def sample_region(
data,
pt_dict,
n_frames,
):
"""Function to sample a region of the data.
Parameters
----------
data : list of lists
List of low dimensional data(output of tica)
pt_dict : dict
Dictionary where the keys are the dimensions and the
value is the value of the dimension.
pt = {0:0.15, 4:0.2}
n_frames: int
Number of frames required
Returns
-------
list of tuples where first number is the trajectory index and
second is the frame index
"""
dimensions = list(pt_dict.keys())
d_data = [i[:, dimensions] for i in data]
tree = KDTree(d_data)
pt = [pt_dict[i] for i in dimensions]
dis, ind = tree.query(pt, n_frames)
return ind
def sample_region(data, pt_dict, n_frames,):
"""Function to sample a region of the data.
Parameters
----------
data : list of lists
List of low dimensional data(output of tica)
pt_dict : dict
Dictionary where the keys are the dimensions and the
value is the value of the dimension.
pt = {0:0.15, 4:0.2}
n_frames: int
Number of frames required
Returns
-------
list of tuples where first number is the trajectory index and
second is the frame index
"""
dimensions = list(pt_dict.keys())
d_data = [i[:, dimensions] for i in data]
tree = KDTree(d_data)
pt = [pt_dict[i] for i in dimensions]
dis, ind = tree.query(pt, n_frames)
return ind
def sample_dimension(data, dimension, n_frames, scheme="linear"):
"""Function to sample a dimension of the data
using one of 3 schemes. All other dimensions are ignored.
Parameters
----------
data : list of lists
List of low dimensional data(output of tica)
dimension : int
dimension to sample on
n_frames: int
Number of frames required
scheme: string
One of either "linear", "random" or "edges". Linear
samples the tic linearly, random samples randomly
thereby taking approximate free energies into account,
and edges samples the edges of the tic only.
Returns
-------
list of tuples where first number is the trajectory index and
second is the frame index
"""
d_data = [i[:, dimension][:, np.newaxis] for i in data]
#sort it because all three sampling schemes use it
all_vals = []
for i in d_data:
all_vals.extend(i.flatten())
all_vals = np.sort(all_vals)
#get lineraly placed points
if scheme == "linear":
max_val = all_vals[-1]
min_val = all_vals[0]
spaced_points = np.linspace(min_val, max_val, n_frames)
elif scheme == "random":
spaced_points = np.sort(np.random.choice(all_vals, n_frames))
elif scheme == "edge":
_cut_point = np.int(n_frames / 2)
spaced_points = np.hstack(
(all_vals[:_cut_point], all_vals[-_cut_point:]))
else:
raise ValueError("Scheme has be to one of linear, random or edge")
tree = KDTree(d_data)
return_vec = []
for pt in spaced_points:
dis, ind = tree.query([pt])
return_vec.append(ind)
return return_vec
def sample_dimension(data, dimension, n_frames, scheme="linear"):
"""Function to sample a dimension of the data
using one of 3 schemes. All other dimensions are ignored.
Parameters
----------
data : list of lists
List of low dimensional data(output of tica)
dimension : int
dimension to sample on
n_frames: int
Number of frames required
scheme: string
One of either "linear", "random" or "edges". Linear
samples the tic linearly, random samples randomly
thereby taking approximate free energies into account,
and edges samples the edges of the tic only.
Returns
-------
list of tuples where first number is the trajectory index and
second is the frame index
"""
d_data = [i[:,dimension][:,np.newaxis] for i in data]
#sort it because all three sampling schemes use it
all_vals = []
for i in d_data:
all_vals.extend(i.flatten())
all_vals = np.sort(all_vals)
#get lineraly placed points
if scheme=="linear":
max_val = all_vals[-1]
min_val = all_vals[0]
spaced_points = np.linspace(min_val, max_val, n_frames)
elif scheme=="random":
spaced_points = np.sort(np.random.choice(all_vals, n_frames))
elif scheme=="edge":
_cut_point = np.int(n_frames / 2)
spaced_points = np.hstack((all_vals[:_cut_point], all_vals[-_cut_point:]))
else:
raise ValueError("Scheme has be to one of linear, random or edge")
tree = KDTree(d_data)
return_vec = []
for pt in spaced_points:
dis, ind = tree.query([pt])
return_vec.append(ind)
return return_vec
def kdtree_maker(prt, stride=1):
key_list = list(prt.tica_data.keys())[::stride]
data = [prt.tica_data[i] for i in key_list]
tree = KDTree(data)
return key_list, tree
msm_mdl = ContinuousTimeMSM(lag_time=10,ergodic_cutoff=1/10)
assignments.fit_with(msm_mdl)
msm_mdl.percent_retained_
### CALCULATING 10 MOST POPULATED CONFORMATIONS
f=open("msm_mdl.pkl",'wb')
pickle.dump({k: msm_mdl.__dict__[k] for k in ['lag_time','n_timescales','ergodic_cutoff','verbose','sliding_window','guess','theta_','ratemat_','transmat_','countsmat_','n_states_',
'mapping_','populations_','information_','loglikelihoods_','eigenvalues_','left_eigenvectors_','right_eigenvectors_','percent_retained_'] }, f)
f.close()
q=msm_mdl.__dict__.get('populations_')
ind=np.argpartition(q, -10)[-10:]
p=ind[np.argsort(q[ind])]
print("The most populated conformations:", q[p])
### EXTRACTING REPRESENTATIVE CONFORMATIONS OF MACROSTATE
ktree=KDTree(tica_features)
trj_ds = dataset("*.nc", topology="s.pdb")
trj_list = []
for cind in p:
pt = kmeans_mdl.cluster_centers_[cind]
_,(t,f) = ktree.query(pt)
print("The trajectory and frame number of representative macrostate:",t,f)
trj_list.append(trj_ds[t][f])
#CALCULATING COMMON FREE ENERGY LANDSCAPE FOR ALL PH
pi_0=msm_mdl.__dict__.get('populations_')[np.concatenate(assignments, axis=0)]
data = np.concatenate(tica_trajs, axis=0)
clip = [(-np.inf, np.inf), (-np.inf, np.inf)]
levels = np.linspace(0,2,21)
def _thermo_transform(Z, temperature):
return - THERMO_CONSTANT * temperature * np.log(Z)
