msmbuilder.featurizer.RMSDFeaturizer¶

class msmbuilder.featurizer.RMSDFeaturizer(reference_traj=None, atom_indices=None, trj0=None)¶

Featurizer based on RMSD to one or more reference structures.

This featurizer inputs a trajectory to be analyzed (‘traj’) and a reference trajectory (‘ref’) and outputs the RMSD of each frame of traj with respect to each frame in ref. The output is a numpy array with n_rows = traj.n_frames and n_columns = ref.n_frames.

Parameters:

reference_traj : md.Trajectory

The reference conformations to superpose each frame with respect to

atom_indices : np.ndarray, shape=(n_atoms,), dtype=int

The indices of the atoms to superpose and compute the distances with. If not specified, all atoms are used.

trj0

Deprecated. Please use reference_traj.

Methods

`describe_features`(traj)	Generic method for describing features.
`featurize`(traj)
`fit`(traj_list[, y])
`fit_transform`(X[, y])	Fit to data, then transform it.
`get_params`([deep])	Get parameters for this estimator.
`partial_transform`(traj)	Featurize an MD trajectory into a vector space via distance
`set_params`(**params)	Set the parameters of this estimator.
`summarize`()	Return some diagnostic summary statistics about this Markov model
`transform`(traj_list[, y])	Featurize a several trajectories.

__init__(reference_traj=None, atom_indices=None, trj0=None)¶

Methods

`__init__`([reference_traj, atom_indices, trj0])
`describe_features`(traj)	Generic method for describing features.
`featurize`(traj)
`fit`(traj_list[, y])
`fit_transform`(X[, y])	Fit to data, then transform it.
`get_params`([deep])	Get parameters for this estimator.
`partial_transform`(traj)	Featurize an MD trajectory into a vector space via distance
`set_params`(**params)	Set the parameters of this estimator.
`summarize`()	Return some diagnostic summary statistics about this Markov model
`transform`(traj_list[, y])	Featurize a several trajectories.

describe_features(traj)¶

Generic method for describing features.

Parameters:

traj : mdtraj.Trajectory

Trajectory to use

Returns:

feature_descs : list of dict

Dictionary describing each feature with the following information about the atoms participating in each feature

resnames: unique names of residues

atominds: the four atom indicies

resseqs: unique residue sequence ids (not necessarily 0-indexed)

resids: unique residue ids (0-indexed)

featurizer: Featurizer name

featuregroup: Other information

Notes

Method resorts to returning N/A for everything if describe_features in not implemented in the sub_class

fit_transform(X, y=None, **fit_params)¶

Fit to data, then transform it.

Fits transformer to X and y with optional parameters fit_params and returns a transformed version of X.

Parameters:

X : numpy array of shape [n_samples, n_features]

Training set.

y : numpy array of shape [n_samples]

Target values.

Returns:

X_new : numpy array of shape [n_samples, n_features_new]

Transformed array.

get_params(deep=True)¶

Get parameters for this estimator.

Parameters:

deep: boolean, optional

If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns:

params : mapping of string to any

Parameter names mapped to their values.

partial_transform(traj)¶

Featurize an MD trajectory into a vector space via distance after superposition

Parameters:

traj : mdtraj.Trajectory

A molecular dynamics trajectory to featurize.

Returns:

features : np.ndarray, shape=(n_frames, n_ref_frames)

The RMSD value of each frame of the input trajectory to be featurized versus each frame in the reference trajectory. The number of features is the number of reference frames.