def main(args, metric):
check_paths(args)
if args.alg == 'sclarans' and args.stride != 1:
logger.error("""You don't want to use a stride with sclarans. The whole point of
sclarans is to use a shrink multiple to accomplish the same purpose, but in parallel with
stochastic subsampling. If you cant fit all your frames into memory at the same time, maybe you
could stride a little at the begining, but its not recommended.""")
sys.exit(1)
trajs = load_trajectories(args.project, args.stride)
logger.info('Loaded %d trajs', len(trajs))
clusterer = cluster(metric, trajs, args)
if not isinstance(clusterer, clustering.Hierarchical):
generators = clusterer.get_generators_as_traj()
logger.info('Saving %s', args.generators)
generators.save_to_lhdf(args.generators)
if args.stride == 1:
assignments = clusterer.get_assignments()
distances = clusterer.get_distances()
logger.info('Since stride=1, Saving %s', args.assignments)
logger.info('Since stride=1, Saving %s', args.distances)
io.saveh(args.assignments, assignments)
io.saveh(args.distances, distances)
def main(args, metric):
check_paths(args)
if args.alg == 'sclarans' and args.stride != 1:
logger.error(
"""You don't want to use a stride with sclarans. The whole point of
sclarans is to use a shrink multiple to accomplish the same purpose, but in parallel with
stochastic subsampling. If you cant fit all your frames into memory at the same time, maybe you
could stride a little at the begining, but its not recommended.""")
sys.exit(1)
trajs = load_trajectories(args.project, args.stride)
logger.info('Loaded %d trajs', len(trajs))
clusterer = cluster(metric, trajs, args)
if not isinstance(clusterer, clustering.Hierarchical):
generators = clusterer.get_generators_as_traj()
logger.info('Saving %s', args.generators)
generators.save_to_lhdf(args.generators)
if args.stride == 1:
assignments = clusterer.get_assignments()
distances = clusterer.get_distances()
logger.info('Since stride=1, Saving %s', args.assignments)
logger.info('Since stride=1, Saving %s', args.distances)
io.saveh(args.assignments, assignments)
io.saveh(args.distances, distances)
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 save_container(filename, dtype):
io.saveh(
filename,
arr_0=np.array(minus_ones, dtype=dtype),
completed_vtrajs=np.zeros((n_vtrajs), dtype=np.bool),
hashes=hashes,
)
def main(args, metric):
if args.alg == "sclarans" and args.stride != 1:
logger.error(
"""You don't want to use a stride with sclarans. The whole point of
sclarans is to use a shrink multiple to accomplish the same purpose, but in parallel with
stochastic subsampling. If you cant fit all your frames into memory at the same time, maybe you
could stride a little at the begining, but its not recommended."""
)
sys.exit(1)
# if we have a metric that explicitly operates on a subset of indices,
# then we provide the option to only load those indices into memory
# WARNING: I also do something a bit dirty, and inject `None` for the
# RMSD.atomindices to get the metric to not splice
if isinstance(metric, metrics.RMSD):
atom_indices = metric.atomindices
metric.atomindices = None # probably bad...
logger.info("RMSD metric - loading only the atom indices required")
else:
atom_indices = None
# In case the clustering / algorithm needs extra arguments, use
# this dictionary
extra_kwargs = {}
# Check to be sure we won't overwrite any data
if args.alg == "hierarchical":
zmatrix_fn = os.path.join(args.output_dir, "ZMatrix.h5")
die_if_path_exists(zmatrix_fn)
extra_kwargs["zmatrix_fn"] = zmatrix_fn
else:
generators_fn = os.path.join(args.output_dir, "Gens.lh5")
die_if_path_exists(generators_fn)
if args.stride == 1:
assignments_fn = os.path.join(args.output_dir, "Assignments.h5")
distances_fn = os.path.join(args.output_dir, "Assignments.h5.distances")
die_if_path_exists([assignments_fn, distances_fn])
trajs = load_trajectories(args.project, args.stride, atom_indices)
logger.info("Loaded %d trajs", len(trajs))
clusterer = cluster(metric, trajs, args, **extra_kwargs)
if not isinstance(clusterer, clustering.Hierarchical):
generators = clusterer.get_generators_as_traj()
logger.info("Saving %s", generators_fn)
generators.save_to_lhdf(generators_fn)
if args.stride == 1:
assignments = clusterer.get_assignments()
distances = clusterer.get_distances()
logger.info("Since stride=1, Saving %s", assignments_fn)
logger.info("Since stride=1, Saving %s", distances_fn)
io.saveh(assignments_fn, assignments)
io.saveh(distances_fn, distances)
def save(self, output):
"""
save the results to file
Parameters:
-----------
output : str
output filename (.h5)
"""
io.saveh(output, timelag_corr_mat=self.timelag_corr_mat,
cov_mat=self.cov_mat, lag=np.array([self.lag]), vals=self.vals,
vecs=self.vecs)
def save_to_disk(self, filename):
"""Save this clusterer to 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
------
Exception if something already exists at `filename`
"""
io.saveh(filename, z_matrix=self.Z, traj_lengths=self.traj_lengths)
def save_to_disk(self, filename):
"""Save this clusterer to 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
------
Exception if something already exists at `filename`
"""
io.saveh(filename, z_matrix=self.Z, traj_lengths=self.traj_lengths)
def save_to_hdf(self, filename):
"""Save a Trajectory instance to a HDF File.
First, remove the XYZList key because it should be written using the
special CArray operation. This file format is roughly equivalent to
an XTC and should comparable file sizes but with better IO performance.
Parameters
----------
Filename: str
location to save to
Precision : float, optional
Precision to save xyzlist
"""
indexlist = self.pop('IndexList', None)
io.saveh(filename, **self)
self['IndexList'] = indexlist
def save_to_lhdf(self, filename, precision=DEFAULT_PRECISION):
"""Save a Trajectory instance to a Lossy HDF File.
First, remove the XYZList key because it should be written using the
special CArray operation. This file format is roughly equivalent to
an XTC and should comparable file sizes but with better IO performance.
Parameters
----------
Filename: str
location to save to
Precision : float, optional
Precision to save xyzlist
"""
self.pop('IndexList')
xyzlist = self.pop('XYZList')
rounded = _convert_to_lossy_integers(xyzlist, precision)
self['XYZList'] = rounded
io.saveh(filename, **self)
self['XYZList'] = xyzlist
def save_to_lhdf(self, filename, precision=DEFAULT_PRECISION):
"""Save a Trajectory instance to a Lossy HDF File.
First, remove the XYZList key because it should be written using the
special CArray operation. This file format is roughly equivalent to
an XTC and should comparable file sizes but with better IO performance.
Parameters
----------
Filename: str
location to save to
Precision : float, optional
Precision to save xyzlist
"""
self.pop("IndexList")
xyzlist = self.pop("XYZList")
rounded = _convert_to_lossy_integers(xyzlist, precision)
self["XYZList"] = rounded
io.saveh(filename, **self)
self["XYZList"] = xyzlist
def main(args, metric):
check_paths(args)
if args.alg == 'sclarans' and args.stride != 1:
logger.error("""You don't want to use a stride with sclarans. The whole point of
sclarans is to use a shrink multiple to accomplish the same purpose, but in parallel with
stochastic subsampling. If you cant fit all your frames into memory at the same time, maybe you
could stride a little at the begining, but its not recommended.""")
sys.exit(1)
# if we have a metric that explicitly operates on a subset of indices,
# then we provide the option to only load those indices into memory
# WARNING: I also do something a bit dirty, and inject `None` for the
# RMSD.atomindices to get the metric to not splice
if isinstance(metric, metrics.RMSD):
atom_indices = metric.atomindices
metric.atomindices = None # probably bad...
logger.info('RMSD metric - loading only the atom indices required')
else:
atom_indices = None
trajs = load_trajectories(args.project, args.stride, atom_indices)
logger.info('Loaded %d trajs', len(trajs))
clusterer = cluster(metric, trajs, args)
if not isinstance(clusterer, clustering.Hierarchical):
generators = clusterer.get_generators_as_traj()
logger.info('Saving %s', args.generators)
generators.save_to_lhdf(args.generators)
if args.stride == 1:
assignments = clusterer.get_assignments()
distances = clusterer.get_distances()
logger.info('Since stride=1, Saving %s', args.assignments)
logger.info('Since stride=1, Saving %s', args.distances)
io.saveh(args.assignments, assignments)
io.saveh(args.distances, distances)
def main_extract(args):
"main method for the extract subcommand"
project = Project.load_from(args.project_info)
close = int(args.close)
stride = int(args.stride)
if args.far < 0:
far = None
else:
far = args.far
die_if_path_exists(args.output)
if args.extract_method == 'rmsd':
atomindices = np.loadtxt(args.atomindices, dtype=int)
AtoB, AtoC = triplets.extract_rmsd(project, close, stride, atomindices, far)
elif args.extract_method == 'dihedral':
if 'types' in args:
AtoB, AtoC = triplets.extract_dihedral(project, close, stride, types=args.types, far=far)
else:
indices = np.loadtxt(args.indices, dtype=int)
AtoB, AtoC = triplets.extract_dihedral(project, close, stride, indices=indices, far=far)
elif args.extract_method == 'recipcontact':
AtoB, AtoC = triplets.extract_recipcontact(project, close, stride, far=far)
elif args.extract_method == 'drmsd':
indices = np.loadtxt(args.indices, dtype=int)
AtoB, AtoC, atom_pairs = triplets.extract_drmsd(project, close, stride, indices=indices, far=far)
io.saveh(args.output, atom_pairs=atom_pairs)
else:
raise NotImplementedError("Sorry, we don't have that metric")
#Serializer({'AtoB': AtoB, 'AtoC': AtoC, 'metric': args.extract_method}).SaveToHDF(args.output)
io.saveh(args.output, AtoB=AtoB, AtoC=AtoC, metric=np.array(list(args.extract_method)))
print 'Saved triplets to {}'.format(args.output)
not_too_short_inds = np.where( traj_lens >= ( args.min_length + args.trim_first ) )[0]
os.mkdir( os.path.join( args.write_dir, 'Trajectories' ) )
print "Will limit this project to %d trajectories." % len( not_too_short_inds )
for i in xrange( len( not_too_short_inds ) ):
print "Copying trajectory %d -> %d (length=%d)" % ( not_too_short_inds[i], i, Proj.traj_lengths[ not_too_short_inds[i] ] - args.trim_first )
trj0 = tables.openFile( Proj.traj_filename( not_too_short_inds[i] ) )
trj1 = tables.openFile( os.path.abspath( os.path.join( args.write_dir, 'Trajectories', '%s%d%s'% ('trj',i, '.lh5' ) ) ), 'w' )
#os.system( 'ln -s %s %s' % ( trj0, trj1 ) )
#os.symlink( trj0, trj1 )
for n0 in trj0.iterNodes('/'):
if n0.name != 'XYZList':
trj0.copyNode( where='/', name=n0.name, newparent=trj1.root )
else:
temp_ary = n0[ args.trim_first : ]
io.saveh( trj1, XYZList=temp_ary )
trj0.close()
trj1.close()
new_records = {'conf_filename': Proj.conf_filename.split('/')[-1],
'traj_lengths': Proj.traj_lengths[ not_too_short_inds ] - args.trim_first,
'traj_paths': Proj._traj_paths[ : len( not_too_short_inds ) ], # This works because they're named relatively and they are re-numbered
'traj_converted_from': Proj._traj_converted_from[ not_too_short_inds ],
'traj_errors': Proj._traj_errors[ not_too_short_inds ] }
new_proj_dir = args.write_dir
# Copy the trajectories
New_Proj = Project( new_records, project_dir = new_proj_dir )
New_Proj.save( os.path.join( args.write_dir, 'ProjectInfo.yaml' ) )
if ass == -1:
continue
CMs_1d[ass] += ptrj_chunk[i]
# StateAssigns = np.array([ np.where( Ass == i )[0].shape[0] for i in np.unique( Ass[ np.where( Ass >= 0 ) ] )] )
StateAssigns = np.bincount(Ass[np.where(Ass != -1)], minlength=Ass.max() + 1)
StateAssigns = StateAssigns.reshape((len(StateAssigns), 1))
AvgCMs_1d = CMs_1d / StateAssigns
num_donors = len(HB.last_donor_ainds)
num_acceptors = len(HB.last_acceptor_ainds)
CMs = AvgCMs_1d.reshape((-1, num_donors, num_acceptors), order="C")
triples = HB.get_angle_list()
io.saveh(args.out_cm, donor_h_acceptor_ainds=triples, HB_maps=np.array(CMs))
# CMs = [ avg_cm.reshape( (num_donors, num_acceptors ), order='C') for avg_cm in AvgCMs_1d ]
num_acceptors = len(np.unique(triples[:, 2]))
num_donors = len(np.unique(triples[:, 0]))
donor_ainds = np.unique(triples[:, 0])
donorH_ainds = np.unique(triples[:, 1])
acceptor_ainds = np.unique(triples[:, 2])
donor_atomnames = pdb["AtomNames"][donor_ainds]
donorH_atomnames = pdb["AtomNames"][donorH_ainds]
acceptor_atomnames = pdb["AtomNames"][acceptor_ainds]
donor_resnames = pdb["ResidueNames"][donor_ainds]
def main(args, metric):
if args.alg == 'sclarans' and args.stride != 1:
logger.error("""You don't want to use a stride with sclarans. The whole point of
sclarans is to use a shrink multiple to accomplish the same purpose, but in parallel with
stochastic subsampling. If you cant fit all your frames into memory at the same time, maybe you
could stride a little at the begining, but its not recommended.""")
sys.exit(1)
# if we have a metric that explicitly operates on a subset of indices,
# then we provide the option to only load those indices into memory
# WARNING: I also do something a bit dirty, and inject `None` for the
# RMSD.atomindices to get the metric to not splice
if isinstance(metric, metrics.RMSD):
atom_indices = metric.atomindices
metric.atomindices = None # probably bad...
logger.info('RMSD metric - loading only the atom indices required')
else:
atom_indices = None
# In case the clustering / algorithm needs extra arguments, use
# this dictionary
extra_kwargs = {}
# Check to be sure we won't overwrite any data
if args.alg == 'hierarchical':
zmatrix_fn = os.path.join(args.output_dir, 'ZMatrix.h5')
die_if_path_exists(zmatrix_fn)
extra_kwargs['zmatrix_fn'] = zmatrix_fn
else:
generators_fn = os.path.join(args.output_dir, 'Gens.lh5')
die_if_path_exists(generators_fn)
if args.stride == 1:
assignments_fn = os.path.join(args.output_dir, 'Assignments.h5')
distances_fn = os.path.join(args.output_dir, 'Assignments.h5.distances')
die_if_path_exists([assignments_fn, distances_fn])
project = Project.load_from(args.project)
if isinstance(metric, metrics.Vectorized) and not args.alg == 'hierarchical':
# if the metric is vectorized then
# we can load prepared trajectories
# which may allow for better memory
# efficiency
ptrajs, which = load_prep_trajectories(project, args.stride, atom_indices, metric)
trajectories = None
n_trajs = len(ptrajs)
num_frames = np.sum([len(p) for p in ptrajs])
if num_frames != len(which):
raise Exception("something went wrong in loading step (%d v %d)" % (num_frames, len(which)))
else:
trajectories = load_trajectories(project, args.stride, atom_indices)
ptrajs = None
which = None
n_trajs = len(trajectories)
logger.info('Loaded %d trajs', n_trajs)
clusterer = cluster(metric, trajectories, ptrajs, args, **extra_kwargs)
if not isinstance(clusterer, clustering.Hierarchical):
if isinstance(metric, metrics.Vectorized):
gen_inds = clusterer.get_generator_indices()
generators = project.load_frame(which[gen_inds,0], which[gen_inds,1])
else:
generators = clusterer.get_generators_as_traj()
logger.info('Saving %s', generators_fn)
generators.save_to_lhdf(generators_fn)
if args.stride == 1:
assignments = clusterer.get_assignments()
distances = clusterer.get_distances()
logger.info('Since stride=1, Saving %s', assignments_fn)
logger.info('Since stride=1, Saving %s', distances_fn)
io.saveh(assignments_fn, assignments)
io.saveh(distances_fn, distances)
===============================================================================
This script is deprecated and will be removed in v2.7
Please use CalculateProjectDistance.py
===============================================================================
"""
parser = arglib.ArgumentParser(description="""
Calculate the RMSD between an input PDB and all conformations in your project.
Output as a HDF5 file (load using msmbuilder.io.loadh())
""" + deprecationmessage)
warnings.warn(deprecationmessage, DeprecationWarning)
parser.add_argument('pdb')
parser.add_argument('atom_indices', help='Indices of atoms to compare',
default='AtomIndices.dat')
parser.add_argument('output', help='''Output file name. Output is an
.h5 file with RMSD entries corresponding to the Assignments.h5 file.''',
default='Data/RMSD.h5')
parser.add_argument('project')
args = parser.parse_args()
arglib.die_if_path_exists(args.output)
project = Project.load_from(args.project)
pdb = Trajectory.load_trajectory_file( args.pdb )
atom_indices = np.loadtxt( args.atom_indices ).astype(int)
distances = run(project, pdb, atom_indices)
io.saveh(args.output, distances)
logger.info('Saved to %s', args.output)
args = parser.parse_args()
traj_fns = [os.path.join(os.path.dirname(args.data_list), fn) for fn in np.loadtxt(args.data_list, dtype=str)]
traj = np.concatenate([np.load(fn) for fn in traj_fns])
metric = EuclideanMetric()
gen_ids, ass_gen_ids, distances = clustering._kcenters(metric, traj, k=args.num_states, seed=np.random.randint(len(traj)))
ass_gen_ids = np.array([ass_gen_ids])
if not os.path.exists(args.output_dir):
os.mkdir(args.output_dir)
ass_contig = np.ones(ass_gen_ids.shape) * -1
ass_contig = ass_contig.astype(int)
for i, j in enumerate(gen_ids):
ass_contig[np.where(ass_gen_ids == j)] = i
ass_contig = ass_contig.reshape((len(traj_fns), -1))
np.savetxt(os.path.join(args.output_dir, 'gen_ids.dat'), gen_ids)
np.save(os.path.join(args.output_dir, 'gens.npy'), traj[gen_ids])
io.saveh(os.path.join(args.output_dir, 'Assignments.h5'), ass_contig)
io.saveh(os.path.join(args.output_dir, 'Assignments.h5.distances'), np.array([distances]))
print "Saved output to %s" % args.output_dir
import numpy as np
from matplotlib import mlab
from msmbuilder import io
ff = "amber96"
#num_frames = 11250
num_frames = 225001
num_frames = 291622
num_frames = 295189
num_frames = 41250
data = []
for i in xrange(num_frames):
print(i)
d = mlab.csv2rec("%s/production/pdbs/frame%d.pdb.cs"%(ff,i))
data.append(d["shift"])
data = np.array(data)
io.saveh("%s/shifts.h5"%ff,data)
np.savetxt("./%s/shifts_atoms.txt"%ff,d["atomname"],"%s")
def save_container(filename, dtype):
io.saveh(
filename,
arr_0=-1 * np.ones(
(project.n_trajs, np.max(project.traj_lengths)), dtype=dtype),
completed_trajs=np.zeros((project.n_trajs), dtype=np.bool))
def save_container(filename, dtype):
io.saveh(filename, arr_0=np.array(minus_ones, dtype=dtype),
completed_vtrajs=np.zeros((n_vtrajs), dtype=np.bool),
hashes=hashes)
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)
num_confs = len(glob.glob("/%s/frame*.pdb" % in_directory))
all_shifts = []
all_errs = []
for i in xrange(num_confs):
print(i)
x = np.loadtxt("%s/frame%d_pred.tab"% (in_directory ,i),'str',skiprows=27)
shifts = x[:,4].astype('float')
errs = x[:,-1].astype('float')
res_id = x[:,0].astype('int')
atom_name = x[:,2]
all_shifts.append(shifts)
all_errs.append(errs)
all_shifts = np.array(all_shifts)
all_errs = np.array(all_errs)
mean_errs = all_errs.mean(0)
atom_name[atom_name == "HN"] = "H"
res_id -= 1
io.saveh("%s/shifts.h5" % out_directory,all_shifts)
np.savetxt("%s/shifts_errs.dat" % out_directory,mean_errs)
np.savetxt("%s/shifts_atoms.txt" % out_directory,atom_name,"%s")
np.savetxt("%s/shifts_resid.dat" % out_directory,res_id,"%d")
#!/usr/bin/env python
from msmbuilder import arglib, io, tICA, Project
parser = arglib.ArgumentParser( get_basic_metric=True )
parser.add_argument( 'project' )
parser.add_argument( 'output' )
parser.add_argument( 'stride', type=int, default=1 )
args, metric = parser.parse_args()
project = Project.load_from( args.project )
arglib.die_if_path_exists( args.output )
stride = int( args.stride )
cov_mat = tICA.CovarianceMatrix( 0 )
for i in xrange( project.n_trajs ):
print "Working on Trajectory %d"
ptraj = metric.prepare_trajectory( project.load_traj( i, stride=stride ) )
if i == 0:
cov_mat.set_size( ptraj.shape[1] )
cov_mat.train( ptraj )
print "Saving matrix to %s" % args.output
io.saveh( args.output, covariance_matrix=cov_mat.get_current_estimate() )
import sys
import numpy as np
import scipy.sparse
import matplotlib.pyplot as pp
from msmbuilder import io, msm_analysis, MSMLib
from bayesmutant import SimpleMutantSampler
wt_tprob = np.loadtxt('cayleytree_tprob_wildtype.dat')
mutant_tprob = np.loadtxt('cayleytree_tprob_mutant.dat')
base_counts = np.zeros_like(wt_tprob)
for i in range(base_counts.shape[0]):
base_counts[i] = np.random.multinomial(200, wt_tprob[i])
print 'base counts'
print base_counts
ms = SimpleMutantSampler(base_counts, mutant_tprob)
ms.step(5000)
#print ms.eff_counts()
#print 'observed counts'
#print ms.counts
io.saveh('sampling2.h5', base_counts=base_counts, samples=ms.samples,
observed_counts=ms.counts, scores=ms.scores,
effective_counts=ms.eff_counts(),
transition_matrix=mutant_tprob)
def save_container(filename, dtype):
io.saveh(filename, arr_0=-1*np.ones((project.n_trajs, np.max(project.traj_lengths)), dtype=dtype),
completed_trajs=np.zeros((project.n_trajs), dtype=np.bool))
ptrj_chunk = get_hb(trj_chunk).astype(float)
ass_chunk = Ass[traj_ind][
chunk_ind * chunk_size : (chunk_ind + 1) * chunk_size
] # this behaves as you want at the end of the array
for i, ass in enumerate(ass_chunk):
if ass == -1:
continue
CMs_1d[ass] += ptrj_chunk[i]
# StateAssigns = np.array([ np.where( Ass == i )[0].shape[0] for i in np.unique( Ass[ np.where( Ass >= 0 ) ] )] )
StateAssigns = np.bincount(Ass[np.where(Ass != -1)], minlength=Ass.max() + 1)
StateAssigns = StateAssigns.reshape((len(StateAssigns), 1))
AvgCMs_1d = CMs_1d / StateAssigns
io.saveh(args.out_cm, which=which, HB_maps=AvgCMs_1d)
uniq_res = np.unique(pdb["ResidueID"])
n_res = uniq_res.shape[0]
acc_res_ids = pdb["ResidueID"][which[:, 0]]
donor_res_ids = pdb["ResidueID"][which[:, 2]]
CMs = np.zeros((len(AvgCMs_1d), n_res, n_res))
CM_pdb = np.zeros((n_res, n_res))
for i in xrange(n_res):
for j in xrange(n_res):
if i == j:
continue
inds = np.where((acc_res_ids == uniq_res[i]) & (donor_res_ids == uniq_res[j]))[0]
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()
# build map dict for orig to coarse unbound states, bound will stay same
unboundass=-1*numpy.ones(( data['orig']['ass'].shape[0], data['orig']['ass'].shape[1]), dtype=int)
newass=-1*numpy.ones(( data['orig']['ass'].shape[0], data['orig']['ass'].shape[1]), dtype=int)
newdist=-1*numpy.ones(( data['orig']['ass'].shape[0], data['orig']['ass'].shape[1]))
for j in range(0, data['orig']['ass'].shape[0]):
rmsd=numpy.loadtxt('Trajectories-metric/trj%s_lprmsd.dat' % j)
frames=numpy.where(data['orig']['ass'][j]!=-1)[0]
if len(rmsd)!=len(frames):
print "trajectory mismatch"
import pdb
pdb.set_trace()
for (n,i) in enumerate(data['orig']['ass'][j]):
# if unbound
if i != -1:
#if data['orig']['rmsd'][i] > float(rcut):
if rmsd[n] > float(rcut):
newstate=data['coarse']['ass'][j][n]
if data['coarse']['rmsd'][newstate] < float(rcut):
newass[j][n]=i
newdist[j][n]=data['orig']['dist'][j][n]
else:
unboundass[j][n]=newstate
newdist[j][n]=data['coarse']['dist'][j][n]
else:
newass[j][n]=i
newdist[j][n]=data['orig']['dist'][j][n]
count=0
unique=sorted(set(newass.flatten()))
newass, boundmap, count=remap_ass(newass, newass, unique, count)
unique=sorted(set(unboundass.flatten()))
newass, unboundmap, count=remap_ass(unboundass, newass, unique, count)
io.saveh('%s/Coarsed_r%s_d%s_Assignments.h5' % (dirs['orig'], rcut, coarse_val), newass)
io.saveh('%s/Coarsed_r%s_d%s_Assignments.distances.h5' % (dirs['orig'], rcut, coarse_val), newdist)
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
otraj='%s/Coarsed%s_r%s_Gens.xtc' % (subdir, coarse_val, rcut)
if os.path.exists(otraj):
os.remove(otraj)
structure.save_to_xtc('%s/Coarsed%s_r%s_Gens.xtc' % (subdir, coarse_val, rcut))
#!/usr/bin/env python
from msmbuilder import io
from msmbuilder import msm_analysis
from scipy.io import mmread
from argparse import ArgumentParser
import os
parser = ArgumentParser()
parser.add_argument('-t', dest='tProb', help='transition matrix', default='./tProb.mtx')
parser.add_argument('-o', dest='output', help='output filename', default='./eigs.h5')
parser.add_argument('-n', dest='num_vecs', help='number of eigenvectors to find.', default=500, type=int)
args = parser.parse_args()
if os.path.exists(args.output):
raise Exception("path (%s) exists!" % args.output)
tProb = mmread(args.tProb)
eigs = msm_analysis.get_eigenvectors(tProb, args.num_vecs)
io.saveh(args.output, vals=eigs[0], vecs=eigs[1])
import os
import sys
import numpy as np
import scipy.sparse
from msmbuilder import io, msm_analysis, MSMLib
from bayesmutant import SimpleMutantSampler
P = np.loadtxt('base_transition_matrix.dat')
mutant_transition_matrix = P + 0.2*scipy.sparse.rand(P.shape[0], P.shape[1], density=0.1).todense()
mutant_transition_matrix /= np.sum(mutant_transition_matrix, axis=1)
trajectory = np.array(msm_analysis.sample(P, 0, 5000))
base_counts = MSMLib.get_counts_from_traj(trajectory).todense()
print 'base counts'
print base_counts
ms = SimpleMutantSampler(base_counts, mutant_transition_matrix)
ms.step(5000)
print 'observed counts'
print ms.counts
io.saveh('sampling.h5', base_counts=base_counts, samples=ms.samples,
observed_counts=ms.counts, scores=ms.scores,
transition_matrix=mutant_transition_matrix)
Please use CalculateProjectDistance.py
===============================================================================
"""
parser = arglib.ArgumentParser(description="""
Calculate the RMSD between an input PDB and all conformations in your project.
Output as a HDF5 file (load using msmbuilder.io.loadh())
""" + deprecationmessage)
warnings.warn(deprecationmessage, DeprecationWarning)
parser.add_argument('pdb')
parser.add_argument('atom_indices',
help='Indices of atoms to compare',
default='AtomIndices.dat')
parser.add_argument('output',
help='''Output file name. Output is an
.h5 file with RMSD entries corresponding to the Assignments.h5 file.''',
default='Data/RMSD.h5')
parser.add_argument('project')
args = parser.parse_args()
arglib.die_if_path_exists(args.output)
project = Project.load_from(args.project)
pdb = Trajectory.load_trajectory_file(args.pdb)
atom_indices = np.loadtxt(args.atom_indices).astype(int)
distances = run(project, pdb, atom_indices)
io.saveh(args.output, distances)
logger.info('Saved to %s', args.output)
if __name__ == '__main__':
parser = arglib.ArgumentParser("""Calculates the Solvent Accessible Surface Area
of all atoms in a given trajectory, or for all trajectories in the project. The
output is a hdf5 file which contains the SASA for each atom in each frame
in each trajectory (or the single trajectory you passed in.""" )
parser.add_argument('project')
parser.add_argument('atom_indices', help='Indices of atoms to calculate SASA',
default='all')
parser.add_argument('output', help='''hdf5 file for output. Note this will
be THREE dimensional: ( trajectory, frame, atom ), unless you just ask for
one trajectory, in which case it will be shape (frame, atom).''',
default='SASA.h5')
parser.add_argument('traj_fn', help='''Pass a trajectory file if you only
want to calclate the SASA for a single trajectory''', default='all' )
args = parser.parse_args()
arglib.die_if_path_exists(args.output)
if args.atom_indices.lower() == 'all':
atom_indices = None
else:
atom_indices = np.loadtxt(args.atom_indices).astype(int)
project = Project.load_from(args.project)
SASA = run(project, atom_indices, args.traj_fn)
io.saveh(args.output, SASA)
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))
def write_msm_output(self,outarray=None,filename="Assignments.h5"):
from msmbuilder import io
if outarray is None:
outarray = self.assignments
io.saveh(filename,outarray)
of all atoms in a given trajectory, or for all trajectories in the project. The
output is a hdf5 file which contains the SASA for each atom in each frame
in each trajectory (or the single trajectory you passed in.""")
parser.add_argument('project')
parser.add_argument('atom_indices',
help='Indices of atoms to calculate SASA',
default='all')
parser.add_argument('output',
help='''hdf5 file for output. Note this will
be THREE dimensional: ( trajectory, frame, atom ), unless you just ask for
one trajectory, in which case it will be shape (frame, atom).''',
default='SASA.h5')
parser.add_argument('traj_fn',
help='''Pass a trajectory file if you only
want to calclate the SASA for a single trajectory''',
default='all')
args = parser.parse_args()
arglib.die_if_path_exists(args.output)
if args.atom_indices.lower() == 'all':
atom_indices = None
else:
atom_indices = np.loadtxt(args.atom_indices).astype(int)
project = Project.load_from(args.project)
SASA = run(project, atom_indices, args.traj_fn)
io.saveh(args.output, SASA)
c = tICA.CovarianceMatrix(args.lag, tProb=tProb, populations=pops)
for i, fn in enumerate(traj_list):
print fn
t = np.load(fn)
c.train(t, ass[i])
#c.train(t)
C, Sigma = c.get_current_estimate()
vals, vecs = scipy.linalg.eig(C, b=Sigma)
print vals
print vecs
io.saveh(args.out, vals=vals, vecs=vecs, C=C, Sigma=Sigma)
muller.plot_v()
ref = io.loadh('ref.h5')
ref['vecs'][:,0] *= -1
vecs[:,0] *= -1
plot([0, vecs[0,0]], [0, vecs[1,0]], color='white', lw=3)
plot([0, vecs[0,1]], [0, vecs[1,1]], color='white', ls='dashed', lw=3)
plot([0, ref['vecs'][0,0]], [0, ref['vecs'][1,0]], color='red', lw=3)
plot([0, ref['vecs'][0,1]], [0, ref['vecs'][1,1]], color='red', ls='dashed', lw=3)
from msmbuilder import io
from msmbuilder.clustering import Hierarchical
from msmbuilder import arglib
import logging
logger = logging.getLogger('msmbuilder.scripts.AssignHierarchical')
parser = arglib.ArgumentParser(description='Assign data using a hierarchical clustering')
parser.add_argument('hierarchical_clustering_zmatrix', default='./Data/ZMatrix.h5',
help='Path to hierarchical clustering zmatrix' )
parser.add_argument('num_states', help='Number of States', default='none')
parser.add_argument('cutoff_distance', help='Maximum cophenetic distance', default='none')
parser.add_argument('assignments', type=str)
def main(k, d, zmatrix_fn):
hierarchical = Hierarchical.load_from_disk(zmatrix_fn)
assignments = hierarchical.get_assignments(k=k, cutoff_distance=d)
return assignments
if __name__ == "__main__":
args = parser.parse_args()
k = int(args.num_states) if args.num_states != 'none' else None
d = float(args.cutoff_distance) if args.cutoff_distance != 'none' else None
arglib.die_if_path_exists(args.assignments)
if k is None and d is None:
logger.error('You need to supply either a number of states or a cutoff distance')
sys.exit(1)
assignments = main(k, d, args.hierarchical_clustering_zmatrix)
io.saveh(args.assignments, assignments)
logger.info('Saved assignments to %s', args.assignments)
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)
