def run(lagtime,
assignments,
symmetrize='MLE',
input_mapping="None",
trim=True,
out_dir="./Data/"):
# set the filenames for output
FnTProb = os.path.join(out_dir, "tProb.mtx")
FnTCounts = os.path.join(out_dir, "tCounts.mtx")
FnMap = os.path.join(out_dir, "Mapping.dat")
FnAss = os.path.join(out_dir, "Assignments.Fixed.h5")
FnPops = os.path.join(out_dir, "Populations.dat")
# make sure none are taken
outputlist = [FnTProb, FnTCounts, FnMap, FnAss, FnPops]
arglib.die_if_path_exists(outputlist)
# Check for valid lag time
assert lagtime > 0, 'Please specify a positive lag time.'
# if given, apply mapping to assignments
if input_mapping != "None":
MSMLib.apply_mapping_to_assignments(assignments, input_mapping)
n_assigns_before_trim = len(np.where(assignments.flatten() != -1)[0])
counts = MSMLib.get_count_matrix_from_assignments(assignments,
lag_time=lagtime,
sliding_window=True)
rev_counts, t_matrix, populations, mapping = MSMLib.build_msm(
counts, symmetrize=symmetrize, ergodic_trimming=trim)
if trim:
MSMLib.apply_mapping_to_assignments(assignments, mapping)
n_assigns_after_trim = len(np.where(assignments.flatten() != -1)[0])
# if had input mapping, then update it
if input_mapping != "None":
mapping = mapping[input_mapping]
# Print a statement showing how much data was discarded in trimming
percent = (1.0 - float(n_assigns_after_trim) /
float(n_assigns_before_trim)) * 100.0
logger.warning("Ergodic trimming discarded: %f percent of your data",
percent)
else:
logger.warning("No ergodic trimming applied")
# Save all output
np.savetxt(FnPops, populations)
np.savetxt(FnMap, mapping, "%d")
scipy.io.mmwrite(str(FnTProb), t_matrix)
scipy.io.mmwrite(str(FnTCounts), rev_counts)
io.saveh(FnAss, assignments)
for output in outputlist:
logger.info("Wrote: %s", output)
return
def entry_point():
args = parser.parse_args()
# load args
try:
assignments = io.loadh(args.assignments, 'arr_0')
except KeyError:
assignments = io.loadh(args.assignments, 'Data')
tProb = scipy.io.mmread(args.tProb)
# workaround for arglib funniness?
if args.do_minimization in ["False", "0"]:
args.do_minimization = False
else:
args.do_minimization = True
if args.algorithm == 'PCCA':
MacroAssignmentsFn = os.path.join(args.output_dir,
"MacroAssignments.h5")
MacroMapFn = os.path.join(args.output_dir, "MacroMapping.dat")
arglib.die_if_path_exists([MacroAssignmentsFn, MacroMapFn])
MAP, assignments = run_pcca(args.num_macrostates, assignments, tProb)
np.savetxt(MacroMapFn, MAP, "%d")
io.saveh(MacroAssignmentsFn, assignments)
logger.info("Saved output to: %s, %s", MacroAssignmentsFn, MacroMapFn)
elif args.algorithm == 'PCCA+':
MacroAssignmentsFn = os.path.join(args.output_dir,
"MacroAssignments.h5")
MacroMapFn = os.path.join(args.output_dir, "MacroMapping.dat")
ChiFn = os.path.join(args.output_dir, 'Chi.dat')
AFn = os.path.join(args.output_dir, 'A.dat')
arglib.die_if_path_exists([MacroAssignmentsFn, MacroMapFn, ChiFn, AFn])
chi, A, MAP, assignments = run_pcca_plus(
args.num_macrostates,
assignments,
tProb,
args.flux_cutoff,
objective_function=args.objective_function,
do_minimization=args.do_minimization)
np.savetxt(ChiFn, chi)
np.savetxt(AFn, A)
np.savetxt(MacroMapFn, MAP, "%d")
io.saveh(MacroAssignmentsFn, assignments)
logger.info('Saved output to: %s, %s, %s, %s', ChiFn, AFn, MacroMapFn,
MacroAssignmentsFn)
else:
raise Exception()
def entry_point():
args = parser.parse_args()
# load args
try:
assignments = io.loadh(args.assignments, 'arr_0')
except KeyError:
assignments = io.loadh(args.assignments, 'Data')
tProb = scipy.io.mmread(args.tProb)
# workaround for arglib funniness?
if args.do_minimization in ["False", "0"]:
args.do_minimization = False
else:
args.do_minimization = True
if args.algorithm == 'PCCA':
MacroAssignmentsFn = os.path.join(
args.output_dir, "MacroAssignments.h5")
MacroMapFn = os.path.join(args.output_dir, "MacroMapping.dat")
arglib.die_if_path_exists([MacroAssignmentsFn, MacroMapFn])
MAP, assignments = run_pcca(args.num_macrostates, assignments, tProb)
np.savetxt(MacroMapFn, MAP, "%d")
io.saveh(MacroAssignmentsFn, assignments)
logger.info("Saved output to: %s, %s", MacroAssignmentsFn, MacroMapFn)
elif args.algorithm == 'PCCA+':
MacroAssignmentsFn = os.path.join(
args.output_dir, "MacroAssignments.h5")
MacroMapFn = os.path.join(args.output_dir, "MacroMapping.dat")
ChiFn = os.path.join(args.output_dir, 'Chi.dat')
AFn = os.path.join(args.output_dir, 'A.dat')
arglib.die_if_path_exists([MacroAssignmentsFn, MacroMapFn, ChiFn, AFn])
chi, A, MAP, assignments = run_pcca_plus(args.num_macrostates,
assignments, tProb, args.flux_cutoff, objective_function=args.objective_function,
do_minimization=args.do_minimization)
np.savetxt(ChiFn, chi)
np.savetxt(AFn, A)
np.savetxt(MacroMapFn, MAP, "%d")
io.saveh(MacroAssignmentsFn, assignments)
logger.info('Saved output to: %s, %s, %s, %s',
ChiFn, AFn, MacroMapFn, MacroAssignmentsFn)
else:
raise Exception()
def run(lagtime, assignments, symmetrize='MLE', input_mapping="None", trim=True, out_dir="./Data/"):
# set the filenames for output
FnTProb = os.path.join(out_dir, "tProb.mtx")
FnTCounts = os.path.join(out_dir, "tCounts.mtx")
FnMap = os.path.join(out_dir, "Mapping.dat")
FnAss = os.path.join(out_dir, "Assignments.Fixed.h5")
FnPops = os.path.join(out_dir, "Populations.dat")
# make sure none are taken
outputlist = [FnTProb, FnTCounts, FnMap, FnAss, FnPops]
arglib.die_if_path_exists(outputlist)
# Check for valid lag time
assert lagtime > 0, 'Please specify a positive lag time.'
# if given, apply mapping to assignments
if input_mapping != "None":
MSMLib.apply_mapping_to_assignments(assignments, input_mapping)
n_assigns_before_trim = len(np.where(assignments.flatten() != -1)[0])
counts = MSMLib.get_count_matrix_from_assignments(assignments, lag_time=lagtime, sliding_window=True)
rev_counts, t_matrix, populations, mapping = MSMLib.build_msm(counts, symmetrize=symmetrize, ergodic_trimming=trim)
if trim:
MSMLib.apply_mapping_to_assignments(assignments, mapping)
n_assigns_after_trim = len(np.where(assignments.flatten() != -1)[0])
# if had input mapping, then update it
if input_mapping != "None":
mapping = mapping[input_mapping]
# Print a statement showing how much data was discarded in trimming
percent = (1.0 - float(n_assigns_after_trim) / float(n_assigns_before_trim)) * 100.0
logger.warning("Ergodic trimming discarded: %f percent of your data", percent)
else:
logger.warning("No ergodic trimming applied")
# Save all output
np.savetxt(FnPops, populations)
np.savetxt(FnMap, mapping, "%d")
scipy.io.mmwrite(str(FnTProb), t_matrix)
scipy.io.mmwrite(str(FnTCounts), rev_counts)
io.saveh(FnAss, assignments)
for output in outputlist:
logger.info("Wrote: %s", output)
return
def entry_point():
args = parser.parse_args()
F = np.loadtxt(args.ending).astype(int)
U = np.loadtxt(args.starting).astype(int)
tprob = scipy.io.mmread(args.tprob)
# deal with case where have single start or end state
# TJL note: this should be taken care of in library now... keeping it just
# in case
if F.shape == ():
tmp = np.zeros(1, dtype=int)
tmp[0] = int(F)
F = tmp.copy()
if U.shape == ():
tmp = np.zeros(1, dtype=int)
tmp[0] = int(U)
U = tmp.copy()
arglib.die_if_path_exists(args.output)
paths, bottlenecks, fluxes = run(tprob, U, F, args.number)
io.saveh(args.output, Paths=paths, Bottlenecks=bottlenecks, fluxes=fluxes)
logger.info('Saved output to %s', args.output)
def entry_point():
args = parser.parse_args()
F = np.loadtxt(args.ending).astype(int)
U = np.loadtxt(args.starting).astype(int)
tprob = scipy.io.mmread(args.tprob)
# deal with case where have single start or end state
# TJL note: this should be taken care of in library now... keeping it just
# in case
if F.shape == ():
tmp = np.zeros(1, dtype=int)
tmp[0] = int(F)
F = tmp.copy()
if U.shape == ():
tmp = np.zeros(1, dtype=int)
tmp[0] = int(U)
U = tmp.copy()
arglib.die_if_path_exists(args.output)
paths, bottlenecks, fluxes = run(tprob, U, F, args.number)
io.saveh(args.output, Paths=paths, Bottlenecks=bottlenecks, fluxes=fluxes)
logger.info('Saved output to %s', args.output)
def main():
wildtype_states_fn = join(root, "wildtype_msm/Data_RMSD2_5A/Gens.h5")
wildtype_counts = scipy.io.mmread(join(root, "wildtype_msm", "Data_RMSD2_5A/500ps_MLE/tCounts.mtx")).todense()
lag_time = 500 * units.picoseconds
ms = OpenMMMutantSampler(
wildtype_counts,
wildtype_states_fn,
wildtype_topology_fn,
mutant_topology_fn,
lag_time,
simulation=setup_simulation(),
)
ms.step(500)
io.saveh(
"sampling.h5",
base_counts=wildtype_counts,
samples=ms.samples,
observed_counts=ms.counts,
scores=ms.scores,
bayesmutant_code_version=np.array([bayesmutant.version.full_version]),
)
# workaround for arglib funniness?
if args.do_minimization in ["False", "0"]:
args.do_minimization = False
else:
args.do_minimization = True
if args.algorithm == 'PCCA':
MacroAssignmentsFn = os.path.join(
args.output_dir, "MacroAssignments.h5")
MacroMapFn = os.path.join(args.output_dir, "MacroMapping.dat")
arglib.die_if_path_exists([MacroAssignmentsFn, MacroMapFn])
MAP, assignments = run_pcca(args.num_macrostates, assignments, tProb)
np.savetxt(MacroMapFn, MAP, "%d")
io.saveh(MacroAssignmentsFn, assignments)
logger.info("Saved output to: %s, %s", MacroAssignmentsFn, MacroMapFn)
elif args.algorithm == 'PCCA+':
MacroAssignmentsFn = os.path.join(
args.output_dir, "MacroAssignments.h5")
MacroMapFn = os.path.join(args.output_dir, "MacroMapping.dat")
ChiFn = os.path.join(args.output_dir, 'Chi.dat')
AFn = os.path.join(args.output_dir, 'A.dat')
arglib.die_if_path_exists([MacroAssignmentsFn, MacroMapFn, ChiFn, AFn])
chi, A, MAP, assignments = run_pcca_plus(args.num_macrostates,
assignments, tProb, args.flux_cutoff, objective_function=args.objective_function,
do_minimization=args.do_minimization)
