def test_that_all_featurizers_run():
dataset = fetch_alanine_dipeptide()
trajectories = dataset["trajectories"]
trj0 = trajectories[0][0]
atom_indices, pair_indices = subset_featurizer.get_atompair_indices(trj0)
featurizer = msmbuilder.featurizer.AtomPairsFeaturizer(pair_indices)
X_all = featurizer.transform(trajectories)
featurizer = msmbuilder.featurizer.SuperposeFeaturizer(np.arange(15), trj0)
X_all = featurizer.transform(trajectories)
featurizer = msmbuilder.featurizer.DihedralFeaturizer(["phi" ,"psi"])
X_all = featurizer.transform(trajectories)
#featurizer = msmbuilder.featurizer.ContactFeaturizer() # Doesn't work on ALA dipeptide
#X_all = featurizer.transform(trajectories)
featurizer = msmbuilder.featurizer.RMSDFeaturizer(trj0)
X_all = featurizer.transform(trajectories)
atom_featurizer0 = subset_featurizer.SubsetAtomPairs(pair_indices, trj0, exponent=-1.0)
cosphi = subset_featurizer.SubsetCosPhiFeaturizer(trj0)
sinphi = subset_featurizer.SubsetSinPhiFeaturizer(trj0)
cospsi = subset_featurizer.SubsetCosPsiFeaturizer(trj0)
sinpsi = subset_featurizer.SubsetSinPsiFeaturizer(trj0)
featurizer = subset_featurizer.SubsetFeatureUnion([("pairs", atom_featurizer0), ("cosphi", cosphi), ("sinphi", sinphi), ("cospsi", cospsi), ("sinpsi", sinpsi)])
featurizer.subsets = [np.arange(1) for i in range(featurizer.n_featurizers)]
X_all = featurizer.transform(trajectories)
eq(X_all[0].shape[1], 1 * featurizer.n_featurizers)
def test_SubsetAtomPairs2():
dataset = fetch_alanine_dipeptide()
trajectories = dataset["trajectories"]
trj0 = trajectories[0][0]
atom_indices, pair_indices = subset_featurizer.get_atompair_indices(trj0)
featurizer = msmbuilder.featurizer.AtomPairsFeaturizer(pair_indices)
X_all0 = featurizer.transform(trajectories)
featurizer = subset_featurizer.SubsetAtomPairs(pair_indices, trj0, subset=np.array([0, 1]))
X_all = featurizer.transform(trajectories)
any([eq(x, x0) for (x, x0) in zip(X_all, X_all0)])
def test_SubsetAtomPairs0():
dataset = fetch_alanine_dipeptide()
trajectories = dataset["trajectories"]
trj0 = trajectories[0][0]
atom_indices, pair_indices = subset_featurizer.get_atompair_indices(trj0)
featurizer = msmbuilder.featurizer.AtomPairsFeaturizer(pair_indices)
X_all0 = featurizer.transform(trajectories)
featurizer = subset_featurizer.SubsetAtomPairs(pair_indices, trj0)
featurizer.subset = np.arange(len(pair_indices))
X_all = featurizer.transform(trajectories)
any([eq(x, x0) for (x, x0) in zip(X_all, X_all0)])
def test_alanine_dipeptide():
# will produce 0 features because not enough peptides
trajectories = AlanineDipeptide().get_cached().trajectories
featurizer = msmbuilder.featurizer.AlphaAngleFeaturizer()
nothing = featurizer.transform(trajectories)
assert (nothing[0].shape[1] == 0)
def test_fs_peptide_nosincos():
# will produce 18 features
trajectories = MinimalFsPeptide().get_cached().trajectories
featurizer = msmbuilder.featurizer.AlphaAngleFeaturizer(sincos=False)
alphas = featurizer.transform(trajectories)
assert (alphas[0].shape[1] == 18)
def test_alanine_dipeptide():
# will produce 0 features because not enough peptides
dataset = fetch_alanine_dipeptide()
trajectories = dataset["trajectories"]
featurizer = msmbuilder.featurizer.AlphaAngleFeaturizer()
nothing = featurizer.transform(trajectories)
assert(nothing[0].shape[1] == 0)
def test_fs_peptide_nosincos():
# will produce 18 features
dataset = fetch_fs_peptide()
trajectories = dataset["trajectories"]
featurizer = msmbuilder.featurizer.AlphaAngleFeaturizer(sincos=False)
alphas = featurizer.transform(trajectories)
assert(alphas[0].shape[1] == 18)
def test_fs_peptide():
# will produce 36 features
dataset = fetch_fs_peptide()
trajectories = dataset["trajectories"]
featurizer = msmbuilder.featurizer.AlphaAngleFeaturizer()
alphas = featurizer.transform(trajectories)
assert(alphas[0].shape[1] == 36)
def test_alanine_dipeptide():
# will produce 0 features because not enough peptides
dataset = fetch_alanine_dipeptide()
trajectories = dataset["trajectories"]
featurizer = msmbuilder.featurizer.AlphaAngleFeaturizer()
nothing = featurizer.transform(trajectories)
assert (nothing[0].shape[1] == 0)
def test_fs_peptide_nosincos():
# will produce 18 features
dataset = fetch_fs_peptide()
trajectories = dataset["trajectories"]
featurizer = msmbuilder.featurizer.AlphaAngleFeaturizer(sincos=False)
alphas = featurizer.transform(trajectories)
assert (alphas[0].shape[1] == 18)
def test_fs_peptide():
# will produce 36 features
dataset = fetch_fs_peptide()
trajectories = dataset["trajectories"]
featurizer = msmbuilder.featurizer.AlphaAngleFeaturizer()
alphas = featurizer.transform(trajectories)
assert (alphas[0].shape[1] == 36)
def test_that_all_featurizers_run():
dataset = fetch_alanine_dipeptide()
trajectories = dataset["trajectories"]
trj0 = trajectories[0][0]
atom_indices, pair_indices = subset_featurizer.get_atompair_indices(trj0)
featurizer = msmbuilder.featurizer.AtomPairsFeaturizer(pair_indices)
X_all = featurizer.transform(trajectories)
featurizer = msmbuilder.featurizer.SuperposeFeaturizer(np.arange(15), trj0)
X_all = featurizer.transform(trajectories)
featurizer = msmbuilder.featurizer.DihedralFeaturizer(["phi", "psi"])
X_all = featurizer.transform(trajectories)
#featurizer = msmbuilder.featurizer.ContactFeaturizer() # Doesn't work on ALA dipeptide
#X_all = featurizer.transform(trajectories)
featurizer = msmbuilder.featurizer.RMSDFeaturizer(trj0)
X_all = featurizer.transform(trajectories)
atom_featurizer0 = subset_featurizer.SubsetAtomPairs(pair_indices,
trj0,
exponent=-1.0)
cosphi = subset_featurizer.SubsetCosPhiFeaturizer(trj0)
sinphi = subset_featurizer.SubsetSinPhiFeaturizer(trj0)
cospsi = subset_featurizer.SubsetCosPsiFeaturizer(trj0)
sinpsi = subset_featurizer.SubsetSinPsiFeaturizer(trj0)
featurizer = subset_featurizer.SubsetFeatureUnion([("pairs",
atom_featurizer0),
("cosphi", cosphi),
("sinphi", sinphi),
("cospsi", cospsi),
("sinpsi", sinpsi)])
featurizer.subsets = [
np.arange(1) for i in range(featurizer.n_featurizers)
]
X_all = featurizer.transform(trajectories)
eq(X_all[0].shape[1], 1 * featurizer.n_featurizers)
def test_alanine_dipeptide():
# This test takes the rmsd of the 0th set of alanine dipeptide
# trajectories relative to the 0th frame of the dataset.
# The test asserts that the first rmsd calculated will be zero.
dataset = fetch_alanine_dipeptide()
trajectories = dataset["trajectories"]
featurizer = msmbuilder.featurizer.StrucRMSDFeaturizer(
trajectories[0], trajectories[0][0], range(trajectories[0].n_atoms))
data = featurizer.transform(trajectories[0])
assert(data[0] < 1e-3)
def test_two_refs():
# This test uses the 0th and 1st frames of the 0th set of
# adp trajectories as the two reference trajectories and
# ensures that the rmsd of the 0th frame of the dataset with
# the 0th reference are identical and the 1st frame of the
# dataset with the 1st reference are identical.
dataset = fetch_alanine_dipeptide()
trajectories = dataset["trajectories"]
featurizer = msmbuilder.featurizer.StrucRMSDFeaturizer(
trajectories[0], trajectories[0][0:2], range(trajectories[0].n_atoms))
data = featurizer.transform(trajectories[0])
# TODO: Figure out why arrays are 3D
assert(data[0][0][0] - data[1][0][1] < 1e-3)
assert(data[1][0][0] - data[0][0][1] < 1e-3)