for this_sim in simulations:
for this_atom_pair in atom_pairs:
this_lig = []
for this_traj in [this_sim]:
this_lig.extend(
md_dist.compute_distances(this_traj, [this_atom_pair]))
distances.append(this_lig)
dist_path = '/home/shenglan/TryMSMbuilder/output/ten_ligands/dist_to_binding'\
+'_s'+str(LOAD_STRIDE)+'.out'
pickle.dump(distances, open(dist_path, 'wb'))
# get N positions
sequences_all = []
for this_sim in simulations:
this_seq = util.featurize_RawPos(inds_N, [this_sim])
sequences_all.extend(this_seq)
seq_path = '/home/shenglan/TryMSMbuilder/output/ten_ligands/sequences' + '_s' + str(
LOAD_STRIDE) + '.out'
pickle.dump(sequences_all, open(seq_path, 'wb'))
clustering = KCenters(n_clusters=N_CLUSTER)
geo_assign = clustering.fit_predict(sequences_all)
centers = clustering.cluster_centers_
geo_assign_path = '/home/shenglan/TryMSMbuilder/output/ten_ligands/KC_geoassign_c' \
+str(N_CLUSTER)+'_s'+str(LOAD_STRIDE)+'.out'
pickle.dump(geo_assign, open(geo_assign_path, 'wb'))
micro_msm = MarkovStateModel(lag_time=1,
reversible_type='transpose',
inds.append(iis)
#track residue Aps113
first_res = str(simulations[0][0].topology.chain(0).residue(0))
import re
match = re.match(r"([a-z]+)([0-9]+)", first_res, re.I)
if match:
items = match.groups()
first_res_number = int(items[-1])
target_res = simulations[0][0].topology.chain(0).residue(113-first_res_number)
res_ind = [atom.index for atom in target_res.atoms if atom.name in ['OD1']]
#sequences of coordinates of ligand aromatic ring and Aps113
sequences_all = []
for this_sim in simulations:
this_seq = util.featurize_RawPos(inds,this_sim)
sequences_all.extend(this_seq)
#print len(sequences_all)
#print sequences_all[-1].shape
#average position of Asp113
#res_pos_ave = np.mean(res_pos_A_1[0],axis = 0)
#
time_step = util.calc_time_step(times_path,stride = LOAD_STRIDE)
#
clustering = KCenters(n_clusters = 10)
assignments = clustering.fit_predict(sequences_all)
centers = clustering.cluster_centers_
#print len(assignments)
ligands = ['ALP%d' % (ii + 1) for ii in range(10)]
print ligands
print test_traj[0].topology.chain(0).atom(4667).residue
for ligand in ligands:
iis = [
atom.index for atom in test_traj[0].topology.chain(0).atoms if
atom.element.symbol in atoms_to_track and str(atom.residue) == ligand
]
inds_N.append(iis)
# inds_N = [[atom.index] for atom in test_traj[0].topology.chain(0).atoms if atom.element.symbol in atoms_to_track
# and atom.residue.name== 'ALP']
print inds_N
test_seq = util.featurize_RawPos(inds_N, test_traj)
print test_seq[0][0]
print test_seq[1][0]
for atom_idx in inds_N:
print(tuple(test_traj[0].xyz[0, atom_idx, :]))
print(tuple(test_traj[0].xyz[0, 4979, :]))
print test_traj[0]
#
# test_traj2 = md.load_dcd(parent_dir + run_dirs[0] + '/' + files[0]
# , top = '/home/shenglan/topologies/test.pdb'
# , stride = LOAD_STRIDE
# )
#
inds_N.append(iis)
inds_all = [] #indices of all atoms, separated by ligands
for ligand in ligands:
iis = [
atom.index for atom in simulations[0][0].topology.chain(0).atoms
if str(atom.residue) == ligand
]
inds_all.append(iis)
# #sequences of coordinates of ligands and Aps113
total_frames = 0
sequences_all = []
for this_sim in simulations:
if use_COM:
this_seq = util.featurize_RawPos(inds_all, this_sim, average=True)
else:
this_seq = util.featurize_RawPos(inds_N, this_sim)
total_frames = this_seq[0].shape[0] * 10 + total_frames
sequences_all.extend(this_seq)
print('the total number of conformations we are clustering is %d.' %
total_frames)
time_step = util.calc_time_step(times_path, stride=LOAD_STRIDE)
clustering = KCenters(n_clusters=N_CLUSTER)
assignments = clustering.fit_predict(sequences_all)
centers = clustering.cluster_centers_
#
# print len(assignments)
# print assignments[1].shape
for ligand in ligands:
iis = [atom.index for atom in simulations[0][0].topology.chain(0).atoms if atom.element.symbol in atoms_to_track
and atom.residue == ligand]
inds_N.append(iis)
inds_all = [] #indices of all atoms, separated by ligands
for ligand in ligands:
iis = [atom.index for atom in simulations[0][0].topology.chain(0).atoms if atom.residue == ligand]
inds_all.append(iis)
#sequences of coordinates of ligands and Aps113
total_frames = 0
sequences_all = []
for this_sim in simulations:
if use_COM:
this_seq = util.featurize_RawPos(inds_all,this_sim,average = True)
else:
this_seq = util.featurize_RawPos(inds_N,this_sim)
total_frames = this_seq[0].shape[0]*10+total_frames
sequences_all.extend(this_seq)
print('the total number of conformations we are clustering is %d.' % total_frames)
# print len(sequences_all)
# print sequences_all[-1].shape
# res_pos = []
# res_pos_ave =[]
# total_frames = 0
# for this_sim in simulations:
# this_seq = util.featurize_RawPos(res_ind,this_sim)
distances = []
for this_sim in simulations:
for this_atom_pair in atom_pairs:
this_lig = []
for this_traj in [this_sim]:
this_lig.extend(md_dist.compute_distances(this_traj,[this_atom_pair]))
distances.append(this_lig)
dist_path = '/home/shenglan/TryMSMbuilder/output/ten_ligands/dist_to_binding'\
+'_s'+str(LOAD_STRIDE)+'.out'
pickle.dump(distances,open(dist_path,'wb'))
# get N positions
sequences_all = []
for this_sim in simulations:
this_seq = util.featurize_RawPos(inds_N,[this_sim])
sequences_all.extend(this_seq)
seq_path = '/home/shenglan/TryMSMbuilder/output/ten_ligands/sequences'+'_s'+str(LOAD_STRIDE)+'.out'
pickle.dump(sequences_all,open(seq_path,'wb'))
clustering = KCenters(n_clusters = N_CLUSTER)
geo_assign = clustering.fit_predict(sequences_all)
centers = clustering.cluster_centers_
geo_assign_path = '/home/shenglan/TryMSMbuilder/output/ten_ligands/KC_geoassign_c' \
+str(N_CLUSTER)+'_s'+str(LOAD_STRIDE)+'.out'
pickle.dump(geo_assign,open(geo_assign_path,'wb'))
micro_msm = MarkovStateModel(lag_time=1, reversible_type = 'transpose',
ergodic_cutoff = 'off'
,verbose=True).fit(geo_assign)
inds_N =[] #indices of N atom
atoms_to_track =['N']
ligands = ['ALP%d'%(ii+1) for ii in range(10)]
print ligands
print test_traj[0].topology.chain(0).atom(4667).residue
for ligand in ligands:
iis = [atom.index for atom in test_traj[0].topology.chain(0).atoms if atom.element.symbol in atoms_to_track
and str(atom.residue)==ligand]
inds_N.append(iis)
# inds_N = [[atom.index] for atom in test_traj[0].topology.chain(0).atoms if atom.element.symbol in atoms_to_track
# and atom.residue.name== 'ALP']
print inds_N
test_seq = util.featurize_RawPos(inds_N,test_traj)
print test_seq[0][0]
print test_seq[1][0]
for atom_idx in inds_N:
print(tuple(test_traj[0].xyz[0, atom_idx,:]))
print(tuple(test_traj[0].xyz[0, 4979,:]))
print test_traj[0]
#
# test_traj2 = md.load_dcd(parent_dir + run_dirs[0] + '/' + files[0]
# , top = '/home/shenglan/topologies/test.pdb'
# , stride = LOAD_STRIDE
# )
#
