This is the current development version of MSMBuilder
version.short_version
is now 3.y instead of 3.y.z (#829).weighted_transform
is no longer supported in tICA methods (#807). Please
used kinetic_mapping
.msmbuilder.example_datasets
is still the same, but the data may
be re-generated instead of using a cached version from a previous installation
of MSMBuilder (gh-854).BinaryContactFeaturizer
featurizes a trajectory into a
boolean array corresponding to whether each residue-residue
distance is below a cutoff (#798).LogisticContactFeaturizer
produces a logistic transform
of residue-residue distances about a center distance (#798).FactorAnalysis
, FastICA
, and KernelPCA
are available in the
decomposition
module (#807).Butterworth
, EWMA
, and DoubleEWMA
are available in the
preprocessing
module (#818).msmb_data
conda package to easily
install example data. The data can be loaded through existing methods
in msmbuilder.example_datasets
(gh-854, gh-867).MinimalFsPeptide
is available. This is a strided
version of the existing FsPeptide
dataset. We use it for testing,
when a fully-converged dataset is not required (gh-867).LandmarkAgglomerative
clustering now features the ward
linkage
option. An algorithm for predicting cluster assignments with the
ward
objective function has been developed and implemented (#874).ktica.py
(gh-833)msmbuilder.decomposition.KernelTICA
now includes all parameters in its
__init__
, making it compatible with Osprey (gh-823).msmbuilder.tpt
methods can now handle BayesianMarkovStateModels
as
input. Please note that we still do not recommend using this module with
BootStrapMarkovStateModel
.We’re pleased to announce the release of MSMBuilder 3.5. This release
wraps more relevant sklearn
estimators and transformers. There are
also some bugfixes and API hygiene improvements. We recommend all users
upgrade to MSMBuilder 3.5.
msmbuilder.featurizer.FeatureUnion
is now deprecated. Please use
msmbuilder.feature_selection.FeatureSelector
instead (#799).msmbuilder.feature_extraction
has been added to conform to the
scikit-learn
API. This is essentially an alias of
msmbuilder.featurizer
(#799).
KernelTICA
,Nystroem
, andLandmarkNystroem
are available in thedecomposition
module (#807).FeatureSelector
andVarianceThreshold
are available in thefeature_selection
module (#799).SparsePCA
andMiniBatchSparsePCA
are available in thedecomposition
module (#791).Binarizer
,FunctionTransformer
,Imputer
,KernelCenterer
,LabelBinarizer
,MultiLabelBinarizer
,MinMaxScaler
,MaxAbsScaler
,Normalizer
,RobustScaler
,StandardScaler
, andPolynomialFeatures
are available in thepreprocessing
module (#796).
ContinuousTimeMSM
. The optimizer_state_
parameter is not saved (#822).We’re pleased to announce MSMBuilder 3.4. It contains a plethora of new features, bug fixes, and improvements.
ds[:]
loads all trajectories in a list (#610).PCCA.trimmed_microstates_to_macrostates
has been removed. This
dictionary was actually keyed by untrimmed microstate labels.
PCCA.transform
would throw an exception when operating on a system
with trimming because it was using this misleading dictionary. Please use
pcca.microstate_mapping_
for this functionality (#709).UnionDataset
has been removed after deprecation in 3.3. Please use
FeatureUnion
instead (#671).SubsetFeaturizer
and ilk have been removed from the
msmbuilder.featurizer
namespace. Please import them from
msmbuilder.featurizer.subset
(#738).FirstSlicer
has been removed. Use Slicer(first=x)
for the same
functionality (#738).msmbuilder.featurizer.load
has been removed. Featurizer.save
has been removed. Please use utils.load
, utils.dump
(#738).fit_transform_with()
to simplify the
common pattern of applying an estimator to a dataset object to produce a
new dataset object (#610).kinetic_mapping
is a new option to tICA
. It’s similar to
weighted_transform
, but based on a better theoretical framework.
weighted_transform
is deprecated (#766).VonMisesFeaturizer
uses soft bins around the unit-circle to give an
alternate representation of dihedral angles (#744).MarkovStateModel
has a partial_transform()
method (#707).KappaAngleFeaturizer
is available via the command line (#681).MarkovStateModel
has a new attribute, percent_retained_
, for
ergodic trimming (#689).AlphaAngleFeaturizer
computes the dihedral angles between alpha
carbons (#691).FunctionFeaturizer
computes features based on an arbitrary Python
function or callable (#717).sklearn.hmm
, which has been removed (#690).RSMDFeaturizer
(#695, #764).SparseTICA
is completely re-written with large performance
improvements when dealing with large numbers of features (#704).We’re pleased to announce the release of MSMBuilder v3.3.0. The focus of this release is a completely re-written module for constructing HMMs as well as bug fixes and incremental improvements.
FeatureUnion
is an estimator that deprecates the functionality of
UnionDataset
. Passing a list of paths to dataset()
will no longer
automatically yield a UnionDataset
. This behavior is still available by
specifying fmt="dir-npy-union"
, but is deprecated (#611).--out
(deprecated in 3.2) now saves
the featurizer as a pickle file (#546). Please use --transformed
for the
old behavior. This is consistent with other command-line commands.MarkovStateModel
is now one less than
the number of states (was 10). This addresses some bugs with
implied_timescales
and PCCA(+) (#603).GaussianHMM
and VonMisesHMM
is rewritten to feature higher code reuse
and code quality (#583, #582, #584, #572, #570).KDTree
can find n nearest points to e.g. a cluster center (#599).Slicer
featurizer can slice feature arrays as part of a pipeline
(#567).PCCAPlus
is compatible with scipy 0.16 (#620).MarkovStateModel.sample()
produced trajectories of incorrect
length. This function is still deprecated (#556).MarkovStateModel.draw_samples
failed if discrete trajectories did not
contain every possible state (#638). Function can now accept a single
trajectory, as well as a list of them.SuperposeFeaturizer
now respects the topology argument when loading the
reference trajectory (#555).tICA
ignores too-short trajectories during fitting instead of raising
an exceptionutils.dump
saves using the pickle protocol. utils.load
is backwards
compatible.--out
is deprecated. Use
--transformed
instead. This is consistent with other command-line
commands.ContinuousTimeMSM
optimizationContinuousTimeMSM.score
to transmat-style GMRQMSMBuilder 3.0 is a complete rewrite of our previous work. The focus is on power and extensibility, with a much wider class of estimators and models supported throughout the codebase. All users are encouraged to switch to MSMBuilder 3.0. Pre-release versions of MSMBuilder 3.0 were called mixtape.