def __init__(self,S,atomindices=None,permuteindices=None):
super(LPTraj,self).__init__(S)
aidx = list(atomindices) if atomindices != None else []
pidx = list(itertools.chain(*permuteindices)) if permuteindices != None else []
if atomindices == None:
self.TD = RMSD.TheoData(S['XYZList'])
else:
self.TD = RMSD.TheoData(S['XYZList'][:,np.array(aidx)])
def run(pdb, traj, atom_indices):
# you could replace this with your own metric if you like
metric = RMSD(atom_indices)
ppdb = metric.prepare_trajectory(pdb)
ptraj = metric.prepare_trajectory(traj)
distances = metric.one_to_all(ppdb, ptraj, 0)
return distances
def run(project, pdb, atom_indices):
distances = -1 * np.ones((project.n_trajs, np.max(project.n_trajs)))
rmsd = RMSD(atom_indices)
ppdb = rmsd.prepare_trajectory(pdb)
for i in xrange(project.n_trajs):
ptraj = rmsd.prepare_trajectory(project.load_traj(i))
d = rmsd.one_to_all(ppdb, ptraj, 0)
distances[i, 0:len(d)] = d
return distances
def run(project, pdb, atom_indices):
distances = -1 * np.ones((project.n_trajs, np.max(project.n_trajs)))
rmsd = RMSD(atom_indices)
ppdb = rmsd.prepare_trajectory(pdb)
for i in xrange(project.n_trajs):
ptraj = rmsd.prepare_trajectory(project.load_traj(i))
d = rmsd.one_to_all(ppdb, ptraj, 0)
distances[i, 0:len(d)] = d
return distances
def test_gpurmsd():
traj = Trajectory.load_trajectory_file(trj_path)
gpurmsd = GPURMSD()
ptraj = gpurmsd.prepare_trajectory(traj)
gpurmsd._gpurmsd.print_params()
gpu_distances = gpurmsd.one_to_all(ptraj, ptraj, 0)
cpurmsd = RMSD()
ptraj = cpurmsd.prepare_trajectory(traj)
cpu_distances = cpurmsd.one_to_all(ptraj, ptraj, 0)
npt.assert_array_almost_equal(cpu_distances, gpu_distances, decimal=4)
def test_gpurmsd():
traj = Trajectory.load_trajectory_file(trj_path)
gpurmsd = GPURMSD()
ptraj = gpurmsd.prepare_trajectory(traj)
gpurmsd._gpurmsd.print_params()
gpu_distances = gpurmsd.one_to_all(ptraj, ptraj, 0)
cpurmsd = RMSD()
ptraj = cpurmsd.prepare_trajectory(traj)
cpu_distances = cpurmsd.one_to_all(ptraj, ptraj, 0)
npt.assert_array_almost_equal(cpu_distances, gpu_distances, decimal=4)
def __init__(self):
'''
Create an empty Voronoi Tessalation object
NOTES
'''
self.storage = None
self._generator = None
self.metric = RMSD(None)
self.atom_indices = None
self.snapshot_distances = None
self.snapshot_indices = None
def test_lprmsd():
t = Trajectory.load_trajectory_file('trj0.lh5')
MyIdx = np.array([1, 4, 5, 6, 8, 10, 14, 15, 16, 18])
lprmsd = LPRMSD(atomindices=MyIdx, debug=True)
lptraj = lprmsd.prepare_trajectory(t)
dists = lprmsd.one_to_all(lptraj, lptraj, 0)
lprmsd_alt = LPRMSD(atomindices=MyIdx, altindices=MyIdx, debug=True)
lptraj_alt = lprmsd_alt.prepare_trajectory(t)
dists_alt = lprmsd_alt.one_to_all(lptraj_alt, lptraj_alt, 0)
rmsd = RMSD(atomindices=MyIdx)
reftraj = rmsd.prepare_trajectory(t)
ref_dists = rmsd.one_to_all(reftraj, reftraj, 0)
npt.assert_array_almost_equal(dists, ref_dists)
npt.assert_array_almost_equal(dists_alt, ref_dists)
def test_lprmsd():
t = Trajectory.load_trajectory_file('trj0.lh5')
MyIdx = np.array([1, 4, 5, 6, 8, 10, 14, 15, 16, 18])
lprmsd = LPRMSD(atomindices=MyIdx, debug=True)
lptraj = lprmsd.prepare_trajectory(t)
dists = lprmsd.one_to_all(lptraj, lptraj, 0)
lprmsd_alt = LPRMSD(atomindices=MyIdx, altindices=MyIdx, debug=True)
lptraj_alt = lprmsd_alt.prepare_trajectory(t)
dists_alt = lprmsd_alt.one_to_all(lptraj_alt, lptraj_alt, 0)
rmsd = RMSD(atomindices=MyIdx)
reftraj = rmsd.prepare_trajectory(t)
ref_dists = rmsd.one_to_all(reftraj, reftraj, 0)
npt.assert_array_almost_equal(dists, ref_dists)
npt.assert_array_almost_equal(dists_alt, ref_dists)
def __init__(self, structure_or_filename, max_rmsd, atom_indices=None):
"""Create an RMSD validator
Parameters
----------
structure_or_filename : {msmbuilder.Trajectory, str}
The structure to measure distances to, either as a trajectory (the first
frame is the only one that counts) or a path to a trajectory
on disk that can be loaded
max_rmsd : float
The threshold rmsd
atom_indices : np.array [ndim=1, dtype=int]
The indices over which you want to measure RMSD
"""
metric = RMSD(atom_indices)
super(RMSDExplosionValidator, self).__init__(structure_or_filename,
metric, max_rmsd)
class VoronoiTesselation(object):
'''
Hold the MSM Clustering description and the associated state assignments to decide if a trajectory has hit a core
Notes
-----
'''
def __init__(self):
'''
Create an empty Voronoi Tessalation object
NOTES
'''
self.storage = None
self._generator = None
self.metric = RMSD(None)
self.atom_indices = None
self.snapshot_distances = None
self.snapshot_indices = None
################################################################################
def update_cluster_from_storage(self):
'''
Update the set of generators from the associates trajectory storage
Notes
-----
'''
traj = self.storage.all_snapshot_coordinates_as_mdtraj( self.atom_indices )
args = Object()
args.hybrid_local_num_iters = 50
args.hybrid_global_iters = 0
args.hybrid_ignore_max_objective = False
args.hybrid_too_close_cutoff = 0.0001
args.hybrid_num_clusters = self.n_centers
args.hybrid_distance_cutoff = None
ptrajs = None
clusterer = clustering.HybridKMedoids(
self.metric,
trajectories=traj,
prep_trajectories=ptrajs,
k=args.hybrid_num_clusters,
distance_cutoff=args.hybrid_distance_cutoff,
local_num_iters=args.hybrid_local_num_iters,
global_num_iters=args.hybrid_global_iters,
too_close_cutoff=args.hybrid_too_close_cutoff,
ignore_max_objective=args.hybrid_ignore_max_objective
)
gen_inds = clusterer.get_generator_indices()
self.generators_indices = gen_inds
self.generators = traj[gen_inds]
return
@property
def size(self):
'''
Return the number of generators used in the tesselation
Returns
-------
length : int
number of generators
'''
return len(self.generators)
def assign_storage(self):
'''
Assign all snapshots in the associates trajectory storage to the generators
Notes
-----
This allows later to access everything fast
'''
traj = self.storage.all_snapshot_coordinates_as_mdtraj( self.atom_indices )
n_frames = len(traj)
assignments = -1 * np.ones(n_frames, dtype='int')
distances = -1 * np.ones(n_frames, dtype='float32')
pgens = self.metric.prepare_trajectory(self.generators)
ptraj = self.metric.prepare_trajectory(traj)
for j in xrange(len(traj)):
d = self.metric.one_to_all(ptraj, pgens, j)
assignments[j] = np.argmin(d)
distances[j] = d[assignments[j]]
self.snapshot_indices = np.array(assignments, dtype='int')
self.snapshot_distances = np.array(distances, dtype='float')
return
def assign_all_trajectories(self):
'''
Assign all trajectories in the associates trajectory storage to the generators
Returns
-------
clusterlist : list of int
list of cluster IDs
Notes
-----
This needs assign_storage() to be run before!
'''
return [ self.snapshot_indices[t] for t in self.storage.all_trajectory_indices() ]
def assign_index_trajectory(self, indices):
'''
Assign snapshots with IDs indices to the generators
Returns
-------
clusterlist (list of int) - list of cluster IDs
NOTES
'''
if self.snapshot_indices is not None:
return self.snapshot_indices[indices]
else:
return None
def assign_snapshot(self, snapshot):
'''
Assign a single snapshot to the cluster centers
Returns
-------
assignment : int
cluster IDs
distance: float
distance to cluster _generator in measure of the metric (RMSD)
'''
assignments, distances = self.assign(Trajectory([snapshot]))
return assignments[0], distances[0]
def assign(self, traj, recalc = False):
'''
Assign a Trajectory object to the cluster
Parameters
----------
traj : Trajectory
trajectory to be clustered
recalc : bool
forces a calculation of the cluster center and not using the cached assignments (Default False)
RETURNS
assignments (numpy.array(n_frames, dtype='int')) - array of cluster IDs
distances (numpy.array(n_frames, dtype='float')) - distances to cluster _generator in measure of the metric (RMSD)
'''
n_frames = len(traj)
if self.snapshot_indices is not None:
# We do not check if the snapshot_indices are properly updated!
# Checking might be too expensive
indices = traj.indices()
assignments = self.snapshot_indices[indices]
distances = self.snapshot_distances[indices]
else:
assignments = -1 * np.ones(n_frames, dtype='int')
distances = -1 * np.ones(n_frames, dtype='float32')
pgens = self.metric.prepare_trajectory( self.generators )
ptraj = self.metric.prepare_trajectory( traj.subset(self.atom_indices).md() )
for j in xrange(len(traj)):
d = self.metric.one_to_all(ptraj, pgens, j)
assignments[j] = np.argmin(d)
distances[j] = d[assignments[j]]
return assignments, distances
def write_trajectory(self,
clone_dir,
output_dir,
trajectory_number,
stride,
max_rmsd,
min_gens,
center_conformations,
memory_check,
omp_parallel_rmsd=True):
"""
This function takes in a path to a CLONE and merges all the XTC files
it finds into a LH5 trajectory:
Parameters
----------
clone_dir : str
the directory in which the xtc files are found. All of the xtc files
in this directory are joined together to make a single trajectory
(.lh5) output file
output_dir : str
directory where the outputted files will be placed
trajectory_number : int
A unique number for this trajectory. This number is used in
constructing the filename to write the outputted .lh5 trajectory to,
and thus must be unique
stride: int
Subsample by only considering every Nth snapshop.
max_rmsd: {int, None}
if this value is not None, calculate the RMSD to the pdb_file from
each snapshot and reject trajectories which have snapshots with RMSD
greated than max_rmsd. If None, no check is performed
min_gens : int
Discard the trajectories that contain fewer than `min_gens` XTC files.
center_conformations : bool
center conformations before saving.
memory_check : bool
if yes, uses the memory dictionary to do an update rather than a
complete re-convert.
omp_parallel_rmsd : bool
If true, use OpenMP accelerated RMSD calculation for max_rmsd check
"""
xtc_files = self.list_xtcs_in_dir(clone_dir)
# Ensure that we're only joining contiguously numbered xtc files -- starting at 0 --
# into a trajectory. If there are gaps in the xtc files in the directory, we only
# want to use the the ones such that they are contiguously numbered
i = 0
for i, filename in enumerate(xtc_files):
if self.integer_component(filename) != i:
logger.error(
"Found discontinuity in xtc numbering - check data in %s",
clone_dir)
xtc_files = xtc_files[0:i]
break
# check the memory object to see which xtc files have already been converted, and
# exclude those from this conversion
if memory_check:
if clone_dir in self.memory.keys():
previous_convert_exists = True
num_xtcs_converted = self.memory[clone_dir][1]
if len(
xtc_files
) == num_xtcs_converted: # if we have converted everything,
logger.info(
"Already converted all files in %s, skipping...",
clone_dir)
return # just bail out
else:
xtc_files = xtc_files[num_xtcs_converted:]
else:
previous_convert_exists = False
else:
previous_convert_exists = False
xtc_file_paths = [os.path.join(clone_dir, f) for f in xtc_files]
logger.info("Processing %d xtc files in clone_dir = %s",
len(xtc_files), clone_dir)
if len(xtc_files) <= min_gens:
logger.info("Skipping trajectory in clone_dir = %s", clone_dir)
logger.info("Too few xtc files (generations).")
return
try:
# [this should check for and discard overlapping snapshots]
trajectory = Trajectory.load_from_xtc(
xtc_file_paths,
PDBFilename=self.pdb_topology,
discard_overlapping_frames=True)
except IOError as e:
logger.error(
"IOError (%s) when processing trajectory in clone_dir = %s", e,
clone_dir)
logger.error(
"Attempting rescue by disregarding final frame, which is often"
)
logger.error("the first/only frame to be corrupted")
if len(xtc_file_paths) == 1:
logger.error(
"Didn't find any other frames in %s, continuing...",
clone_dir)
return
try:
trajectory = Trajectory.load_from_xtc(
xtc_file_paths[0:-1], PDBFilename=self.pdb_topology)
except IOError:
logger.error(
"Unfortunately, the error remained even after ignoring the final frame."
)
logger.error("Skipping the trajectory in clone_dir = %s",
clone_dir)
return
else:
logger.error(
"Sucessfully recovered from IOError by disregarding final frame."
)
if max_rmsd is not None:
atomindices = [int(i) - 1 for i in trajectory['AtomID']]
rmsdmetric = RMSD(atomindices, omp_parallel=omp_parallel_rmsd)
ppdb = rmsdmetric.prepare_trajectory(
Trajectory.load_trajectory_file(self.pdb_topology))
ptraj = rmsdmetric.prepare_trajectory(trajectory)
rmsds = rmsdmetric.one_to_all(ppdb, ptraj, 0)
if max(rmsds) > max_rmsd:
logger.warning("Snapshot %d RMSD %f > the %f cutoff",
argmax(rmsds), max(rmsds), max_rmsd)
logger.warning("Dropping trajectory")
return
if center_conformations:
RMSD.TheoData.centerConformations(trajectory["XYZList"])
# if we are adding to a previous trajectory, we have to load that traj up and extend it
if previous_convert_exists:
output_filename = self.memory[clone_dir][0]
output_file_path = output_filename
logger.info("Extending: %s", output_filename)
assert os.path.exists(output_filename)
# load the traj and extend it [this should check for and discard overlapping snapshots]
Trajectory.append_frames_to_file(output_filename,
trajectory['XYZList'][::stride],
discard_overlapping_frames=True)
num_xtcs_processed = len(
xtc_file_paths) + self.memory[clone_dir][1]
# if we are not adding to a traj, then we create a new one
else:
output_filename = 'trj%s.lh5' % trajectory_number
output_file_path = os.path.join(output_dir, output_filename)
if os.path.exists(output_file_path):
logger.info("The file name %s already exists. Skipping it.",
output_file_path)
return
# stide and discard by snapshot
trajectory['XYZList'] = trajectory['XYZList'][::stride]
trajectory.save(output_file_path)
num_xtcs_processed = len(xtc_file_paths)
# log what we did into the memory object
self.memory[clone_dir] = [output_file_path, num_xtcs_processed]
return
target = c_xyzlist[which, :, :]
progressive = False
for i in range(1, len(xyzlist)):
if progressive:
target = c_xyzlist[i - i]
rmsd, operator = kabsch(c_xyzlist[i], target, operator=True)
c_xyzlist[i] = operator(c_xyzlist[i])
return c_xyzlist
if __name__ == '__main__':
"Some test code"
N = 40
query = np.arange(N)[:, np.newaxis] * np.random.randn(N, 3)
target = np.arange(N)[:, np.newaxis] * np.random.randn(N, 3)
dist, op = kabsch(query, target)
print('my rmsd ', dist)
from msmbuilder.metrics import RMSD
_rmsdcalc = RMSD()
t0 = RMSD.TheoData(query[np.newaxis, :, :])
t1 = RMSD.TheoData(target[np.newaxis, :, :])
print('msmbuilder rmsd', _rmsdcalc.one_to_all(t0, t1, 0)[0])
print(np.sqrt(np.sum(np.square(target - op(query))) / N))
def cpudist(t):
rmsd = RMSD()
pt = rmsd.prepare_trajectory(t)
return rmsd.one_to_all(pt, pt, 0)
else:
target = c_xyzlist[which, :, :]
progressive = False
for i in range(1, len(xyzlist)):
if progressive:
target = c_xyzlist[i-i]
rmsd, operator = kabsch(c_xyzlist[i], target, operator=True)
c_xyzlist[i] = operator(c_xyzlist[i])
return c_xyzlist
if __name__ == '__main__':
"Some test code"
N = 40
query = np.arange(N)[:, np.newaxis] * np.random.randn(N, 3)
target = np.arange(N)[:, np.newaxis] * np.random.randn(N, 3)
dist, op = kabsch(query, target)
print 'my rmsd ', dist
from msmbuilder.metrics import RMSD
_rmsdcalc = RMSD()
t0 = RMSD.TheoData(query[np.newaxis, :, :])
t1 = RMSD.TheoData(target[np.newaxis, :, :])
print 'msmbuilder rmsd', _rmsdcalc.one_to_all(t0, t1, 0)[0]
print np.sqrt(np.sum(np.square(target - op(query))) / N)
def construct_metric(args):
if args.metric == 'rmsd':
if args.rmsd_atom_indices != 'all':
atom_indices = np.loadtxt(args.rmsd_atom_indices, np.int)
else:
atom_indices = None
metric = RMSD(atom_indices) #, omp_parallel=args.rmsd_omp_parallel)
elif args.metric == 'dihedral':
metric = Dihedral(metric=args.dihedral_metric,
p=args.dihedral_p,
angles=args.dihedral_angles)
elif args.metric == 'contact':
if args.contact_which != 'all':
contact_which = np.loadtxt(args.contact_which, np.int)
else:
contact_which = 'all'
if args.contact_cutoff_file != None: #getattr(args, 'contact_cutoff_file'):
contact_cutoff = np.loadtxt(args.contact_cutoff_file, np.float)
elif args.contact_cutoff != None:
contact_cutoff = float(args.contact_cutoff)
else:
contact_cutoff = None
if contact_cutoff != None and contact_cutoff < 0:
metric = ContinuousContact(contacts=contact_which,
scheme=args.contact_scheme)
else:
metric = BooleanContact(contacts=contact_which,
cutoff=contact_cutoff,
scheme=args.contact_scheme)
elif args.metric == 'atompairs':
if args.atompairs_which != None:
pairs = np.loadtxt(args.atompairs_which, np.int)
else:
pairs = None
metric = AtomPairs(metric=args.atompairs_metric,
p=args.atompairs_p,
atom_pairs=pairs)
elif args.metric == 'custom':
with open(args.picklemetric_input) as f:
metric = pickle.load(f)
print '#' * 80
print 'Loaded custom metric:'
print metric
print '#' * 80
else:
# apply the constructor on args and take the first non-none element
# note that using these itertools constructs, we'll only actual
# execute the constructor until the match is achieved
metrics = itertools.imap(lambda c: c(args),
locate_metric_plugins('construct_metric'))
try:
metric = itertools.dropwhile(lambda c: not c, metrics).next()
except StopIteration:
# This means that none of the plugins acceptedthe metric
raise RuntimeError(
"Bad metric. Could not be constructed by any built-in or plugin metric. Perhaps you have a poorly written plugin?"
)
if not isinstance(metric, AbstractDistanceMetric):
return ValueError("%s is not a AbstractDistanceMetric" % metric)
return metric
def cpudist(t):
rmsd = RMSD()
pt = rmsd.prepare_trajectory(t)
return rmsd.one_to_all(pt, pt, 0)
def write_trajectory(self, clone_dir, output_dir, trajectory_number, stride,
max_rmsd, min_gens, center_conformations, memory_check,
omp_parallel_rmsd=True):
"""
This function takes in a path to a CLONE and merges all the XTC files
it finds into a H5 trajectory:
Parameters
----------
clone_dir : str
the directory in which the xtc files are found. All of the xtc files
in this directory are joined together to make a single trajectory
(.h5) output file
output_dir : str
directory where the outputted files will be placed
trajectory_number : int
A unique number for this trajectory. This number is used in
constructing the filename to write the outputted .h5 trajectory to,
and thus must be unique
stride: int
Subsample by only considering every Nth snapshop.
max_rmsd: {int, None}
if this value is not None, calculate the RMSD to the pdb_file from
each snapshot and reject trajectories which have snapshots with RMSD
greated than max_rmsd. If None, no check is performed
min_gens : int
Discard the trajectories that contain fewer than `min_gens` XTC files.
center_conformations : bool
center conformations before saving.
memory_check : bool
if yes, uses the memory dictionary to do an update rather than a
complete re-convert.
omp_parallel_rmsd : bool
If true, use OpenMP accelerated RMSD calculation for max_rmsd check
"""
xtc_files = self.list_xtcs_in_dir(clone_dir)
# Ensure that we're only joining contiguously numbered xtc files -- starting at 0 --
# into a trajectory. If there are gaps in the xtc files in the directory, we only
# want to use the the ones such that they are contiguously numbered
i = 0
for i, filename in enumerate(xtc_files):
if self.integer_component(filename) != i:
logger.error("Found discontinuity in xtc numbering - check data in %s", clone_dir)
xtc_files = xtc_files[0:i]
break
# check the memory object to see which xtc files have already been converted, and
# exclude those from this conversion
if memory_check:
if clone_dir in self.memory.keys():
previous_convert_exists = True
num_xtcs_converted = self.memory[clone_dir][1]
if len(xtc_files) == num_xtcs_converted: # if we have converted everything,
logger.info("Already converted all files in %s, skipping...", clone_dir)
return # just bail out
else:
xtc_files = xtc_files[num_xtcs_converted:]
else:
previous_convert_exists = False
else:
previous_convert_exists = False
xtc_file_paths = [os.path.join(clone_dir, f) for f in xtc_files]
logger.info("Processing %d xtc files in clone_dir = %s", len(xtc_files), clone_dir)
if len(xtc_files) <= min_gens:
logger.info("Skipping trajectory in clone_dir = %s", clone_dir)
logger.info("Too few xtc files (generations).")
return
try:
# [this should check for and discard overlapping snapshots]
trajectory = Trajectory.load_from_xtc(xtc_file_paths, PDBFilename=self.pdb_topology,
discard_overlapping_frames=True)
except IOError as e:
logger.error("IOError (%s) when processing trajectory in clone_dir = %s", e, clone_dir)
logger.error("Attempting rescue by disregarding final frame, which is often")
logger.error("the first/only frame to be corrupted")
if len(xtc_file_paths) == 1:
logger.error("Didn't find any other frames in %s, continuing...", clone_dir)
return
try:
trajectory = Trajectory.load_from_xtc(xtc_file_paths[0:-1], PDBFilename=self.pdb_topology)
except IOError:
logger.error("Unfortunately, the error remained even after ignoring the final frame.")
logger.error("Skipping the trajectory in clone_dir = %s", clone_dir)
return
else:
logger.error("Sucessfully recovered from IOError by disregarding final frame.")
if max_rmsd is not None:
atomindices = [ int(i)-1 for i in trajectory['AtomID'] ]
rmsdmetric = RMSD(atomindices, omp_parallel=omp_parallel_rmsd)
ppdb = rmsdmetric.prepare_trajectory(Trajectory.load_trajectory_file(self.pdb_topology))
ptraj = rmsdmetric.prepare_trajectory(trajectory)
rmsds = rmsdmetric.one_to_all(ppdb, ptraj, 0)
if max(rmsds) > max_rmsd:
logger.warning("Snapshot %d RMSD %f > the %f cutoff" , argmax(rmsds), max(rmsds), max_rmsd)
logger.warning("Dropping trajectory")
return
if center_conformations:
RMSD.TheoData.centerConformations(trajectory["XYZList"])
# if we are adding to a previous trajectory, we have to load that traj up and extend it
if previous_convert_exists:
output_filename = self.memory[clone_dir][0]
output_file_path = output_filename
logger.info("Extending: %s", output_filename)
assert os.path.exists( output_filename )
# load the traj and extend it [this should check for and discard overlapping snapshots]
Trajectory.append_frames_to_file( output_filename,
trajectory['XYZList'][::stride],
discard_overlapping_frames=True )
num_xtcs_processed = len(xtc_file_paths) + self.memory[clone_dir][1]
# if we are not adding to a traj, then we create a new one
else:
output_filename = 'trj%s.h5' % trajectory_number
output_file_path = os.path.join(output_dir, output_filename)
if os.path.exists(output_file_path):
logger.info("The file name %s already exists. Skipping it.", output_file_path)
return
# stide and discard by snapshot
trajectory['XYZList'] = trajectory['XYZList'][::stride]
trajectory.save(output_file_path)
num_xtcs_processed = len(xtc_file_paths)
# log what we did into the memory object
self.memory[clone_dir] = [ output_file_path, num_xtcs_processed ]
return
def construct_metric(args):
metric_name = args.metric
if metric_name == 'rmsd':
if args.rmsd_atom_indices != 'all':
atom_indices = np.loadtxt(args.rmsd_atom_indices, np.int)
else:
atom_indices = None
metric = RMSD(atom_indices) # , omp_parallel=args.rmsd_omp_parallel)
elif metric_name == 'dihedral':
metric = Dihedral(metric=args.dihedral_metric,
p=args.dihedral_p,
angles=args.dihedral_angles,
userfilename=args.dihedral_userfilename)
elif metric_name == 'contact':
if args.contact_which != 'all':
contact_which = np.loadtxt(args.contact_which, np.int)
else:
contact_which = 'all'
if args.contact_cutoff_file != None:
contact_cutoff = np.loadtxt(args.contact_cutoff_file, np.float)
elif args.contact_cutoff != None:
contact_cutoff = float(args.contact_cutoff)
else:
contact_cutoff = None
if contact_cutoff != None and contact_cutoff < 0:
metric = ContinuousContact(contacts=contact_which,
scheme=args.contact_scheme)
else:
metric = BooleanContact(contacts=contact_which,
cutoff=contact_cutoff,
scheme=args.contact_scheme)
elif metric_name == 'atompairs':
if args.atompairs_which != None:
pairs = np.loadtxt(args.atompairs_which, np.int)
else:
pairs = None
metric = AtomPairs(metric=args.atompairs_metric,
p=args.atompairs_p,
atom_pairs=pairs)
elif metric_name == 'positions':
target = md.load(args.target)
if args.pos_atom_indices != None:
atom_indices = np.loadtxt(args.pos_atom_indices, np.int)
else:
atom_indices = None
if args.align_indices != None:
align_indices = np.loadtxt(args.align_indices, np.int)
else:
align_indices = None
metric = Positions(target,
atom_indices=atom_indices,
align_indices=align_indices,
metric=args.positions_metric,
p=args.positions_p)
elif metric_name == "tica":
tica_obj = tICA.load(args.tica_fn)
metric = RedDimPNorm(tica_obj,
num_vecs=args.num_vecs,
metric=args.projected_metric,
p=args.p)
elif metric_name == 'custom':
with open(args.picklemetric_input) as f:
metric = pickle.load(f)
print('#' * 80)
print('Loaded custom metric:')
print(metric)
print('#' * 80)
else:
# apply the constructor on args and take the first non-none element
# note that using these itertools constructs, we'll only actual
# execute the constructor until the match is achieved
metrics = [c(args) for c in locate_metric_plugins('construct_metric')]
try:
metric = next(itertools.dropwhile(lambda c: not c, metrics))
except StopIteration:
# This means that none of the plugins acceptedthe metric
raise RuntimeError(
"Bad metric. Could not be constructed by any built-in or plugin metric. Perhaps you have a poorly written plugin?"
)
if not isinstance(metric, AbstractDistanceMetric):
return ValueError("%s is not a AbstractDistanceMetric" % metric)
return metric
