def fit_protein_tica(yaml_file,sparse=False):
mdl_dir = yaml_file["mdl_dir"]
mdl_params = yaml_file["mdl_params"]
current_mdl_params={}
for i in mdl_params.keys():
if i.startswith("tica__"):
current_mdl_params[i.split("tica__")[1]] = mdl_params[i]
if sparse==True:
protein_tica_mdl = SparseTICA(**current_mdl_params)
else:
protein_tica_mdl = tICA(**current_mdl_params)
for protein in yaml_file["protein_list"]:
print("Fitting to protein %s" % protein)
with enter_protein_data_dir(yaml_file, protein):
featurized_traj = sorted(glob.glob("./%s/*.jl" %
yaml_file["feature_dir"]), key=keynat)
for f in featurized_traj:
featurized_path = verboseload(f)
try:
protein_tica_mdl.partial_fit(featurized_path)
except:
pass
print("Done partial fitting to protein %s" % protein)
# dumping the tica_mdl
tica_mdl_path = os.path.join(mdl_dir, "tica_mdl.pkl")
verbosedump(protein_tica_mdl, tica_mdl_path)
return
def fit_protein_tica(yaml_file,sparse=False,ksparse=None):
mdl_dir = yaml_file["mdl_dir"]
mdl_params = yaml_file["mdl_params"]
current_mdl_params={}
for i in mdl_params.keys():
if i.startswith("tica__"):
current_mdl_params[i.split("tica__")[1]] = mdl_params[i]
if sparse==True:
protein_tica_mdl = SparseTICA(**current_mdl_params)
elif type(ksparse)==int:
current_mdl_params["k"] = ksparse
protein_tica_mdl = KSparseTICA(**current_mdl_params)
else:
protein_tica_mdl = tICA(**current_mdl_params)
for protein in yaml_file["protein_list"]:
print("Fitting to protein %s" % protein)
with enter_protein_data_dir(yaml_file, protein):
if os.path.exists("./normalized_features"):
featurized_traj = sorted(glob.glob("./normalized_features/*.jl"), key=keynat)
else:
print('Warning: features have not been scaled')
featurized_traj = sorted(glob.glob("./%s/*.jl" %
yaml_file["feature_dir"]), key=keynat)
for f in featurized_traj:
featurized_path = verboseload(f)
try:
protein_tica_mdl.partial_fit(featurized_path)
except:
print('Error')
print("Done partial fitting to protein %s" % protein)
# dumping the tica_mdl
tica_mdl_path = os.path.join(mdl_dir, "tica_mdl.pkl")
verbosedump(protein_tica_mdl, tica_mdl_path)
return
def fit_and_transform(features_directory,
model_dir,
stride=5,
lag_time=10,
n_components=5,
wolf=True,
shrinkage=None,
rho=0.05,
parallel=True,
sparse=True,
traj_ext=".h5",
normalize=True,
partial_fit=True,
subsample=1,
recompute_tica=False,
features=None):
if not os.path.exists(model_dir):
os.makedirs(model_dir)
projected_data_filename = "%s/phi_psi_chi2_allprot_projected.h5" % model_dir
fit_model_filename = "%s/phi_psi_chi2_allprot_tica_coords.h5" % model_dir
normalizer = "%s/normalizer.h5" % features_directory
n = compat_verboseload(normalizer)
#active_pdb_file = "/scratch/users/enf/b2ar_analysis/renamed_topologies/A-00.pdb"
if not sparse:
if shrinkage is None:
tica_model = tICA(n_components=n_components, lag_time=lag_time)
else:
tica_model = tICA(n_components=n_components,
lag_time=lag_time,
shrinkage=shrinkage)
else:
if shrinkage is None:
tica_model = SparseTICA(n_components=n_components,
lag_time=lag_time,
rho=rho)
else:
tica_model = SparseTICA(n_components=n_components,
lag_time=lag_time,
rho=rho,
shrinkage=shrinkage)
if not os.path.exists(projected_data_filename) or recompute_tica:
print("loading feature files")
feature_files = get_trajectory_files(features_directory,
ext=".dataset")
if partial_fit:
transformed_data = []
for i, feature_file in enumerate(feature_files):
print("fitting tICA model to %s" % feature_file)
if features is None:
featurized_traj = load_file(feature_file)
else:
featurized_traj = features[i]
normalized_featurized_traj = n.transform(featurized_traj)
tica_model.partial_fit(normalized_featurized_traj)
print("Finished computing tICA model. Now transforming.")
for i, feature_file in enumerate(feature_files):
print("Transforming %s" % feature_file)
if features is None:
featurized_traj = load_file(feature_file)
else:
featurized_traj = features[i]
normalized_featurized_traj = n.transform(featurized_traj)
transformed_data.append(
tica_model.partial_transform(n.transform(featurized_traj)))
fit_model = tica_model
else:
if features is None:
if not parallel:
features = []
for feature_file in feature_files:
#if "A-00" not in feature_file and "A-01" not in feature_file: continue
#print("Loading feature files one at a time")
print("loading %s" % feature_file)
#if sparse:
# features.append(load_features(feature_file)[0:1000,0:10])
#else:
features.append(
load_file(feature_file)[::subsample, :])
else:
pool = mp.Pool(mp.cpu_count())
features = pool.map(load_file, feature_files)
pool.terminate()
transpose = False
for i in range(0, len(features)):
if np.shape(features[0])[1] != np.shape(features[i])[1]:
transpose = True
break
if transpose:
for i in range(0, len(features)):
features[i] = np.transpose(features[i])
print(np.shape(features[0]))
#print np.shape(features[1])
print((features[0][0][0:10]))
#print(features[1][0][0:10])
print((np.shape(features)))
if normalize:
features = [n.transform(f) for f in features]
print("fitting data to tICA model")
fit_model = tica_model.fit(features)
if subsample == 1:
transformed_data = fit_model.transform(features)
else:
transformed_data = [
fit_model.transform(n.transform(load_file(f)))
for f in feature_files
]
print("transformed data with tICA model")
print((fit_model.summarize()))
#print(dir(fit_model))
#save_dataset(fit_model, fit_model_filename)
verbosedump(fit_model, fit_model_filename)
print("saved tICA model")
verbosedump(transformed_data, projected_data_filename)
print("saved data projected onto tICA coords")
else:
print("already computed tICA model")