def create_simulation(base_dir, starting_dir,
gpu_index,tic_index,
plumed_script,
sim_save_rate,
platform):
print("Creating simulation for tic %d"%tic_index)
os.chdir((os.path.join(base_dir,"tic_%d"%tic_index)))
state, system, integrator, pdb = load_sim_files(starting_dir)
with open("./plumed_script.dat",'w') as f:
f.writelines(plumed_script)
new_f = PlumedForce(str(plumed_script))
force_group = 30
new_f.setForceGroup(force_group)
system.addForce(new_f)
platform, properties = get_platform(platform,gpu_index)
simulation = app.Simulation(pdb.topology, system, integrator, platform, properties)
if os.path.isfile("./checkpt.chk"):
with open("checkpt.chk",'rb') as f:
simulation.context.loadCheckpoint(f.read())
else:
simulation.context.setState(state)
print("Done creating simulation for tic %d"%tic_index)
f = open("./speed_report.txt",'w')
backup("trajectory.dcd")
simulation.reporters.append(app.DCDReporter('trajectory.dcd', sim_save_rate))
simulation.reporters.append(app.StateDataReporter(f, 1000, step=True,\
potentialEnergy=True, temperature=True, progress=True, remainingTime=True,\
speed=True, totalSteps=200*100, separator='\t'))
return simulation, force_group
def create_neutral_simulation(base_dir, starting_dir,
gpu_index,
sim_save_rate,
platform):
print("Creating simulation for neutral_replica")
os.chdir((os.path.join(base_dir,"neutral_replica")))
state, system, integrator, pdb = load_sim_files(starting_dir)
platform, properties = get_platform(platform,gpu_index)
simulation = app.Simulation(pdb.topology, system, integrator,
platform, properties)
if os.path.isfile("./checkpt.chk"):
with open("checkpt.chk",'rb') as f:
simulation.context.loadCheckpoint(f.read())
else:
simulation.context.setState(state)
print("Done creating simulation neutral_replica")
f = open("./speed_report.txt",'w')
backup("trajectory.dcd")
simulation.reporters.append(app.DCDReporter('trajectory.dcd', sim_save_rate))
simulation.reporters.append(app.StateDataReporter(f, 1000, step=True,\
potentialEnergy=True, temperature=True, progress=True, remainingTime=True,\
speed=True, totalSteps=200*100, separator='\t'))
return simulation
def run_simulation(simulation, n_steps):
os.path.chdir(base_dir, "tic_%d" % tic_index)
simulation.step(n_steps)
backup("state.xml")
state=simulation.context.getState(getPositions=True, getVelocities=True,\
getForces=True,getEnergy=True,getParameters=True,enforcePeriodicBox=True)
serializeObject(state, 'state.xml')
return simulation
def create_simulation(base_dir, tic_index, plumed_script):
print("Creating simulation for tic %d" % tic_index)
starting_dir = os.path.join(base_dir, "starting_coordinates")
os.chdir((os.path.join(base_dir, "tic_%d" % tic_index)))
if os.path.isfile("./state.xml"):
state = XmlSerializer.deserialize(open("./state.xml").read())
else:
state = XmlSerializer.deserialize(
open("%s/state0.xml" % starting_dir).read())
system = XmlSerializer.deserialize(
open("%s/system.xml" % starting_dir).read())
integrator = XmlSerializer.deserialize(
open("%s/integrator.xml" % starting_dir).read())
pdb = app.PDBFile("%s/0.pdb" % starting_dir)
new_f = PlumedForce(plumed_script)
new_f.setForceGroup(1)
system.addForce(new_f)
platform = Platform.getPlatformByName("CUDA")
properties = {'CudaPrecision': 'mixed', 'CudaDeviceIndex': str(tic_index)}
simulation = app.Simulation(pdb.topology, system, integrator, platform,
properties)
if os.path.isfile("./checkpt.chk"):
with open("checkpt.chk", 'rb') as f:
simulation.context.loadCheckpoint(f.read())
else:
simulation.context.setState(state)
print("Done creating simulation for tic %d" % tic_index)
f = open("./speed_report.txt", 'w')
backup("trajectory.dcd")
simulation.reporters.append(app.DCDReporter('trajectory.dcd', 100000))
simulation.reporters.append(app.StateDataReporter(f, 1000, step=True,\
potentialEnergy=True, temperature=True, progress=True, remainingTime=True,\
speed=True, totalSteps=200*100, separator='\t'))
return simulation
def sample_clusters(meta, trajs, df):
clust_id = df['Trajectory'].unique()
for i in clust_id:
print(i)
df_smp = df.ix[df['Trajectory'] == i, ['Key', 'Frame']].sample(1000)
inds = zip(df_smp['Key'], df_smp['Frame'])
# Use loc because sample_dimension is nice
traj = md.join(
md.load_frame(meta.loc[traj_i]['traj_fn'],
index=int(frame_i),
top=meta.loc[traj_i]['top_fn'])
for traj_i, frame_i in inds)
# Save
traj_fn = "/Users/robert_arbon/Code/AADH/Analysis/KR_Comparison/pcca_cluster-{}.dcd".format(
i)
backup(traj_fn)
traj.save(traj_fn)
def continue_running():
print(plumed_script)
if os.path.isfile("./state.xml"):
state = XmlSerializer.deserialize(open("./state.xml").read())
else:
state = XmlSerializer.deserialize(
open("../../starting_coordinates/state.xml").read())
system = XmlSerializer.deserialize(
open("../../starting_coordinates/system.xml").read())
integrator = XmlSerializer.deserialize(
open("../../starting_coordinates/integrator.xml").read())
pdb = app.PDBFile("../../starting_coordinates/0.pdb")
system.addForce(PlumedForce(plumed_script))
print("here")
platform = Platform.getPlatformByName("CUDA")
properties = {'CudaPrecision': 'mixed', 'CudaDeviceIndex': str(0)}
simulation = app.Simulation(pdb.topology, system, integrator, platform,
properties)
simulation.context.setState(state)
backup("trajectory.dcd")
f = open("./speed_report.txt", 'w')
simulation.reporters.append(app.DCDReporter('trajectory.dcd', 5000))
simulation.reporters.append(app.StateDataReporter(f, 5000, step=True,\
potentialEnergy=True, temperature=True, progress=True, remainingTime=True,\
speed=True, totalSteps=200*100000, separator='\t'))
#run for 23hrs
simulation.runForClockTime(3, stateFile="state.xml")
backup("state.xml")
state=simulation.context.getState(getPositions=True, getVelocities=True,\
getForces=True,getEnergy=True,getParameters=True,enforcePeriodicBox=True)
serializeObject(state, 'state.xml')
def sample_tica_dim(dim=0, n_frames=200, meta=None, ttrajs=None):
## Load
if (not meta is None) & (not ttrajs is None):
## Sample
# These are apparently ordered according tica value
inds = sample_dimension(ttrajs,
dimension=dim,
n_frames=n_frames,
scheme='random')
save_generic(inds, "tica-dimension-{}-inds.pickl".format(dim + 1))
## Get tica components
tica_values = np.array(
[ttrajs[traj_i][frame_i][dim] for traj_i, frame_i in inds])
tica_values = (tica_values - tica_values.min()) / (tica_values.max() -
tica_values.min())
tica_values *= 10
## Make trajectory
top = preload_top(meta)
# Use loc because sample_dimension is nice
traj = md.join(
md.load_frame(meta.loc[traj_i]['traj_fn'], index=frame_i, top=top)
for traj_i, frame_i in inds)
## Supperpose
## Save
traj_fn = "tica-dimension-{}.dcd".format(dim + 1)
backup(traj_fn)
traj.save(traj_fn)
else:
raise ValueError('Specify meta data and trajectory objects')
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)
## Try to limit RAM usage
def guestimate_stride():
total_data = meta['nframes'].sum()
want = kmed.n_clusters * 10
stride = max(1, total_data // want)
print("Since we have", total_data, "frames, we're going to stride by",
stride, "during fitting, because this is probably adequate for",
kmed.n_clusters, "clusters")
return stride
## Fit
kmed.fit([traj for _, traj in itertrajs(meta, stride=guestimate_stride())])
print(kmed.summarize())
## Save
save_generic(kmed, 'clusterer.pickl')
## Save centroids
def frame(traj_i, frame_i):
# Note: kmedoids does 0-based, contiguous integers so we use .iloc
row = meta.iloc[traj_i]
return md.load_frame(row['traj_fn'], frame_i, top=row['top_fn'])
centroids = md.join((frame(ti, fi) for ti, fi in kmed.cluster_ids_),
check_topology=False)
centroids_fn = 'centroids.xtc'
backup(centroids_fn)
centroids.save("centroids.xtc")
please cite msmbuilder in any publications
"""
import mdtraj as md
import os
from msmbuilder.io.sampling import sample_states
from msmbuilder.io import load_trajs, save_generic, preload_top, backup, load_generic
## Load
meta, ttrajs = load_trajs('ttrajs')
kmeans = load_generic("kmeans.pickl")
## Sample
inds = sample_states(ttrajs, kmeans.cluster_centers_, k=10)
save_generic(inds, "cluster-sample-inds.pickl")
## Make trajectories
top = preload_top(meta)
out_folder = "cluster_samples"
backup(out_folder)
os.mkdir(out_folder)
for state_i, state_inds in enumerate(inds):
traj = md.join(
md.load_frame(meta.loc[traj_i]['traj_fn'], index=frame_i, top=top)
for traj_i, frame_i in state_inds)
traj.save("{}/{}.xtc".format(out_folder, state_i))
please cite msmbuilder in any publications
"""
import mdtraj as md
from msmbuilder.io import load_trajs, save_generic, preload_top, backup, load_generic
from msmbuilder.io.sampling import sample_msm
## Load
meta, ttrajs = load_trajs('ttrajs')
msm = load_generic('msm.pickl')
kmeans = load_generic('kmeans.pickl')
## Sample
# Warning: make sure ttrajs and kmeans centers have
# the same number of dimensions
inds = sample_msm(ttrajs, kmeans.cluster_centers_, msm, n_steps=200, stride=1)
save_generic(inds, "msm-traj-inds.pickl")
## Make trajectory
top = preload_top(meta)
traj = md.join(
md.load_frame(meta.loc[traj_i]['traj_fn'], index=frame_i, top=top)
for traj_i, frame_i in inds)
## Save
traj_fn = "msm-traj.xtc"
backup(traj_fn)
traj.save(traj_fn)
- trajs
"""
import mdtraj as md
from msmbuilder.io import load_trajs, save_generic, preload_top, backup, load_generic
from msmbuilder.io.sampling import sample_msm
## Load
meta, ttrajs = load_trajs('ttrajs')
msm = load_generic('msm.pickl')
kmeans = load_generic('kmeans.pickl')
## Sample
# Warning: make sure ttrajs and kmeans centers have
# the same number of dimensions
inds = sample_msm(ttrajs, kmeans.cluster_centers_, msm, n_steps=200, stride=1)
save_generic(inds, "msm-traj-inds.pickl")
## Make trajectory
top = preload_top(meta)
traj = md.join(
md.load_frame(meta.loc[traj_i]['traj_fn'], index=frame_i, top=top)
for traj_i, frame_i in inds
)
## Save
traj_fn = "msm-traj.xtc"
backup(traj_fn)
traj.save(traj_fn)
def guestimate_stride():
total_data = meta['nframes'].sum()
want = kmed.n_clusters * 10
stride = max(1, total_data // want)
print("Since we have", total_data, "frames, we're going to stride by",
stride, "during fitting, because this is probably adequate for",
kmed.n_clusters, "clusters")
return stride
## Fit
kmed.fit([traj for _, traj in itertrajs(meta, stride=guestimate_stride())])
print(kmed.summarize())
## Save
save_generic(kmed, 'clusterer.pickl')
## Save centroids
def frame(traj_i, frame_i):
# Note: kmedoids does 0-based, contiguous integers so we use .iloc
row = meta.iloc[traj_i]
return md.load_frame(row['traj_fn'], frame_i, top=row['top_fn'])
centroids = md.join((frame(ti, fi) for ti, fi in kmed.cluster_ids_),
check_topology=False)
centroids_fn = 'centroids.xtc'
backup(centroids_fn)
centroids.save("centroids.xtc")
print(args)
if len(args.traj) == 1:
traj_name = os.path.basename(args.traj[0])[:-3] # drop the .nc ending
print('Loading traj...')
traj = mdtraj.load(args.traj[0], top=args.top)
print('Superposing...')
atoms = traj.topology.select('name CA')
if args.ref is None:
traj.superpose(traj, 0, atom_indices=atoms)
else:
ref = mdtraj.load(args.ref)
traj.superpose(ref, 0, atom_indices=atoms)
if args.width > 1:
print('Smoothing...')
traj.smooth(args.width, inplace=True)
backup(args.name)
traj.save_netcdf(args.name)
elif len(args.traj) > 1:
print('Loading {} trajs as one...'.format(len(args.traj)))
traj = mdtraj.load(args.traj, top=args.top)
print('Superposing...')
atoms = traj.topology.select('name CA')
if args.ref is None:
traj.superpose(traj, 0, atom_indices=atoms)
else:
ref = mdtraj.load(args.ref)
traj.superpose(ref, 0, atom_indices=atoms)
if args.width > 1:
print('Smoothing...')
traj.smooth(args.width, inplace=True)
backup(args.name)
import mdtraj as md
import os
from msmbuilder.io.sampling import sample_states
from msmbuilder.io import load_trajs, save_generic, preload_top, backup, load_generic
## Load
meta, ttrajs = load_trajs('ttrajs')
kmeans = load_generic("kmeans.pickl")
## Sample
inds = sample_states(ttrajs,
kmeans.cluster_centers_,
k=10)
save_generic(inds, "cluster-sample-inds.pickl")
## Make trajectories
top = preload_top(meta)
out_folder = "cluster_samples"
backup(out_folder)
os.mkdir(out_folder)
for state_i, state_inds in enumerate(inds):
traj = md.join(
md.load_frame(meta.loc[traj_i]['traj_fn'], index=frame_i, top=top)
for traj_i, frame_i in state_inds
)
traj.save("{}/{}.xtc".format(out_folder, state_i))
