def test(self):
# extract xtcs to a temp dir
xtc_fn = get('XTC.tgz', just_filename=True)
fh = tarfile.open(xtc_fn, mode='r:gz')
fh.extractall(self.td)
fh.close()
outfn = pjoin(self.td, 'ProjectInfo.yaml')
# move to that directory
os.chdir(self.td)
atom_indices = np.arange(4)
ConvertDataToHDF.run(projectfn=outfn,
conf_filename=get('native.pdb', just_filename=True),
input_dir=pjoin(self.td, 'XTC'),
source='file',
min_length=0,
stride=1,
rmsd_cutoff=np.inf,
atom_indices=atom_indices, iext=".xtc")
project = load(outfn)
traj = project.load_conf()
eq(traj.n_atoms, 4)
def test(self):
num_macro = 5
TC = get("PCCA_ref/tProb.mtx")
A = get("PCCA_ref/Assignments.Fixed.h5")['arr_0']
macro_map, macro_assign = PCCA.run_pcca(num_macro, A, TC)
r_macro_map = get("PCCA_ref/MacroMapping.dat")
macro_map = macro_map.astype(np.int)
r_macro_map = r_macro_map.astype(np.int)
# The order of macrostates might be different between the reference and
# new lumping. We therefore find a permutation to match them.
permutation_mapping = np.zeros(macro_assign.max() + 1, 'int')
for i in range(num_macro):
j = np.where(macro_map == i)[0][0]
permutation_mapping[i] = r_macro_map[j]
macro_map_permuted = permutation_mapping[macro_map]
MSMLib.apply_mapping_to_assignments(macro_assign, permutation_mapping)
r_macro_assign = get("PCCA_ref/MacroAssignments.h5")['arr_0']
eq(macro_map_permuted, r_macro_map)
eq(macro_assign, r_macro_assign)
def test(self):
args, metric = Cluster.parser.parse_args([
'-p', get('points_on_cube/ProjectInfo.yaml', just_filename=True),
'-o', self.td,
'rmsd', '-a', get('points_on_cube/AtomIndices.dat', just_filename=True),
'hybrid', '-k', '4'], print_banner=False)
Cluster.main(args, metric)
def test(self):
num_macro = 5
TC = get("PCCA_ref/tProb.mtx")
A = get("PCCA_ref/Assignments.Fixed.h5")['arr_0']
print A
macro_map, macro_assign = PCCA.run_pcca(num_macro, A, TC)
r_macro_map = get("PCCA_ref/MacroMapping.dat")
macro_map = macro_map.astype(np.int)
r_macro_map = r_macro_map.astype(np.int)
# The order of macrostates might be different between the reference and
# new lumping. We therefore find a permutation to match them.
permutation_mapping = np.zeros(macro_assign.max() + 1, 'int')
for i in range(num_macro):
j = np.where(macro_map == i)[0][0]
permutation_mapping[i] = r_macro_map[j]
macro_map_permuted = permutation_mapping[macro_map]
MSMLib.apply_mapping_to_assignments(macro_assign, permutation_mapping)
r_macro_assign = get("PCCA_ref/MacroAssignments.h5")['arr_0']
eq(macro_map_permuted, r_macro_map)
eq(macro_assign, r_macro_assign)
def test(self):
prep_metric = metrics.Dihedral(angles='phi/psi')
project = get('ProjectInfo.yaml')
os.chdir(self.td)
tICA_train.run(prep_metric, project, delta_time=10, atom_indices=None,
output='tICAtest.h5', min_length=0, stride=1)
ref_tICA = get('tICA_ref_mle.h5')
ref_vals = ref_tICA['vals']
ref_vecs = ref_tICA['vecs']
ref_inds = np.argsort(ref_vals)
ref_vals = ref_vals[ref_inds]
ref_vecs = ref_vecs[:, ref_inds]
test_tICA = load('tICAtest.h5')
test_vals = test_tICA['vals']
test_vecs = test_tICA['vecs']
test_inds = np.argsort(test_vals)
test_vals = test_vals[test_inds]
test_vecs = test_vecs[:, test_inds]
eq(test_vals, ref_vals)
eq(test_vecs, test_vecs)
def test(self):
from msmbuilder.scripts.SaveStructures import save
project = get('ProjectInfo.yaml')
assignments = get('Assignments.h5')['arr_0']
which_states = [0, 1, 2]
list_of_trajs = project.get_random_confs_from_states(assignments,
which_states, num_confs=2, replacement=True,
random=np.random.RandomState(42))
assert isinstance(list_of_trajs, list)
assert isinstance(list_of_trajs[0], Trajectory)
eq(len(list_of_trajs), len(which_states))
for t in list_of_trajs:
eq(len(t), 2)
print list_of_trajs[0].keys()
# sep, tps, one
save(list_of_trajs, which_states, style='sep', format='lh5', outdir=self.td)
save(list_of_trajs, which_states, style='tps', format='lh5', outdir=self.td)
save(list_of_trajs, which_states, style='one', format='lh5', outdir=self.td)
names = ['State0-0.lh5', 'State0-1.lh5', 'State0.lh5', 'State1-0.lh5',
'State1-1.lh5', 'State1.lh5', 'State2-0.lh5', 'State2-1.lh5',
'State2.lh5']
for name in names:
t = Trajectory.load_trajectory_file(pjoin(self.td, name))
eq(t, get('save_structures/' + name))
def test(self):
from msmbuilder.scripts.SaveStructures import save
os.chdir(self.td)
project = get('ProjectInfo.yaml')
assignments = get('Assignments.h5')['arr_0']
which_states = [0, 1, 2]
list_of_trajs = project.get_random_confs_from_states(assignments,
which_states, num_confs=2, replacement=True,
random=np.random.RandomState(42))
assert isinstance(list_of_trajs, list)
assert isinstance(list_of_trajs[0], md.Trajectory)
eq(len(list_of_trajs), len(which_states))
for t in list_of_trajs:
eq(len(t), 2)
# sep, tps, one
save(list_of_trajs, which_states, style='sep', format='lh5', outdir=self.td)
save(list_of_trajs, which_states, style='tps', format='lh5', outdir=self.td)
save(list_of_trajs, which_states, style='one', format='lh5', outdir=self.td)
names = ['State0-0.lh5', 'State0-1.lh5', 'State0.lh5', 'State1-0.lh5',
'State1-1.lh5', 'State1.lh5', 'State2-0.lh5', 'State2-1.lh5',
'State2.lh5']
for name in names:
t = md.load(pjoin(self.td, name))
eq(t.xyz, get('save_structures/' + name).xyz) # Just checking coordinates because atom names / bonds in reference data are incompatible with MDTraj.
def test(self):
args, metric = Cluster.parser.parse_args([
'-p', get('ProjectInfo.yaml', just_filename=True),
'-s', '10',
'-o', self.td,
'rmsd', '-a', get('AtomIndices.dat', just_filename=True),
'hierarchical'],
print_banner=False)
Cluster.main(args, metric)
eq(load(pjoin(self.td, 'ZMatrix.h5')), get('ZMatrix.h5'))
def test_CalculateTPT():
T = get("transition_path_theory_reference/tProb.mtx")
sources = [0] # chosen arb. for ref. by TJL
sinks = [70] # chosen arb. for ref. by TJL
script_out = CalculateTPT.run(T, sources, sinks)
committors_ref = get(pjoin("transition_path_theory_reference",
"committors.h5"))['Data']
net_flux_ref = get(pjoin("transition_path_theory_reference",
"net_flux.h5"))['Data']
eq(script_out[0], committors_ref)
eq(script_out[1].toarray(), net_flux_ref)
def test_CalculateTPT():
T = get("transition_path_theory_reference/tProb.mtx")
sources = [0] # chosen arb. for ref. by TJL
sinks = [70] # chosen arb. for ref. by TJL
script_out = CalculateTPT.run(T, sources, sinks)
committors_ref = get(pjoin("transition_path_theory_reference",
"committors.h5"))['Data']
net_flux_ref = get(pjoin("transition_path_theory_reference",
"net_flux.h5"))['Data']
eq(script_out[0], committors_ref)
eq(script_out[1].toarray(), net_flux_ref)
def test_FindPaths():
tprob = get("transition_path_theory_reference/tProb.mtx")
sources = [0]
sinks = [70]
paths, bottlenecks, fluxes = FindPaths.run(tprob, sources, sinks, 10)
# paths are hard to test due to type issues, adding later --TJL
bottlenecks_ref = get(pjoin("transition_path_theory_reference",
"dijkstra_bottlenecks.h5"))['Data']
fluxes_ref = get(pjoin("transition_path_theory_reference",
"dijkstra_fluxes.h5"))['Data']
eq(bottlenecks, bottlenecks_ref)
eq(fluxes, fluxes_ref)
def setUp(self):
self.generators = get('cfep_reference/Gens.lh5')
N = len(self.generators)
self.counts = get('cfep_reference/tCounts.mtx')
self.lag_time = 1.0
self.pfolds = np.random.rand(N)
self.rescale = False
self.reactant = 0
self.product = N
def test_FindPaths():
tprob = get("transition_path_theory_reference/tProb.mtx")
sources = [0]
sinks = [70]
paths, bottlenecks, fluxes = FindPaths.run(tprob, sources, sinks, 10)
# paths are hard to test due to type issues, adding later --TJL
bottlenecks_ref = get(pjoin("transition_path_theory_reference",
"dijkstra_bottlenecks.h5"))['Data']
fluxes_ref = get(pjoin("transition_path_theory_reference",
"dijkstra_fluxes.h5"))['Data']
eq(bottlenecks, bottlenecks_ref)
eq(fluxes, fluxes_ref)
def test(self):
args, metric = Assign.parser.parse_args([
'-p', get('ProjectInfo.yaml', just_filename=True),
'-g', get('Gens.lh5', just_filename=True),
'-o', self.td,
'rmsd', '-a', get('AtomIndices.dat', just_filename=True)],
print_banner=False)
Assign.main(args, metric)
eq(load(pjoin(self.td, 'Assignments.h5')),
get('assign/Assignments.h5'))
eq(load(pjoin(self.td, 'Assignments.h5.distances')),
get('assign/Assignments.h5.distances'))
def test(self):
args, metric = Cluster.parser.parse_args([
'-p', get('points_on_cube/ProjectInfo.yaml', just_filename=True),
'-o', self.td,
'rmsd', '-a', get('points_on_cube/AtomIndices.dat', just_filename=True),
'kcenters', '-k', '4'], print_banner=False)
Cluster.main(args, metric)
assignments = load(pjoin(self.td, 'Assignments.h5'))["arr_0"]
assignment_counts = np.bincount(assignments.flatten())
eq(assignment_counts, np.array([2, 2, 2, 2]))
distances = load(pjoin(self.td, 'Assignments.h5.distances'))["arr_0"]
eq(distances, np.zeros((1,8)))
def setUp(self):
if PY3:
raise nose.SkipTest("TestCfep requires scipy.weave which doesnt exist on python3")
self.generators = get("cfep_reference/Gens.lh5")
N = len(self.generators)
self.counts = get("cfep_reference/tCounts.mtx")
self.lag_time = 1.0
self.pfolds = np.random.rand(N)
self.rescale = False
self.reactant = 0
self.product = N
def setUp(self):
if PY3:
raise nose.SkipTest(
'TestCfep requires scipy.weave which doesnt exist on python3')
self.generators = get('cfep_reference/Gens.lh5')
N = len(self.generators)
self.counts = get('cfep_reference/tCounts.mtx')
self.lag_time = 1.0
self.pfolds = np.random.rand(N)
self.rescale = False
self.reactant = 0
self.product = N
def test(self):
args, metric = Cluster.parser.parse_args([
'-p', get('ProjectInfo.yaml', just_filename=True),
'-a', pjoin(self.td, 'Assignments.h5'),
'-d', pjoin(self.td, 'Assignments.h5.distances'),
'-g', pjoin(self.td, 'Gens.lh5'),
'rmsd', '-a', get('AtomIndices.dat', just_filename=True),
'kcenters', '-k', '100'], print_banner=False)
Cluster.main(args, metric)
eq(load(pjoin(self.td, 'Assignments.h5')),
get('Assignments.h5'))
eq(load(pjoin(self.td, 'Assignments.h5.distances')),
get('Assignments.h5.distances'))
eq(load(pjoin(self.td, 'Gens.lh5')),
get('Gens.lh5'))
def test(self):
args, metric = Assign.parser.parse_args([
'-p', get('ProjectInfo.yaml', just_filename=True),
'-g', get('Gens.lh5', just_filename=True),
'-o', self.td,
'rmsd', '-a', get('OldAtomIndices.dat', just_filename=True)],
print_banner=False)
if os.getenv('TRAVIS', None) == 'true':
raise nose.SkipTest('Skipping test_Assign on TRAVIS')
Assign.main(args, metric)
eq(load(pjoin(self.td, 'Assignments.h5')),
get('assign/Assignments.h5'))
eq(load(pjoin(self.td, 'Assignments.h5.distances')),
get('assign/Assignments.h5.distances'), decimal=5)
def test(self):
try:
import fastcluster
except ImportError:
raise nose.SkipTest("Cannot find fastcluster, so skipping hierarchical clustering test.")
args, metric = Cluster.parser.parse_args([
'-p', get('ProjectInfo.yaml', just_filename=True),
'-s', '10',
'-o', self.td,
'rmsd', '-a', get('AtomIndices.dat', just_filename=True),
'hierarchical'],
print_banner=False)
Cluster.main(args, metric)
eq(load(pjoin(self.td, 'ZMatrix.h5')), get('ZMatrix.h5'))
def test(self):
if os.getenv('TRAVIS', None) == 'true':
raise nose.SkipTest('Skipping test_Assign on TRAVIS')
try:
import fastcluster
except ImportError:
raise nose.SkipTest("Cannot find fastcluster, so skipping hierarchical clustering test.")
args, metric = Cluster.parser.parse_args([
'-p', get('ProjectInfo.yaml', just_filename=True),
'-s', '10',
'-o', self.td,
'rmsd', '-a', get('AtomIndices.dat', just_filename=True),
'hierarchical'],
print_banner=False)
Cluster.main(args, metric)
eq(load(pjoin(self.td, 'ZMatrix.h5')), get('ZMatrix.h5'))
def test(self):
# extract xtcs to a temp dir
xtc_fn = get('XTC.tgz', just_filename=True)
fh = tarfile.open(xtc_fn, mode='r:gz')
fh.extractall(self.td)
fh.close()
outfn = pjoin(self.td, 'ProjectInfo.yaml')
# mode to that directory
os.chdir(self.td)
ConvertDataToHDF.run(projectfn=outfn,
PDBfn=get('native.pdb', just_filename=True),
InputDir=pjoin(self.td, 'XTC'),
source='file',
min_length=0,
stride=1,
rmsd_cutoff=np.inf)
eq(load(outfn), get('ProjectInfo.yaml'))
def test(self):
BuildMSM.run(LagTime=1, assignments=get('Assignments.h5')['arr_0'], Symmetrize='MLE',
OutDir=self.td)
eq(load(pjoin(self.td, 'tProb.mtx')), get('tProb.mtx'))
eq(load(pjoin(self.td, 'tCounts.mtx')), get('tCounts.mtx'))
eq(load(pjoin(self.td, 'Mapping.dat')), get('Mapping.dat'))
eq(load(pjoin(self.td, 'Assignments.Fixed.h5')), get('Assignments.Fixed.h5'))
eq(load(pjoin(self.td, 'Populations.dat')), get('Populations.dat'))
def test(self):
BuildMSM.run(lagtime=1, assignments=get('Assignments.h5')['arr_0'], symmetrize='MLE',
out_dir=self.td)
eq(load(pjoin(self.td, 'tProb.mtx')), get('tProb.mtx'), decimal=5)
eq(load(pjoin(self.td, 'tCounts.mtx')), get('tCounts.mtx'), decimal=3)
eq(load(pjoin(self.td, 'Mapping.dat')), get('Mapping.dat'))
eq(load(pjoin(self.td, 'Assignments.Fixed.h5')), get('Assignments.Fixed.h5'))
eq(load(pjoin(self.td, 'Populations.dat')), get('Populations.dat'))
def test(self):
BuildMSM.run(lagtime=1, assignments=get('Assignments.h5')['arr_0'], symmetrize='MLE',
out_dir=self.td)
eq(load(pjoin(self.td, 'tProb.mtx')), get('tProb.mtx'), decimal=5)
eq(load(pjoin(self.td, 'tCounts.mtx')), get('tCounts.mtx'), decimal=3)
eq(load(pjoin(self.td, 'Mapping.dat')), get('Mapping.dat'))
eq(load(pjoin(self.td, 'Assignments.Fixed.h5')), get('Assignments.Fixed.h5'))
eq(load(pjoin(self.td, 'Populations.dat')), get('Populations.dat'))
def setUp(self):
# load in the reference data
self.tprob = get("transition_path_theory_reference/tProb.mtx")
self.sources = [0] # chosen arbitarily by TJL
self.sinks = [70] # chosen arbitarily by TJL
self.waypoints = [60] # chosen arbitarily by TJL
self.lag_time = 1.0 # chosen arbitarily by TJL
self.multi_sources = get("transition_path_theory_reference/many_state/sources.dat").astype(int)
self.multi_sinks = get("transition_path_theory_reference/many_state/sinks.dat").astype(int)
self.num_paths = 10
# set up the reference data for hub scores
K = np.loadtxt( hub_get('ratemat_1.dat') )
#self.hub_T = scipy.linalg.expm( K ) # delta-t should not affect hub scores
self.hub_T = np.transpose( np.genfromtxt( hub_get('mat_1.dat') )[:,:-3] )
for i in range(self.hub_T.shape[0]):
self.hub_T[i,:] /= np.sum(self.hub_T[i,:])
self.hc = np.loadtxt( hub_get('fraction_visited.dat') )
self.Hc = np.loadtxt( hub_get('hub_scores.dat') )[:,2]
def setUp(self):
# load in the reference data
self.tprob = get("transition_path_theory_reference/tProb.mtx")
self.sources = [0] # chosen arbitarily by TJL
self.sinks = [70] # chosen arbitarily by TJL
self.waypoints = [60] # chosen arbitarily by TJL
self.lag_time = 1.0 # chosen arbitarily by TJL
self.multi_sources = get("transition_path_theory_reference/many_state/sources.dat").astype(int)
self.multi_sinks = get("transition_path_theory_reference/many_state/sinks.dat").astype(int)
self.num_paths = 10
# set up the reference data for hub scores
K = np.loadtxt( hub_get('ratemat_1.dat') )
#self.hub_T = scipy.linalg.expm( K ) # delta-t should not affect hub scores
self.hub_T = np.transpose( np.genfromtxt( hub_get('mat_1.dat') )[:,:-3] )
for i in range(self.hub_T.shape[0]):
self.hub_T[i,:] /= np.sum(self.hub_T[i,:])
self.hc = np.loadtxt( hub_get('fraction_visited.dat') )
self.Hc = np.loadtxt( hub_get('hub_scores.dat') )[:,2]
def test_CalculateImpliedTimescales():
impTimes = CalculateImpliedTimescales.run(MinLagtime=3, MaxLagtime=5,
Interval=1, NumEigen=10, AssignmentsFn=get('Assignments.h5', just_filename=True),
trimming=True, symmetrize='Transpose', nProc=1)
eq(impTimes, get('ImpliedTimescales.dat'))
def hub_get(filename):
""" a little hack to save headache -- returns the path to a file in
the hub_ref subdir inside reference/ """
return get( os.path.join('transition_path_theory_reference', 'hub_ref', filename), just_filename=True )
def test_CalculateClusterRadii():
cr = CalculateClusterRadii.main(get("Assignments.h5")['arr_0'],
get("Assignments.h5.distances")['arr_0'])
cr_r = get("ClusterRadii.dat")
eq(cr, cr_r)
def test_CreateAtomIndices():
indices = CreateAtomIndices.run(get('native.pdb', just_filename=True),
'minimal')
eq(indices, get('AtomIndices.dat'))
def test_CalculateMFPTs(mfpt_state=70):
mfpt = CalculateMFPTs.run(get('transition_path_theory_reference/tProb.mtx'), mfpt_state)
mfpt0 = get(pjoin("transition_path_theory_reference", "mfpt.h5"))['Data']
eq(mfpt, mfpt0)
def test_CalculateImpliedTimescales():
impTimes = CalculateImpliedTimescales.run(MinLagtime=3, MaxLagtime=5,
Interval=1, NumEigen=10, AssignmentsFn=get('Assignments.h5', just_filename=True),
trimming=True, symmetrize='Transpose', nProc=1)
eq(impTimes, get('ImpliedTimescales.dat'))
def test_CalculateMFPTs(mfpt_state=70):
mfpt = CalculateMFPTs.run(get('transition_path_theory_reference/tProb.mtx'), mfpt_state)
mfpt0 = get(pjoin("transition_path_theory_reference", "mfpt.h5"))['Data']
eq(mfpt, mfpt0)
def test_CreateAtomIndices():
indices = CreateAtomIndices.run(get('native.pdb', just_filename=True),
'minimal')
eq(indices, get('AtomIndices.dat'))
def hub_get(filename):
""" a little hack to save headache -- returns the path to a file in
the hub_ref subdir inside reference/ """
return get( os.path.join('hub_ref', filename), just_filename=True )
def tpt_get(filename):
""" a little hack to save headache -- returns the path to a file in
the hub_ref subdir inside reference/ """
return get( os.path.join('transition_path_theory_reference', filename), just_filename=True )
def test(self):
project = get('ProjectInfo.yaml')
asgn = AssignHierarchical.main(k=100, d=None,
zmatrix_fn=get('ZMatrix.h5', just_filename=True), stride=10, project=project)
eq(asgn, get('WardAssignments.h5')['arr_0'])
def test_AssignHierarchical():
asgn = AssignHierarchical.main(k=100, d=None,
zmatrix_fn=get('ZMatrix.h5', just_filename=True))
eq(asgn, get('WardAssignments.h5')['Data'])
def test_CalculateClusterRadii():
cr = CalculateClusterRadii.main(get("Assignments.h5")['arr_0'],
get("Assignments.h5.distances")['arr_0'])
cr_r = get("ClusterRadii.dat")
eq(cr, cr_r)