def test_fs_mutinf():
traj = FsPeptide().get().trajectories[0]
idx = [at.index for at in traj.topology.atoms
if at.residue.index in [3, 4, 5, 6, 7, 8]]
traj = traj.atom_slice(atom_indices=idx)[::100]
yield _test_mi_alpha, traj
yield _test_mi_contact, traj
yield _test_mi_dihedral, traj
def test_fs_mutinf():
traj = FsPeptide().get().trajectories[0]
idx = [
at.index for at in traj.topology.atoms
if at.residue.index in [3, 4, 5, 6, 7, 8]
]
traj = traj.atom_slice(atom_indices=idx)[::100]
yield _test_mi_alpha, traj
yield _test_mi_contact, traj
yield _test_mi_dihedral, traj
def test_fs_tent():
traj1, traj2 = FsPeptide().get().trajectories[:2]
idx = [at.index for at in traj1.topology.atoms
if at.residue.index in [3, 4, 5, 6, 7, 8]]
traj1 = traj1.atom_slice(atom_indices=idx)[::100]
traj2 = traj2.atom_slice(atom_indices=idx)[::100]
traj = (traj1, traj2)
yield _test_tent_alpha, traj
yield _test_tent_contact, traj
yield _test_tent_dihedral, traj
def test_fs_tent():
cwd = os.path.abspath(os.curdir)
dirname = tempfile.mkdtemp()
FsPeptide(dirname).get()
try:
os.chdir(dirname)
top = md.load(dirname + '/fs_peptide/fs-peptide.pdb')
idx = [
at.index for at in top.topology.atoms
if at.residue.index in [3, 4, 5, 6, 7, 8]
]
traj1 = md.load(dirname + '/fs_peptide/trajectory-1.xtc',
stride=100,
top=top,
atom_indices=idx)
traj2 = md.load(dirname + '/fs_peptide/trajectory-2.xtc',
stride=100,
top=top,
atom_indices=idx)
traj = (traj1, traj2)
yield _test_tent_alpha, traj
yield _test_tent_contact, traj
yield _test_tent_dihedral, traj
finally:
os.chdir(cwd)
shutil.rmtree(dirname)
def test_msmb_feat_select_skeleton():
try:
from msmbuilder.example_datasets import FsPeptide
except ImportError as e:
raise SkipTest(e)
assert OSPREY_BIN is not None
cwd = os.path.abspath(os.curdir)
dirname = tempfile.mkdtemp()
FsPeptide(dirname).get()
try:
os.chdir(dirname)
subprocess.check_call([
OSPREY_BIN, 'skeleton', '-t', 'msmb_feat_select', '-f',
'config.yaml'
])
subprocess.check_call([OSPREY_BIN, 'worker', 'config.yaml', '-n', '1'])
assert os.path.exists('osprey-trials.db')
yield _test_dump_1
yield _test_plot_1
finally:
os.chdir(cwd)
shutil.rmtree(dirname)
def test_fs_tent():
traj1, traj2 = FsPeptide().get().trajectories[:2]
idx = [
at.index for at in traj1.topology.atoms
if at.residue.index in [3, 4, 5, 6, 7, 8]
]
traj1 = traj1.atom_slice(atom_indices=idx)[::100]
traj2 = traj2.atom_slice(atom_indices=idx)[::100]
traj = (traj1, traj2)
yield _test_tent_alpha, traj
yield _test_tent_contact, traj
yield _test_tent_dihedral, traj
def test_MDTrajDatasetLoader_1():
try:
from msmbuilder.example_datasets import FsPeptide
except ImportError as e:
raise SkipTest(e)
cwd = os.path.abspath(os.curdir)
dirname = tempfile.mkdtemp()
fs_pept = FsPeptide(dirname)
fs_pept.get()
try:
loader = MDTrajDatasetLoader(os.path.join(fs_pept.data_dir, '*.xtc'),
topology=os.path.join(fs_pept.data_dir, 'fs-peptide.pdb'))
X, y = loader.load()
assert len(X) == 28
assert y is None
finally:
shutil.rmtree(dirname)
def test_MDTrajDatasetLoader_1():
from msmbuilder.example_datasets import FsPeptide
fs_pept = FsPeptide()
loader = MDTrajDatasetLoader(os.path.join(fs_pept.data_dir, '*.xtc'),
topology=os.path.join(fs_pept.data_dir,
'fs-peptide.pdb'))
X, y = loader.load()
assert len(X) == 28
assert y is None
def test_MDTrajDatasetLoader_1():
try:
from msmbuilder.example_datasets import FsPeptide
except ImportError as e:
raise SkipTest(e)
cwd = os.path.abspath(os.curdir)
dirname = tempfile.mkdtemp()
fs_pept = FsPeptide(dirname)
fs_pept.get()
try:
loader = MDTrajDatasetLoader(os.path.join(fs_pept.data_dir, '*.xtc'),
topology=os.path.join(
fs_pept.data_dir, 'fs-peptide.pdb'))
X, y = loader.load()
assert len(X) == 28
assert y is None
finally:
shutil.rmtree(dirname)
num_clusters = args.num_clusters
which_dataset = args.which_dataset
feature = args.feature
# Folder to save everything
folder = '/scratch/users/mincheol/' + which_dataset + '/sim_datasets/'
import tempfile
import os
os.chdir(tempfile.mkdtemp())
xyz = [] # placeholder
print(which_dataset)
if which_dataset == 'fspeptide':
# Get data
fs_peptide = FsPeptide()
fs_peptide.cache()
xyz = dataset(fs_peptide.data_dir + "/*.xtc",
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)
========================= """ from msmbuilder.example_datasets import FsPeptide 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)
import numpy as np
import mdtraj as md
import pandas as pd
import glob
import os
from scipy.stats import vonmises as vm
from msmbuilder.example_datasets import fetch_fs_peptide, FsPeptide
from msmbuilder.featurizer import DihedralFeaturizer, AlphaAngleFeaturizer,\
KappaAngleFeaturizer,ContactFeaturizer,VonMisesFeaturizer
"""
Series of tests to make sure all the describe features are putting the right features in the
right place
"""
fs = FsPeptide()
fs.cache()
dirname = fs.data_dir
top = md.load(dirname + "/fs-peptide.pdb")
if np.random.choice([True, False]):
atom_ind = [
i.index for i in top.top.atoms if i.residue.is_protein and (
i.residue.index in range(15) or i.residue.index in range(20, 23))
]
else:
atom_ind = [i.index for i in top.top.atoms]
trajectories = [
md.load(fn, stride=100, top=top, atom_indices=atom_ind)
for fn in glob.glob(os.path.join(dirname, "trajectory*.xtc"))
"""Get sample data for testing and experimenting
msmbuilder autogenerated template version 2
created 2017-05-30T15:16:59.061464
please cite msmbuilder in any publications
"""
import os
from msmbuilder.example_datasets import FsPeptide
FsPeptide("./").cache()
if not os.path.exists("trajs"):
os.symlink("fs_peptide", "trajs")
if not os.path.exists("top.pdb"):
os.symlink("fs_peptide/fs-peptide.pdb", "top.pdb")
def load(self):
from msmbuilder.example_datasets import FsPeptide
trajectories = FsPeptide(verbose=False).get().trajectories
return trajectories, None
import mdtraj as md
import numpy as np
from mdtraj.testing import eq
from msmbuilder.featurizer import SASAFeaturizer
from msmbuilder.example_datasets import FsPeptide
t = FsPeptide().get().trajectories[0][:10]
def _test_sasa_featurizer(t, value):
sasa = md.shrake_rupley(t)
rids = np.array([a.residue.index for a in t.top.atoms])
for i, rid in enumerate(np.unique(rids)):
mask = (rids == rid)
eq(value[:, i], np.sum(sasa[:, mask], axis=1))
def test_sasa_featurizer_1():
# t = md.load(get_fn('frame0.h5'))
value = SASAFeaturizer(mode='residue').partial_transform(t)
assert value.shape == (t.n_frames, t.n_residues)
_test_sasa_featurizer(t, value)
def test_sasa_featurizer_2():
# t = md.load(get_fn('frame0.h5'))
# scramle the order of the atoms, and which residue each is a
""" Trace Plot ========== """ from msmbuilder.example_datasets import FsPeptide from msmbuilder.featurizer import RMSDFeaturizer import msmexplorer as msme # Load Fs Peptide Data traj = FsPeptide().get().trajectories[0] # Calculate RMSD featurizer = RMSDFeaturizer(reference_traj=traj[0]) rmsd = featurizer.partial_transform(traj).flatten() # Plot Trace msme.plot_trace(rmsd, label='traj0', xlabel='Timestep', ylabel='RMSD (nm)')
2)) # keeps track of visited frames (frame, # of times visited)
visited[:, 0] = range(X.shape[0])
for k in range(0, num_traj):
if len(choices) == 0:
idx = np.where(visited[:, 1] == min(visited[:, 1]))[0]
choices = set(visited[idx, 0])
start = random.sample(choices, 1)[0]
choices.remove(start)
traj = [start]
visited[start, 1] += 1
for i in range(0, length - 1):
neighbor = graph_dict[traj[i]]
next_frame = random_frame_smart(neighbor, choices)
traj.append(next_frame)
visited[next_frame, 1] += 1
our_traj = np.reshape(X[traj, :], (len(traj), len(X[0]) / 3, 3))
md_traj = md.Trajectory(
our_traj,
md.load(fs_peptide.data_dir + '/fs-peptide.pdb').topology)
filename = which_dataset + '_sim_' + str(cluster_degree) + '_' + str(
frame_degree) + '_' + str(k + 1) + '.xtc'
md_traj.save_xtc(folder_name + filename)
traj_folder = '/scratch/users/mincheol/' + which_dataset + '/trajectories/temp/'
#generate_md_traj_old(edges, X, traj_folder, num_traj, traj_length, random=sample_rand)
fs_peptide = FsPeptide()
generate_md_traj_smart(edges, X, traj_folder, num_traj, traj_length)
