def calculate_scores(data,
kde_bw=0.15,
pca_component=0.95,
score_weights=None):
"""Calculate scores based on probability density.
Parameters
----------
data : ndarray, shape=(n_atoms, n_samples, n_dims)
kde_bw : scalar
pca_component : scalar
score_weights : None or dict
A dictionary that contains the weight for n_dims, {n_dim: weight}
Returns
---------
scores : ndarray, shape=(n_samples,)
See also
--------
pylipid.func.collect_bound_poses
pylipid.func.vectorize_poses
"""
weights = {atom_idx: 1 for atom_idx in np.arange(np.shape(data)[0])}
if score_weights is not None:
weights.update(score_weights)
kde_funcs = {}
try:
for atom_idx in np.arange(np.shape(data)[0]):
transformed_data = PCA(n_components=pca_component).fit_transform(
data[atom_idx])
var_type = ""
bw = []
for dummy in range(len(transformed_data[0])):
var_type += "c"
bw.append(kde_bw)
kde_funcs[atom_idx] = kde(data=transformed_data,
var_type=var_type,
bw=bw)
# evaluate binding poses
scores = np.sum([
weights[atom_idx] * kde_funcs[atom_idx].pdf()
for atom_idx in np.arange(np.shape(data)[0])
],
axis=0)
return scores
except ValueError:
print(
"Pose generation error -- possibly due to insufficient number of binding event."
)
bins = np.linspace(0, XL, 50)
# Illustrate
axs[0].hist(P, bins, density=True, label='Example sample')
axs[1].hist(q, bins, density=True, label='Proposal sample and pdf')
axs[2].hist(q,
bins,
density=True,
label='Proposal sample - weighted',
weights=w)
axs[3].hist(r, bins, density=True, label='resmpl: Residual')
axs[4].hist(s, bins, density=True, label='resmpl: Systematic')
axs[5].hist(t, bins, density=True, label='resmpl: Stochastic')
# Add actual pdfs
axs[0].plot(xx, pdf(xx, dof), label='pdf: Target')
axs[1].plot(xx, qdf(xx, scl), label='pdf: Proposal')
# kde pdf comparison
axs[6].plot(xx, pdf(xx, dof), c='k', lw=3, label='pdf: Target')
axs[6].plot(xx, qdf(xx, scl), c='k', lw=2, label='pdf: Proposal')
axs[6].plot(xx, kde(r, 'c', bw=[0.1]).pdf(xx), label='kde: Residual')
axs[6].plot(xx, kde(s, 'c', bw=[0.1]).pdf(xx), label='kde: Systematic')
axs[6].plot(xx, kde(t, 'c', bw=[0.1]).pdf(xx), label='kde: Stochastic')
axs[0].set_yticklabels([])
for ax in f.axes:
ax.legend()
plt.pause(.1)
def calculate_scores(dist_matrix,
kde_bw=0.15,
pca_component=0.90,
score_weights=None):
r"""Calculate scores based on probability density.
This function first lower the dimension of dist_matrix by using a
`PCA <https://scikit-learn.org/stable/modules/generated/sklearn.decomposition.PCA.html>`_. Then the distribution of
the distance vectors for each atom is estimated using
`KDEMultivariate <https://www.statsmodels.org/devel/generated/statsmodels.nonparametric.kernel_density.KDEMultivariate.html>`_.
The score of a lipid pose is calculated based on the probability density function of the atom positions in the binding
site and weights given to the atoms:
.. math::
\text { score }=\sum_{i} W_{i} \cdot \hat{f}_{i, H}(D)
where :math:`W_{i}` is the weight given to atom i of the lipid molecule, H is the bandwidth and
:math:`\hat{f}_{i, H}(D)` is a multivariate kernel density etimation of the position of atom i in the specified
binding site. :math:`\hat{f}_{i, H}(D)` is calculated from all the bound lipid poses in that binding site.
Parameters
----------
dist_matrix : numpy.ndarray, shape=(n_lipid_atoms, n_poses, n_binding_site_residues)
The distance vectors describing the position of bound poses in the binding site. This dist_matrix can be
generated by :meth:`~vectorize_poses`.
kde_bw : scalar, default=0.15
The bandwidth for kernel density estimation. Used by
`KDEMultivariate <https://www.statsmodels.org/devel/generated/statsmodels.nonparametric.kernel_density.KDEMultivariate.html>`_.
By default, the bandwidth is set to 0.15nm which roughly corresponds to the vdw radius of MARTINI 2 beads.
pca_component : scalar, default=0.9
The number of components to keep. if ``0 < pca_component<1``, select the number of components such that the
amount of variance that needs to be explained is greater than the percentage specified by n_components. It is used
by `PCA <https://scikit-learn.org/stable/modules/generated/sklearn.decomposition.PCA.html>`_.
score_weights : None or dict
A dictionary that contains the weight for n_lipid_atoms, {idx_atom: weight}
Returns
---------
scores : numpy.ndarray, shape=(n_samples,)
Scores for bound poses.
See also
--------
pylipid.func.collect_bound_poses
Collect bound poses from trajectories.
pylipid.func.vectorize_poses
Convert bound poses to distance vectors.
"""
weights = {atom_idx: 1 for atom_idx in np.arange(np.shape(dist_matrix)[0])}
if score_weights is not None:
weights.update(score_weights)
kde_funcs = {}
try:
for atom_idx in np.arange(np.shape(dist_matrix)[0]):
transformed_data = PCA(n_components=pca_component).fit_transform(
dist_matrix[atom_idx])
var_type = ""
bw = []
for dummy in range(len(transformed_data[0])):
var_type += "c"
bw.append(kde_bw)
kde_funcs[atom_idx] = kde(data=transformed_data,
var_type=var_type,
bw=bw)
# evaluate binding poses
scores = np.sum([
weights[atom_idx] * kde_funcs[atom_idx].pdf()
for atom_idx in np.arange(np.shape(dist_matrix)[0])
],
axis=0)
return scores
except ValueError:
print(
"Pose generation error -- possibly due to insufficient number of binding event."
)