def ensure_connectivity_msm(msm):
if msm.nstates_full == msm.nstates:
return msm.stationary_distribution
else:
counts = msm.count_matrix_full
counts += 1 / counts.shape[0]
trans = utils.buildRevTransitionMatrix(counts)
_, eic = getSortedEigen(trans)
return getStationaryDistr(eic[:, 0])
import numpy as np
from scipy import linalg
from collections import Counter
import toy_matrices as mat
from AdaptivePELE.analysis import autoCorrelation as autoC
from AdaptivePELE.freeEnergies import runMarkovChainModel as run
from AdaptivePELE.freeEnergies import utils
import time
import matplotlib.pyplot as plt
plt.style.use("ggplot")
C = mat.pre_docking
n = C.shape[0]
# T = run.buildTransitionMatrix(C)
T = utils.buildRevTransitionMatrix(C.astype(np.float))
eigenvals, eigenvectors = linalg.eig(T, left=True, right=False)
sortedIndices = np.argsort(eigenvals)[::-1]
# stationary distribution
goldenStationary = run.getStationaryDistr(eigenvectors[:, sortedIndices[0]])
test_initial = False
run_simulation = True
# test generation of initial structures according to a distribution
numberOfSimulations = 127
possible_state = []
for l in range(n):
possible_state.extend([
l for _ in range(
np.round(goldenStationary[l] * numberOfSimulations).astype(int))
])
def estimateTransitionMatrix(trajectories, n, tau, symm=True):
C = estimateCountMatrix(trajectories, n, tau) + 1. / n
if symm:
return utils.buildRevTransitionMatrix(C)
return buildTransitionMatrix(C)
def reestimate_transition_matrix(count_matrix):
count_matrix += 1 / float(count_matrix.shape[0])
return utils.buildRevTransitionMatrix(count_matrix)
def main(path, native, resname, nEigen, path_sasa):
# Z = np.array([[4380, 153, 15, 2, 0, 0], [211, 4788, 1, 0, 0, 0], [169, 1, 4604, 226, 0, 0],
# [3, 13, 158, 4823, 3, 0], [0, 0, 0, 4, 4978, 18], [7, 5, 0, 0, 62, 4926]])
MSM = utilities.readClusteringObject(os.path.join(path, "MSM_object_0.pkl"))
Z = MSM.count_matrix_full
np.set_printoptions(precision=4)
m = 100
k = Z.shape[0]
alpha = 1/float(k)
U_counts = Z + alpha
w = U_counts.sum(axis=1)
P_rev = utils.buildRevTransitionMatrix(U_counts)
P = U_counts / w[:, np.newaxis]
P = P_rev
eigvalues, _ = np.linalg.eig(P)
eigvalues.sort()
eigvalues = eigvalues[::-1]
eigvalues_rev, _ = np.linalg.eig(P_rev)
eigvalues_rev.sort()
eigvalues_rev = eigvalues_rev[::-1]
ek = np.zeros(k)
ek[k-1] = 1.0
variance = []
contribution = []
nEigs = 10
for index in range(1, nEigs):
A = P - eigvalues[index]*np.eye(k)
q = calculate_q(A, P, k, ek)
score = (q/(w+1))-(q/(w+1+m))
norm_q = q/q.sum()
contribution.append(score/score.sum())
variance.append(norm_q)
sasa = getSASAvalues(os.path.join(path, "representative_structures", "representative_structures_0.dat"), 4, path_sasa)
pdb_native = atomset.PDB()
pdb_native.initialise(u"%s" % native, resname=resname)
minim = pdb_native.getCOM()
clusters = np.loadtxt(os.path.join(path, "clusterCenters_0.dat"))
distance = np.linalg.norm(clusters-minim, axis=1)
variance = np.array(variance[:nEigen])
variance = variance.sum(axis=0)
variance /= variance.sum()
print(variance)
# states = variance.argsort()[-1:-10:-1]
# print(" ".join(["structures/cluster_%d.pdb" % st for st in states]))
f, axarr = plt.subplots(1, 2)
axarr[0].scatter(distance, variance)
axarr[0].set_xlabel("Distance to minimum")
axarr[0].set_ylabel("Variance")
axarr[1].scatter(sasa, variance)
axarr[1].set_xlabel("SASA")
axarr[0].set_ylabel("Variance")
f.suptitle("Variance for eigenvalues 2-%d" % (nEigen+1))
# for ind, var in enumerate(variance[:5]):
# f, axarr = plt.subplots(1, 2)
# axarr[0].scatter(distance, var)
# axarr[0].set_xlabel("Distance to minimum")
# axarr[0].set_ylabel("Variance")
# axarr[1].scatter(sasa, var)
# axarr[1].set_xlabel("SASA")
# axarr[0].set_ylabel("Variance")
# f.suptitle("Variance for eigenvalue %d" % (ind+2))
plt.show()