def main(modeldir, genfile, type, write=False):
data=dict()
pops=numpy.loadtxt('%s/Populations.dat' % modeldir)
map=numpy.loadtxt('%s/Mapping.dat' % modeldir)
frames=numpy.where(map!=-1)[0]
unbound=numpy.loadtxt('%s/tpt-rmsd-%s/unbound_%s_states.txt' % (modeldir, type, type), dtype=int)
bound=numpy.loadtxt('%s/tpt-rmsd-%s/bound_%s_states.txt' % (modeldir, type, type), dtype=int)
dir=modeldir.split('Data')[0]
name=glob.glob('%s/fkbp*xtal*pdb' % dir)
pdb=Trajectory.load_from_pdb(name[0])
paths=io.loadh('%s/tpt-rmsd-%s/Paths.h5' % (modeldir, type))
committors=numpy.loadtxt('%s/commitor_states.txt' % modeldir, dtype=int)
colors=['red', 'orange', 'green', 'cyan', 'blue', 'purple']
colors=colors*40
if type=='strict':
ref=5
elif type=='super-strict':
ref=3
elif type=='medium':
ref=10
elif type=='loose':
ref=15
#for p in range(0, 3):
for p in range(0, 1):
path=paths['Paths'][p]
print "Bottleneck", paths['Bottlenecks'][p]
flux=paths['fluxes'][p]/paths['fluxes'][0]
if flux < 0.2:
break
print "flux %s" % flux
frames=numpy.where(path!=-1)[0]
path=numpy.array(path[frames], dtype=int)
print path
if write==True:
size=(paths['fluxes'][p]/paths['fluxes'][0])*1000
traj=Trajectory.load_from_xtc('%s/tpt-rmsd-%s/path%s_sample20.xtc' % (modeldir, type, p), Conf=pdb)
data=build_metric(dir, pdb, traj)
dir=modeldir.split('Data')[0]
for op in sorted(data.keys()):
#for op in residues:
pylab.figure()
pylab.scatter(data['rmsd'], data[op], c=colors[p], alpha=0.7) #, s=size)
for j in paths['Bottlenecks'][p]:
frame=numpy.where(paths['Paths'][p]==j)[0]
pylab.scatter(data['rmsd'][frame*20], data[op][frame*20], marker='x', c='k', alpha=0.7, s=50)
location=numpy.where(committors==paths['Paths'][p][frame])[0]
if location.size:
print "path %s state %s bottleneck in committors" % (p, j)
print data['rmsd'][frame*20], data[op][frame*20]
pylab.title('path %s' % p)
pylab.xlabel('P-L RMSD')
#pylab.xlabel('P-L COM')
pylab.ylabel(op)
pylab.xlim(0,max(data['rmsd'])+5)
#pylab.ylim(0,max(data[op])+5)
pylab.show()
def test_xtc_dcd():
pdb_filename = get("native.pdb", just_filename=True)
xtc_filename = get('RUN00_frame0.xtc', just_filename=True)
dcd_filename = get('RUN00_frame0.dcd', just_filename=True)
r_xtc = Trajectory.load_from_xtc(xtc_filename, pdb_filename)
r_dcd = Trajectory.load_from_dcd(dcd_filename, pdb_filename)
x_xtc = r_xtc["XYZList"]
x_dcd = r_dcd["XYZList"]
eq(x_xtc, x_dcd, decimal=4)
def _load_traj(self, file_list):
"""
Load a set of xtc or dcd files as a single trajectory
Note that the ordering of `file_list` is relevant, as the trajectories
are catted together.
Returns
-------
traj : msmbuilder.Trajectory
"""
if self.input_traj_ext == '.xtc':
traj = Trajectory.load_from_xtc(file_list, PDBFilename=self.conf_filename,
discard_overlapping_frames=True)
elif self.input_traj_ext == '.dcd':
traj = Trajectory.load_from_xtc(file_list, PDBFilename=self.conf_filename)
else:
raise ValueError()
return traj
def main(modeldir, start, type):
start=int(start)
data=dict()
project=Project.load_from('%s/ProjectInfo.yaml' % modeldir.split('Data')[0])
files=glob.glob('%s/fkbp*xtal.pdb' % modeldir.split('Data')[0])
pdb=files[0]
unbound=numpy.loadtxt('%s/tpt-%s/unbound_%s_states.txt' % (modeldir, type, type), dtype=int)
T=mmread('%s/tProb.mtx' % modeldir)
startstate=unbound[start]
ass=io.loadh('%s/Assignments.Fixed.h5' % modeldir)
steps=100000
print "on start state %s" % startstate
if os.path.exists('%s/tpt-%s/movie_state%s_1millisec.states.dat' % (modeldir, type, startstate)):
print "loading from states"
traj=numpy.loadtxt('%s/tpt-%s/movie_state%s_1millisec.states.dat' % (modeldir, type, startstate))
else:
traj=msm_analysis.sample(T, int(startstate),int(steps))
numpy.savetxt('%s/tpt-%s/movie_state%s_1millisec.states.dat' % (modeldir, type, startstate), traj)
print "checking for chkpt file"
checkfile=glob.glob('%s/tpt-%s/movie_state%s_*chkpt' % (modeldir, type, startstate))
if len(checkfile) > 0:
movie=Trajectory.load_from_xtc(checkfile[0], PDBFilename=pdb)
n=int(checkfile[0].split('xtc.state')[1].split('chkpt')[0])
os.system('mv %s %s.chkpt.cp' % (checkfile[0], checkfile[0].split('.xtc')[0]))
print "checkpointing at state index %s out of %s" % (n, len(traj))
checkfile=checkfile[0]
restart=True
else:
restart=False
n=0
movie=project.empty_traj()
while n < len(traj):
print "on state %s" % n
state=int(traj[n])
t=project.get_random_confs_from_states(ass['arr_0'], [int(state),], 10)
if n==0:
movie['XYZList']=t[0]['XYZList']
n+=1
continue
elif n % 100==0:
movie['XYZList']=numpy.vstack((movie['XYZList'], t[0]['XYZList']))
if restart==True:
os.system('mv %s %s.chkpt.cp' % (checkfile, checkfile.split('.xtc')[0]))
movie.save_to_xtc('%s/tpt-%s/movie_state%s_1millisec.xtc.state%schkpt' % (modeldir, type, startstate, n))
checkfile='%s/tpt-%s/movie_state%s_1millisec.xtc.state%schkpt' % (modeldir, type, startstate, n)
n+=1
continue
elif n!=0:
movie['XYZList']=numpy.vstack((movie['XYZList'], t[0]['XYZList']))
n+=1
continue
movie.save_to_xtc('%s/tpt-%s/movie_state%s_1millisec.xtc' % (modeldir, type, startstate))
def _load_traj(self, file_list):
"""
Load a set of xtc or dcd files as a single trajectory
Note that the ordering of `file_list` is relevant, as the trajectories
are catted together.
Returns
-------
traj : msmbuilder.Trajectory
"""
if self.input_traj_ext == '.xtc':
traj = Trajectory.load_from_xtc(file_list, Conf=self.conf,
discard_overlapping_frames=True)
elif self.input_traj_ext == '.dcd':
traj = Trajectory.load_from_dcd(file_list, Conf=self.conf,
discard_overlapping_frames=True)
else:
raise ValueError()
# return the number of files loaded, which in this case is all or
# nothing, since an error is raised if the Trajectory.load_from_<ext>
# doesn't work
return traj, len(file_list)
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 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
from msmbuilder import Trajectory
import os
import numpy as np
r = Trajectory.load_from_xtc("../trajout.xtc","../pdbs/frame0.pdb")
a = r["AtomNames"]
a[a=="OT1"] = "O"
a[a=="OT2"] = "OXT"
r.save_to_pdb("traj.pdb")
cmd = """~/src/Software/ppm/ppm_linux_64.exe -pdb ./traj.pdb -mode detail"""
os.system(cmd)
x = np.loadtxt("./bb_details.dat",'str')
res_id = x[:,0].astype('int')
atom_name = x[:,2]
shifts = x[:,4:].astype('float').T
#os.mkdir("./ppm")
#np.savez_compressed("ppm/shifts.npz", shifts)
#np.savetxt("ppm/shifts_atoms.txt", atom_name,"%s")
#np.savetxt("ppm/shifts_resid.dat", res_id,"%d")
import numpy as np
from msmbuilder import Trajectory
from msmbuilder.geometry import dihedral
ff_list = ["amber96","amber99","amber99sbnmr-ildn","oplsaa","charmm27"]
for ff in ff_list:
print(ff)
directory = "/home/kyleb/dat/lvbp/%s/" % ff
R = Trajectory.load_from_xtc([directory + "/production/trajout.xtc"],directory + "/final.pdb")
ind = dihedral.get_indices(R)
di = dihedral.compute_dihedrals(R,ind).T
phi = di[0]
psi = di[3]
data = np.array([phi,psi])
np.savez_compressed(directory + "/rama.npz", data)
"""
ff = "amber99"
R = Trajectory.load_from_xtc(["/home/kyleb/dat/lvbp/GA-%s/md/trajout.xtc"%ff],"/home/kyleb/dat/lvbp/GA-%s/equil/native.pdb"%ff)
ind = dihedral.get_indices(R)
di = dihedral.compute_dihedrals(R,ind)
io.saveh("/home/kyleb/dat/lvbp/GA-%s/rama.h5"%ff,di)
"""
