def featurize(featurizer, meta_data):
tops = preload_tops(meta)
def feat(irow):
i, row = irow
traj = md.load(row['traj_fn'], top=tops[row['top_fn']])
feat_traj = featurizer.partial_transform(traj)
return i, feat_traj
feature_trajs = dict(map(feat, meta.iterrows()))
save_trajs(feature_trajs, 'ftrajs', meta)
save_generic(featurizer, 'featurizer.pickl')
return feature_trajs
def sample_clusters():
meta = load_meta()
tops = preload_tops(meta)
print('Sampling trajectories')
ref = md.load('topology.pdb')
for i in range(int(num_clusters)):
print(i)
df_smp = df.ix[df['Trajectory']==i, ['Key', 'Time_ps']].sample(100)
inds = zip(df_smp['Key'], df_smp['Time_ps'])
# Use loc because sample_dimension is nice
traj = md.join(
md.load_frame(meta.loc[traj_i]['traj_fn'], index=frame_i, top=meta.loc[traj_i]['top_fn'])
for traj_i, frame_i in inds
)
# Original trajectories include both BT1 and BT2 so need to superpose
traj.superpose(reference=ref)
# Save
traj_fn = "clusters/rmsd_cluster-{}.dcd".format(i)
backup(traj_fn)
traj.save(traj_fn)
from msmbuilder.featurizer import RawPositionsFeaturizer
import numpy as np
import mdtraj as md
from msmbuilder.io import load_meta, preload_tops, save_trajs, save_generic
from multiprocessing import Pool
import matplotlib
matplotlib.use('Agg')
from matplotlib.pylab import plt
from utilities import plot_box, feat
if __name__ == '__main__':
# Load
meta = load_meta()
tops = preload_tops(meta)
# Select featurizer
feature_name = 'Positions'
reference = md.load('topology.pdb')
featurizer = RawPositionsFeaturizer(ref_traj=reference)
args = zip(meta.iterrows(), [featurizer] * meta.shape[0],
[tops] * meta.shape[0])
# Do it in parallel
with Pool() as pool:
feature_trajs = dict(pool.imap_unordered(feat, args))
# Plot unscaled features
ftrajs = np.concatenate([fx[::100] for fx in feature_trajs.values()])
Meta
----
depends:
- meta.pandas.pickl
- trajs
- top.pdb
"""
import mdtraj as md
from msmbuilder.featurizer import DihedralFeaturizer
from msmbuilder.io import load_meta, preload_tops, save_trajs, save_generic
from multiprocessing import Pool
## Load
meta = load_meta()
tops = preload_tops(meta)
dihed_feat = DihedralFeaturizer()
## Featurize logic
def feat(irow):
i, row = irow
traj = md.load(row['traj_fn'], top=tops[row['top_fn']])
feat_traj = dihed_feat.partial_transform(traj)
return i, feat_traj
## Do it in parallel
with Pool() as pool:
dihed_trajs = dict(pool.imap_unordered(feat, meta.iterrows()))