def test_setup_series_analysis():
base_dir = os.path.join("./fake_series")
mdl_dir = os.path.join(base_dir,"new_mdl_dir")
feature_dir = "feature_dir"
series_name = "fake_series"
protein_list = ["fake_kinase1", "fake_kinase2"]
project_dict = {"fake_kinase1": ["fake_proj1", "fake_proj2"],
"fake_kinase2": ["fake_proj3"]}
mdl_params = {'tica__n_components': 1, 'tica__lag_time': 2,
'tica__kinetic_mapping': True, 'tica__shrinkage': 0.01,
'cluster__n_clusters': 174}
with enter_temp_directory():
create_fake_series()
setup_series_analysis(base_dir, mdl_dir, feature_dir,
series_name, protein_list,
project_dict, mdl_params)
assert os.path.isdir(mdl_dir)
for protein in protein_list:
assert os.path.isdir(os.path.join(mdl_dir, protein))
assert(os.path.isfile(os.path.join(base_dir,"series.yaml")))
fin = open(os.path.join(mdl_dir,"project.yaml"), 'r')
yaml_file = yaml.load(fin)
assert yaml_file["base_dir"] == base_dir
assert yaml_file["series_name"] == series_name
assert yaml_file["protein_list"] == protein_list
assert yaml_file["project_dict"] == project_dict
assert yaml_file["mdl_params"] == mdl_params
return
def test_project():
with enter_temp_directory():
base_dir = os.path.abspath(os.path.curdir)
print(base_dir)
print(type(base_dir))
mdl_dir = os.path.join(base_dir,"mdl_dir")
feature_dir = "feature_dir"
series_name = "fake_series"
protein_list = ["kinase_1", "kinase_2"]
project_dict = {"kinase_1": ["fake_proj1",],
"kinase_2": ["fake_proj2"]}
mdl_params = {'tica__n_components': 1, 'tica__lag_time': 1,
'tica__weighted_transform': True, 'tica__shrinkage': 0.01,
'cluster__n_clusters': 2,'msm__lag_time': 1,
'bootstrap__n_samples':1}
create_fake_data(base_dir, protein_list, project_dict)
setup_series_analysis(base_dir, mdl_dir, feature_dir,
series_name, protein_list,
project_dict, mdl_params)
fit_pipeline(base_dir)
prj = ProteinSeries(os.path.join(mdl_dir,"project.yaml"))
assert isinstance(prj, ProteinSeries)
assert isinstance(prj.tica_mdl ,tICA)
assert _test_protein_without_project()
assert _test_protein_with_project(prj)
assert _test_tic_dict(prj)
assert _test_obs_mapping(prj)
return
def _setup_test():
#remove previous mdl_dir
try:
shutil.rmtree(os.path.join(base_dir,"mdl_dir"))
except:
pass
setup_series_analysis(base_dir =base_dir,
mdl_dir = os.path.abspath(os.path.join(base_dir,"mdl_dir")),
feature_dir = "features",
series_name="fake_series",
protein_list = ["kinase_1", "kinase_2"],
project_dict = {"kinase_1":["fake_proj1","fake_proj2"],
"kinase_2":["fake_proj3"]},
mdl_params= {"cluster__n_clusters": 2,
"msm__lag_time": 1,
"tica__shrinkage": 0.005,
"tica__lag_time": 1,
"tica__n_components": 2,
"tica__weighted_transform": True},
)
def test_multiple_mdls():
base_dir = os.path.join("./fake_series")
mdl_dir = os.path.join(base_dir,"new_mdl_dir")
feature_dir = "feature_dir"
series_name = "fake_series"
protein_list = ["fake_kinase1", "fake_kinase2"]
project_dict = {"fake_kinase1": ["fake_proj1", "fake_proj2"],
"fake_kinase2": ["fake_proj3"]}
mdl_params = {'tica__n_components': 4, 'tica__lag_time': 223,
'tica__kinetic_mapping': True, 'tica__gamma': 0.0121,
'cluster__n_clusters': 212}
with enter_temp_directory():
create_fake_series()
for i in range(3):
setup_series_analysis(base_dir, mdl_dir, feature_dir,
series_name, protein_list,
project_dict, mdl_params)
time.sleep(1)
assert len(glob.glob("./fake_series/*/project.yaml")) == 3
return
def test_pipeline():
with enter_temp_directory():
base_dir = os.path.abspath(os.path.curdir)
mdl_dir = os.path.join(base_dir, "mdl_dir")
feature_dir = "feature_dir"
series_name = "fake_series"
protein_list = ["kinase_1", "kinase_2"]
project_dict = {
"kinase_1": [
"fake_proj1",
],
"kinase_2": ["fake_proj2"]
}
mdl_params = {
'tica__n_components': 1,
'tica__lag_time': 1,
'tica__kinetic_mapping': True,
'tica__shrinkage': 0.01,
'cluster__n_clusters': 2,
'msm__lag_time': 1,
'bootstrap__n_samples': 1
}
create_fake_data(base_dir, protein_list, project_dict)
yaml_file = setup_series_analysis(base_dir, mdl_dir, feature_dir,
series_name, protein_list,
project_dict, mdl_params)
fit_protein_tica(yaml_file)
transform_protein_tica(yaml_file)
fit_protein_kmeans(yaml_file)
transform_protein_kmeans(yaml_file)
fit_msms(yaml_file)
fit_bootstrap(yaml_file)
raw_count_obs = 0
for p in protein_list:
for j in glob.glob(os.path.join(base_dir, p, feature_dir, "*.jl")):
raw_count_obs += verboseload(j).shape[0]
tica_mdl = verboseload(os.path.join(mdl_dir, "tica_mdl.pkl"))
#make sure the mdl is seeing all the data, could probably have a far stronger test here
assert tica_mdl.n_observations_ == raw_count_obs
assert os.path.exists(os.path.join(mdl_dir, "kinase_1/tica_data.pkl"))
assert os.path.exists(os.path.join(mdl_dir, "kinase_2/tica_data.pkl"))
assert os.path.exists(os.path.join(mdl_dir, "kinase_1/msm_mdl.pkl"))
assert os.path.exists(os.path.join(mdl_dir, "kinase_2/msm_mdl.pkl"))
assert os.path.exists(
os.path.join(mdl_dir, "kinase_2/bootstrap_msm_mdl.pkl"))
assert os.path.exists(os.path.join(mdl_dir, "kmeans_mdl.pkl"))
return
def test_pipeline():
with enter_temp_directory():
base_dir = os.path.abspath(os.path.curdir)
mdl_dir = os.path.join(base_dir,"mdl_dir")
feature_dir = "feature_dir"
series_name = "fake_series"
protein_list = ["kinase_1", "kinase_2"]
project_dict = {"kinase_1": ["fake_proj1",],
"kinase_2": ["fake_proj2"]}
mdl_params = {'tica__n_components': 1, 'tica__lag_time': 1,
'tica__kinetic_mapping': True, 'tica__shrinkage': 0.01,
'cluster__n_clusters': 2,
'msm__lag_time': 1, 'bootstrap__n_samples':1 }
create_fake_data(base_dir, protein_list, project_dict)
yaml_file = setup_series_analysis(base_dir, mdl_dir, feature_dir,
series_name, protein_list,
project_dict, mdl_params)
fit_protein_tica(yaml_file)
transform_protein_tica(yaml_file)
fit_protein_kmeans(yaml_file)
transform_protein_kmeans(yaml_file)
fit_msms(yaml_file)
fit_bootstrap(yaml_file)
raw_count_obs = 0
for p in protein_list:
for j in glob.glob(os.path.join(base_dir,p,feature_dir,"*.jl")):
raw_count_obs += verboseload(j).shape[0]
tica_mdl = verboseload(os.path.join(mdl_dir,"tica_mdl.pkl"))
#make sure the mdl is seeing all the data, could probably have a far stronger test here
assert tica_mdl.n_observations_ == raw_count_obs
assert os.path.exists(os.path.join(mdl_dir,"kinase_1/tica_data.pkl"))
assert os.path.exists(os.path.join(mdl_dir,"kinase_2/tica_data.pkl"))
assert os.path.exists(os.path.join(mdl_dir,"kinase_1/msm_mdl.pkl"))
assert os.path.exists(os.path.join(mdl_dir,"kinase_2/msm_mdl.pkl"))
assert os.path.exists(os.path.join(mdl_dir,"kinase_2/bootstrap_msm_mdl.pkl"))
assert os.path.exists(os.path.join(mdl_dir,"kmeans_mdl.pkl"))
return
def test_slicer():
with enter_temp_directory():
base_dir = os.path.abspath(os.path.curdir)
mdl_dir = os.path.join(base_dir,"mdl_dir")
feature_dir = "feature_dir"
series_name = "fake_series"
protein_list = ["kinase_1", "kinase_2"]
project_dict = {"kinase_1": ["fake_proj1",],
"kinase_2": ["fake_proj2"]}
mdl_params = {'tica__n_components': 1, 'tica__lag_time': 1,
'tica__kinetic_mapping': True, 'tica__shrinkage': 0.01,
'cluster__n_clusters': 2,
'msm__lag_time': 1, 'bootstrap__n_samples':1 }
create_fake_data(base_dir, protein_list, project_dict)
yaml_file = setup_series_analysis(base_dir, mdl_dir, feature_dir,
series_name, protein_list,
project_dict, mdl_params)
dict_feat_ind={}
dict_feat_ind["kinase_1"] =[0, 2]
dict_feat_ind["kinase_2"] =[1, 1, 0, 2]
series_feature_slicer(yaml_file, dict_feat_ind)
for protein in protein_list:
with enter_protein_data_dir(yaml_file, protein):
assert (os.path.isdir("sliced_feature_dir"))
flist = glob.glob("./%s/*.jl"%feature_dir)
for fname in flist:
original_file = verboseload(fname)
expected_file = original_file[:, dict_feat_ind[protein]]
written_file = verboseload("./%s/%s"%("sliced_feature_dir",
os.path.basename(fname)
))
assert (expected_file==written_file).all()
return
def test_plotting_utils():
with enter_temp_directory():
base_dir = os.path.abspath(os.path.curdir)
mdl_dir = os.path.join(base_dir, "mdl_dir")
feature_dir = "feature_dir"
series_name = "fake_series"
protein_list = ["kinase_1", "kinase_2"]
project_dict = {
"kinase_1": [
"fake_proj1",
],
"kinase_2": ["fake_proj2"]
}
mdl_params = {
'tica__n_components': 1,
'tica__lag_time': 1,
'tica__kinetic_mapping': True,
'tica__shrinkage': 0.01,
'cluster__n_clusters': 2,
'msm__lag_time': 1,
'bootrap__n_samples': 1
}
create_fake_data(base_dir, protein_list, project_dict)
setup_series_analysis(base_dir, mdl_dir, feature_dir, series_name,
protein_list, project_dict, mdl_params)
fit_pipeline(base_dir)
prj = ProteinSeries(os.path.join(mdl_dir, "project.yaml"))
prt1 = Protein(prj, "kinase_1")
prt2 = Protein(prj, "kinase_2")
prt1._mlpt_fct = 0.0
prt2._mlpt_fct = 0.0
n_bins = 100
lin_spaced_tic_dict = global_tic_boundaries([prt1, prt2],
range(prt1.n_tics_),
n_bins)
def test_bounds():
locally_calc = {}
for i in range(prt1.n_tics_):
locally_calc[i] = []
global_min = min(
min([min(i) for i in prt1.tica_data.values()]),
min([min(i) for i in prt2.tica_data.values()]))
locally_calc[i].append(global_min)
global_max = max(
max([max(i) for i in prt1.tica_data.values()]),
max([max(i) for i in prt2.tica_data.values()]))
locally_calc[i].append(global_max)
for i in range(prt1.n_tics_):
assert (lin_spaced_tic_dict[i][0] == locally_calc[i][0])
assert (lin_spaced_tic_dict[i][-1] == locally_calc[i][-1])
assert (len(lin_spaced_tic_dict[i]) == n_bins)
return True
def test_histogram_data():
H_dict, H_calc, _ = tica_histogram(prj,
prt1, [0],
x_array=lin_spaced_tic_dict[0],
n_bins=None)
assert (len(H_dict.keys()) == prt1.n_states_)
assert (len(H_calc) == len(lin_spaced_tic_dict[0]) - 1)
rnd_state = np.random.randint(0, prt1.n_states_)
assert (np.allclose(
H_dict[rnd_state],
np.histogram(prt1.tic_dict[0][rnd_state],
bins=lin_spaced_tic_dict[0],
normed=True)[0]))
return True
def test_one_dim_free_energy():
df = one_dim_tic_free_energy(prj,
prt1,
0,
n_bins=None,
lin_spaced_tic=lin_spaced_tic_dict[0],
errorbars=False)
assert ((df.protein_name == prt1.name).all())
assert ((df.mdl_index == "mle").all())
return True
assert (test_bounds())
assert (test_histogram_data())
assert (test_one_dim_free_energy())
return
def test_plotting_utils():
with enter_temp_directory():
base_dir = os.path.abspath(os.path.curdir)
mdl_dir = os.path.join(base_dir,"mdl_dir")
feature_dir = "feature_dir"
series_name = "fake_series"
protein_list = ["kinase_1", "kinase_2"]
project_dict = {"kinase_1": ["fake_proj1",],
"kinase_2": ["fake_proj2"]}
mdl_params = {'tica__n_components': 1, 'tica__lag_time': 1,
'tica__kinetic_mapping': True, 'tica__shrinkage': 0.01,
'cluster__n_clusters': 2,'msm__lag_time': 1,
'bootrap__n_samples':1
}
create_fake_data(base_dir, protein_list, project_dict)
setup_series_analysis(base_dir, mdl_dir, feature_dir,
series_name, protein_list,
project_dict, mdl_params)
fit_pipeline(base_dir)
prj = ProteinSeries(os.path.join(mdl_dir,"project.yaml"))
prt1 = Protein(prj, "kinase_1")
prt2 = Protein(prj, "kinase_2")
prt1._mlpt_fct = 0.0
prt2._mlpt_fct = 0.0
n_bins = 100
lin_spaced_tic_dict = global_tic_boundaries([prt1, prt2],
range(prt1.n_tics_), n_bins)
def test_bounds():
locally_calc={}
for i in range(prt1.n_tics_):
locally_calc[i] =[]
global_min = min(min([min(i) for i in prt1.tica_data.values()]),
min([min(i) for i in prt2.tica_data.values()]))
locally_calc[i].append(global_min)
global_max = max(max([max(i) for i in prt1.tica_data.values()]),
max([max(i) for i in prt2.tica_data.values()]))
locally_calc[i].append(global_max)
for i in range(prt1.n_tics_):
assert(lin_spaced_tic_dict[i][0]==locally_calc[i][0])
assert(lin_spaced_tic_dict[i][-1]==locally_calc[i][-1])
assert(len(lin_spaced_tic_dict[i])==n_bins)
return True
def test_histogram_data():
H_dict, H_calc, _ = tica_histogram(prj, prt1, [0],
x_array=lin_spaced_tic_dict[0],
n_bins=None)
assert(len(H_dict.keys()) == prt1.n_states_)
assert(len(H_calc) == len(lin_spaced_tic_dict[0])-1)
rnd_state = np.random.randint(0,prt1.n_states_)
assert(np.allclose(H_dict[rnd_state], np.histogram(prt1.tic_dict[0][rnd_state],
bins = lin_spaced_tic_dict[0],
normed=True)[0]))
return True
def test_one_dim_free_energy():
df = one_dim_tic_free_energy(prj, prt1, 0, n_bins=None ,
lin_spaced_tic=lin_spaced_tic_dict[0], errorbars=False)
assert((df.protein_name==prt1.name).all())
assert((df.mdl_index=="mle").all())
return True
assert(test_bounds())
assert(test_histogram_data())
assert(test_one_dim_free_energy())
return
