.chemid == st_pt_j.chemid and i < j:
obj.products[j] = obj.products[i]
'''
# generate and compare inchis
if len(stpt_inchis) == 0:
well0_inchi = cheminfo.create_inchi_from_geom(self.species.atom,self.species.geom)
well0_chemicalFormula = well0_inchi.split('S/')[1].split('/')[0]
well0_stereochem = ''
if "/t" in str(well0_inchi):
well0_stereochem = well0_inchi.split('/t')[1].split('/')[0]
well0_info = [self.species.chemid, well0_chemicalFormula, well0_inchi, well0_stereochem]
stpt_inchis.append(well0_info)
for st_pt in obj.products:
prod_chemid = st_pt.chemid
prod_inchi = cheminfo.create_inchi_from_geom(st_pt.atom,st_pt.geom)
prod_chemicalFormula = prod_inchi.split('S/')[1].split('/')[0]
prod_stereochem = ''
if "/t" in str(prod_inchi):
prod_stereochem = prod_inchi.split('/t')[1].split('/')[0]
prod_info = [prod_chemid, prod_chemicalFormula, prod_inchi, prod_stereochem]
stpt_inchis.append(prod_info)
inchiFile = open('inchis.log','w')
well0_chemid = stpt_inchis[0][0]
well0_chemicalFormula = stpt_inchis[0][1]
well0_stereochem = stpt_inchis[0][3]
for inchi in stpt_inchis:
inchiFile.write("{}\t|{}\t|{}\t|{}\n".format(inchi[0],inchi[1],inchi[2],inchi[3]))
prod_chemid = inchi[0]
prod_stereochem = inchi[3]
prod_chemicalFormula = inchi[1]
if well0_chemicalFormula == prod_chemicalFormula:
if str(well0_stereochem) != str(prod_stereochem):
logging.warning("\t\t!WARNING! Stereochemistry for product {} differs from the initial well ({}) for reaction {}".format(prod_chemid, well0_chemid, instance_name))
inchiFile.close()
'''
err = 0
for st_pt in obj.products:
chemid = st_pt.chemid
e, st_pt.geom = self.qc.get_qc_geom(
str(st_pt.chemid) + '_well', st_pt.natom)
if e < 0:
logging.info(
'\tProduct optimization failed for {}, product {}'
.format(instance_name, st_pt.chemid))
self.species.reac_ts_done[index] = -999
err = -1
elif e != 0:
err = -1
else:
e2, st_pt.energy = self.qc.get_qc_energy(
str(st_pt.chemid) + '_well')
e2, st_pt.zpe = self.qc.get_qc_zpe(
str(st_pt.chemid) + '_well')
st_pt.characterize(
dimer=0
) # not allowed to use the dimer option here
if chemid != st_pt.chemid:
# product was optimized to another structure, give warning but don't remove reaction
logging.info(
'\tb) Product optimized to other structure for {}, product {} to {}'
.format(instance_name, chemid,
st_pt.chemid))
e, st_pt.geom = self.qc.get_qc_geom(
str(st_pt.chemid) + '_well', st_pt.natom)
if e < 0:
err = -1
if err == 0:
self.species.reac_ts_done[index] = 4
elif self.species.reac_ts_done[index] == 4:
# Do the TS and product optimization
# make a stationary point object of the ts
bond_mx = np.zeros(
(self.species.natom, self.species.natom))
for i in range(self.species.natom):
for j in range(self.species.natom):
bond_mx[i][j] = max(self.species.bond[i][j],
obj.product_bonds[i][j])
err, geom = self.qc.get_qc_geom(instance_name,
self.species.natom)
ts = StationaryPoint(instance_name,
self.species.charge,
self.species.mult,
atom=self.species.atom,
geom=geom,
wellorts=1)
err, ts.energy = self.qc.get_qc_energy(instance_name)
err, ts.zpe = self.qc.get_qc_zpe(
instance_name) # NEW STOPS HERE
ts.bond = bond_mx
ts.find_cycle()
ts.find_conf_dihedral()
obj.ts = ts
#do the ts optimization
obj.ts_opt = Optimize(obj.ts, self.par, self.qc)
obj.ts_opt.do_optimization()
#do the products optimizations
for st_pt in obj.products:
#do the products optimizations
#check for products of other reactions that are the same as this product
#in the case such products are found, use the same Optimize object for both
for i, inst_i in enumerate(self.species.reac_inst):
new = 1
if not i == index:
obj_i = self.species.reac_obj[i]
if self.species.reac_ts_done[i] > 3:
for j, st_pt_i in enumerate(
obj_i.products):
if st_pt_i.chemid == st_pt.chemid:
if len(obj_i.prod_opt) > j:
prod_opt = obj_i.prod_opt[j]
new = 0
break
if new:
prod_opt = Optimize(st_pt, self.par, self.qc)
prod_opt.do_optimization()
obj.prod_opt.append(prod_opt)
for st_pt in obj.products:
#section where comparing products in same reaction occurs
if len(obj.prod_opt) > 0:
for j, st_pt_opt in enumerate(obj.prod_opt):
if st_pt.chemid == st_pt_opt.species.chemid:
if len(obj.prod_opt) > j:
prod_opt = obj.prod_opt[j]
break
elog = open("energy.log", 'a')
for prod_opt in obj.prod_opt:
elog.write("prod_opt: {} |\tenergy: {}\n".format(
prod_opt.species.chemid, prod_opt.species.energy))
elog.close()
self.species.reac_ts_done[index] = 5
elif self.species.reac_ts_done[index] == 5:
#check up on the TS and product optimizations
opts_done = 1
fails = 0
#check if ts is done
if not obj.ts_opt.shir == 1:
opts_done = 0
obj.ts_opt.do_optimization()
if obj.ts_opt.shigh == -999:
logging.info("Reaction {} ts_opt_shigh failure".format(
instance_name))
fails = 1
for pr_opt in obj.prod_opt:
if not pr_opt.shir == 1:
opts_done = 0
pr_opt.do_optimization()
if pr_opt.shigh == -999:
logging.info(
"Reaction {} pr_opt_shigh failure".format(
instance_name))
fails = 1
if fails:
self.species.reac_ts_done[index] = -999
elif opts_done:
self.species.reac_ts_done[index] = 6
elif self.species.reac_ts_done[index] == 6:
#Finilize the calculations
#continue to PES search in case a new well was found
if self.par.par['pes']:
#verify if product is monomolecular, and if it is new
if len(obj.products) == 1:
st_pt = obj.prod_opt[0].species
chemid = st_pt.chemid
energy = st_pt.energy
well_energy = self.species.energy
new_barrier_threshold = self.par.par[
'barrier_threshold'] - (
energy - well_energy) * constants.AUtoKCAL
dir = os.path.dirname(os.getcwd())
jobs = open(dir + '/chemids',
'r').read().split('\n')
jobs = [ji for ji in jobs]
if not str(chemid) in jobs:
#this well is new, add it to the jobs
while 1:
try:
#try to open the file and write to it
pes.write_input(
self.par, obj.products[0],
new_barrier_threshold, dir)
f = open(dir + '/chemids', 'a')
f.write('{}\n'.format(chemid))
f.close()
break
except IOError:
#wait a second and try again
time.sleep(1)
pass
# copy the files of the species to an upper directory
frags = obj.products
for frag in frags:
filecopying.copy_to_database_folder(
self.species.chemid, frag.chemid, self.qc)
#check for wrong number of negative frequencies
neg_freq = 0
for st_pt in obj.products:
if any([fi < 0. for fi in st_pt.reduced_freqs]):
neg_freq = 1
if any([fi < 0. for fi in obj.ts.reduced_freqs[1:]]):
neg_freq = 1
if neg_freq:
logging.info('\tFound negative frequency for ' +
instance_name)
self.species.reac_ts_done[index] = -999
else:
#the reaction search is finished
self.species.reac_ts_done[
index] = -1 # this is the success code
# write a temporary pes input file
# remove old xval and im_extent files
if os.path.exists('{}_xval.txt'.format(
self.species.chemid)):
os.remove('{}_xval.txt'.format(
self.species.chemid))
if os.path.exists('{}_im_extent.txt'.format(
self.species.chemid)):
os.remove('{}_im_extent.txt'.format(
self.species.chemid))
postprocess.createPESViewerInput(
self.species, self.qc, self.par)
elif self.species.reac_ts_done[index] == -999:
if self.par.par['delete_intermediate_files'] == 1:
if not self.species.reac_obj[
index].instance_name in deleted:
self.delete_files(
self.species.reac_obj[index].instance_name)
deleted.append(
self.species.reac_obj[index].instance_name)
alldone = 1
for index, instance in enumerate(self.species.reac_inst):
if any(self.species.reac_ts_done[i] >= 0
for i in range(len(self.species.reac_inst))):
alldone = 1
break
else:
alldone = 0
# write a small summary while running
wr = 1
if wr:
f_out = open('kinbot_monitor.out', 'w')
for index, instance in enumerate(self.species.reac_inst):
f_out.write('{}\t{}\t{}\n'.format(
self.species.reac_ts_done[index],
self.species.reac_step[index],
self.species.reac_obj[index].instance_name))
f_out.close()
time.sleep(1)
s = []
for index, instance in enumerate(self.species.reac_inst):
obj = self.species.reac_obj[index]
instance_name = obj.instance_name
# Write a summary on the combinatorial exploration
if 'combinatorial' in instance_name:
s.append('NAME\t' + instance_name)
# Write the bonds that were broken and formed
s.append('BROKEN_BONDS\t' +
'\t'.join('[{}, {}]'.format(re[0], re[1])
for re in obj.reac))
s.append('FORMED_BONDS\t' +
'\t'.join('[{}, {}]'.format(pr[0], pr[1])
for pr in obj.prod))
# Populate the ts_bond_lengths dict with the values
# of this reaction
if self.species.reac_ts_done[index] == -1:
for i in range(self.species.natom - 1):
for j in range(i + 1, self.species.natom):
if self.species.bond[i][j] != obj.product_bonds[i][
j]:
if (self.species.bond[i][j] == 0
or obj.product_bonds[i][j] == 0):
syms = []
syms.append(self.species.atom[i])
syms.append(self.species.atom[j])
syms = ''.join(sorted(syms))
dist = np.linalg.norm(obj.ts.geom[i] -
obj.ts.geom[j])
s.append('TS_BOND_LENGTHS\t{}\t{}'.format(
syms, dist))
# write the expected inchis
s.append('EXPECTED_INCHIS\t' +
'\t'.join(inchi for inchi in obj.prod_inchi))
# get the inchis the reaction found
if self.species.reac_ts_done[index] == -1:
inchis = obj.get_final_inchis()
s.append('FOUND_INCHIS\t' + '\t'.join(inchis))
s.append('\n')
with open('combinatorial.txt', 'w') as f:
f.write('\n'.join(s) + '\n')
logging.info("Reaction generation done!")
def main():
try:
input_file = sys.argv[1]
except IndexError:
print('To use KinBot, supply one argument being the input file!')
sys.exit(-1)
# print the license message to the console
print(license_message.message)
# initialize the parameters for this run
masterpar = Parameters(input_file)
par = masterpar.par
input_file = masterpar.input_file
# set up the logging environment
if par['verbose']:
logging.basicConfig(filename='kinbot.log', level=logging.DEBUG)
else:
logging.basicConfig(filename='kinbot.log', level=logging.INFO)
# write the license message to the log file
logging.info(license_message.message)
logging.info('Input parameters')
for param in par:
logging.info('{} {}'.format(param, par[param]))
# time stamp of the KinBot start
logging.info('Starting KinBot at {}'.format(datetime.datetime.now()))
# Make the necessary directories
if not os.path.exists('perm'):
os.makedirs('perm')
if not os.path.exists('scratch'):
os.makedirs('scratch')
if not os.path.exists(par['single_point_qc']):
os.mkdir(par['single_point_qc'])
if par['rotor_scan'] == 1:
if not os.path.exists('hir'):
os.mkdir('hir')
if not os.path.exists('hir_profiles'):
os.mkdir('hir_profiles')
if not os.path.exists('perm/hir/'):
os.makedirs('perm/hir/')
if par['conformer_search'] == 1:
if not os.path.exists('conf'):
os.mkdir('conf')
if not os.path.exists('perm/conf'):
os.makedirs('perm/conf')
if not os.path.exists('me'):
os.mkdir('me')
# initialize the reactant
well0 = StationaryPoint('well0',
par['charge'],
par['mult'],
smiles=par['smiles'],
structure=par['structure'])
well0.short_name = 'w1'
# write the initial reactant geometry to a file for visualization
geom_out = open('geometry.xyz', 'w')
geom_out.write('{}\n\n'.format(well0.natom))
for i, at in enumerate(well0.atom):
x, y, z = well0.geom[i]
geom_out.write('{} {:.6f} {:.6f} {:.6f}\n'.format(at, x, y, z))
geom_out.write('\n\n')
geom_out.close()
# characterize the initial reactant
well0.characterize(dimer=par['dimer'])
well0.name = str(well0.chemid)
start_name = well0.name
# initialize the qc instance
qc = QuantumChemistry(par)
# only run filecopying if PES is turned on
# if par['pes']:
# check if this well was calcualted before in another directory
# this flag indicates that this kinbot run
# should wait for the information from another
# kinbot run to become available and copy the necessary information
# wait_for_well = 1
# while wait_for_well:
# wait_for_well = filecopying.copy_from_database_folder(well0.chemid, well0.chemid, qc)
# if wait_for_well:
# time.sleep(1)
# start the initial optimization of the reactant
logging.info('Starting optimization of intial well')
qc.qc_opt(well0, well0.geom)
err, well0.geom = qc.get_qc_geom(str(well0.chemid) + '_well',
well0.natom,
wait=1)
err, well0.freq = qc.get_qc_freq(str(well0.chemid) + '_well',
well0.natom,
wait=1)
if err < 0:
logging.error('Error with initial structure optimization.')
return
if any(well0.freq[i] <= 0 for i in range(len(well0.freq))):
logging.error('Found imaginary frequency for initial structure.')
return
# characterize again and look for differences
well0.characterize(dimer=par['dimer'])
well0.name = str(well0.chemid)
if well0.name != start_name:
logging.error(
'The first well optimized to a structure different from the input.'
)
return
# do an MP2 optimization of the reactant,
# to compare some scan barrier heigths to
if par['families'] == ['all'] or \
'birad_recombination_R' in par['families'] or \
'r12_cycloaddition' in par['families'] or \
'r14_birad_scission' in par['families'] or \
'R_Addition_MultipleBond' in par['families'] or \
(par['skip_families'] != ['none'] and \
('birad_recombination_R' not in par['skip_families'] or \
'r12_cycloaddition' not in par['skip_families'] or \
'r14_birad_scission' not in par['skip_families'] or \
'R_Addition_MultipleBond' not in par['skip_families'])) or \
par['reaction_search'] == 0:
logging.info('Starting MP2 optimization of intial well')
qc.qc_opt(well0, well0.geom, mp2=1)
err, geom = qc.get_qc_geom(
str(well0.chemid) + '_well_mp2', well0.natom, 1)
# comparison for barrierless scan
if par['barrierless_saddle']:
logging.info(
'Optimization of intial well for barrierless at {}/{}'.format(
par['barrierless_saddle_method'],
par['barrierless_saddle_basis']))
qc.qc_opt(well0, well0.geom, bls=1)
err, geom = qc.get_qc_geom(
str(well0.chemid) + '_well_bls', well0.natom, 1)
# characterize again and look for differences
well0.characterize(dimer=par['dimer'])
well0.name = str(well0.chemid)
err, well0.energy = qc.get_qc_energy(str(well0.chemid) + '_well', 1)
err, well0.zpe = qc.get_qc_zpe(str(well0.chemid) + '_well', 1)
well_opt = Optimize(well0, par, qc, wait=1)
well_opt.do_optimization()
if well_opt.shigh == -999:
logging.error(
'Error with high level optimization of initial structure.')
return
if par['pes']:
filecopying.copy_to_database_folder(well0.chemid, well0.chemid, qc)
if par['reaction_search'] == 1:
logging.info('Starting reaction searches of intial well')
rf = ReactionFinder(well0, par, qc)
rf.find_reactions()
rg = ReactionGenerator(well0, par, qc, input_file)
rg.generate()
if par['homolytic_scissions'] == 1:
logging.info('Starting the search for homolytic scission products')
well0.homolytic_scissions = HomolyticScissions(well0, par, qc)
well0.homolytic_scissions.find_homolytic_scissions()
if par['me'] > 0: # it will be 2 for kinbots when the mess file is needed but not run
mess = MESS(par, well0)
mess.write_input(qc)
if par['me'] == 1:
logging.info('Starting Master Equation calculations')
if par['me_code'] == 'mess':
mess.run()
postprocess.createSummaryFile(well0, qc, par)
postprocess.createPESViewerInput(well0, qc, par)
postprocess.creatMLInput(well0, qc, par)
logging.info('Finished KinBot at {}'.format(datetime.datetime.now()))
print("Done!")
def find_homolytic_scissions(self):
"""
Enumerate all unique homolytic scission reactions
"""
# set of unique bonds to break
bonds = []
for i in range(len(self.species.atom)-1):
for j in range(i+1, len(self.species.atom)):
# only consider a bond of which both
# atoms are not in the same cycle
cycle = []
for cyc in self.species.cycle_chain:
if i in cyc:
cycle.extend(cyc)
if j not in cycle:
# only consider single bonds for homolytic scissions
if self.species.bond[i][j] == 1:
# check if a bond with identical atomids
# has been added to the bonds list yet
new = 1
for bi in bonds:
if sorted([self.species.atomid[at] for at in bi]) == sorted([self.species.atomid[i], self.species.atomid[j]]):
new = 0
if new:
bonds.append([i, j])
hs = HomolyticScission(self.species, self.par,
self.qc, [i, j])
hs.create_geometries()
self.hss.append(hs)
# optimize the products of the hss
while 1:
for index, hs in enumerate(self.hss):
if hs.status == 0:
# do the initial optimization
for prod in hs.products:
hs.qc.qc_opt(prod, prod.geom)
hs.status = 1
if hs.status == 1:
# wait for the optimization to finish
err = 0
for prod in hs.products:
e, prod.geom = hs.qc.get_qc_geom(str(prod.chemid) + '_well', prod.natom)
if e < 0:
# optimizatin failed
hs.status = -999
err = -1
elif e != 0:
err = -1
else:
e2, prod.energy = hs.qc.get_qc_energy(str(prod.chemid) + '_well', prod.natom)
e2, prod.zpe = hs.qc.get_qc_zpe(str(prod.chemid) + '_well', prod.natom)
if err == 0:
hs.status = 2
if hs.status == 2:
# Do the product conf search, high level opt and HIR
for prod in hs.products:
prod_opt = Optimize(prod, self.par, self.qc)
prod_opt.do_optimization()
hs.prod_opt.append(prod_opt)
hs.status = 3
if hs.status == 3:
# check up on the optimization
opts_done = 1
fails = 0
for pr_opt in hs.prod_opt:
if not pr_opt.shir == 1:
opts_done = 0
pr_opt.do_optimization()
if pr_opt.shigh == -999:
fails = 1
if fails:
hs.status = -999
elif opts_done:
# check if the energy is higher
# than the barrier threshold
species_energy = self.species.energy
prod_energy = 0.
for pr_opt in hs.prod_opt:
prod_energy += pr_opt.species.energy
barrier = (prod_energy - species_energy)*constants.AUtoKCAL
if barrier > self.par.par['barrier_threshold']:
hs.status = -999
else:
hs.status = -1
if all([hs.status < 0 for hs in self.hss]):
break
def generate(self):
"""
Creates the input for each reaction, runs them, and tests for success.
If successful, it creates the barrier and product objects.
It also then does the conformational search, and finally, the hindered rotor scans.
To make the code the most efficient, all of these happen in parallel, in a sense that
the jobs are not waiting for each other. E.g., one reaction can still be in the stage
of TS search, while the other can be already at the hindered rotor scan. This way,
all cores are occupied efficiently.
The switching between the various stages are done via the reac_ts_done variable.
0: initiate the TS search
1: check barrier height and errors in TS, and initiates normal mode displacement test, start the irc calculations
2: submit product optimization
3: submit the frequency calculation
4: do the optimization of the ts and the products
5: follow up on the optimizations
6: finalize calculations, check for wrong number of negative frequencies
If at any times the calculation fails, reac_ts_done is set to -999.
If all steps are successful, reac_ts_done is set to -1.
"""
deleted = []
if len(self.species.reac_inst) > 0:
alldone = 1
else:
alldone = 0
# status to see of kinbot needs to wait for the product optimizations
# from another kinbot run, to avoid duplication of calculations
products_waiting_status = [[] for i in self.species.reac_inst]
count = 0
for i in self.species.reac_inst:
count = count + 1
frag_unique = []
while alldone:
for index, instance in enumerate(self.species.reac_inst):
obj = self.species.reac_obj[index]
# START REACTION SEARCH
if self.species.reac_ts_done[
index] == 0 and self.species.reac_step[index] == 0:
# verify after restart if search has failed in previous kinbot run
status = self.qc.check_qc(obj.instance_name)
if status == 'error' or status == 'killed':
logging.info(
'\tRxn search failed (error or killed) for {}'.
format(obj.instance_name))
self.species.reac_ts_done[index] = -999
if self.species.reac_type[
index] == 'hom_sci' and self.species.reac_ts_done[
index] == 0: # no matter what, set to 2
# somewhat messy manipulation to force the new bond matrix for hom_sci
obj.products = copy.deepcopy(obj.species)
obj.products.bonds = copy.deepcopy(
obj.species.bond) # plural/non plural!
obj.products.bonds[obj.instance[0]][
obj.instance[1]] = 0 # delete bond
obj.products.bonds[obj.instance[1]][
obj.instance[0]] = 0 # delete bond
obj.products.bond[obj.instance[0]][
obj.instance[1]] = 0 # delete bond
obj.products.bond[obj.instance[1]][
obj.instance[0]] = 0 # delete bond
obj.product_bonds = copy.deepcopy(
obj.species.bonds[0]) # the first resonance structure
obj.product_bonds[obj.instance[0]][
obj.instance[1]] = 0 # delete bond
obj.product_bonds[obj.instance[1]][
obj.instance[0]] = 0 # delete bond
self.species.reac_ts_done[index] = 2
if self.species.reac_ts_done[
index] == 0: # ts search is ongoing
if obj.scan == 0: # don't do a scan of a bond
if self.species.reac_step[index] == obj.max_step + 1:
status, freq = self.qc.get_qc_freq(
obj.instance_name, self.species.natom)
if status == 0 and freq[0] < 0. and freq[1] > 0.:
self.species.reac_ts_done[index] = 1
elif status == 0 and freq[0] > 0.:
logging.info(
'\tRxn search failed for {}, no imaginary freq.'
.format(obj.instance_name))
self.species.reac_ts_done[index] = -999
elif status == 0 and freq[1] < 0.:
logging.info(
'\tRxn search failed for {}, more than one imaginary freq.'
.format(obj.instance_name))
self.species.reac_ts_done[index] = -999
elif status == -1:
logging.info(
'\tRxn search failed for {}'.format(
obj.instance_name))
self.species.reac_ts_done[index] = -999
else:
self.species.reac_step[
index] = reac_family.carry_out_reaction(
obj, self.species.reac_step[index],
self.par['qc_command'])
else: # do a bond scan
if self.species.reac_step[
index] == self.par['scan_step'] + 1:
status, freq = self.qc.get_qc_freq(
obj.instance_name, self.species.natom)
if status == 0 and freq[0] < 0. and freq[1] > 0.:
self.species.reac_ts_done[index] = 1
elif status == 0 and freq[0] > 0.:
logging.info(
'\tRxn search failed for {}, no imaginary freq.'
.format(obj.instance_name))
self.species.reac_ts_done[index] = -999
elif status == 0 and freq[1] < 0.:
logging.info(
'\tRxn search failed for {}, more than one imaginary freq.'
.format(obj.instance_name))
self.species.reac_ts_done[index] = -999
elif status == -1:
logging.info(
'\tRxn search using scan failed for {} in TS optimization stage.'
.format(obj.instance_name))
self.species.reac_ts_done[index] = -999
else:
if self.species.reac_step[index] == 0:
self.species.reac_step[
index] = reac_family.carry_out_reaction(
obj, self.species.reac_step[index],
self.par['qc_command'])
elif self.species.reac_step[index] < self.par[
'scan_step']:
status = self.qc.check_qc(obj.instance_name)
if status == 'error' or status == 'killed':
logging.info(
'\tRxn search using scan failed for {} in step {}'
.format(obj.instance_name,
self.species.reac_step[index]))
self.species.reac_ts_done[index] = -999
else:
err, energy = self.qc.get_qc_energy(
obj.instance_name)
if err == 0:
self.species.reac_scan_energy[
index].append(energy)
# need at least 3 points for a maximum
if len(self.species.
reac_scan_energy[index]) >= 3:
ediff = np.diff(
self.species.
reac_scan_energy[index])
if ediff[-1] < 0 and ediff[
-2] > 0: # max
self.species.reac_step[
index] = self.par[
'scan_step'] # ending the scan
if len(ediff) >= 3:
if 10. * (
ediff[-3] / ediff[-2]
) < (
ediff[-2] / ediff[-1]
): # sudden change in slope
self.species.reac_step[
index] = self.par[
'scan_step'] # ending the scan
logging.info(
'\tCurrent raw scan energy for {}: {} Hartree.'
.format(
obj.instance_name,
self.species.
reac_scan_energy[index][-1]))
# scan continues, and if reached scan_step, then goes for full optimization
self.species.reac_step[
index] = reac_family.carry_out_reaction(
obj,
self.species.reac_step[index],
self.par['qc_command'])
else: # the last step was reached, and no max or inflection was found
logging.info(
'\tRxn search using scan failed for {}, no saddle guess found.'
.format(obj.instance_name))
db = connect('{}/kinbot.db'.format(
os.getcwd()))
rows = db.select(name=obj.instance_name)
for row in self.reversed_iterator(rows):
row.data['status'] = 'error'
break # only write error to the last calculation
self.species.reac_ts_done[index] = -999
elif self.species.reac_ts_done[index] == 1:
status = self.qc.check_qc(obj.instance_name)
if status == 'running':
continue
elif status == 'error':
logging.info(
'\tRxn search failed (gaussian error) for {}'.
format(obj.instance_name))
self.species.reac_ts_done[index] = -999
else:
# check the barrier height:
ts_energy = self.qc.get_qc_energy(obj.instance_name)[1]
ts_zpe = self.qc.get_qc_zpe(obj.instance_name)[1]
if self.species.reac_type[
index] == 'R_Addition_MultipleBond':
ending = 'well_mp2'
elif self.species.reac_type[
index] == 'barrierless_saddle':
ending = 'well_bls'
else:
ending = 'well'
sp_energy = self.qc.get_qc_energy('{}_{}'.format(
str(self.species.chemid), ending))[1]
sp_zpe = self.qc.get_qc_zpe('{}_{}'.format(
str(self.species.chemid), ending))[1]
try:
barrier = (ts_energy + ts_zpe - sp_energy -
sp_zpe) * constants.AUtoKCAL
except TypeError:
logging.error(
f'Faulty calculations, check or delete files for {obj.instance_name}.'
)
sys.exit(-1)
if barrier > self.par['barrier_threshold']:
logging.info(
'\tRxn barrier too high ({0:.2f} kcal/mol) for {1}'
.format(barrier, obj.instance_name))
self.species.reac_ts_done[index] = -999
else:
obj.irc = IRC(
obj, self.par
) # TODO: this doesn't seem like a good design
irc_status = obj.irc.check_irc()
if 0 in irc_status:
logging.info(
'\tRxn barrier is {0:.2f} kcal/mol for {1}'
.format(barrier, obj.instance_name))
# No IRC started yet, start the IRC now
logging.info(
'\tStarting IRC calculations for {}'.
format(obj.instance_name))
obj.irc.do_irc_calculations()
elif irc_status[0] == 'running' or irc_status[
1] == 'running':
continue
else:
# IRC's have successfully finished, have an error or were killed, in any case
# read the geometries and try to make products out of them
# verify which of the ircs leads back to the reactant, if any
prod = obj.irc.irc2stationary_pt()
if prod == 0:
logging.info(
'\t\tNo product found for {}'.format(
obj.instance_name))
self.species.reac_ts_done[index] = -999
else:
obj.products = prod
obj.product_bonds = prod.bond
self.species.reac_ts_done[index] = 2
elif self.species.reac_ts_done[index] == 2:
if len(products_waiting_status[index]) == 0:
# identify bimolecular products and wells
fragments, maps = obj.products.start_multi_molecular()
obj.products = []
a = []
for frag in fragments:
a.append(frag)
if len(frag_unique) == 0:
frag_unique.append(frag)
elif len(frag_unique) > 0:
new = 1
for fragb in frag_unique:
if frag.chemid == fragb.chemid:
e, geom2 = self.qc.get_qc_geom(
str(fragb.chemid) + '_well',
fragb.natom)
if e == 0:
a.pop()
frag = fragb
a.append(frag)
new = 0
break
if new:
frag_unique.append(frag)
obj.products_final = []
for frag in a:
self.qc.qc_opt(frag, frag.geom)
e, geom2 = self.qc.get_qc_geom(
str(frag.chemid) + '_well', frag.natom)
obj.products_final.append(frag)
# check products make sure they are the same
for i, st_pt_i in enumerate(obj.products_final):
for j, st_pt_j in enumerate(obj.products_final):
if st_pt_i.chemid == st_pt_j.chemid and i < j:
obj.products_final[j] = obj.products_final[
i]
# print products generated by IRC
products = []
for i, st_pt in enumerate(obj.products_final):
products.append(st_pt.chemid)
products.extend([' ', ' ', ' '])
logging.info(
'\tReaction {} leads to products {} {} {}'.format(
obj.instance_name, products[0], products[1],
products[2]))
for i, st_pt in enumerate(obj.products_final):
chemid = st_pt.chemid
e, st_pt.geom = self.qc.get_qc_geom(
str(st_pt.chemid) + '_well', st_pt.natom)
if e < 0:
logging.info(
'\tProduct optimization failed for {}, product {}'
.format(obj.instance_name, st_pt.chemid))
self.species.reac_ts_done[index] = -999
err = -1
elif e != 0:
err = -1
else:
e2, st_pt.energy = self.qc.get_qc_energy(
str(st_pt.chemid) + '_well')
e2, st_pt.zpe = self.qc.get_qc_zpe(
str(st_pt.chemid) + '_well')
st_pt.characterize(
dimer=0
) # not allowed to use the dimer option here
if chemid != st_pt.chemid:
obj.products_final.pop(i)
newfrags, newmaps = st_pt.start_multi_molecular(
) # newfrags is list of stpt obj
products_waiting_status[index] = [
0 for frag in newfrags
]
frag_chemid = []
for i, newfr in enumerate(newfrags):
newfr.characterize(dimer=0)
for prod in frag_unique:
if newfr.chemid == prod.chemid:
newfrags.pop(i)
newfr = prod
j = i - 1
newfrags.insert(j, newfr)
j = i - 1
obj.products_final.insert(j, newfr)
self.qc.qc_opt(newfr, newfr.geom, 0)
frag_chemid.append(newfr.chemid)
if len(frag_chemid) == 1:
frag_chemid.append(" ")
for i, frag in enumerate(newfrags):
products_waiting_status[index][i] = 1
logging.info(
'\ta) Product optimized to other structure for {}'
', product {} to {} {}'.format(
obj.instance_name, chemid,
frag_chemid[0], frag_chemid[1]))
obj.products = []
for prod in obj.products_final:
obj.products.append(prod)
obj.products_final = []
if all([pi == 1 for pi in products_waiting_status[index]]):
self.species.reac_ts_done[index] = 3
elif self.species.reac_ts_done[index] == 3:
# wait for the optimization to finish
# if two st_pt are the same in the products, we make them exactly identical otherwise
# the different ordering of the atoms causes the chemid of the second to be seemingly wrong
for i, st_pt_i in enumerate(obj.products):
for j, st_pt_j in enumerate(obj.products):
if st_pt_i.chemid == st_pt_j.chemid and i < j:
obj.products[j] = obj.products[i]
err = 0
for st_pt in obj.products:
chemid = st_pt.chemid
e, st_pt.geom = self.qc.get_qc_geom(
str(st_pt.chemid) + '_well', st_pt.natom)
if e < 0:
logging.info(
'\tProduct optimization failed for {}, product {}'
.format(obj.instance_name, st_pt.chemid))
self.species.reac_ts_done[index] = -999
err = -1
elif e != 0:
err = -1
else:
e2, st_pt.energy = self.qc.get_qc_energy(
str(st_pt.chemid) + '_well')
e2, st_pt.zpe = self.qc.get_qc_zpe(
str(st_pt.chemid) + '_well')
st_pt.characterize(
dimer=0
) # not allowed to use the dimer option here
if chemid != st_pt.chemid:
# product was optimized to another structure, give warning but don't remove reaction
logging.info(
'\tb) Product optimized to other structure for {}'
', product {} to {}'.format(
obj.instance_name, chemid,
st_pt.chemid))
e, st_pt.geom = self.qc.get_qc_geom(
str(st_pt.chemid) + '_well', st_pt.natom)
if e < 0:
err = -1
if err == 0:
self.species.reac_ts_done[index] = 4
elif self.species.reac_ts_done[index] == 4:
# Do the TS and product optimization
# make a stationary point object of the ts
bond_mx = np.zeros(
(self.species.natom, self.species.natom), dtype=int)
for i in range(self.species.natom):
for j in range(self.species.natom):
bond_mx[i][j] = max(self.species.bond[i][j],
obj.product_bonds[i][j])
if self.species.reac_type[index] != 'hom_sci':
err, geom = self.qc.get_qc_geom(
obj.instance_name, self.species.natom)
ts = StationaryPoint(obj.instance_name,
self.species.charge,
self.species.mult,
atom=self.species.atom,
geom=geom,
wellorts=1)
err, ts.energy = self.qc.get_qc_energy(
obj.instance_name)
err, ts.zpe = self.qc.get_qc_zpe(
obj.instance_name) # NEW STOPS HERE
err, ts.freq = self.qc.get_qc_freq(
obj.instance_name, self.species.natom)
ts.distance_mx()
ts.bond = bond_mx
ts.find_cycle()
ts.find_conf_dihedral()
obj.ts = ts
# do the ts optimization
obj.ts_opt = Optimize(obj.ts, self.par, self.qc)
obj.ts_opt.do_optimization()
else:
obj.ts = copy.deepcopy(
obj.species
) # the TS will be for now the species itself
obj.ts.wellorts = 1
# do the products optimizations
for st_pt in obj.products:
# do the products optimizations
# check for products of other reactions that are the same as this product
# in the case such products are found, use the same Optimize object for both
for i, inst_i in enumerate(self.species.reac_inst):
new = 1
if not i == index:
obj_i = self.species.reac_obj[i]
if self.species.reac_ts_done[i] > 3:
for j, st_pt_i in enumerate(
obj_i.products):
if st_pt_i.chemid == st_pt.chemid:
if len(obj_i.prod_opt) > j:
prod_opt = obj_i.prod_opt[j]
new = 0
break
if new:
prod_opt = Optimize(st_pt, self.par, self.qc)
prod_opt.do_optimization()
obj.prod_opt.append(prod_opt)
for st_pt in obj.products:
# section where comparing products in same reaction occurs
if len(obj.prod_opt) > 0:
for j, st_pt_opt in enumerate(obj.prod_opt):
if st_pt.chemid == st_pt_opt.species.chemid:
if len(obj.prod_opt) > j:
prod_opt = obj.prod_opt[j]
break
self.species.reac_ts_done[index] = 5
elif self.species.reac_ts_done[index] == 5:
# check up on the TS and product optimizations
opts_done = 1
fails = 0
# check if ts is done
if self.species.reac_type[index] != 'hom_sci':
if not obj.ts_opt.shir == 1: # last stage in optimize
opts_done = 0
obj.ts_opt.do_optimization()
if obj.ts_opt.shigh == -999:
logging.info(
"Reaction {} ts_opt_shigh failure".format(
obj.instance_name))
fails = 1
for pr_opt in obj.prod_opt:
if not pr_opt.shir == 1:
opts_done = 0
pr_opt.do_optimization()
if pr_opt.shigh == -999:
logging.info(
"Reaction {} pr_opt_shigh failure".format(
obj.instance_name))
fails = 1
break
if fails:
self.species.reac_ts_done[index] = -999
elif opts_done:
self.species.reac_ts_done[index] = 6
elif self.species.reac_ts_done[index] == 6:
# Finilize the calculations
# continue to PES search in case a new well was found
if self.par['pes']:
# verify if product is monomolecular, and if it is new
if len(obj.products) == 1:
st_pt = obj.prod_opt[0].species
chemid = st_pt.chemid
new_barrier_threshold = self.par[
'barrier_threshold'] - (
st_pt.energy -
self.species.energy) * constants.AUtoKCAL
dirwell = os.path.dirname(os.getcwd())
jobs = open(dirwell + '/chemids',
'r').read().split('\n')
jobs = [ji for ji in jobs]
if not str(chemid) in jobs:
# this well is new, add it to the jobs
while 1:
try:
# try to open the file and write to it
pes.write_input(
self.inp, obj.products[0],
new_barrier_threshold, dirwell)
with open(dirwell + '/chemids',
'a') as f:
f.write('{}\n'.format(chemid))
break
except IOError:
# wait a second and try again
time.sleep(1)
pass
# copy the files of the species to an upper directory
frags = obj.products
for frag in frags:
filecopying.copy_to_database_folder(
self.species.chemid, frag.chemid, self.qc)
# check for wrong number of negative frequencies
neg_freq = 0
for st_pt in obj.products:
if any([fi < 0. for fi in st_pt.reduced_freqs]):
neg_freq = 1
if any([fi < 0. for fi in obj.ts.reduced_freqs[1:]]):
neg_freq = 1
if neg_freq:
logging.info('\tFound negative frequency for ' +
obj.instance_name)
self.species.reac_ts_done[index] = -999
else:
# the reaction search is finished
self.species.reac_ts_done[
index] = -1 # this is the success code
# write a temporary pes input file
# remove old xval and im_extent files
if os.path.exists('{}_xval.txt'.format(
self.species.chemid)):
os.remove('{}_xval.txt'.format(
self.species.chemid))
if os.path.exists('{}_im_extent.txt'.format(
self.species.chemid)):
os.remove('{}_im_extent.txt'.format(
self.species.chemid))
postprocess.createPESViewerInput(
self.species, self.qc, self.par)
elif self.species.reac_ts_done[index] == -999:
if self.par['delete_intermediate_files'] == 1:
if not self.species.reac_obj[
index].instance_name in deleted:
self.delete_files(
self.species.reac_obj[index].instance_name)
deleted.append(
self.species.reac_obj[index].instance_name)
alldone = 1
for index, instance in enumerate(self.species.reac_inst):
if any(self.species.reac_ts_done[i] >= 0
for i in range(len(self.species.reac_inst))):
alldone = 1
break
else:
alldone = 0
# write a small summary while running
with open('kinbot_monitor.out', 'w') as f_out:
for index, instance in enumerate(self.species.reac_inst):
if self.species.reac_ts_done[index] == -1:
prodstring = []
for pp in self.species.reac_obj[index].products:
prodstring.append(str(pp.chemid))
f_out.write('{}\t{}\t{}\t{}\n'.format(
self.species.reac_ts_done[index],
self.species.reac_step[index],
self.species.reac_obj[index].instance_name,
' '.join(prodstring)))
else:
f_out.write('{}\t{}\t{}\n'.format(
self.species.reac_ts_done[index],
self.species.reac_step[index],
self.species.reac_obj[index].instance_name))
time.sleep(1)
# Create molpro file for the BLS products
for index, instance in enumerate(self.species.reac_inst):
if self.species.reac_type[index] == 'barrierless_saddle':
obj = self.species.reac_obj[index]
if len(obj.products) == 2:
blsprodatom = np.append(obj.products[0].atom,
obj.products[1].atom)
# vector connecting the centers
# assumed: the two structures are naturally separated at the end of the IRC
x0 = 0
y0 = 0
z0 = 0
for g in obj.products[0].geom:
x0 += g[0]
y0 += g[1]
z0 += g[1]
x0 /= obj.products[0].natom
y0 /= obj.products[0].natom
z0 /= obj.products[0].natom
x1 = 0
y1 = 0
z1 = 0
for g in obj.products[1].geom:
x1 += g[0]
y1 += g[1]
z1 += g[1]
x1 /= obj.products[1].natom
y1 /= obj.products[1].natom
z1 /= obj.products[1].natom
center_vec = [x1 - x0, y1 - y0, z1 - z0]
blsprodgeom = np.append(obj.products[0].geom,
obj.products[1].geom)
blsprodgeom = np.reshape(blsprodgeom, (-1, 3))
bps = list(zip(blsprodatom, blsprodgeom))
bps1 = [item for sublist in bps for item in sublist]
blsprodstruct = [
item for sublist in bps1 for item in sublist
]
blsprod = StationaryPoint('blsprod',
self.par['charge'],
self.par['mult'],
structure=blsprodstruct)
blsprod.characterize()
molp = Molpro(blsprod, self.par)
molpname = '{}_prod'.format(obj.instance_name)
molp.create_molpro_input(bls=1,
name=molpname,
shift_vec=center_vec,
natom1=len(obj.products[1].geom))
molp.create_molpro_submit(name=molpname)
s = []
for index, instance in enumerate(self.species.reac_inst):
obj = self.species.reac_obj[index]
# Write a summary on the combinatorial exploration
if 'combinatorial' in obj.instance_name:
s.append('NAME\t' + obj.instance_name)
# Write the bonds that were broken and formed
s.append('BROKEN_BONDS\t' +
'\t'.join('[{}, {}]'.format(re[0], re[1])
for re in obj.reac))
s.append('FORMED_BONDS\t' +
'\t'.join('[{}, {}]'.format(pr[0], pr[1])
for pr in obj.prod))
# Populate the ts_bond_lengths dict with the values
# of this reaction
if self.species.reac_ts_done[index] == -1:
for i in range(self.species.natom - 1):
for j in range(i + 1, self.species.natom):
if self.species.bond[i][j] != obj.product_bonds[i][
j]:
if (self.species.bond[i][j] == 0
or obj.product_bonds[i][j] == 0):
syms = []
syms.append(self.species.atom[i])
syms.append(self.species.atom[j])
syms = ''.join(sorted(syms))
dist = np.linalg.norm(obj.ts.geom[i] -
obj.ts.geom[j])
s.append('TS_BOND_LENGTHS\t{}\t{}'.format(
syms, dist))
# write the expected inchis
s.append('EXPECTED_INCHIS\t' +
'\t'.join(inchi for inchi in obj.prod_inchi))
# get the inchis the reaction found
if self.species.reac_ts_done[index] == -1:
inchis = obj.get_final_inchis()
s.append('FOUND_INCHIS\t' + '\t'.join(inchis))
s.append('\n')
with open('combinatorial.txt', 'w') as f:
f.write('\n'.join(s) + '\n')
logging.info("Reaction generation done!")
def find_homolytic_scissions(self):
"""
Enumerate all unique homolytic scission reactions
"""
# set of unique bonds to break
bonds = []
for i in range(len(self.species.atom)-1):
for j in range(i+1, len(self.species.atom)):
# only consider a bond of which both
# atoms are not in the same cycle
cycle = []
for cyc in self.species.cycle_chain:
if i in cyc:
cycle.extend(cyc)
if j not in cycle:
# only consider single bonds for homolytic scissions
if self.species.bond[i][j] == 1:
# check if the bond is present in the 'homolytic_bonds' list, or if the list is empty
# add is a boolean that tells if the bond needs to be added to the homolytic scissions
# to be considered (i.e. the 'bonds' list)
add = 0
# get the elements of the current bond under consideration, and put them
# in alphabetical order
bond_elements = sorted([self.species.atom[i], self.species.atom[j]])
# check all bonds to be considered, supplied by the user
for user_bond in self.par['homolytic_bonds']:
if sorted(user_bond) == bond_elements:
# if there is a match between the current bond and a user-defined
# bond, put the add boolean to 1
add = 1
# add the bond if the 'add' boolean is 1 or if the user defined list is empty
# (in the latter case, all single bonds that are not in a cycle are considered.
if len(self.par['homolytic_bonds']) == 0 or add:
# check if a bond with identical atomids
# has been added to the bonds list yet
new = 1
for bi in bonds:
if sorted([self.species.atomid[at] for at in bi]) == sorted([self.species.atomid[i], self.species.atomid[j]]):
new = 0
if new:
bonds.append([i, j])
hs = HomolyticScission(self.species, self.par,
self.qc, [i, j])
hs.create_geometries()
self.hss.append(hs)
# optimize the products of the hss
while not all([hs.status < 0 for hs in self.hss]):
for index, hs in enumerate(self.hss):
if hs.status == 0:
# do the initial optimization
for prod in hs.products:
hs.qc.qc_opt(prod, prod.geom)
hs.status = 1
if hs.status == 1:
# wait for the optimization to finish
err = 0
for prod in hs.products:
e, prod.geom = hs.qc.get_qc_geom(str(prod.chemid) + '_well', prod.natom)
if e < 0:
# optimizatin failed
logging.info("HS optimization failed for {}".format(prod.chemid))
hs.status = -999
err = -1
elif e != 0:
err = -1
else:
e2, prod.energy = hs.qc.get_qc_energy(str(prod.chemid) + '_well')
e2, prod.zpe = hs.qc.get_qc_zpe(str(prod.chemid) + '_well')
if err == 0:
hs.status = 2
if hs.status == 2:
# Do the product conf search, high level opt and HIR
err = 0
for i, prod in enumerate(hs.products):
chemid = prod.chemid
prod_opt = Optimize(prod, self.par, self.qc)
if str(chemid) != str(prod_opt.species.chemid):
logging.info("HS product {} changed to {} during optimization.".format(chemid, prod_opt.species.chemid))
hs.qc.qc_opt(prod_opt.species, prod_opt.species.geom)
j = i - 1
# wait for new opt to finish
er, prod.geom = hs.qc.get_qc_geom(str(prod_opt.species.chemid) + '_well', prod_opt.species.natom)
if er < 0:
# optimization failed
logging.info("HS optimization failed for {}".format(prod_opt.species.chemid))
err = -1
elif er != 0:
err = -1
else:
er2, prod.energy = hs.qc.get_qc_energy(str(prod_opt.species.chemid) + '_well')
er2, prod.zpe = hs.qc.get_qc_zpe(str(prod_opt.species.chemid) + '_well')
hs.products.pop(i)
hs.products.insert(j, prod_opt.species)
prod_opt.do_optimization()
hs.prod_opt.append(prod_opt)
if err == 0:
hs.status = 3
if hs.status == 3:
# check up on the optimization
opts_done = 1
fails = 0
for pr_opt in hs.prod_opt:
if not pr_opt.shir == 1:
opts_done = 0
pr_opt.do_optimization()
if pr_opt.shigh == -999:
fails = 1
if fails:
hs.status = -999
elif opts_done:
# check if the energy is higher
# than the barrier threshold
species_zeroenergy = self.species.energy + self.species.zpe
prod_zeroenergy = 0.
for pr_opt in hs.prod_opt:
prod_zeroenergy += pr_opt.species.energy + pr_opt.species.zpe
barrier = (prod_zeroenergy - species_zeroenergy) * constants.AUtoKCAL
prod_name = ' '.join(sorted([str(prod.species.chemid) for prod in hs.prod_opt]))
if barrier > self.par['barrier_threshold']:
logging.info("Energy of HS product {}, {:.2f} kcal/mol, is too high.".format(prod_name, barrier))
hs.status = -999
else:
hs.status = -1
name = '_'.join(sorted([str(prod.species.chemid) for prod in hs.prod_opt]))
logging.info('Homolytic scission (asymptote {:.2f} kcal/mol) lead to products {}'.format(barrier, name))
def main():
try:
input_file = sys.argv[1]
except IndexError:
print('To use KinBot, supply one argument being the input file!')
sys.exit(-1)
# print the license message to the console
print(license_message.message)
# initialize the parameters for this run
par = Parameters(input_file)
# set up the logging environment
if par.par['verbose']:
logging.basicConfig(filename='kinbot.log', level=logging.DEBUG)
else:
logging.basicConfig(filename='kinbot.log', level=logging.INFO)
# write the license message to the log file
logging.info(license_message.message)
# time stamp of the KinBot start
logging.info('Starting KinBot at {}'.format(datetime.datetime.now()))
# Make the necessary directories
if not os.path.exists('perm'):
os.makedirs('perm')
if not os.path.exists('scratch'):
os.makedirs('scratch')
if not os.path.exists(par.par['single_point_qc']):
os.mkdir(par.par['single_point_qc'])
if par.par['rotor_scan'] == 1:
if not os.path.exists('hir'):
os.mkdir('hir')
if not os.path.exists('hir_profiles'):
os.mkdir('hir_profiles')
if not os.path.exists('perm/hir/'):
os.makedirs('perm/hir/')
if par.par['conformer_search'] == 1:
if not os.path.exists('conf'):
os.mkdir('conf')
if not os.path.exists('perm/conf'):
os.makedirs('perm/conf')
if not os.path.exists('me'):
os.mkdir('me')
if par.par['pes'] and par.par['specific_reaction']:
logging.error('Specific reaction cannot be searched in PES mode.')
return
# initialize the reactant
well0 = StationaryPoint('well0',
par.par['charge'],
par.par['mult'],
smiles=par.par['smiles'],
structure=par.par['structure'])
well0.short_name = 'w1'
# wrtie the initial reactant geometry to a file for visualization
geom_out = open('geometry.xyz', 'w')
geom_out.write('{}\n\n'.format(well0.natom))
for i, at in enumerate(well0.atom):
x, y, z = well0.geom[i]
geom_out.write('{} {:.6f} {:.6f} {:.6f}\n'.format(at, x, y, z))
geom_out.write('\n\n')
geom_out.close()
# characterize the initial reactant
well0.characterize(par.par['dimer'])
well0.name = str(well0.chemid)
start_name = well0.name
# initialize the qc instance
qc = QuantumChemistry(par)
# start the initial optimization of the reactant
logging.info('Starting optimization of intial well')
qc.qc_opt(well0, well0.geom)
err, well0.geom = qc.get_qc_geom(str(well0.chemid) + '_well',
well0.natom, wait=1)
err, well0.freq = qc.get_qc_freq(str(well0.chemid) + '_well',
well0.natom, wait=1)
if err < 0:
logging.error('Error with initial structure optimization.')
return
if any(well0.freq[i] <= 0 for i in range(len(well0.freq))):
logging.error('Found imaginary frequency for initial structure.')
return
# characterize again and look for differences
well0.characterize(par.par['dimer'])
well0.name = str(well0.chemid)
if well0.name != start_name:
logging.error('The first well optimized to a structure different from the input.')
return
# do an MP2 optimization of the reactant,
# to compare Beta scission barrier heigths to
logging.info('Starting MP2 optimization of intial well')
qc.qc_opt(well0, well0.geom, mp2=1)
err, geom = qc.get_qc_geom(str(well0.chemid) + '_well_mp2', well0.natom, 1)
# characterize again and look for differences
well0.characterize(par.par['dimer'])
well0.name = str(well0.chemid)
# read the energy and the zpe corrected energy
err, well0.energy = qc.get_qc_energy(str(well0.chemid) + '_well', 1)
err, well0.zpe = qc.get_qc_zpe(str(well0.chemid) + '_well', 1)
well_opt = Optimize(well0, par, qc, wait=1)
well_opt.do_optimization()
if well_opt.shigh == -999:
logging.error('Error with high level optimization of initial structure.')
return
# do the reaction search using heuristics
if par.par['reaction_search'] == 1:
logging.info('Starting reaction searches of intial well')
rf = ReactionFinder(well0, par, qc)
rf.find_reactions()
rg = ReactionGenerator(well0, par, qc)
rg.generate()
# do the homolytic scission products search
if par.par['homolytic_scissions'] == 1:
logging.info('Starting the search for homolytic scission products')
well0.homolytic_scissions = HomolyticScissions(well0, par, qc)
well0.homolytic_scissions.find_homolytic_scissions()
# initialize the master equation instance
mess = MESS(par, well0)
mess.write_input()
mesmer = MESMER(par, well0)
mesmer.write_input()
if par.par['me'] == 1:
logging.info('Starting Master Equation calculations')
if par.par['me_code'] == 'mess':
mess.run()
elif par.par['me_code'] == 'mesmer':
mesmer.run()
else:
logging.error('Cannot recognize me code {}'.format(par.par['me_code']))
# postprocess the calculations
postprocess.createSummaryFile(well0, qc, par)
postprocess.createPESViewerInput(well0, qc, par)
postprocess.creatMLInput(well0, qc, par)
logging.info('Finished KinBot at {}'.format(datetime.datetime.now()))
print("Done!")
def generate(self):
"""
Creates the input for each reaction, runs them, and tests for success.
If successful, it creates the barrier and product objects.
It also then does the conformational search, and finally, the hindered rotor scans.
To make the code the most efficient, all of these happen in parallel, in a sense that
the jobs are not waiting for each other. E.g., one reaction can still be in the stage
of TS search, while the other can be already at the hindered rotor scan. This way,
all cores are occupied efficiently.
The switching between the various stages are done via the reac_ts_done variable.
0: initiate the TS search
1: check barrier height and errors in TS, and initiates normal mode displacement test, start the irc calculations
2: submit product optimization
3: submit the frequency calculation
4: do the optimization of the ts and the products
5: follow up on the optimizations
6: finalize calculations, check for wrong number of negative frequencies
If at any times the calculation fails, reac_ts_done is set to -999.
If all steps are successful, reac_ts_done is set to -1.
"""
if len(self.species.reac_inst) > 0:
alldone = 1
else:
alldone = 0
while alldone:
for index, instance in enumerate(self.species.reac_inst):
obj = self.species.reac_obj[index]
instance_name = obj.instance_name
# START REATION SEARCH
if self.species.reac_ts_done[
index] == 0 and self.species.reac_step[index] == 0:
#verify after restart if search has failed in previous kinbot run
status = self.qc.check_qc(instance_name)
if status == 'error' or status == 'killed':
logging.info(
'\tRxn search failed (error or killed) for {}'.
format(instance_name))
self.species.reac_ts_done[index] = -999
if self.species.reac_ts_done[
index] == 0: # ts search is ongoing
if obj.scan == 0: #don't do a scan of a bond
if self.species.reac_step[index] == obj.max_step + 1:
status = self.qc.get_qc_freq(
instance_name, self.species.natom)[0]
if status == 0:
self.species.reac_ts_done[index] = 1
elif status == -1:
logging.info(
'\tRxn search failed for {}'.format(
instance_name))
self.species.reac_ts_done[index] = -999
else:
self.species.reac_step[
index] = reac_family.carry_out_reaction(
obj, self.species.reac_step[index],
self.par.par['qc_command'])
else: # do a bond scan
if self.species.reac_step[
index] == self.par.par['scan_step'] + 1:
status = self.qc.get_qc_freq(
instance_name, self.species.natom)[0]
if status == 0:
self.species.reac_ts_done[index] = 1
elif status == -1:
logging.info(
'\tRxn search failed for {}'.format(
instance_name))
self.species.reac_ts_done[index] = -999
else:
if self.species.reac_step[index] == 0:
self.species.reac_step[
index] = reac_family.carry_out_reaction(
obj, self.species.reac_step[index],
self.par.par['qc_command'])
elif self.species.reac_step[index] > 0:
status = self.qc.check_qc(instance_name)
if status == 'error' or status == 'killed':
logging.info(
'\tRxn search failed for {}'.format(
instance_name))
self.species.reac_ts_done[index] = -999
else:
err, energy = self.qc.get_qc_energy(
instance_name)
if err == 0:
self.species.reac_scan_energy[
index].append(energy)
if len(self.species.
reac_scan_energy[index]) > 1:
if self.species.reac_scan_energy[
index][
-1] < self.species.reac_scan_energy[
index][-2]:
self.species.reac_step[
index] = self.par.par[
'scan_step']
self.species.reac_step[
index] = reac_family.carry_out_reaction(
obj,
self.species.reac_step[index],
self.par.par['qc_command'])
elif self.species.reac_ts_done[index] == 1:
status = self.qc.check_qc(instance_name)
if status == 'running': continue
elif status == 'error':
logging.info(
'\tRxn search failed (gaussian error) for {}'.
format(instance_name))
self.species.reac_ts_done[index] = -999
else:
#check the barrier height:
if self.species.reac_type[
index] == 'R_Addition_MultipleBond':
sp_energy = self.qc.get_qc_energy(
str(self.species.chemid) + '_well_mp2')[1]
barrier = (self.qc.get_qc_energy(instance_name)[1]
- sp_energy) * constants.AUtoKCAL
else:
sp_energy = self.qc.get_qc_energy(
str(self.species.chemid) + '_well')[1]
barrier = (self.qc.get_qc_energy(instance_name)[1]
- sp_energy) * constants.AUtoKCAL
if barrier > self.par.par['barrier_threshold']:
logging.info(
'\tRxn barrier too high ({val}) for {name}'.
format(val=barrier, name=instance_name))
self.species.reac_ts_done[index] = -999
else:
obj.irc = IRC(
obj, self.par
) #TODO: this doesn't seem like a good design
irc_status = obj.irc.check_irc()
if 0 in irc_status:
# No IRC started yet, start the IRC now
logging.info(
'\tStarting IRC calculations for {}'.
format(instance_name))
obj.irc.do_irc_calculations()
elif irc_status[0] == 'running' or irc_status[
1] == 'running':
continue
else:
#IRC's have succesfully finished, have an error or were killed, in any case
#read the geometries and try to make products out of them
#verify which of the ircs leads back to the reactant, if any
prod = obj.irc.irc2stationary_pt()
if prod == 0:
logging.info(
'\t\tNo product found for {}'.format(
instance_name))
self.species.reac_ts_done[index] = -999
else:
#IRC's are done
obj.products = prod
obj.product_bonds = prod.bond
self.species.reac_ts_done[index] = 2
elif self.species.reac_ts_done[index] == 2:
#identify bimolecular products and wells
fragments, maps = obj.products.start_multi_molecular()
obj.products = []
for i, frag in enumerate(fragments):
obj.products.append(frag)
self.qc.qc_opt(frag, frag.geom)
self.species.reac_ts_done[index] = 3
elif self.species.reac_ts_done[index] == 3:
#wait for the optimization to finish
err = 0
for st_pt in obj.products:
chemid = st_pt.chemid
orig_geom = copy.deepcopy(st_pt.geom)
e, st_pt.geom = self.qc.get_qc_geom(
str(st_pt.chemid) + '_well', st_pt.natom)
if e < 0:
logging.info(
'\tProduct optimization failed for {}, product {}'
.format(instance_name, st_pt.chemid))
self.species.reac_ts_done[index] = -999
err = -1
elif e != 0:
err = -1
else:
e2, st_pt.energy = self.qc.get_qc_energy(
str(st_pt.chemid) + '_well')
e2, st_pt.zpe = self.qc.get_qc_zpe(
str(st_pt.chemid) + '_well')
st_pt.bond_mx()
st_pt.characterize(
0) # not allowed to use the dimer option here
st_pt.calc_chemid()
if chemid != st_pt.chemid:
# product was optimized to another structure, give warning and remove this reaction
logging.info(
'\tProduct optimizatied to other structure for {}, product {} to {}'
.format(instance_name, chemid,
st_pt.chemid))
self.species.reac_ts_done[index] = -999
err = -1
if err == 0:
self.species.reac_ts_done[index] = 4
elif self.species.reac_ts_done[index] == 4:
# Do the TS and product optimization
#make a stationary point object of the ts
bond_mx = np.zeros(
(self.species.natom, self.species.natom), dtype=int)
for i in range(self.species.natom):
for j in range(self.species.natom):
bond_mx[i][j] = max(self.species.bond[i][j],
obj.product_bonds[i][j])
err, geom = self.qc.get_qc_geom(instance_name,
self.species.natom)
ts = StationaryPoint(instance_name,
self.species.charge,
self.species.mult,
atom=self.species.atom,
geom=geom,
wellorts=1)
err, ts.energy = self.qc.get_qc_energy(instance_name)
err, ts.zpe = self.qc.get_qc_zpe(instance_name)
ts.bond = bond_mx
ts.find_cycle()
ts.find_conf_dihedral()
obj.ts = ts
#do the ts optimization
obj.ts_opt = Optimize(obj.ts, self.par, self.qc)
obj.ts_opt.do_optimization()
#do the products optimizations
for st_pt in obj.products:
#check for products of other reactions that are the same as this product
#in the case such products are found, use the same Optimize object for both
new = 1
for i, inst_i in enumerate(self.species.reac_inst):
if not i == index:
obj_i = self.species.reac_obj[i]
if self.species.reac_ts_done[i] > 3:
for j, st_pt_i in enumerate(
obj_i.products):
if st_pt_i.chemid == st_pt.chemid:
if len(obj_i.prod_opt) > j:
prod_opt = obj_i.prod_opt[j]
new = 0
break
if new:
prod_opt = Optimize(st_pt, self.par, self.qc)
prod_opt.do_optimization()
obj.prod_opt.append(prod_opt)
self.species.reac_ts_done[index] = 5
elif self.species.reac_ts_done[index] == 5:
#check up on the TS and product optimizations
opts_done = 1
fails = 0
#check if ts is done
if not obj.ts_opt.shir == 1:
opts_done = 0
obj.ts_opt.do_optimization()
if obj.ts_opt.shigh == -999:
fails = 1
for pr_opt in obj.prod_opt:
if not pr_opt.shir == 1:
opts_done = 0
pr_opt.do_optimization()
if pr_opt.shigh == -999:
fails = 1
if fails:
self.species.reac_ts_done[index] = -999
elif opts_done:
self.species.reac_ts_done[index] = 6
elif self.species.reac_ts_done[index] == 6:
#Finilize the calculations
#continue to PES search in case a new well was found
if self.par.par['pes']:
#verify if product is monomolecular, and if it is new
if len(obj.products) == 1:
st_pt = obj.prod_opt[0].species
chemid = st_pt.chemid
energy = st_pt.energy
well_energy = self.species.energy
new_barrier_threshold = self.par.par[
'barrier_threshold'] - (
energy - well_energy) * constants.AUtoKCAL
dir = os.path.dirname(os.getcwd())
jobs = open(dir + '/chemids',
'r').read().split('\n')
jobs = [ji for ji in jobs]
if not str(chemid) in jobs:
#this well is new, add it to the jobs
while 1:
try:
#try to open the file and write to it
pes.write_input(
self.par, obj.products[0],
new_barrier_threshold, dir)
f = open(dir + '/chemids', 'a')
f.write('{}\n'.format(chemid))
f.close()
break
except IOError:
#wait a second and try again
time.sleep(1)
pass
#check for wrong number of negative frequencies
neg_freq = 0
for st_pt in obj.products:
if any([fi < 0. for fi in st_pt.reduced_freqs]):
neg_freq = 1
if any([fi < 0. for fi in obj.ts.reduced_freqs[1:]]):
neg_freq = 1
if neg_freq:
logging.info('\tFound negative frequency for ' +
instance_name)
self.species.reac_ts_done[index] = -999
else:
#the reaction search is finished
self.species.reac_ts_done[
index] = -1 # this is the success code
# write a temporary pes input file
# remove old xval and im_extent files
if os.path.exists('{}_xval.txt'.format(
self.species.chemid)):
os.remove('{}_xval.txt'.format(
self.species.chemid))
if os.path.exists('{}_im_extent.txt'.format(
self.species.chemid)):
os.remove('{}_im_extent.txt'.format(
self.species.chemid))
postprocess.createPESViewerInput(
self.species, self.qc, self.par)
alldone = 1
for index, instance in enumerate(self.species.reac_inst):
if any(self.species.reac_ts_done[i] >= 0
for i in range(len(self.species.reac_inst))):
alldone = 1
break
else:
alldone = 0
# write a small summary while running
wr = 1
if wr:
f_out = open('kinbot_monitor.out', 'w')
for index, instance in enumerate(self.species.reac_inst):
f_out.write('{}\t{}\t{}\n'.format(
self.species.reac_ts_done[index],
self.species.reac_step[index],
self.species.reac_obj[index].instance_name))
f_out.close()
time.sleep(1)
s = []
for index, instance in enumerate(self.species.reac_inst):
obj = self.species.reac_obj[index]
instance_name = obj.instance_name
# Write a summary on the combinatorial exploration
if 'combinatorial' in instance_name:
s.append('NAME\t' + instance_name)
# Write the bonds that were broken and formed
s.append('BROKEN_BONDS\t' +
'\t'.join('[{}, {}]'.format(re[0], re[1])
for re in obj.reac))
s.append('FORMED_BONDS\t' +
'\t'.join('[{}, {}]'.format(pr[0], pr[1])
for pr in obj.prod))
# Populate the ts_bond_lengths dict with the values
# of this reaction
if self.species.reac_ts_done[index] == -1:
for i in range(self.species.natom - 1):
for j in range(i + 1, self.species.natom):
if self.species.bond[i][j] != obj.product_bonds[i][
j]:
if (self.species.bond[i][j] == 0
or obj.product_bonds[i][j] == 0):
syms = []
syms.append(self.species.atom[i])
syms.append(self.species.atom[j])
syms = ''.join(sorted(syms))
dist = np.linalg.norm(obj.ts.geom[i] -
obj.ts.geom[j])
s.append('TS_BOND_LENGTHS\t{}\t{}'.format(
syms, dist))
# write the expected inchis
s.append('EXPECTED_INCHIS\t' +
'\t'.join(inchi for inchi in obj.prod_inchi))
# get the inchis the reaction found
if self.species.reac_ts_done[index] == -1:
inchis = obj.get_final_inchis()
s.append('FOUND_INCHIS\t' + '\t'.join(inchis))
s.append('\n')
with open('combinatorial.txt', 'w') as f:
f.write('\n'.join(s) + '\n')
logging.info("Reaction generation done!")
def find_homolytic_scissions(self):
"""
Enumerate all unique homolytic scission reactions
"""
# set of unique bonds to break
bonds = []
for i in range(len(self.species.atom) - 1):
for j in range(i + 1, len(self.species.atom)):
# only consider a bond of which both
# atoms are not in the same cycle
cycle = []
for cyc in self.species.cycle_chain:
if i in cyc:
cycle.extend(cyc)
if j not in cycle:
# only consider single bonds for homolytic scissions
if self.species.bond[i][j] == 1:
# check if a bond with identical atomids
# has been added to the bonds list yet
new = 1
for bi in bonds:
if sorted([self.species.atomid[at]
for at in bi]) == sorted([
self.species.atomid[i],
self.species.atomid[j]
]):
new = 0
if new:
bonds.append([i, j])
hs = HomolyticScission(self.species, self.par,
self.qc, [i, j])
hs.create_geometries()
self.hss.append(hs)
# optimize the products of the hss
while 1:
for index, hs in enumerate(self.hss):
if hs.status == 0:
# do the initial optimization
for prod in hs.products:
hs.qc.qc_opt(prod, prod.geom)
hs.status = 1
if hs.status == 1:
# wait for the optimization to finish
err = 0
for prod in hs.products:
e, prod.geom = hs.qc.get_qc_geom(
str(prod.chemid) + '_well', prod.natom)
if e < 0:
# optimizatin failed
hs.status = -999
err = -1
elif e != 0:
err = -1
else:
e2, prod.energy = hs.qc.get_qc_energy(
str(prod.chemid) + '_well', prod.natom)
e2, prod.zpe = hs.qc.get_qc_zpe(
str(prod.chemid) + '_well', prod.natom)
if err == 0:
hs.status = 2
if hs.status == 2:
# Do the product conf search, high level opt and HIR
for prod in hs.products:
prod_opt = Optimize(prod, self.par, self.qc)
prod_opt.do_optimization()
hs.prod_opt.append(prod_opt)
hs.status = 3
if hs.status == 3:
# check up on the optimization
opts_done = 1
fails = 0
for pr_opt in hs.prod_opt:
if not pr_opt.shir == 1:
opts_done = 0
pr_opt.do_optimization()
if pr_opt.shigh == -999:
fails = 1
if fails:
hs.status = -999
elif opts_done:
# check if the energy is higher
# than the barrier threshold
species_energy = self.species.energy
prod_energy = 0.
for pr_opt in hs.prod_opt:
prod_energy += pr_opt.species.energy
barrier = (prod_energy -
species_energy) * constants.AUtoKCAL
if barrier > self.par.par['barrier_threshold']:
hs.status = -999
else:
hs.status = -1
if all([hs.status < 0 for hs in self.hss]):
break
def generate(self):
"""
Creates the input for each reaction, runs them, and tests for success.
If successful, it creates the barrier and product objects.
It also then does the conformational search, and finally, the hindered rotor scans.
To make the code the most efficient, all of these happen in parallel, in a sense that
the jobs are not waiting for each other. E.g., one reaction can still be in the stage
of TS search, while the other can be already at the hindered rotor scan. This way,
all cores are occupied efficiently.
The switching between the various stages are done via the reac_ts_done variable.
0: initiate the TS search
1: check barrier height and errors in TS, and initiates normal mode displacement test, start the irc calculations
2: submit product optimization
3: submit the frequency calculation
4: do the optimization of the ts and the products
5: follow up on the optimizations
6: finalize calculations, check for wrong number of negative frequencies
If at any times the calculation fails, reac_ts_done is set to -999.
If all steps are successful, reac_ts_done is set to -1.
"""
deleted = []
if len(self.species.reac_inst) > 0:
alldone = 1
else:
alldone = 0
while alldone:
for index, instance in enumerate(self.species.reac_inst):
obj = self.species.reac_obj[index]
instance_name = obj.instance_name
# START REATION SEARCH
if self.species.reac_ts_done[index] == 0 and self.species.reac_step[index] == 0:
#verify after restart if search has failed in previous kinbot run
status = self.qc.check_qc(instance_name)
if status == 'error' or status == 'killed':
logging.info('\tRxn search failed (error or killed) for {}'.format(instance_name))
self.species.reac_ts_done[index] = -999
if self.species.reac_ts_done[index] == 0: # ts search is ongoing
if obj.scan == 0: #don't do a scan of a bond
if self.species.reac_step[index] == obj.max_step + 1:
status = self.qc.get_qc_freq(instance_name, self.species.natom)[0]
if status == 0:
self.species.reac_ts_done[index] = 1
elif status == -1:
logging.info('\tRxn search failed for {}'.format(instance_name))
self.species.reac_ts_done[index] = -999
else:
self.species.reac_step[index] = reac_family.carry_out_reaction(obj, self.species.reac_step[index], self.par.par['qc_command'])
else: # do a bond scan
if self.species.reac_step[index] == self.par.par['scan_step'] + 1:
status = self.qc.get_qc_freq(instance_name, self.species.natom)[0]
if status == 0:
self.species.reac_ts_done[index] = 1
elif status == -1:
logging.info('\tRxn search failed for {}'.format(instance_name))
self.species.reac_ts_done[index] = -999
else:
if self.species.reac_step[index] == 0:
self.species.reac_step[index] = reac_family.carry_out_reaction(obj, self.species.reac_step[index], self.par.par['qc_command'])
elif self.species.reac_step[index] > 0:
status = self.qc.check_qc(instance_name)
if status == 'error' or status == 'killed':
logging.info('\tRxn search failed for {}'.format(instance_name))
self.species.reac_ts_done[index] = -999
else:
err, energy = self.qc.get_qc_energy(instance_name)
if err == 0:
self.species.reac_scan_energy[index].append(energy)
if len(self.species.reac_scan_energy[index]) > 1:
if self.species.reac_scan_energy[index][-1] < self.species.reac_scan_energy[index][-2]:
self.species.reac_step[index] = self.par.par['scan_step']
self.species.reac_step[index] = reac_family.carry_out_reaction(obj, self.species.reac_step[index], self.par.par['qc_command'])
elif self.species.reac_ts_done[index] == 1:
status = self.qc.check_qc(instance_name)
if status == 'running': continue
elif status == 'error':
logging.info('\tRxn search failed (gaussian error) for {}'.format(instance_name))
self.species.reac_ts_done[index] = -999
else:
#check the barrier height:
if self.species.reac_type[index] == 'R_Addition_MultipleBond':
sp_energy = self.qc.get_qc_energy(str(self.species.chemid) + '_well_mp2')[1]
barrier = (self.qc.get_qc_energy(instance_name)[1] - sp_energy) * constants.AUtoKCAL
else:
sp_energy = self.qc.get_qc_energy(str(self.species.chemid) + '_well')[1]
barrier = (self.qc.get_qc_energy(instance_name)[1] - sp_energy) * constants.AUtoKCAL
if barrier > self.par.par['barrier_threshold']:
logging.info('\tRxn barrier too high ({val}) for {name}'.format(val=barrier,name=instance_name))
self.species.reac_ts_done[index] = -999
else:
obj.irc = IRC(obj, self.par) #TODO: this doesn't seem like a good design
irc_status = obj.irc.check_irc()
if 0 in irc_status:
# No IRC started yet, start the IRC now
logging.info('\tStarting IRC calculations for {}'.format(instance_name))
obj.irc.do_irc_calculations()
elif irc_status[0] == 'running' or irc_status[1] == 'running':
continue
else:
#IRC's have succesfully finished, have an error or were killed, in any case
#read the geometries and try to make products out of them
#verify which of the ircs leads back to the reactant, if any
prod = obj.irc.irc2stationary_pt()
if prod == 0:
logging.info('\t\tNo product found for {}'.format(instance_name))
self.species.reac_ts_done[index] = -999
else:
#IRC's are done
obj.products = prod
obj.product_bonds = prod.bond
self.species.reac_ts_done[index] = 2
elif self.species.reac_ts_done[index] == 2:
#identify bimolecular products and wells
fragments, maps = obj.products.start_multi_molecular()
obj.products = []
for i, frag in enumerate(fragments):
obj.products.append(frag)
self.qc.qc_opt(frag, frag.geom)
self.species.reac_ts_done[index] = 3
elif self.species.reac_ts_done[index] == 3:
#wait for the optimization to finish
err = 0
for st_pt in obj.products:
chemid = st_pt.chemid
orig_geom = copy.deepcopy(st_pt.geom)
e, st_pt.geom = self.qc.get_qc_geom(str(st_pt.chemid) + '_well', st_pt.natom)
if e < 0:
logging.info('\tProduct optimization failed for {}, product {}'.format(instance_name,st_pt.chemid))
self.species.reac_ts_done[index] = -999
err = -1
elif e != 0:
err = -1
else:
e2, st_pt.energy = self.qc.get_qc_energy(str(st_pt.chemid) + '_well')
e2, st_pt.zpe = self.qc.get_qc_zpe(str(st_pt.chemid) + '_well')
st_pt.bond_mx()
st_pt.characterize(0) # not allowed to use the dimer option here
st_pt.calc_chemid()
if chemid != st_pt.chemid:
# product was optimized to another structure, give warning and remove this reaction
logging.info('\tProduct optimizatied to other structure for {}, product {} to {}'.format(instance_name,chemid,st_pt.chemid))
self.species.reac_ts_done[index] = -999
err = -1
if err == 0:
self.species.reac_ts_done[index] = 4
elif self.species.reac_ts_done[index] == 4:
# Do the TS and product optimization
#make a stationary point object of the ts
bond_mx = np.zeros((self.species.natom, self.species.natom), dtype=int)
for i in range(self.species.natom):
for j in range(self.species.natom):
bond_mx[i][j] = max(self.species.bond[i][j],obj.product_bonds[i][j])
err, geom = self.qc.get_qc_geom(instance_name, self.species.natom)
ts = StationaryPoint( instance_name, self.species.charge, self.species.mult,
atom = self.species.atom, geom = geom, wellorts = 1)
err, ts.energy = self.qc.get_qc_energy(instance_name)
err, ts.zpe = self.qc.get_qc_zpe(instance_name)
ts.bond = bond_mx
ts.find_cycle()
ts.find_conf_dihedral()
obj.ts = ts
#do the ts optimization
obj.ts_opt = Optimize(obj.ts,self.par,self.qc)
obj.ts_opt.do_optimization()
#do the products optimizations
for st_pt in obj.products:
#check for products of other reactions that are the same as this product
#in the case such products are found, use the same Optimize object for both
new = 1
for i, inst_i in enumerate(self.species.reac_inst):
if not i == index:
obj_i = self.species.reac_obj[i]
if self.species.reac_ts_done[i] > 3:
for j,st_pt_i in enumerate(obj_i.products):
if st_pt_i.chemid == st_pt.chemid:
if len(obj_i.prod_opt) > j:
prod_opt = obj_i.prod_opt[j]
new = 0
break
if new:
prod_opt = Optimize(st_pt,self.par,self.qc)
prod_opt.do_optimization()
obj.prod_opt.append(prod_opt)
self.species.reac_ts_done[index] = 5
elif self.species.reac_ts_done[index] == 5:
#check up on the TS and product optimizations
opts_done = 1
fails = 0
#check if ts is done
if not obj.ts_opt.shir == 1:
opts_done = 0
obj.ts_opt.do_optimization()
if obj.ts_opt.shigh == -999:
fails = 1
for pr_opt in obj.prod_opt:
if not pr_opt.shir == 1:
opts_done = 0
pr_opt.do_optimization()
if pr_opt.shigh == -999:
fails = 1
if fails:
self.species.reac_ts_done[index] = -999
elif opts_done:
self.species.reac_ts_done[index] = 6
elif self.species.reac_ts_done[index] == 6:
#Finilize the calculations
#continue to PES search in case a new well was found
if self.par.par['pes']:
#verify if product is monomolecular, and if it is new
if len(obj.products) ==1:
st_pt = obj.prod_opt[0].species
chemid = st_pt.chemid
energy = st_pt.energy
well_energy = self.species.energy
new_barrier_threshold = self.par.par['barrier_threshold'] - (energy-well_energy)*constants.AUtoKCAL
dir = os.path.dirname(os.getcwd())
jobs = open(dir+'/chemids','r').read().split('\n')
jobs = [ji for ji in jobs]
if not str(chemid) in jobs:
#this well is new, add it to the jobs
while 1:
try:
#try to open the file and write to it
pes.write_input(self.par,obj.products[0],new_barrier_threshold,dir)
f = open(dir+'/chemids','a')
f.write('{}\n'.format(chemid))
f.close()
break
except IOError:
#wait a second and try again
time.sleep(1)
pass
#check for wrong number of negative frequencies
neg_freq = 0
for st_pt in obj.products:
if any([fi < 0. for fi in st_pt.reduced_freqs]):
neg_freq = 1
if any([fi < 0. for fi in obj.ts.reduced_freqs[1:]]):
neg_freq = 1
if neg_freq:
logging.info('\tFound negative frequency for ' + instance_name)
self.species.reac_ts_done[index] = -999
else:
#the reaction search is finished
self.species.reac_ts_done[index] = -1 # this is the success code
# write a temporary pes input file
# remove old xval and im_extent files
if os.path.exists('{}_xval.txt'.format(self.species.chemid)):
os.remove('{}_xval.txt'.format(self.species.chemid))
if os.path.exists('{}_im_extent.txt'.format(self.species.chemid)):
os.remove('{}_im_extent.txt'.format(self.species.chemid))
postprocess.createPESViewerInput(self.species, self.qc, self.par)
elif self.species.reac_ts_done[index] == -999:
if not self.species.reac_obj[index].instance_name in deleted:
self.delete_files(self.species.reac_obj[index].instance_name)
deleted.append(self.species.reac_obj[index].instance_name)
alldone = 1
for index, instance in enumerate(self.species.reac_inst):
if any(self.species.reac_ts_done[i] >= 0 for i in range(len(self.species.reac_inst))):
alldone = 1
break
else:
alldone = 0
# write a small summary while running
wr = 1
if wr:
f_out = open('kinbot_monitor.out','w')
for index, instance in enumerate(self.species.reac_inst):
f_out.write('{}\t{}\t{}\n'.format(self.species.reac_ts_done[index],self.species.reac_step[index],self.species.reac_obj[index].instance_name))
f_out.close()
time.sleep(1)
s = []
for index, instance in enumerate(self.species.reac_inst):
obj = self.species.reac_obj[index]
instance_name = obj.instance_name
# Write a summary on the combinatorial exploration
if 'combinatorial' in instance_name:
s.append('NAME\t' + instance_name)
# Write the bonds that were broken and formed
s.append('BROKEN_BONDS\t' + '\t'.join('[{}, {}]'.format(re[0], re[1]) for re in obj.reac))
s.append('FORMED_BONDS\t' + '\t'.join('[{}, {}]'.format(pr[0], pr[1]) for pr in obj.prod))
# Populate the ts_bond_lengths dict with the values
# of this reaction
if self.species.reac_ts_done[index] == -1:
for i in range(self.species.natom - 1):
for j in range(i + 1, self.species.natom):
if self.species.bond[i][j] != obj.product_bonds[i][j]:
if (self.species.bond[i][j] == 0 or
obj.product_bonds[i][j] == 0):
syms = []
syms.append(self.species.atom[i])
syms.append(self.species.atom[j])
syms = ''.join(sorted(syms))
dist = np.linalg.norm(obj.ts.geom[i] - obj.ts.geom[j])
s.append('TS_BOND_LENGTHS\t{}\t{}'.format(syms, dist))
# write the expected inchis
s.append('EXPECTED_INCHIS\t' + '\t'.join(inchi for inchi in obj.prod_inchi))
# get the inchis the reaction found
if self.species.reac_ts_done[index] == -1:
inchis = obj.get_final_inchis()
s.append('FOUND_INCHIS\t' + '\t'.join(inchis))
s.append('\n')
with open('combinatorial.txt', 'w') as f:
f.write('\n'.join(s) + '\n')
logging.info("Reaction generation done!")