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)
#featurization
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"))
]