def test_that_all_featurizers_run():
# TODO: include all featurizers, perhaps with generator tests
trajectories = AlanineDipeptide().get_cached().trajectories
trj0 = trajectories[0][0]
atom_indices, pair_indices = get_atompair_indices(trj0)
featurizer = AtomPairsFeaturizer(pair_indices)
X_all = featurizer.transform(trajectories)
featurizer = SuperposeFeaturizer(np.arange(15), trj0)
X_all = featurizer.transform(trajectories)
featurizer = DihedralFeaturizer(["phi", "psi"])
X_all = featurizer.transform(trajectories)
featurizer = VonMisesFeaturizer(["phi", "psi"])
X_all = featurizer.transform(trajectories)
# Below doesn't work on ALA dipeptide
# featurizer = msmbuilder.featurizer.ContactFeaturizer()
# X_all = featurizer.transform(trajectories)
featurizer = RMSDFeaturizer(trj0)
X_all = featurizer.transform(trajectories)
def read_and_featurize(filename, dihedrals=['chi2'], stride=10):
#print("reading and featurizing %s" %(filename))
top = md.load_frame(filename, 0).topology
#print("got top")
atom_indices = [a.index for a in top.atoms if a.residue.resSeq == 93 and a.residue != "POPC" and str(a.residue)[0] == "H"]
print((len(atom_indices)))
#atom_indices = [a.index for a in top.atoms if a.residue.chain.index == 0 and a.residue.resSeq != 93 and a.residue != "POPC" and a.residue.resSeq != 130 and a.residue.resSeq != 172 and a.residue.resSeq != 79 and a.residue.resSeq != 341]
#print("got indices")
traj = md.load(filename, stride=1000, atom_indices=atom_indices)
#print("got traj")
featurizer = DihedralFeaturizer(types = dihedrals)
features = featurizer.transform(traj_list = traj)
#print(np.shape(features))
#print("finished featurizing")
directory = filename.split("/")
condition = directory[len(directory)-2]
dcd_file = directory[len(directory)-1]
new_file = "%s_features_stride%d.h5" %(dcd_file.rsplit( ".", 1 )[ 0 ] , stride)
new_root_dir = "/scratch/users/enf/b2ar_analysis/subsampled_features"
new_condition_dir = "%s/%s" %(new_root_dir, condition)
new_file_full = "%s/%s/%s" %(new_root_dir, condition, new_file)
#print("saving features as %s" %new_file_full)
verbosedump(features, new_file_full)
return features
def test_function_featurizer():
trajectories = AlanineDipeptide().get_cached().trajectories
trj0 = trajectories[0]
# use the dihedral to compute phi for ala
atom_ind = [[4, 6, 8, 14]]
func = compute_dihedrals
# test with args
f = FunctionFeaturizer(func, func_args={"indices": atom_ind})
res1 = f.transform([trj0])
# test with function in a function without any args
def funcception(trj):
return compute_phi(trj)[1]
f = FunctionFeaturizer(funcception)
res2 = f.transform([trj0])
# know results
f3 = DihedralFeaturizer(['phi'], sincos=False)
res3 = f3.transform([trj0])
# compare all
for r in [res2, res3]:
np.testing.assert_array_almost_equal(res1, r)
def test_pipeline():
trajs = AlanineDipeptide().get_cached().trajectories
p = Pipeline([('diheds', DihedralFeaturizer(['phi', 'psi'], sincos=False)),
('hmm', VonMisesHMM(n_states=4))])
predict = p.fit_predict(trajs)
p.named_steps['hmm'].summarize()
def _test_tic_sampling(yaml_file, protein_name, tic_list, n_frames, scheme):
#test to make sure we are sampling right
sample_for_all_proteins(yaml_file, [protein_name],
tic_list, n_frames, scheme=scheme)
ser = ProteinSeries(yaml_file)
prt = Protein(ser, protein_name)
for tic_index in [0,1]:
traj_path = os.path.join(base_dir,yaml_file["mdl_dir"],
protein_name,"tic%d.xtc"%tic_index)
traj_top = os.path.join(base_dir,yaml_file["mdl_dir"],
protein_name, "prot.pdb")
tica_traj = mdt.load(traj_path,top=traj_top)
print(tica_traj.n_frames)
feat = DihedralFeaturizer(types=['phi', 'psi','chi1'])
f = feat.partial_transform(tica_traj)
t_f = np.round(prt.tica_mdl.transform([f]))
#check that the tic goes from min to max
print("Look here",t_f[0])
assert t_f[0][0][tic_index] <= t_f[0][-1][tic_index]
all_vals = []
for traj_tica_data in prt.tica_data.values():
all_vals.extend(traj_tica_data[:,tic_index])
#sort it because all three sampling schemes use it
all_vals = np.round(np.sort(all_vals))
print(tic_index)
print(t_f[0][:,tic_index] >= all_vals[0])
print(t_f[0][:,tic_index] <= all_vals[-1])
#make sure the frames are within limitsss
assert (t_f[0][:,tic_index] >= all_vals[0]).all()
assert (t_f[0][:,tic_index] <= all_vals[-1]).all()
return True
def read_and_featurize_divided(filename,
dihedrals=['phi', 'psi', 'chi2'],
stride=10):
#print("reading and featurizing %s" %(filename))
traj_top = md.load_frame(filename, 0).topology
atom_indices = [
a.index for a in traj_top.atoms if a.residue.name[0:2] != "HI"
]
traj = md.load(filename, atom_indices=atom_indices)
#print("got traj")
featurizer = DihedralFeaturizer(types=dihedrals)
features = featurizer.transform(traj_list=traj)
#print(np.shape(features))
#print("finished featurizing")
directory = filename.split("/")
condition = directory[len(directory) - 2]
dcd_file = directory[len(directory) - 1]
new_file = "%s_features_stride%d.h5" % (dcd_file.rsplit(".", 1)[0], stride)
new_root_dir = "/scratch/users/enf/b2ar_analysis/subsampled_features"
new_condition_dir = "%s/%s" % (new_root_dir, condition)
new_file_full = "%s/%s/%s" % (new_root_dir, condition, new_file)
#print("saving features as %s" %new_file_full)
verbosedump(features, new_file_full)
return features
def read_and_featurize(filename, dihedrals=['phi', 'psi', 'chi2'], stride=10):
print(("reading and featurizing %s" % (filename)))
traj = md.load(filename)
#test_traj_init = md.load_frame(filename,5)
#test_traj_init.save_pdb("/scratch/users/enf/b2ar_analysis/test_init.pdb")
#traj.topology = fix_topology(traj.topology)
#traj[-1].save_pdb("/scratch/users/enf/b2ar_analysis/test_fixed.pdb")
#traj.save_dcd("/scratch/users/enf/b2ar_analysis/test_fixed.dcd")
#print("got traj")
featurizer = DihedralFeaturizer(types=dihedrals)
features = featurizer.transform(traj_list=traj)
#print("finished featurizing")
directory = filename.split("/")
traj_file = directory[len(directory) - 1]
condition = traj_file.split("_")[0].split(".")[0]
print(("Condition %s has features of shape %s" %
(condition, np.shape(features))))
new_file = "/scratch/users/enf/b2ar_analysis/combined_features/%s_features.h5" % condition
verbosedump(features, new_file)
def featurize_project(proj_folder, top_folder, featurizer_object, stride,
view):
#if already featurized dont bother(should add a warning about this)
if os.path.exists(proj_folder + "/featurized_traj.pkl"):
return verboseload(proj_folder + "/featurized_traj.pkl")
if featurizer_object is None:
featurizer = DihedralFeaturizer(types=['phi', 'psi', 'chi1'])
else:
try:
featurizer = verboseload(featurizer_object)
except:
sys.exit("Cant Load Featurizer using msmbuilder verboseload")
feature_dict = {}
traj_list = glob.glob(proj_folder + "/trajectories/*.dcd")
jobs = [(proj_folder, top_folder, featurizer, traj, stride)
for traj in traj_list]
results = view.map_sync(featurize_traj, jobs)
for result in results:
feature_dict[result[0]] = result[1]
verbosedump(feature_dict, proj_folder + "/featurized_traj.pkl")
return feature_dict
def featurize_file(job_tuple):
yaml_file, protein, feat, traj_file,stride = job_tuple
yaml_file = load_yaml_file(yaml_file)
if feat is None:
feat = DihedralFeaturizer(types=['phi', 'psi','chi1'])
_check_output_folder_exists(yaml_file, protein)
output_folder = os.path.join(yaml_file["base_dir"],
protein,
yaml_file["feature_dir"])
traj_name = os.path.splitext(os.path.basename(traj_file))[0]
output_fname = os.path.join(output_folder, traj_name+".jl")
feat_descriptor = os.path.join(output_folder, "feature_descriptor.h5")
try:
trj = mdt.load(traj_file)
except :
warnings.warn("Removing %s because of misformed trajectory"%traj_file)
os.remove(traj_file)
return
features = feat.partial_transform(trj)
verbosedump(features, output_fname)
if not os.path.isfile(feat_descriptor) and hasattr(feat, "describe_features"):
dih_df = pd.DataFrame(feat.describe_features(trj[0]))
verbosedump(dih_df, feat_descriptor)
return
def test_dihedral_feat():
print(base_dir)
pool = Pool(6)
yaml_file = load_yaml_file(os.path.join(base_dir,"mdl_dir","project.yaml"))
for prt in ["kinase_1", "kinase_2"]:
print(prt)
prj = yaml_file["project_dict"][prt][0]
featurize_project_wrapper(yaml_file, prt, feat=None, stride=1, view=pool)
feat = DihedralFeaturizer(types=['phi', 'psi','chi1'])
flist = glob.glob(os.path.join(base_dir, prt , yaml_file["protein_dir"],"*.hdf5"))
for i in np.random.choice(flist, 3):
trj = mdt.load(i)
my_feat = feat.partial_transform(trj)
expected_fname = os.path.join(base_dir, prt,
yaml_file["feature_dir"],
os.path.splitext(os.path.basename(i))[0]+".jl")
calc_feat = verboseload(expected_fname)
assert np.allclose(my_feat, calc_feat)
return True
def individual_traj_featurize(data_to_process):
#print('Running individual traj featurize\n')
test = 1
#print("Data process to do is :", data_to_process)
featurizer_type = data_to_process[0]
if featurizer_type == 'Dihedral':
featurizer_data = DihedralFeaturizer(types=['phi', 'psi'])
# print('Featurizer created:\n')
featurized_data = featurizer_data.fit_transform(data_to_process[2])
#print('Finished individual traj featurize\n')
return [data_to_process[1], featurized_data]
def featurize_trajectories(coords, featurizer):
if featurizer == 'RMSDFeaturizer':
from msmbuilder.featurizer import RMSDFeaturizer
feat = RMSDFeaturizer(reference_traj=coords[0])
elif featurizer == 'DRIDFeaturizer':
from msmbuilder.featurizer import DRIDFeaturizer
feat = DRIDFeaturizer()
elif featurizer == 'ContactFeaturizer':
from msmbuilder.featurizer import ContactFeaturizer
feat = ContactFeaturizer(scheme='ca')
elif featurizer == 'DihedralFeaturizer':
from msmbuilder.featurizer import DihedralFeaturizer
feat = DihedralFeaturizer(types=['phi', 'psi'])
return feat.fit_transform(coords)
def load_met():
from msmbuilder.example_datasets import MetEnkephalin
print(type(MetEnkephalin))
trajs = MetEnkephalin().get().trajectories
from msmbuilder.featurizer import AtomPairsFeaturizer
pairs = []
for i in range(75):
for j in range(i):
pairs.append((j,i))
X = AtomPairsFeaturizer(pairs).fit_transform(trajs)
from msmbuilder.featurizer import DihedralFeaturizer
Y = DihedralFeaturizer().fit_transform(trajs)
return X, Y
def load_fs():
from msmbuilder.example_datasets import MinimalFsPeptide
trajs = MinimalFsPeptide().get().trajectories
from msmbuilder.featurizer import AtomPairsFeaturizer
pairs = []
for i in range(264):
for j in range(i):
pairs.append((j, i))
X = AtomPairsFeaturizer(pairs).fit_transform(trajs)
from msmbuilder.featurizer import DihedralFeaturizer
Y = DihedralFeaturizer().fit_transform(trajs)
return X, Y
def build_model(self, user_defined_model):
"""
Load or build a model (Pipeline from scikit-learn) to do all the transforming and fitting
:param user_defined_model: Either a string (to load from disk) or a Pipeline object to use as model
:return model: Return the model back
"""
if user_defined_model is None:
if os.path.exists(self.model_pkl_fname):
logger.info('Loading model pkl file {}'.format(
self.model_pkl_fname))
model = load_generic(self.model_pkl_fname)
else:
logger.info('Building default model based on dihedrals')
# build a lag time of 1 ns for tICA and msm
# if the stride is too big and we can't do that
# use 1 frame and report how much that is in ns
if self.app.meta is not None:
lag_time = max(1, int(1 / self.timestep))
logger.info(
'Using a lag time of {} ns for the tICA and MSM'.
format(lag_time * self.timestep))
else:
self.timestep = None
lag_time = 1
logger.warning(
'Cannot determine timestep. Defaulting to 1 frame.'.
format(lag_time))
model = Pipeline([('feat', DihedralFeaturizer()),
('scaler', RobustScaler()),
('tICA',
tICA(lag_time=lag_time,
commute_mapping=True,
n_components=10)),
('clusterer',
MiniBatchKMeans(n_clusters=200)),
('msm',
MarkovStateModel(lag_time=lag_time,
ergodic_cutoff='off',
reversible_type=None))])
else:
if not isinstance(user_defined_model, Pipeline):
raise ValueError(
'model is not an sklearn.pipeline.Pipeline object')
else:
logger.info('Using user defined model')
model = user_defined_model
return model
def test_code_works():
# creates a 4-state HMM on the ALA2 data. Nothing fancy, just makes
# sure the code runs without erroring out
trajectories = AlanineDipeptide().get_cached().trajectories
topology = trajectories[0].topology
indices = topology.select('symbol C or symbol O or symbol N')
featurizer = DihedralFeaturizer(['phi', 'psi'], trajectories[0][0])
sequences = featurizer.transform(trajectories)
hmm = VonMisesHMM(n_states=4, n_init=1)
hmm.fit(sequences)
assert len(hmm.timescales_ == 3)
assert np.any(hmm.timescales_ > 50)
def setUp(self):
numpy.random.seed(12)
self.top = 'data_app/runs/structure.prmtop'
self.traj_1 = 'data_app/runs/run-000.nc'
self.traj_2 = 'data_app/runs/run-001.nc'
self.feat = DihedralFeaturizer()
self.traj_dict = {
0: load(self.traj_1, top=self.top),
1: load(self.traj_2, top=self.top)
}
self.scaler = RobustScaler()
self.tica = tICA(n_components=2)
self.ftrajs = {
0: numpy.random.rand(100, 50),
1: numpy.random.rand(100, 50),
}
def Get_dihedral_features_villin():
import os
import shutil
import mdtraj as md
os.chdir('/homes/anuginueni/traj_villin')
if(os.path.isdir('./diheds')):
shutil.rmtree('./diheds')
from msmbuilder.dataset import dataset
t=md.load( "/homes/anuginueni/traj_villin/trajectory-331.xtc",top='/homes/anuginueni/traj_villin/filtered.pdb',stride=5)
xyz = dataset( "/homes/anuginueni/traj_villin/*.xtc",topology='/homes/anuginueni/traj_villin/filtered.pdb',stride=5)
from msmbuilder.featurizer import DihedralFeaturizer #for dihedrals
featurizer = DihedralFeaturizer(types=['phi', 'psi']) #for dihedrals
diheds = xyz.fit_transform_with(featurizer, 'diheds/', fmt='dir-npy') #for dihedrals
des_feat=featurizer.describe_features(t)
res = [ sub['resids'] for sub in des_feat ]
print(str(res))
return diheds
def test_DihedralFeaturizer_describe_features_nosincos():
feat = DihedralFeaturizer(sincos=False)
rnd_traj = np.random.randint(len(trajectories))
features = feat.transform([trajectories[rnd_traj]])
df = pd.DataFrame(feat.describe_features(trajectories[rnd_traj]))
for f in range(25):
f_index = np.random.choice(len(df))
atom_inds = df.iloc[f_index].atominds
feature_value = md.compute_dihedrals(trajectories[rnd_traj],
[atom_inds])
if feat.sincos:
func = getattr(np, '%s' % df.iloc[f_index].otherinfo)
feature_value = func(feature_value)
assert (features[0][:, f_index] == feature_value.flatten()).all()
def fit_and_transform(directory, stride=5):
projected_data_filename = "/scratch/users/enf/b2ar_analysis/phi_psi_chi_stride%d_projected.h5" % stride
fit_model_filename = "/scratch/users/enf/b2ar_analysis/phi_psi_chi2_stride%s_tica_coords.h5" % stride
#active_pdb_file = "/scratch/users/enf/b2ar_analysis/3P0G_pymol_prepped.pdb"
active_pdb_file = "/scratch/users/enf/b2ar_analysis/system_B.pdb"
tica_model = tICA(n_components=4)
if not os.path.exists(projected_data_filename):
print("loading feature files")
feature_files = get_trajectory_files(directory)
pool = mp.Pool(mp.cpu_count())
features = pool.map(load_features, feature_files)
pool.terminate()
if not os.path.exists(fit_model_filename):
print("fitting data to tICA model")
fit_model = tica_model.fit(features)
verbosedump(fit_model, fit_model_filename)
transformed_data = fit_model.transform(features)
verbosedump(transformed_data, projected_data_filename)
else:
print("loading tICA model")
fit_model = verboseload(fit_model_filename)
transformed_data = fit_model.transform(features)
verbosedump(transformed_data, projected_data_filename)
else:
fit_model = verboseload(fit_model_filename)
transformed_data = verboseload(projected_data_filename)
active_pdb = md.load(active_pdb_file)
top = active_pdb.topology
atom_indices = [
a.index for a in top.atoms
if a.residue.is_protein and a.residue.resSeq != 341
and a.residue.name[0:2] != "HI" and a.residue.resSeq != 79
and a.residue.resSeq != 296 and a.residue.resSeq != 269 and a.residue.
resSeq != 178 and a.residue.resSeq != 93 and a.residue.name != "NMA"
and a.residue.name != "NME" and a.residue.name != "ACE"
]
active_pdb = md.load(active_pdb_file, atom_indices=atom_indices)
featurizer = DihedralFeaturizer(types=['phi', 'psi', 'chi2'])
active_pdb_features = featurizer.transform(active_pdb)
active_pdb_projected = fit_model.transform(active_pdb_features)
print((active_pdb_projected[0:4]))
def Get_combined_features_villin():
from msmbuilder.featurizer import DihedralFeaturizer
from msmbuilder.featurizer import ContactFeaturizer
diheds= DihedralFeaturizer()
contacts=ContactFeaturizer()
features=[("di_villin",diheds),("con_villin",contacts)]
import os
import shutil
os.chdir('/homes/anuginueni/traj_villin')
if(os.path.isdir('/homes/anuginueni/traj_villin/combined')):
shutil.rmtree('/homes/anuginueni/traj_villin/combined')
from msmbuilder.dataset import dataset
xyz = dataset( "/homes/anuginueni/traj_villin/*.xtc",topology='/homes/anuginueni/traj_villin/filtered.pdb',stride=5)
from msmbuilder.feature_selection import FeatureSelector
comb_features=FeatureSelector(features)
co=xyz.fit_transform_with(comb_features, '/homes/anuginueni/traj_villin/combined/', fmt='dir-npy')
return co
def test_pickle():
"""Test pickling an HMM"""
trajectories = AlanineDipeptide().get_cached().trajectories
topology = trajectories[0].topology
indices = topology.select('symbol C or symbol O or symbol N')
featurizer = DihedralFeaturizer(['phi', 'psi'], trajectories[0][0])
sequences = featurizer.transform(trajectories)
hmm = VonMisesHMM(n_states=4, n_init=1)
hmm.fit(sequences)
logprob, hidden = hmm.predict(sequences)
with tempfile.TemporaryFile() as savefile:
pickle.dump(hmm, savefile)
savefile.seek(0, 0)
hmm2 = pickle.load(savefile)
logprob2, hidden2 = hmm2.predict(sequences)
assert (logprob == logprob2)
def test_feature_slicer():
trajectories = AlanineDipeptide().get_cached().trajectories
f = DihedralFeaturizer()
fs = FeatureSlicer(f, indices=[0, 1])
y1 = fs.transform(trajectories)
assert y1[0].shape[1] == 2
df = pd.DataFrame(fs.describe_features(trajectories[0]))
assert len(df) == 2
assert 'psi' not in df.featuregroup[0]
assert 'psi' not in df.featuregroup[1]
fs = FeatureSlicer(f, indices=[2, 3])
y1 = fs.transform(trajectories)
assert y1[0].shape[1] == 2
df = pd.DataFrame(fs.describe_features(trajectories[0]))
assert len(df) == 2
assert 'phi' not in df.featuregroup[0]
assert 'phi' not in df.featuregroup[1]
def featurize_trajectories(coords, featurizer):
'''
Input
coords : list of 'MDTrajDataset' object
Output
features : list of arrays, length n_trajs, each of shape (n_samples, n_features)
'''
if featurizer == 'RMSDFeaturizer':
from msmbuilder.featurizer import RMSDFeaturizer
feat = RMSDFeaturizer(reference_traj=coords[0])
elif featurizer == 'DRIDFeaturizer':
from msmbuilder.featurizer import DRIDFeaturizer
feat = DRIDFeaturizer()
elif featurizer == 'ContactFeaturizer':
from msmbuilder.featurizer import ContactFeaturizer
feat = ContactFeaturizer(scheme='ca')
elif featurizer == 'DihedralFeaturizer':
from msmbuilder.featurizer import DihedralFeaturizer
feat = DihedralFeaturizer(types=['phi', 'psi'])
return feat.fit_transform(coords)
def read_and_featurize(filename, dihedrals=['phi', 'psi', 'chi2'], stride=10):
print(("reading and featurizing %s" % (filename)))
traj = md.load(filename).select('chain A and protein')
featurizer = DihedralFeaturizer(types=dihedrals)
features = featurizer.transform(traj_list=traj)
print("finished featurizing")
directory = filename.split("/")
condition = directory[len(directory) - 2]
dcd_file = directory[len(directory) - 1]
new_file = "%s_features_stride%d.h5" % (dcd_file.rsplit(".", 1)[0], stride)
new_root_dir = "/home/enf/b2ar_analysis/subsampled_features/"
new_condition_dir = "%s/%s" % (new_root_dir, condition)
if not os.path.exists(new_condition_dir):
os.makedirs(new_condition_dir)
new_file_full = "%s/%s/%s" % (new_root_dir, condition, new_file)
print(("saving features as %s" % new_file_full))
verbosedump(features, new_file_full)
return features
def test_FeatureSelector_describe_features():
rnd_traj = np.random.randint(len(trajectories))
f_ca = ContactFeaturizer(scheme='CA', ignore_nonprotein=True)
f1 = f_ca.transform([trajectories[rnd_traj]])
df1 = pd.DataFrame(f_ca.describe_features(trajectories[rnd_traj]))
f_dih = DihedralFeaturizer()
f2 = f_dih.transform([trajectories[rnd_traj]])
df2 = pd.DataFrame(f_dih.describe_features(trajectories[rnd_traj]))
df_dict = {}
df_dict["ca"] = df1
df_dict["dih"] = df2
f_comb = FeatureSelector([('ca', f_ca), ('dih', f_dih)])
f3 = f_comb.transform([trajectories[rnd_traj]])
df3 = pd.DataFrame(f_comb.describe_features(trajectories[rnd_traj]))
assert len(df3) == len(df1) + len(df2)
df4 = pd.concat([df_dict[i] for i in f_comb.feat_list])
# lets randomly compare 40 features
for i in np.random.choice(range(len(df3)), 40):
for j in df3.columns:
assert eq(df3.iloc[i][j], df4.iloc[i][j])
topology=fs_peptide.data_dir + '/fs-peptide.pdb',
stride=10)
print("{} trjaectories".format(len(xyz)))
# msmbuilder does not keep track of units! You must keep track of your
# data's timestep
to_ns = 0.5
print("with length {} ns".format(set(len(x) * to_ns for x in xyz)))
if which_dataset == 'apo_calmodulin':
print('correct')
xyz = dataset('/scratch/users/mincheol/apo_trajectories' + '/*.lh5',
stride=10)
#featurization
from msmbuilder.featurizer import DihedralFeaturizer
featurizer = DihedralFeaturizer(types=['phi', 'psi'], sincos=False)
print(xyz)
diheds = xyz.fit_transform_with(featurizer, 'diheds/', fmt='dir-npy')
#tICA
from msmbuilder.decomposition import tICA
if which_dataset == 'fspeptide':
tica_model = tICA(lag_time=2, n_components=4)
if which_dataset == 'apo_calmodulin':
tica_model = tICA(lag_time=40, n_components=20)
# fit and transform can be done in seperate steps:
tica_model = diheds.fit_with(tica_model)
tica_trajs = diheds.transform_with(tica_model, 'ticas/', fmt='dir-npy')
from msmbuilder.featurizer import DihedralFeaturizer
import os, glob
from msmbuilder.decomposition import tICA
import mdtraj as md
import pandas as pd
from msmbuilder.msm import MarkovStateModel
from msmbuilder.cluster import KMeans
flist = glob.glob("../trajectory.xtc")
top = md.load("../top.pdb")
trj_list = [md.load(i, top=top) for i in flist]
print("Found %d trajs" % len(trj_list))
f = DihedralFeaturizer(sincos=False)
dump(f, "raw_featurizer.pkl")
feat = f.transform(trj_list)
dump(feat, "raw_features.pkl")
f = load("./featurizer.pkl")
dump(f, "featurizer.pkl")
df1 = pd.DataFrame(f.describe_features(trj_list[0]))
dump(df1, "feature_descriptor.pkl")
feat = f.transform(trj_list)
dump(feat, "features.pkl")
t = tICA(lag_time=100, n_components=2, kinetic_mapping=False)
from msmbuilder.featurizer import DihedralFeaturizer from msmbuilder.decomposition import tICA from msmbuilder.cluster import MiniBatchKMeans from msmbuilder.msm import MarkovStateModel import numpy as np import msmexplorer as msme rs = np.random.RandomState(42) # Load Fs Peptide Data trajs = FsPeptide().get().trajectories # Extract Backbone Dihedrals featurizer = DihedralFeaturizer(types=['chi1']) diheds = featurizer.fit_transform(trajs) # Perform Dimensionality Reduction tica_model = tICA(lag_time=2, n_components=2) tica_trajs = tica_model.fit_transform(diheds) # Perform Clustering clusterer = MiniBatchKMeans(n_clusters=12, random_state=rs) clustered_trajs = clusterer.fit_transform(tica_trajs) # Construct MSM msm = MarkovStateModel(lag_time=2) assignments = msm.fit_transform(clustered_trajs) # Plot Stacked Distributions
"""
Histogram Plot
==============
"""
from msmbuilder.example_datasets import FsPeptide
from msmbuilder.featurizer import DihedralFeaturizer
from msmbuilder.decomposition import tICA
import numpy as np
import msmexplorer as msme
# Load Fs Peptide Data
trajs = FsPeptide().get().trajectories
# Extract Backbone Dihedrals
featurizer = DihedralFeaturizer(types=['phi', 'psi'])
diheds = featurizer.fit_transform(trajs)
# Perform Dimensionality Reduction
tica_model = tICA(lag_time=2, n_components=4)
tica_trajs = tica_model.fit_transform(diheds)
# Plot Histogram
data = np.concatenate(tica_trajs, axis=0)
msme.plot_histogram(data,
color='oxblood',
quantiles=(0.5, ),
labels=['$tIC1$', '$tIC2$', '$tIC3$', '$tIC4$'],
show_titles=True)
