def generate_dhl_samples(self,MaxNa=25,fmax=0.005,fpref='dhl_scan-', freqname="vib."):
ts = ani_tortion_scanner(self.ens, fmax)
dhls = self.get_index_set(self.smiles, self.Nmol, MaxNa=MaxNa)
for i, dhl in enumerate(dhls):
mol = dhl[0]
X, S, p, e, s = ts.tortional_sampler(mol, self.Nsamp, dhl[1], 10.0, 36, sigma=self.sigma, rng=self.rng, freqname=freqname)
if e.size > 0:
comment = Chem.MolToSmiles(dhl[0]) + '[' + ' '.join([str(j) for j in dhl[1]]) + ']'
comment = [comment for i in range(e.size * self.Nsamp)]
hdt.writexyzfilewc(self.storedir + fpref + str(i).zfill(3) + '.xyz', xyz=X, typ=S, cmt=comment)
def mol_dyn_sampling(self,md_work, i, N, T1, T2, dt, Nc, Ns, sig, gpuid):
activ = aat.moldynactivelearning(self.netdict['cnstfile'],
self.netdict['saefile'],
self.netdict['nnfprefix'],
self.netdict['num_nets'],
gpuid)
difo = open(self.ldtdir + self.datdir + '/info_data_mdso-'+str(i)+'.nfo', 'w')
Nmol = 0
dnfo = 'MD Sampler running: ' + str(md_work.size)
difo.write(dnfo + '\n')
Nmol = md_work.size
ftme_t = 0.0
for di, id in enumerate(md_work):
data = hdt.read_rcdb_coordsandnm(id)
#print(di, ') Working on', id, '...')
S = data["species"]
if "charge" in data and "multip" in data:
chg = data["charge"]
mlt = data["multip"]
else:
chg = "0"
mlt = "1"
# Set mols
activ.setmol(data["coordinates"], S)
# Generate conformations
X = activ.generate_conformations(N, T1, T2, dt, Nc, Ns, dS=sig)
ftme_t += activ.failtime
nfo = activ._infostr_
m = id.rsplit('/',1)[1].rsplit('.',1)[0]
difo.write(' -' + m + ': ' + nfo + '\n')
difo.flush()
#print(nfo)
if X.size > 0:
hdt.writexyzfilewc(self.cdir + 'mds_' + m.split('.')[0] + '_' + str(i).zfill(2) + str(di).zfill(4) + '.xyz', X, S, ' '+chg+' '+mlt)
difo.write('Complete mean fail time: ' + "{:.2f}".format(ftme_t / float(Nmol)) + '\n')
print(Nmol)
del activ
difo.close()
def prepare_confs_iso(self):
prefix = 'ad'
confs_dir = self.ldtdir + self.datdir + '/confs/'
isoms_dir = self.ldtdir + self.datdir + '/confs_iso/'
files = os.listdir(confs_dir)
files = [f for f in files if f.rsplit('.', maxsplit=1)[-1] == 'xyz']
#print(len(files))
ds = dict()
of = open(self.ldtdir + self.datdir + '/info_confstoiso_map.dat', 'w')
for i, f in enumerate(files):
#print(confs_dir + f)
X, S, N, C = hdt.readxyz2(confs_dir + f)
S = np.array(S)
idx = sorted(range(len(S)), key=lambda k: S[k])
S = S[np.array(idx)]
for j, x in enumerate(X):
X[j] = x[idx]
id = "".join(S)
if id in ds:
sid = len(ds[id])
of.write(f + ' ' + convert_eformula(S) + ' ' + str(sid) + ' ' +
str(X.shape[0]) + '\n')
ds[id].append((X, S, C))
else:
of.write(f + ' ' + convert_eformula(S) + ' ' + str(0) + ' ' +
str(X.shape[0]) + '\n')
ds.update({id: [(X, S, C)]})
of.close()
Nt = 0
for i in ds.keys():
X = []
S = []
C = []
for j in ds[i]:
X.append(j[0])
S.append(j[1])
C.extend(j[2])
X = np.vstack(X)
S = list(S[0])
N = X.shape[0]
Nt += N
if N < 40:
#print(type(S), S)
fn = prefix + '_' + convert_eformula(S) + '-' + str(N).zfill(
3) + '.xyz'
#print('Writing: ', fn)
hdt.writexyzfilewc(isoms_dir + '/' + fn, X, S, C)
else:
Nsplit = int(math.ceil(N / float(40)))
X = np.array_split(X, Nsplit)
C = np.array_split(np.array(C), Nsplit)
for l, (x, c) in enumerate(zip(X, C)):
fn = prefix + '_' + convert_eformula(S) + '_' + str(
l).zfill(2) + '-' + str(x.shape[0]).zfill(3) + '.xyz'
hdt.writexyzfilewc(isoms_dir + '/' + fn, x, S, c)
def normal_mode_sampling(self, T, Ngen, Nkep, maxd, sig, gpuid):
of = open(self.ldtdir + self.datdir + '/info_data_nms.nfo', 'w')
aevsize = self.netdict['aevsize']
anicv = aat.anicrossvalidationconformer(self.netdict['cnstfile'],
self.netdict['saefile'],
self.netdict['nnfprefix'],
self.netdict['num_nets'],
[gpuid], False)
dc = aat.diverseconformers(self.netdict['cnstfile'],
self.netdict['saefile'],
self.netdict['nnfprefix'] + '0/networks/',
aevsize, gpuid, False)
Nkp = 0
Nkt = 0
Ntt = 0
idx = 0
for di, id in enumerate(self.idir):
of.write(
str(di) + ' of ' + str(len(self.idir)) + ') dir: ' + str(id) +
'\n')
#print(di,'of',len(self.idir),') dir:', id)
files = os.listdir(id)
files.sort()
Nk = 0
Nt = 0
for fi, f in enumerate(files):
print(f)
data = hdt.read_rcdb_coordsandnm(id + f)
#print(id+f)
spc = data["species"]
xyz = data["coordinates"]
nmc = data["nmdisplacements"]
frc = data["forceconstant"]
if "charge" in data and "multip" in data:
chg = data["charge"]
mlt = data["multip"]
else:
chg = "0"
mlt = "1"
nms = nmt.nmsgenerator(xyz,
nmc,
frc,
spc,
T,
minfc=5.0E-2,
maxd=maxd)
conformers = nms.get_Nrandom_structures(Ngen)
if conformers.shape[0] > 0:
if conformers.shape[0] > Nkep:
ids = dc.get_divconfs_ids(conformers, spc, Ngen, Nkep,
[])
conformers = conformers[ids]
sigma = anicv.compute_stddev_conformations(conformers, spc)
sid = np.where(sigma > sig)[0]
Nt += sigma.size
Nk += sid.size
if 100.0 * sid.size / float(Ngen) > 0:
Nkp += sid.size
cfn = f.split('.')[0].split('-')[0] + '_' + str(
idx).zfill(5) + '-' + f.split('.')[0].split(
'-')[1] + '_2.xyz'
cmts = [' ' + chg + ' ' + mlt for c in range(Nk)]
hdt.writexyzfilewc(self.cdir + cfn, conformers[sid],
spc, cmts)
idx += 1
Nkt += Nk
Ntt += Nt
of.write(' -Total: ' + str(Nk) + ' of ' + str(Nt) +
' percent: ' + "{:.2f}".format(100.0 * Nk / Nt) + '\n')
of.flush()
#print(' -Total:',Nk,'of',Nt,'percent:',"{:.2f}".format(100.0*Nk/Nt))
del anicv
del dc
of.write('\nGrand Total: ' + str(Nkt) + ' of ' + str(Ntt) +
' percent: ' + "{:.2f}".format(100.0 * Nkt / Ntt) + ' Kept ' +
str(Nkp) + '\n')
#print('\nGrand Total:', Nkt, 'of', Ntt,'percent:',"{:.2f}".format(100.0*Nkt/Ntt), 'Kept',Nkp)
of.close()
def structural_sampling(self, N, sig, gpuid):
of = open(self.ldtdir + self.datdir + '/info_data_strucs.nfo', 'w')
aevsize = self.netdict['aevsize']
anicv = aat.anicrossvalidationconformer(self.netdict['cnstfile'],
self.netdict['saefile'],
self.netdict['nnfprefix'],
self.netdict['num_nets'],
[gpuid], False)
dc = aat.diverseconformers(self.netdict['cnstfile'],
self.netdict['saefile'],
self.netdict['nnfprefix']+'0/networks/',
aevsize,
gpuid, False)
files = os.listdir(self.strucsfolder)
files.sort()
Nkt = 0
Ntt = 0
cnt = 0
for fi,f in enumerate(files):
print(f)
fil = open(self.strucsfolder+f,'r')
lines = fil.readlines()
fil.close()
nlines = len(lines)
# Reading all conformations
nat = int(lines[0])
nconfs=int(round(len(lines)/(nat+2)))
crds=[]
for conf in range(nconfs):
crd =[]
if (conf==0):
if (not re.search("Charge:",lines[1]) or not re.search("Mul:",lines[1])):
raise ValueError('Error: the first comment line in %s must have charge and multiplicity. Please add something like " Charge: 0 Mul: 1 "'%(self.strucsfolder+f))
chg = lines[1].split("Charge:")[1].split()[0]
mul = lines[1].split("Mul:")[1].split()[0]
spc = []
for i in range(nat):
var = lines[conf*(nat+2)+2+i].split()
spc.append(var[0])
crd.append([float(var[1]),float(var[2]),float(var[3])])
else:
for i in range(nat):
var = lines[conf*(nat+2)+2+i].split()
crd.append([float(var[1]),float(var[2]),float(var[3])])
crds.append(crd)
# Select up to N random structures, if needed
if (nconfs>N):
list=[]
for i in range(N):
num=np.random.random_integers(0,nconfs-1)
while(num in list):
num=num=np.random.random_integers(0,nconfs-1)
list.append(num)
ncrds=[]
for i in sorted(list):
ncrds.append(crds[i])
del crds
crds=ncrds
del ncrds
# Converting list to numpy array
crds=np.asarray(crds, dtype=np.float32)
# Filter by QBC
sigma = anicv.compute_stddev_conformations(crds,spc)
sid = np.where( sigma > sig )[0]
Ntt += sigma.size
Nkt += sid.size
of.write(str(cnt+1)+' of '+str(len(files))+') file: '+ str(self.strucsfolder+f) +'\n')
of.write(' -Total: '+str(sid.size)+' of '+str(sigma.size)+' percent: '+"{:.2f}".format(100.0*sid.size/sigma.size)+'\n')
of.flush()
if sid.size > 0:
cfn = f.split('.')[0]+'_strucs.xyz'
cmts = [' '+chg+' '+mul for c in range(sid.size)]
hdt.writexyzfilewc(self.cdir+cfn,crds[sid],spc,cmts)
cnt += 1
of.write('\nGrand Total: '+ str(Nkt)+ ' of '+ str(Ntt)+' percent: '+"{:.2f}".format(100.0*Nkt/Ntt)+'\n')
of.close()
def __fragmentbox__(self, file, sighat):
self.X = self.mol.get_positions()
self.frag_list = []
self.Nd = 0
self.Nt = 0
self.maxsig = 0
CUT = 7.0
for i in range(len(self.Na)):
si = self.ctd[i][2]
di = self.ctd[i][1]
Nai = self.Na[i]
Xi = self.X[si:si + Nai, :]
Xci = np.sum(Xi, axis=0) / Nai
if np.all(Xci > CUT + di) and np.all(Xci <= self.L - (CUT + di)):
#if np.all(Xci > di) and np.all(Xci <= self.L-di):
Xf = Xi
Sf = self.S[si:si + Nai]
Nmax = np.random.randint(100, 101)
Nmol = 0
ridx = np.arange(len(self.Na))
np.random.shuffle(ridx)
for j in ridx:
if i != j:
sj = self.ctd[j][2]
dj = self.ctd[j][1]
Naj = self.Na[j]
Xcj = np.sum(self.X[sj:sj + Naj, :], axis=0) / Naj
Xj = self.X[sj:sj + Naj, :]
if np.all(Xcj > dj) and np.all(Xcj < self.L - dj):
dc = np.linalg.norm(Xci - Xcj)
if dc < di + dj + CUT:
minl = 10.0
for ii in range(Nai):
Xiii = Xi[ii]
for jj in range(Naj):
Xjjj = Xj[jj]
v = np.linalg.norm(Xiii - Xjjj)
if v < minl:
minl = v
#inc = np.random.uniform(0.0, 4.0)
#if minl < 2.0+inc and minl > 0.0+inc:
if minl < CUT and minl > 0.5:
Xf = np.vstack([Xf, Xj])
Sf.extend(self.S[sj:sj + Naj])
Nmol += 1
if Nmol >= Nmax:
break
Xcf = np.sum(Xf, axis=0) / float(len(Sf))
Xf = Xf
E = np.empty(len(self.aens.ncl), dtype=np.float64)
for idx, nc in enumerate(self.aens.ncl):
nc.setMolecule(coords=np.array(Xf, dtype=np.float32),
types=Sf)
E[idx] = nc.energy()[0]
sig = np.std(hdn.hatokcal * E) / np.sqrt(Nai + Naj)
#print('Mol(',i,'): sig=',sig)
self.Nt += 1
if sig > sighat:
if sig > self.maxsig:
self.maxsig = sig
self.Nd += 1
hdn.writexyzfilewc(file + str(i).zfill(4) + '.xyz',
Xf.reshape(1, Xf.shape[0], 3),
Sf,
cmt=['sigma:' + str(sig)])
self.frag_list.append(dict({'coords': Xf, 'spec': Sf}))