def build_metadata(self, meta):
"""
Builds an msmbuilder metadata object
"""
if meta is None:
try:
self.parser = GenericParser(
fn_re='{}/(e\d+s\d+)_.*/Production.nc'.format(
self.data_folder),
group_names=['sim'],
group_transforms=[lambda x: x],
top_fn='',
step_ps=self.timestep)
meta = gather_metadata('{}/e*/*nc'.format(self.data_folder),
parser)
except:
logger.warning("Could not automatically build metadata")
return None
else:
if not isinstance(meta, pd.DataFrame):
meta = load_meta(meta)
return meta
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)
{{header}}
Meta
----
depends:
- meta.pandas.pickl
- trajs
- top.pdb
"""
import mdtraj as md
from msmbuilder.io import load_meta, itertrajs, save_trajs, preload_top
## Load
meta = load_meta()
centroids = md.load("centroids.xtc", top=preload_top(meta))
## Kernel
SIGMA = 0.3 # nm
from msmbuilder.featurizer import RMSDFeaturizer
import numpy as np
featurizer = RMSDFeaturizer(centroids)
lfeats = {}
for i, traj in itertrajs(meta):
lfeat = featurizer.partial_transform(traj)
lfeat = np.exp(-lfeat**2 / (2 * (SIGMA**2)))
lfeats[i] = lfeat
save_trajs(lfeats, 'ftrajs', meta)
from msmbuilder.io import load_meta, preload_tops
from mdtraj import load
from hbonds import HBondFeaturizer
# from msmbuilder.feature_selection import FeatureSelector
from featureselector import FeatureSelector
meta = load_meta('meta.pandas.pickl')
tops = preload_tops(meta)
trajs = [load(row['traj_fn'], top=tops[row['top_fn']], stride=10)
for i, row in meta.iterrows()]
def traj_summary(ftrajs):
print('Length of ftraj {}'.format(len(ftrajs)))
for traj in ftrajs:
print('\t Shape: {}'.format(traj.shape))
def test_HBondFeaturizer(traj_list):
feat = HBondFeaturizer(freq=0.0)
feat.fit(traj_list)
ftraj = feat.transform(traj_list)
traj_summary(ftraj)
def test_HBondsFeatExtr(traj_list):
features = [('hbonds', HBondFeaturizer())]
feat = FeatureSelector(features, which_feat=['hbonds'])
feat.fit(traj_list)
ftrajs = feat.transform(traj_list)
"""Check for abnormally high rmsd values to a reference structure
{{header}}
Meta
----
depends:
- meta.pandas.pickl
- trajs
- top.pdb
"""
import mdtraj as md
from msmbuilder.io import load_meta, itertrajs, save_trajs
## Load reference structure
ref = md.load("top.pdb")
meta = load_meta()
## Do calculation and save
rmsds = {k: md.rmsd(traj, ref) for k, traj in itertrajs(meta)}
save_trajs(rmsds, 'rmsds', meta)
#!/usr/bin/env python
from msmbuilder.dataset import dataset
from msmbuilder.io import save_trajs, load_meta
import argparse
parser = argparse.ArgumentParser(
prog='dataset_h5_to_npy_dir.py',
formatter_class=argparse.RawDescriptionHelpFormatter,
description='''version1''')
parser.add_argument("dataset", help="""An HDF5 dataset""", type=str)
parser.add_argument("meta", help="A metadata pickl file", type=str)
parser.add_argument("trajs",
help="The folder in which to store the trajs",
type=str,
default='trajs')
if __name__ == '__main__':
args = parser.parse_args()
meta = load_meta(args.meta)
ds = dataset(args.dataset)
trajs = {}
for k, v in ds.items():
trajs[k] = v
save_trajs(trajs, args.trajs, meta)
#!/bin/env python
from msmbuilder.io import gather_metadata, save_meta, NumberedRunsParser
import numpy as np
import mdtraj as md
from msmbuilder.featurizer import DihedralFeaturizer, AtomPairsFeaturizer
from msmbuilder.io import load_meta, preload_tops, save_trajs, save_generic
from multiprocessing import Pool
import contextlib
meta = load_meta("meta.pandas.pickl")
tops = preload_tops(meta)
alpha_carbon_number = np.array([
9, 26, 40, 59, 80, 92, 104, 111, 118, 139, 151, 170, 187, 194, 215, 234,
253, 270, 289, 306, 320, 346, 358, 374, 386, 403, 419, 434, 453, 462, 474,
490, 502, 516, 527, 538, 548, 567, 586, 605, 616, 628, 647, 669, 686, 708,
720, 736, 748, 767, 783, 804, 814, 825, 840, 850, 870, 889, 910, 927, 941,
948, 969, 980, 994, 1004, 1019, 1035, 1054, 1061, 1085, 1099, 1109, 1133,
1153, 1172, 1189, 1202, 1214, 1226, 1233, 1250, 1266, 1290, 1302, 1324,
1335, 1349, 1373, 1395, 1416, 1432, 1444, 1455, 1469, 1483, 1502, 1516,
1530, 1547, 1571, 1593, 1603, 1622, 1634, 1658, 1672, 1682, 1697, 1713,
1730, 1746, 1761, 1777, 1793, 1807, 1827, 1849, 1871, 1885, 1892, 1909,
1933, 1953, 1969, 1983, 2003, 2022, 2036, 2053, 2074, 2086, 2102, 2126,
2138, 2153, 2167, 2174, 2189, 2210, 2234, 2255, 2266, 2283, 2290, 2310,
2327, 2338
])
num = len(alpha_carbon_number)
atompair = []
for i in range(num):
