def main():
global data2d
global As
# First I need to turn the assignments matrix into a 1D list of assignments
sys.stdout = os.fdopen(sys.stdout.fileno(),'w',0)
print "Reading in Assignments... from %s " % options.assFN
As = io.loadh(options.assFN)['arr_0'].astype(int)
print "Reading in data... from %s " % options.dataFN
try:
f = io.loadh( options.dataFN )
try:
data2d = f['arr_0']
except:
data2d = f['Data']
except:
data = load(options.dataFN)
proj = Project.load_from( options.projFN )
data2d = msmTools.reshapeRawData( data, proj )
print "Calculating averages for:"
pool = mp.Pool(options.procs)
clusters = range( As.max() + 1)
result = pool.map_async(calcAvg,clusters[:])
result.wait()
sol = result.get()
sol = array(sol)
savetxt(options.outFN, sol)
return
def main(modeldir, genfile, type):
project=Project.load_from('%s/ProjectInfo.yaml' % modeldir.split('Data')[0])
data=dict()
pops=numpy.loadtxt('%s/Populations.dat' % modeldir)
map=numpy.loadtxt('%s/Mapping.dat' % modeldir)
frames=numpy.where(map!=-1)[0]
data['rmsd']=numpy.loadtxt('%s.rmsd.dat' % genfile.split('.lh5')[0])
data['rmsd']=data['rmsd'][frames]
com=numpy.loadtxt('%s.vmd_com.dat' % genfile.split('.lh5')[0], usecols=(1,))
refcom=com[0]
data['com']=com[1:]
data['com']=numpy.array(data['com'])
data['com']=data['com'][frames]
ass=io.loadh('%s/Assignments.Fixed.h5' % modeldir)
T=mmread('%s/tProb.mtx' % modeldir)
paths=io.loadh('%s/tpt-rmsd-%s/Paths.h5' % (modeldir, type))
for p in range(0, 20):
movie=project.empty_traj()
path=paths['Paths'][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)
for (n, state) in enumerate(path):
t=project.get_random_confs_from_states(ass['arr_0'], [int(state),], 20)
if n==0:
movie['XYZList']=t[0]['XYZList']
else:
movie['XYZList']=numpy.vstack((movie['XYZList'], t[0]['XYZList']))
movie.save_to_xtc('%s/tpt-rmsd-%s/path%s_sample20.xtc' % (modeldir, type, p))
def run(MinLagtime, MaxLagtime, Interval, NumEigen, AssignmentsFn, symmetrize,
nProc, output):
arglib.die_if_path_exists(output)
# Setup some model parameters
try:
Assignments = io.loadh(AssignmentsFn, 'arr_0')
except KeyError:
Assignments = io.loadh(AssignmentsFn, 'Data')
NumStates = max(Assignments.flatten()) + 1
if NumStates <= NumEigen - 1:
NumEigen = NumStates - 2
logger.warning(
"Number of requested eigenvalues exceeds the rank of the transition matrix! Defaulting to the maximum possible number of eigenvalues."
)
del Assignments
logger.info("Getting %d eigenvalues (timescales) for each lagtime...",
NumEigen)
lagTimes = range(MinLagtime, MaxLagtime + 1, Interval)
logger.info("Building MSMs at the following lag times: %s", lagTimes)
# Get the implied timescales (eigenvalues)
impTimes = msm_analysis.get_implied_timescales(AssignmentsFn,
lagTimes,
n_implied_times=NumEigen,
sliding_window=True,
symmetrize=symmetrize,
n_procs=nProc)
numpy.savetxt(output, impTimes)
return
def test_2(self):
try:
subprocess.Popen('ipcluster start --cluster-id=testclusterid --n=1 --daemonize', shell=True)
time.sleep(5)
args = self.Args()
args.output_dir = tempfile.mkdtemp()
args.cluster_id = 'testclusterid'
logger = AssignParallel.setup_logger()
AssignParallel.main(args, self.metric, logger)
assignments = io.loadh(os.path.join(args.output_dir, 'Assignments.h5'), 'arr_0')
r_assignments = io.loadh(os.path.join(fixtures_dir(), 'Assignments.h5'), 'Data')
distances = io.loadh(os.path.join(args.output_dir, 'Assignments.h5.distances'), 'arr_0')
r_distances = io.loadh(os.path.join(fixtures_dir(), 'Assignments.h5.distances'), 'Data')
npt.assert_array_equal(assignments, r_assignments)
npt.assert_array_almost_equal(distances, r_distances)
except:
raise
finally:
shutil.rmtree(args.output_dir)
subprocess.Popen('ipcluster stop --cluster-id=testclusterid', shell=True).wait()
def main():
"""Parse command line inputs, load up files, and build a movie."""
parser = arglib.ArgumentParser(description="""
Create an MSM movie by sampling a sequence of states and sampling a
random conformation from each state in the sequence.
""")
parser.add_argument('project')
parser.add_argument('assignments', default='Data/Assignments.Fixed.h5')
parser.add_argument('tprob', default='Data/tProb.mtx')
parser.add_argument('num_steps')
parser.add_argument('starting_state', type=int, help='''Which state to start trajectory from.''')
parser.add_argument('output', default='sample_traj.pdb', help="""The filename of your output trajectory. The filetype suffix will be used to select the output file format.""")
args = parser.parse_args()
try:
assignments = io.loadh(args.assignments, 'arr_0')
except KeyError:
assignments = io.loadh(args.assignments, 'Data')
num_steps = int(args.num_steps)
starting_state = int(args.starting_state)
project = Project.load_from(args.project)
T = scipy.io.mmread(args.tprob).tocsr()
state_traj = msm_analysis.sample(T, starting_state, num_steps)
sampled_traj = project.get_random_confs_from_states(assignments, state_traj, 1)
traj = sampled_traj[0]
traj["XYZList"] = np.array([t["XYZList"][0] for t in sampled_traj])
traj.save(args.output)
def test_2(self):
try:
subprocess.Popen(
'ipcluster start --cluster-id=testclusterid --n=1 --daemonize',
shell=True)
time.sleep(5)
args = self.Args()
args.output_dir = tempfile.mkdtemp()
args.cluster_id = 'testclusterid'
logger = AssignParallel.setup_logger()
AssignParallel.main(args, self.metric, logger)
assignments = io.loadh(
os.path.join(args.output_dir, 'Assignments.h5'), 'arr_0')
r_assignments = io.loadh(
os.path.join(fixtures_dir(), 'Assignments.h5'), 'Data')
distances = io.loadh(
os.path.join(args.output_dir, 'Assignments.h5.distances'),
'arr_0')
r_distances = io.loadh(
os.path.join(fixtures_dir(), 'Assignments.h5.distances'),
'Data')
npt.assert_array_equal(assignments, r_assignments)
npt.assert_array_almost_equal(distances, r_distances)
except:
raise
finally:
shutil.rmtree(args.output_dir)
subprocess.Popen('ipcluster stop --cluster-id=testclusterid',
shell=True).wait()
def run(MinLagtime, MaxLagtime, Interval, NumEigen, AssignmentsFn, symmetrize, nProc, output):
arglib.die_if_path_exists(output)
# Setup some model parameters
try:
Assignments = io.loadh(AssignmentsFn, "arr_0")
except KeyError:
Assignments = io.loadh(AssignmentsFn, "Data")
NumStates = max(Assignments.flatten()) + 1
if NumStates <= NumEigen - 1:
NumEigen = NumStates - 2
logger.warning(
"Number of requested eigenvalues exceeds the rank of the transition matrix! Defaulting to the maximum possible number of eigenvalues."
)
del Assignments
logger.info("Getting %d eigenvalues (timescales) for each lagtime...", NumEigen)
lagTimes = range(MinLagtime, MaxLagtime + 1, Interval)
logger.info("Building MSMs at the following lag times: %s", lagTimes)
# Get the implied timescales (eigenvalues)
impTimes = msm_analysis.get_implied_timescales(
AssignmentsFn, lagTimes, n_implied_times=NumEigen, sliding_window=True, symmetrize=symmetrize, n_procs=nProc
)
numpy.savetxt(output, impTimes)
return
def load(tica_fn, metric):
"""
load a tICA solution to use in projecting data.
Parameters:
-----------
tica_fn : str
filename pointing to tICA solutions
metric : metrics.Vectorized subclass instance
metric used to prepare trajectories
"""
# the only variables we need to save are the two matrices
# and the eigenvectors / values as well as the lag time
logger.warn("NOTE: You can only use the tICA solution, you will "
"not be able to continue adding data")
f = io.loadh(tica_fn)
tica_obj = tICA(f['lag'][0], prep_metric=metric)
# lag entry is an array... with a single item
tica_obj.timelag_corr_mat = f['timelag_corr_mat']
tica_obj.cov_mat = f['cov_mat']
tica_obj.vals = f['vals']
tica_obj.vecs = f['vecs']
tica_obj._sort()
return tica_obj
def run(tProb, observable, init_pops=None, num_vecs=10, output='evec_amps.h5'):
if init_pops is None:
init_pops = np.ones(tProb.shape[0]).astype(float) / float(tProb.shape[0])
else:
init_pops = init_pops.astype(float)
init_pops /= init_pops.sum()
assert (observable.shape[0] == init_pops.shape[0])
assert (observable.shape[0] == tProb.shape[0])
try:
f = io.loadh('eigs%d.h5' % num_vecs)
vals = f['vals']
vecsL = f['vecs']
except:
vals, vecsL = msm_analysis.get_eigenvectors(tProb, num_vecs + 1, right=False)
io.saveh('eigs%d.h5' % num_vecs, vals=vals, vecs=vecsL)
equil = vecsL[:,0] / vecsL[:,0].sum()
dyn_vecsL = vecsL[:, 1:]
# normalize the left and right eigenvectors
dyn_vecsL /= np.sqrt(np.sum(dyn_vecsL * dyn_vecsL / np.reshape(equil, (-1, 1)), axis=0))
dyn_vecsR = dyn_vecsL / np.reshape(equil, (-1, 1))
amps = dyn_vecsL.T.dot(observable) * dyn_vecsR.T.dot(init_pops)
io.saveh(output, evals=vals[1:], amplitudes=amps)
logger.info("saved output to %s" % output)
def main(file):
ass=io.loadh(file)
dir=os.path.dirname(file)
base=os.path.basename(file)
newdir='%s/subsample' % dir
if not os.path.exists(newdir):
os.mkdir(newdir)
p=Project.load_from('%s/ProjectInfo.yaml' % dir.split('Data')[0])
data=dict()
totals=dict()
iterations=int(ass['arr_0'].shape[1]/10.0)
start=max(p.traj_lengths)
for iter in range(0, iterations):
new=start-10
if new < 10:
break
totals[new]=0
data[new]=-numpy.ones((ass['arr_0'].shape[0], new), dtype=int)
for i in range(0, ass['arr_0'].shape[0]):
data[new][i]=ass['arr_0'][i][:new]
frames=numpy.where(data[new][i]!=-1)[0]
totals[new]+=len(frames)
start=new
ohandle=open('%s/times.h5' % (newdir), 'w')
for key in sorted(data.keys()):
print data[key].shape
print "total time is %s" % totals[key]
ohandle.write('%s\t%s\t%s\n' % (data[key].shape[0], data[key].shape[1], totals[key]))
def load_from(cls, filename):
"""
Load project from disk
Parameters
----------
filename : string
filename_or_file can be a path to a legacy .h5 or current
.yaml file.
Returns
-------
project : the loaded project object
"""
rootdir = os.path.abspath(os.path.dirname(filename))
if filename.endswith('.yaml'):
with open(filename) as f:
ondisk = yaml.load(f)
records = {
'conf_filename': ondisk['conf_filename'],
'traj_lengths': [],
'traj_paths': [],
'traj_converted_from': [],
'traj_errors': []
}
for trj in ondisk['trajs']:
records['traj_lengths'].append(trj['length'])
records['traj_paths'].append(trj['path'])
records['traj_errors'].append(trj['errors'])
records['traj_converted_from'].append(
trj['converted_from'])
elif filename.endswith('.h5'):
ondisk = io.loadh(filename, deferred=False)
n_trajs = len(ondisk['TrajLengths'])
records = {
'conf_filename': str(ondisk['ConfFilename'][0]),
'traj_lengths': ondisk['TrajLengths'],
'traj_paths': [],
'traj_converted_from': [None] * n_trajs,
'traj_errors': [None] * n_trajs
}
for i in xrange(n_trajs):
# this is the convention used in the hdf project format to get the traj paths
path = os.path.join(
ondisk['TrajFilePath'][0], ondisk['TrajFileBaseName'][0] +
str(i) + ondisk['TrajFileType'][0])
records['traj_paths'].append(path)
else:
raise ValueError('Sorry, I can only open files in .yaml'
' or .h5 format: %s' % filename)
return cls(records, validate=True, project_dir=rootdir)
def main(assfile, lag, nproc):
lag=int(lag)
nproc=int(nproc)
Assignments=io.loadh(assfile)
num=int(assfile.split('Assignments_sub')[1].split('.h5')[0])
dir=os.path.dirname(assfile)
newdir='%s/boot-sub%s' % (dir, num)
ref_sub=numpy.loadtxt('%s/times.h5' % dir, usecols=(1,))
ref_total=numpy.loadtxt('%s/times.h5' % dir, usecols=(2,))
times=dict()
for (i,j) in zip(ref_sub, ref_total):
times[i]=j
proj=Project.load_from('%s/ProjectInfo.yaml' % dir.split('Data')[0])
multinom=int(times[num])
if not os.path.exists(newdir):
os.mkdir(newdir)
if 'Data' in Assignments.keys():
Assignments=Assignments['Data']
else:
Assignments=Assignments['arr_0']
print Assignments.shape
NumStates = max(Assignments.flatten()) + 1
Counts = MSMLib.get_count_matrix_from_assignments(Assignments, lag_time=int(lag), sliding_window=True)
Counts=Counts.todense()
Counts=Counts*(1.0/lag)
T=numpy.array(Counts)
frames=numpy.where(T==0)
T[frames]=1
Popsample=dict()
iteration=0
total_iteration=100/nproc
print "%s total iterations" % total_iteration
if 100 % nproc != 0:
remain=100 % nproc
else:
remain=False
print "iterating thru tCount samples"
count=0
while iteration < 100:
if count*nproc > 100:
nproc=remain
print "sampling iteration %s" % iteration
Tfresh=T.copy()
input = zip([Tfresh]*nproc, [multinom]*nproc, range(0, NumStates))
pool = multiprocessing.Pool(processes=nproc)
result = pool.map_async(parallel_get_matrix, input)
result.wait()
all = result.get()
pool.terminate()
for c_matrix in all:
scipy.io.mmwrite('%s/tCounts-%s' % (newdir, iteration), c_matrix)
#rev_counts, t_matrix, Populations, Mapping=x
#scipy.io.mmwrite('%s/tProb-%s' % (newdir, iteration), t_matrix)
#numpy.savetxt('%s/Populations-%s' % (newdir, iteration), Populations)
#numpy.savetxt('%s/Mapping-%s' % (newdir, iteration), Mapping)
iteration+=1
count+=1
print "dont with iteration %s" % iteration*nproc
def main(modeldir, genfile, type, write=False):
proj=Project.load_from('%s/ProjectInfo.yaml' % modeldir.split('Data')[0])
pops=numpy.loadtxt('%s/Populations.dat' % modeldir)
map=numpy.loadtxt('%s/Mapping.dat' % modeldir)
frames=numpy.where(map!=-1)[0]
data=dict()
data['rmsd']=numpy.loadtxt('%s.rmsd.dat' % genfile.split('.lh5')[0])
data['rmsd']=data['rmsd'][frames]
com=numpy.loadtxt('%s.vmd_com.dat' % genfile.split('.lh5')[0], usecols=(1,))
refcom=com[0]
data['com']=com[1:]
data['com']=numpy.array(data['com'][frames])
residues=['F36', 'H87', 'I56', 'I90', 'W59', 'Y82', 'hydrophob_dist', 'oxos_dist']
loops=['loop1', 'loop2', 'loop3']
for loop in loops:
data[loop]=numpy.loadtxt('%s.%srmsd.dat' % (genfile.split('.lh5')[0], loop))
data[loop]=data[loop][frames]
for res in residues:
file='%s_%spair.dat' % (genfile.split('.lh5')[0], res)
if os.path.exists(file):
data[res]=numpy.loadtxt(file)
data[res]=data[res][frames]
angles=['phi', 'omega']
for ang in angles:
file='%s_%s.dat' % (genfile.split('.lh5')[0], ang)
if os.path.exists(file):
data[ang]=numpy.loadtxt(file)
data[ang]=data[ang][frames]
ass=io.loadh('%s/Assignments.Fixed.h5' % modeldir)
T=mmread('%s/tProb.mtx' % modeldir)
unbound=numpy.loadtxt('%s/tpt-%s/unbound_%s_states.txt' % (modeldir, type, type), dtype=int)
bound=numpy.loadtxt('%s/tpt-%s/bound_%s_states.txt' % (modeldir, type, type), dtype=int)
Tdense=T.todense()
Tdata=dict()
for i in unbound:
for j in unbound:
if Tdense[i,j]!=0:
if i not in Tdata.keys():
Tdata[i]=[]
Tdata[i].append(j)
#print Tdata
cm=pylab.cm.get_cmap('RdYlBu_r') #blue will be negative components, red positive
Q=tpt.calculate_committors(unbound, bound, T)
ohandle=open('%s/commitor_states.txt' % modeldir, 'w')
for i in range(0,len(Q)):
if Q[i]>0.40 and Q[i]<0.6:
ohandle.write('%s\n' % i)
#t=project.get_random_confs_from_states(ass['arr_0'], [int(i),], 20)
#t[0].save_to_xtc('%s/commottor_state%s.xtc' % (modeldir, i))
if write==True:
for op in sorted(data.keys()):
pylab.figure()
pylab.scatter(data['com'], data[op], c=Q, cmap=cm, alpha=0.7, s=[map_size(i) for i in Q])
pylab.xlabel('L RMSD')
pylab.ylabel(op)
pylab.colorbar()
pylab.show()
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 check_container(filename):
ondisk = io.loadh(filename, deferred=False)
if n_vtrajs != len(ondisk['hashes']):
raise ValueError('You asked for {} vtrajs, but your checkpoint \
file has {}'.format(n_vtrajs, len(ondisk['hashes'])))
if not np.all(ondisk['hashes'] ==
hashes):
raise ValueError('Hash mismatch. Are these checkpoint files for \
the right project?')
def dump_count_matrix(self,assignfn,lagtime=1,outfn="count_matrix.txt"):
from msmbuilder import io
from msmbuilder import MSMLib
assignments = io.loadh(assignfn, 'arr_0')
# returns sparse lil_matrix
counts = MSMLib.get_count_matrix_from_assignments(assignments, lag_time=lagtime,
sliding_window=True)
counts = counts.tocoo()
np.savetxt(outfn,(counts.row, counts.col, counts.data))
def main(assfile, lag, nproc):
lag=int(lag)
nproc=int(nproc)
Assignments=io.loadh(assfile)
dir=os.path.dirname(assfile)
newdir='%s/sample-counts' % dir
proj=Project.load_from('%s/ProjectInfo.yaml' % dir.split('Data')[0])
multinom=sum(proj.traj_lengths)
if not os.path.exists(newdir):
os.mkdir(newdir)
if 'Data' in Assignments.keys():
Assignments=Assignments['Data']
else:
Assignments=Assignments['arr_0']
print Assignments.shape
NumStates = max(Assignments.flatten()) + 1
Counts = MSMLib.get_count_matrix_from_assignments(Assignments, lag_time=int(lag), sliding_window=True)
Counts=Counts.todense()
Counts=Counts*(1.0/lag)
T=numpy.array(Counts)
frames=numpy.where(T==0)
T[frames]=1
Popsample=dict()
iteration=0
total_iteration=100/nproc
print "%s total iterations" % total_iteration
if 100 % nproc != 0:
remain=100 % nproc
else:
remain=False
print "iterating thru tCount samples"
count=0
while iteration < 100:
if count*nproc > 100:
nproc=remain
print "sampling iteration %s" % iteration
Tfresh=T.copy()
counts=range(0, nproc)
input = zip([Tfresh]*nproc, [multinom]*nproc, [NumStates]*nproc, counts)
pool = multiprocessing.Pool(processes=nproc)
result = pool.map_async(parallel_get_matrix, input)
result.wait()
all = result.get()
print "computed resampled matrices"
pool.terminate()
for count_matrix in all:
#rev_counts, t_matrix, Populations, Mapping=x
scipy.io.mmwrite('%s/tCounts-%s' % (newdir, iteration), count_matrix)
# scipy.io.mmwrite('%s/tProb-%s' % (newdir, iteration), t_matrix)
# numpy.savetxt('%s/Populations-%s' % (newdir, iteration), Populations)
# numpy.savetxt('%s/Mapping-%s' % (newdir, iteration), Mapping)
iteration+=1
count+=1
print "dont with iteration %s" % iteration*nproc
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 main(modeldir, gensfile, rcut=None):
mapdata=dict()
ass=io.loadh('%s/Assignments.Fixed.h5' % modeldir)
data=dict()
data['rmsd']=numpy.loadtxt('%s.rmsd.dat' % gensfile.split('.lh5')[0])
com=numpy.loadtxt('%s.vmd_com.dat' % gensfile.split('.lh5')[0], usecols=(1,))
data['com']=com[1:]
pops=numpy.loadtxt('%s/Populations.dat' % modeldir)
map=numpy.loadtxt('%s/Mapping.dat' % modeldir)
mapdata['rmsd']=[]
mapdata['com']=[]
for x in range(0, len(data['rmsd'])):
if map[x]!=-1:
mapdata['com'].append(data['com'][x])
mapdata['rmsd'].append(data['rmsd'][x])
#RMSD cutoff
cutoffs=numpy.arange(1,30,0.5)
bound_pops=[]
for type in mapdata.keys():
pylab.figure()
ohandle=open('%s/%s_msm_frees.dat' % (modeldir, type), 'w')
data=[]
for cutoff in cutoffs:
bound_pops=[]
for (state, x) in enumerate(mapdata['rmsd']):
if x < cutoff:
bound_pops.append(pops[state])
### calculate binding free energy from populations
if len(bound_pops)==0:
dG=100
else:
bound=numpy.sum(bound_pops)
unbound=1-bound
dG=-0.6*numpy.log(bound/unbound)
#dG=-0.6*numpy.log(bound/(unbound**2))
### calculate standard state correction, in ansgtroms here
boxvolume=244.80*(10**3)
v0=1600
corr=-0.6*numpy.log(boxvolume/v0)
dG_corr=dG+corr
if cutoff==float(rcut):
print cutoff, dG_corr
data.append(dG_corr)
ohandle.write('%s\t%s\n' % (cutoff, dG_corr))
pylab.plot(cutoffs, data, label=type)
pylab.legend()
pylab.ylim(-8, (-1)*corr)
pylab.show()
def load_from(cls, filename):
"""
Load project from disk
Parameters
----------
filename : string
filename_or_file can be a path to a legacy .h5 or current
.yaml file.
Returns
-------
project : the loaded project object
"""
rootdir = os.path.abspath(os.path.dirname(filename))
if filename.endswith('.yaml'):
with open(filename) as f:
ondisk = yaml.load(f)
records = {'conf_filename': ondisk['conf_filename'],
'traj_lengths': [],
'traj_paths': [],
'traj_converted_from': [],
'traj_errors': []}
for trj in ondisk['trajs']:
records['traj_lengths'].append(trj['length'])
records['traj_paths'].append(trj['path'])
records['traj_errors'].append(trj['errors'])
records['traj_converted_from'].append(trj['converted_from'])
elif filename.endswith('.h5'):
ondisk = io.loadh(filename, deferred=False)
n_trajs = len(ondisk['TrajLengths'])
records = {'conf_filename': str(ondisk['ConfFilename'][0]),
'traj_lengths': ondisk['TrajLengths'],
'traj_paths': [],
'traj_converted_from': [ [None] ] * n_trajs,
'traj_errors': [None] * n_trajs}
for i in xrange(n_trajs):
# this is the convention used in the hdf project format to get the traj paths
path = os.path.join( ondisk['TrajFilePath'][0], ondisk['TrajFileBaseName'][0] + str(i) + ondisk['TrajFileType'][0] )
records['traj_paths'].append(path)
else:
raise ValueError('Sorry, I can only open files in .yaml'
' or .h5 format: %s' % filename)
return cls(records, validate=False, project_dir=rootdir)
def check_container(filename):
ondisk = io.loadh(filename, deferred=False)
if n_vtrajs != len(ondisk["hashes"]):
raise ValueError(
"You asked for {} vtrajs, but your checkpoint \
file has {}".format(
n_vtrajs, len(ondisk["hashes"])
)
)
if not np.all(ondisk["hashes"] == hashes):
raise ValueError(
"Hash mismatch. Are these checkpoint files for \
the right project?"
)
def main(modeldir):
proj=Project.load_from('%s/ProjectInfo.yaml' % modeldir.split('Data')[0])
ass=io.loadh('%s/Assignments.Fixed.h5' % modeldir)
data=dict()
data['dist']=numpy.loadtxt('%s/prot_lig_distance.dat' % modeldir, usecols=(1,))
data['rmsd']=numpy.loadtxt('%s/Gens.rmsd.dat' % modeldir, usecols=(2,))
com=numpy.loadtxt('%s/Gens.vmd_com.dat' % modeldir, usecols=(1,))
refcom=com[0]
data['com']=com[1:]
data['com']=numpy.array(data['com'])
pops=numpy.loadtxt('%s/Populations.dat' % modeldir)
map=numpy.loadtxt('%s/Mapping.dat' % modeldir)
frames=numpy.where(map!=-1)[0]
pylab.scatter(data['com'][frames], data['rmsd'][frames])
pylab.scatter([refcom,], [0,], c='k', marker='x', s=100)
pylab.xlabel('P-L COM')
pylab.ylabel('P-L RMSD')
pylab.show()
def main(modeldir):
data=dict()
project=Project.load_from('%s/ProjectInfo.yaml' % modeldir.split('Data')[0])
ass=io.loadh('%s/Assignments.Fixed.h5' % modeldir)
T=mmread('%s/tProb.mtx' % modeldir)
if not os.path.exists('%s/adaptive-states/' % modeldir):
os.mkdir('%s/adaptive-states/' % modeldir)
for state in sorted(set(ass['arr_0'].flatten())):
if state!=-1:
t=project.get_random_confs_from_states(ass['arr_0'], [int(state),], 5)
for i in range(0, 5):
print state, i
(a, b, c) =t[0]['XYZList'].shape
movie=project.empty_traj()
movie['XYZList']=numpy.zeros((1, b, c), dtype=numpy.float32)
movie['XYZList'][0]=t[0]['XYZList'][i]
movie.save_to_pdb('%s/adaptive-states/state%s-%s.pdb' % (modeldir, int(state), i))
def load_from_disk(cls, filename):
"""Load up a clusterer from disk
This is useful because computing the Z-matrix
(done in __init__) is the most expensive part, and assigning is cheap
Parameters
----------
filename : str
location to save to
Raises
------
TODO: Probablt raises something if filename doesn't exist?
"""
data = io.loadh(filename, deferred=False)
Z, traj_lengths = data['z_matrix'], data['traj_lengths']
#Next two lines are a hack to fix Serializer bug. KAB
if np.rank(traj_lengths)==0:
traj_lengths = [traj_lengths]
return cls(None, None, precomputed_values=(Z, traj_lengths))
def load_from_disk(cls, filename):
"""Load up a clusterer from disk
This is useful because computing the Z-matrix
(done in __init__) is the most expensive part, and assigning is cheap
Parameters
----------
filename : str
location to save to
Raises
------
TODO: Probablt raises something if filename doesn't exist?
"""
data = io.loadh(filename, deferred=False)
Z, traj_lengths = data['z_matrix'], data['traj_lengths']
#Next two lines are a hack to fix Serializer bug. KAB
if np.rank(traj_lengths) == 0:
traj_lengths = [traj_lengths]
return cls(None, None, precomputed_values=(Z, traj_lengths))
def test_load_2(self):
"load using deferred=False"
TestData = io.loadh(self.filename1, deferred=False)['arr_0']
npt.assert_array_equal(TestData, self.data)
def main_learn(args):
"main method for the learn subcommand"
s = io.loadh(args.triplets)
metric_string = ''.join(s['metric'])
if args.learn_method == 'diagonal':
# type conversion
alpha = float(args.alpha)
rho, weights = lmmdm.optimize_diagonal(s['AtoB'], s['AtoC'], alpha, loss='huber')
if metric_string == 'dihedral':
metric = metrics.Dihedral(metric='seuclidean', V=weights)
elif metric_string == 'drmsd':
metric = metrics.AtomPairs(metric='seuclidean', V=weights, atom_pairs=s['atom_pairs'])
elif metric_string == 'rmsd':
metric = WRMSD(metric='seuclidean', V=weights)
elif metric_string == 'recipcontact':
metric = metrics.ContinuousContact(contacts='all', scheme='CA',
metric='seuclidean', V=weights)
else:
raise NotImplementedError('Sorry')
# save to disk
pickle.dump(metric, open(args.metric, 'w'))
print 'Saved metric pickle to {}'.format(args.metric)
np.save(args.matrix, [weights, rho])
print 'Saved weights as flat text to {}'.format(args.matrix)
elif args.learn_method == 'dense':
initialize = args.initialize
if not args.initialize in ['euclidean', 'diagonal']:
try:
initialize = np.load(initialize)
except IOError as e:
print >> sys.stderr, '''-i --initialize must be either "euclidean",
"diagonal", or the path to a flat text matrix'''
print >> sys.stderr, e
sys.exit(1)
# type conversion
alpha, epsilon = map(float, [args.alpha, args.epsilon])
outer_iterations, inner_iterations = map(int,
[args.outer_iterations, args.inner_iterations])
rho, weights = lmmdm.optimize_diagonal(s['AtoB'], s['AtoC'], alpha, loss='huber')
rho, metric_matrix = lmmdm.optimize_dense(s['AtoB'], s['AtoC'], alpha, rho, np.diag(weights),
loss='huber', epsilon=1e-5, max_outer_iterations=outer_iterations,
max_inner_iterations=inner_iterations)
if metric_string == 'dihedral':
metric = metrics.Dihedral(metric='mahalanobis', VI=metric_matrix)
elif metric_string == 'drmsd':
metric = metrics.AtomPairs(metric='mahalanobis', VI=metric_matrix, atom_pairs=s['atom_pairs'])
elif metric_string == 'rmsd':
metric = WRMSD(metric='mahalanobis', VI=metric_matrix)
elif metric_string == 'recipcontact':
metric = metrics.ContinuousContact(contacts='all', scheme='CA', metric='mahalanobis',
VI=metrix_matrix)
else:
raise NotImplementedError('Sorry')
# save to disk
pickle.dump(metric, open(args.metric, 'w'))
print 'Saved metric pickle to {}'.format(args.metric)
np.save(args.matrix, [metric_matrix, rho])
print 'Saved weights, rho to {}'.format(args.matrix)
def test_load_2(self):
"load using deferred=True"
deferred = io.loadh(self.filename1, deferred=True)
npt.assert_array_equal(deferred['arr_0'], self.data)
deferred.close()
def test_save(self):
"""Save HDF5 to disk and load it back up"""
io.saveh(self.filename2, self.data)
TestData = io.loadh(self.filename2, 'arr_0')
npt.assert_array_equal(TestData, self.data)
def test_load_1(self):
"Load by specifying array name"
TestData = io.loadh(self.filename1, 'arr_0')
npt.assert_array_equal(TestData, self.data)
#!/usr/bin/env python
from msmbuilder import io, MSMLib
from scipy.io import mmwrite
import sys
from msmbuilder import arglib
parser = arglib.ArgumentParser()
parser.add_argument("assignments")
parser.add_argument("lagtime", type=int, default=1)
parser.add_argument("sliding_window", default=False, action="store_true")
parser.add_argument("output", default="tCounts.raw.mtx")
args = parser.parse_args()
try:
ass = io.loadh(args.assignments)["Data"]
except:
ass = io.loadh(args.assignments)["arr_0"]
C = MSMLib.get_count_matrix_from_assignments(ass, lag_time=args.lagtime, sliding_window=args.sliding_window)
print C.sum()
mmwrite(args.output, C)
def main(modeldir, gensfile, write=False):
if not os.path.exists('%s/eig-states/' % modeldir):
os.mkdir('%s/eig-states/' % modeldir)
ohandle=open('%s/eig-states/eiginfo.txt' % modeldir, 'w')
project=Project.load_from('%s/ProjectInfo.yaml' % modeldir.split('Data')[0])
ass=io.loadh('%s/Assignments.Fixed.h5' % modeldir)
gens=Trajectory.load_from_lhdf(gensfile)
T=mmread('%s/tProb.mtx' % modeldir)
data=dict()
data['rmsd']=numpy.loadtxt('%s.rmsd.dat' % gensfile.split('.lh5')[0])
com=numpy.loadtxt('%s.vmd_com.dat' % gensfile.split('.lh5')[0], usecols=(1,))
data['com']=com[1:]
pops=numpy.loadtxt('%s/Populations.dat' % modeldir)
map=numpy.loadtxt('%s/Mapping.dat' % modeldir)
map_rmsd=[]
map_com=[]
for x in range(0, len(data['rmsd'])):
if map[x]!=-1:
map_com.append(data['com'][x])
map_rmsd.append(data['rmsd'][x])
map_com=numpy.array(map_com)
map_rmsd=numpy.array(map_rmsd)
T=mmread('%s/tProb.mtx' % modeldir)
eigs_m=msm_analysis.get_eigenvectors(T, 10)
cm=pylab.cm.get_cmap('RdYlBu_r') #blue will be negative components, red positive
print numpy.shape(eigs_m[1][:,1])
for i in range(0,1):
order=numpy.argsort(eigs_m[1][:,i])
if i==0:
maxes=[]
gen_maxes=[]
values=[]
ohandle.write('eig%s maxes\n' % i)
ohandle.write('state\tgenstate\tmagnitude\trmsd\tcom\n')
for n in order[::-1][:5]:
gen_maxes.append(numpy.where(map==n)[0])
maxes.append(n)
values.append(eigs_m[1][n,i])
ohandle.write('%s\t%s\t%s\t%s\t%s\n' % (n, numpy.where(map==n)[0], eigs_m[1][n,i], map_rmsd[n], map_com[n]))
print "maxes at ", maxes, values
maxes=numpy.array(maxes)
if write==True:
get_structure(modeldir, i, gen_maxes, maxes, gens, project, ass, type='max')
else:
maxes=[]
gen_maxes=[]
values=[]
ohandle.write('eig%s maxes\n' % i)
for n in order[::-1][:5]:
gen_maxes.append(numpy.where(map==n)[0])
maxes.append(n)
values.append(eigs_m[1][n,i])
ohandle.write('%s\t%s\t%s\t%s\t%s\n' % (n, numpy.where(map==n)[0], eigs_m[1][n,i], map_rmsd[n], map_com[n]))
print "maxes at ", maxes, values
order=numpy.argsort(eigs_m[1][:,i])
mins=[]
gen_mins=[]
values=[]
ohandle.write('eig%s mins\n' % i)
for n in order[:5]:
gen_mins.append(numpy.where(map==n)[0])
mins.append(n)
values.append(eigs_m[1][n,i])
ohandle.write('%s\t%s\t%s\t%s\t%s\n' % (n, numpy.where(map==n)[0], eigs_m[1][n,i], map_rmsd[n], map_com[n]))
print "mins at ", mins, values
if write==True:
get_structure(modeldir, i, gen_maxes, maxes, gens, project, ass, type='max')
get_structure(modeldir, i, gen_mins, mins, gens, project, ass, type='min')
pylab.scatter(map_com[order], map_rmsd[order], c=eigs_m[1][order,i], cmap=cm, s=1000*abs(eigs_m[1][order,i]), alpha=0.5)
print map_com[order][numpy.argmax(eigs_m[1][order,i])]
print eigs_m[1][order,i][1]
CB=pylab.colorbar()
l,b,w,h=pylab.gca().get_position().bounds
ll, bb, ww, hh=CB.ax.get_position().bounds
CB.ax.set_position([ll, b+0.1*h, ww, h*0.8])
CB.set_label('Eig%s Magnitudes' % i)
ylabel=pylab.ylabel('Ligand RMSD to Xtal ($\AA$)')
xlabel=pylab.xlabel(r'P Active Site - L COM Distance ($\AA$)')
pylab.legend(loc=8, frameon=False)
pylab.savefig('%s/2deigs%i_com_prmsd.png' %(modeldir, i),dpi=300)
the structures of each of the cluster centers. Produced using Cluster.py.''', default='Data/Gens.lh5')
parser.add_argument('output_dir', default='PDBs')
args = parser.parse_args()
if -1 in args.states:
print "Ripping PDBs for all states"
args.states = 'all'
if args.conformations_per_state == -1:
print "Getting all PDBs for each state"
args.conformations_per_state = 'all'
atom_indices = np.loadtxt(args.lprmsd_atom_indices, np.int)
assignments = io.loadh(args.assignments)
project = Project.load_from(args.project)
if args.lprmsd_permute_atoms == 'None':
permute_indices = None
else:
permute_indices = ReadPermFile(args.lprmsd_permute_atoms)
if args.lprmsd_alt_indices == 'None':
alt_indices = None
else:
alt_indices = np.loadtxt(args.lprmsd_alt_indices, np.int)
run(project, assignments, args.conformations_per_state,
args.states, args.output_dir, args.generators, atom_indices, permute_indices, alt_indices, args.total_memory_gb)
conformations to randomly sample from your data per state''',
type=int)
parser.add_argument('format',
help='''Format to output the data in. Note
that the PDB format is uncompressed and not efficient. For XTC, you can view
the trajectory using your project's topology file''',
default='lh5',
choices=['pdb', 'xtc', 'lh5'])
args = parser.parse_args()
if args.output == 'XRandomConfs':
args.output = '%dRandomConfs.%s' % (args.conformations_per_state,
args.format)
try:
assignments = io.loadh(args.assignments, 'arr_0')
except KeyError:
assignments = io.loadh(args.assignments, 'Data')
project = Project.load_from(args.project)
random_confs = run(project, assignments, args.conformations_per_state)
if args.format == 'pdb':
random_confs.SaveToPDB(args.output)
elif args.format == 'lh5':
random_confs.SaveToLHDF(args.output)
elif args.format == 'xtc':
random_confs.SaveToXTC(args.output)
else:
raise ValueError('Unrecognized format')
discards (expensive!) data, so should only be used if an optimal
clustering is not available.
Note: Check your cluster sized with CalculateClusterRadii.py to get
a handle on how big they are before you trim. Recall the radius is the
*average* distance to the generator, here you are enforcing the
*maximum* distance.
Output: A trimmed assignments file (Assignments.Trimmed.h5).""")
parser.add_argument('assignments', default='Data/Assignments.Fixed.h5')
parser.add_argument('distances', default='Data/Assignments.h5.distances')
parser.add_argument('rmsd_cutoff', help="""distance value at which to trim,
in. Data further than this value to its generator will be
discarded. Note: this is measured with whatever distance metric you used to cluster""", type=float)
parser.add_argument('output', default='Data/Assignments.Trimmed.h5')
args = parser.parse_args()
arglib.die_if_path_exists(args.output)
try:
assignments = io.loadh(args.assignments, 'arr_0')
distances = io.loadh(args.distances, 'arr_0')
except KeyError:
assignments = io.loadh(args.assignments, 'Data')
distances = io.loadh(args.distances, 'Data')
trimmed = run(assignments, distances, args.rmsd_cutoff)
io.saveh(args.output, trimmed)
logger.info('Saved output to %s', args.output)
parser.add_argument('-N',dest='N',default=0,type=int,help='Which eigenvector to look at.')
parser.add_argument('--double',dest='double',default=False,action='store_true',help='Pass this flag if you used msmbuilder.metrics.Dihedrals, which means there is a sin and cosine entry for each angle')
options = parser.parse_args()
import numpy as np
from msmbuilder import io, Trajectory
from msmbuilder import metrics
from msmbuilder.geometry import dihedral
import matplotlib
matplotlib.use('pdf')
from matplotlib.pyplot import *
import os, sys, re
pdb = Trajectory.load_trajectory_file( options.pdbFN )
pca = io.loadh( options.pcaFN )
decInd = np.argsort( pca['vals'] )[::-1]
v0 = np.abs(pca['vecs'][:,decInd][:,options.N])
if options.double:
if v0.shape[0] % 2:
print "There are an odd number of entries, so --double should not be passed here, or something else has gone wrong."
exit()
n0 = v0.shape[0]
v0 = v0[:n0/2] + v0[n0/2:]
def main(coarse_val, orig_val, rcut):
data=dict()
data['coarse']=dict()
data['orig']=dict()
dirs=dict()
dirs['coarse']='./d%s' % coarse_val
dirs['orig']='./d%s' % orig_val
proj=Project.load_from('ProjectInfo.yaml')
types=['ass', 'rmsd', 'dist', 'gens']
for key in ['coarse', 'orig']:
for type in types:
if 'ass' in type:
ass=io.loadh('%s/Data/Assignments.h5' % dirs[key])
data[key][type]=ass['arr_0']
elif 'dist' in type:
ass=io.loadh('%s/Data/Assignments.h5.distances' % dirs[key])
data[key][type]=ass['arr_0']
elif 'rmsd' in type:
rmsd=numpy.loadtxt('%s/Gens.rmsd.dat' % dirs[key])
data[key][type]=rmsd
elif 'gens' in type:
gens=Trajectory.load_from_lhdf('%s/Gens.lh5' % dirs[key])
data[key][type]=gens
unboundmap=dict()
boundmap=dict()
#unboundstates=dict()
#unboundrmsd=dict()
# build map dict for orig to coarse unbound states, bound will stay same
newass=-1*numpy.ones(( data['orig']['ass'].shape[0], data['orig']['ass'].shape[1]), dtype=int)
for j in range(0, data['orig']['ass'].shape[0]):
for (n,i) in enumerate(data['orig']['ass'][j]):
# if unbound
if i != -1:
if data['orig']['rmsd'][i] > float(rcut):
state=data['coarse']['ass'][j][n]
newass[j][n]=state+10000
else:
newass[j][n]=i
count=0
unique=set(newass.flatten())
boundmap=dict()
unboundmap=dict()
for x in unique:
locations=numpy.where(newass==x)
newass[locations]=count
if x >= 10000:
unboundmap[count]=(x-10000)
else:
boundmap[count]=x
count+=1
io.saveh('%s/Coarsed_r%s_Assignments.h5' % (dirs['orig'], rcut), newass)
subdir='%s/Coarsed_r%s_gen/' % (dirs['orig'], rcut)
if not os.path.exists(subdir):
os.mkdir(subdir)
ohandle=open('%s/Coarsed%s_r%s_Gens.rmsd.dat' % (subdir, coarse_val, rcut), 'w')
b=data['orig']['gens']['XYZList'].shape[1]
c=data['orig']['gens']['XYZList'].shape[2]
dicts=[boundmap, unboundmap]
names=['bound', 'unbound']
labels=['orig', 'coarse']
total=len(boundmap.keys()) + len(unboundmap.keys())
structure=proj.empty_traj()
structure['XYZList']=numpy.zeros((total, b, c), dtype='float32')
count=0
for (name, label, mapdata) in zip( names, labels, dicts):
print "writing coarse gen %s out of %s pdbs" % (count, len(mapdata.keys()))
for i in sorted(mapdata.keys()):
macro=mapdata[i]
structure['XYZList'][count]=data[label]['gens']['XYZList'][macro]
ohandle.write('%s\t%s\t%s\n' % (name, count, data[label]['rmsd'][macro]))
print name, count
count+=1
structure.save_to_xtc('%s/Coarsed%s_r%s_Gens.xtc' % (subdir, coarse_val, rcut))
import numpy as np
from scipy.optimize import fsolve
from msmbuilder import io
import argparse
import matplotlib
from matplotlib.pyplot import *
import IPython
parser = argparse.ArgumentParser()
parser.add_argument('-d', dest='data', help='data for each state')
parser.add_argument('-f', dest='eig', help='eigenvector value of each state')
args = parser.parse_args()
M = io.loadh(args.data, 'HB_maps')
if len(M.shape) > 2:
M = M.reshape((M.shape[0], -1))
M = M - M.mean(0)
print M.shape
eig = io.loadh(args.eig, 'arr_0')
b = eig / np.sqrt(eig.dot(eig) / eig.shape[0])
b = np.reshape(b, (-1, 1))
sigma = M.T.dot(M)
pca_vals, pca_vecs = np.linalg.eig(sigma)
ind = np.where(pca_vals > 1E-8)[0]
parser.add_argument('output', help="""The name of the RandomConfs
trajectory (.lh5) to write. XRandomConfs.lh5, where X=Number of
Conformations.""", default='XRandomConfs')
parser.add_argument('conformations_per_state', help='''Number of
conformations to randomly sample from your data per state''', type=int)
parser.add_argument('format', help='''Format to output the data in. Note
that the PDB format is uncompressed and not efficient. For XTC, you can view
the trajectory using your project's topology file''', default='lh5',
choices=['pdb', 'xtc', 'lh5'])
args = parser.parse_args()
if args.output == 'XRandomConfs':
args.output = '%dRandomConfs.%s' % (args.conformations_per_state, args.format)
try:
assignments = io.loadh(args.assignments, 'arr_0')
except KeyError:
assignments = io.loadh(args.assignments, 'Data')
project = Project.load_from(args.project)
random_confs = run(project, assignments, args.conformations_per_state)
if args.format == 'pdb':
random_confs.SaveToPDB(args.output)
elif args.format == 'lh5':
random_confs.SaveToLHDF(args.output)
elif args.format == 'xtc':
random_confs.SaveToXTC(args.output)
else:
raise ValueError('Unrecognized format')
def get_implied_timescales_helper(args):
"""Helper function to compute implied timescales with multiprocessing
Does not work in interactive mode
Parameters
----------
assignments_fn : str
Path to Assignments.h5 file on disk
n_states : int
Number of states
lag_time : list
List of lag times to calculate the timescales at
n_implied_times : int, optional
Number of implied timescales to calculate at each lag time
sliding_window : bool, optional
Use sliding window
trimming : bool, optional
Use ergodic trimming
symmetrize : {'MLE', 'Transpose', None}
Symmetrization method
Returns
-------
lagTimes : ndarray
vector of lag times
impTimes : ndarray
vector of implied timescales
See Also
--------
MSMLib.build_msm
get_eigenvectors
"""
assignments_fn, lag_time, n_implied_times, sliding_window, trimming, symmetrize = args
try:
assignments = io.loadh(assignments_fn, 'arr_0')
except KeyError:
assignments = io.loadh(assignments_fn, 'Data')
try:
from msmbuilder import MSMLib
t_matrix = MSMLib.build_msm(assignments, lag_time, symmetrize,
sliding_window, trimming)[1]
except ValueError as e:
logger.critical(e)
sys.exit(1)
#TJL: set Epsilon high, should not raise err here
n_eigenvectors = n_implied_times + 1
e_values = get_eigenvectors(t_matrix, n_eigenvectors, epsilon=1)[0]
# make sure to leave off equilibrium distribution
lag_times = lag_time * np.ones((n_implied_times))
imp_times = -lag_times / np.log(e_values[1:n_eigenvectors])
# save intermediate result in case of failure
# res = np.zeros((n_implied_times, 2))
# res[:,0] = lag_times
# res[:,1] = np.real(imp_times)
return (lag_times, imp_times)
def get_implied_timescales_helper(args):
"""Helper function to compute implied timescales with multiprocessing
Does not work in interactive mode
Parameters
----------
assignments_fn : str
Path to Assignments.h5 file on disk
n_states : int
Number of states
lag_time : list
List of lag times to calculate the timescales at
n_implied_times : int, optional
Number of implied timescales to calculate at each lag time
sliding_window : bool, optional
Use sliding window
trimming : bool, optional
Use ergodic trimming
symmetrize : {'MLE', 'Transpose', None}
Symmetrization method
Returns
-------
lagTimes : ndarray
vector of lag times
impTimes : ndarray
vector of implied timescales
See Also
--------
MSMLib.build_msm
get_eigenvectors
"""
assignments_fn, lag_time, n_implied_times, sliding_window, trimming, symmetrize = args
try:
assignments = io.loadh(assignments_fn, 'arr_0')
except KeyError:
assignments = io.loadh(assignments_fn, 'Data')
try:
from msmbuilder import MSMLib
counts = MSMLib.get_count_matrix_from_assignments(assignments, lag_time=lag_time,
sliding_window=sliding_window)
rev_counts, t_matrix, populations, mapping = MSMLib.build_msm(counts, symmetrize, trimming)
except ValueError as e:
logger.critical(e)
sys.exit(1)
#TJL: set Epsilon high, should not raise err here
n_eigenvectors = n_implied_times + 1
e_values = get_eigenvectors(t_matrix, n_eigenvectors, epsilon=1)[0]
# make sure to leave off equilibrium distribution
lag_times = lag_time * np.ones((n_implied_times))
imp_times = -lag_times / np.log(e_values[1: n_eigenvectors])
# save intermediate result in case of failure
# res = np.zeros((n_implied_times, 2))
# res[:,0] = lag_times
# res[:,1] = np.real(imp_times)
return (lag_times, imp_times)
dcds=numpy.loadtxt('mapped_trajs.txt', usecols=(0,), dtype=str)
xtcs=numpy.loadtxt('mapped_trajs.txt', usecols=(1,), dtype=str)
mapping=dict()
for (i,j) in zip(dcds, xtcs):
name=i.split('_nowat_')[0]
mapping[j]=name
#for j in mapping.keys():
# total=mapping[j]+bw[j]
# if total!=totals[j]:
# print "problem"
# import pdb
# pdb.set_trace()
ohandle=open('d6/msml1000_coarse_r10_d20/traj_frames.txt', 'w')
ass=io.loadh('d6/msml1000_coarse_r10_d20/Assignments.Fixed.h5')
mapfile=numpy.loadtxt('d6/msml1000_coarse_r10_d20/Mapping.dat')
sample=False
for state in sorted(set(ass['arr_0'].flatten())):
if state!=-1:
traj=numpy.where(ass['arr_0']==state)[0]
frames=numpy.where(ass['arr_0']==state)[1]
indices=numpy.random.random_integers(0, len(traj)-1, len(traj))
for ind in indices:
traj_ind=traj[ind]
mapped_traj=mapping['trj%s' % traj_ind]
if mapped_traj in bw.keys():
minval=bw[mapped_traj]
else:
minval=0
location=numpy.where((traj==traj_ind)&(frames>minval))[0]
from time import time
import logging
logger = logging.getLogger(__name__)
logger.setLevel(logging.INFO)
sh = logging.StreamHandler(sys.stdout)
formatter = logging.Formatter(fmt="%(asctime)s - %(message)s", datefmt="%H:%M:%S")
sh.setFormatter(formatter)
logger.addHandler(sh)
logger.propagate = False
logger.info("start")
Proj = Project.load_from(args.proj_FN)
logger.info("loaded project info")
try:
Ass = io.loadh(args.ass_FN)["arr_0"]
except:
Ass = io.loadh(args.ass_FN)["Data"]
pdb = Trajectory.load_from_pdb(Proj.conf_filename)
which = np.loadtxt(args.which).astype(int)
distance_cutoff = 0.32
angle_cutoff = 120
def get_hb(traj):
# get accH - donor distance:
dists = contact.atom_distances(traj["XYZList"], atom_contacts=which[:, 1:])
import sys, os
import scipy.io
from msmbuilder import MSMLib
from msmbuilder.io import loadh, saveh
try:
Assignments = loadh("%s" % (sys.argv[1]), 'arr_0').astype(int)
except KeyError:
Assignments = loadh("%s" % (sys.argv[1]), 'Data').astype(int)
NumStates = max(Assignments.flatten()) + 1
LagTime = int(sys.argv[2])
Counts = MSMLib.get_count_matrix_from_assignments(Assignments,
n_states=NumStates,
lag_time=LagTime,
sliding_window=True)
scipy.io.mmwrite('%s' % (sys.argv[3]), Counts)
