def test_ContactFeaturizer_describe_features():
scheme = np.random.choice(['ca','closest','closest-heavy'])
feat = ContactFeaturizer(scheme=scheme, ignore_nonprotein=True)
rnd_traj = np.random.randint(len(trajectories))
features = feat.transform([trajectories[rnd_traj]])
df = pd.DataFrame(feat.describe_features(trajectories[rnd_traj]))
for f in range(25):
f_index = np.random.choice(len(df))
residue_ind = df.iloc[f_index].resids
feature_value, _ = md.compute_contacts(trajectories[rnd_traj],
contacts=[residue_ind],
scheme=scheme)
assert (features[0][:, f_index] == feature_value.flatten()).all()
def test_distance_to_logistic():
trajectories = MinimalFsPeptide().get_cached().trajectories
steepness = np.absolute(10 * np.random.randn())
center = np.absolute(np.random.randn())
contactfeaturizer = ContactFeaturizer()
contacts = contactfeaturizer.transform(trajectories)
logisticcontactfeaturizer = LogisticContactFeaturizer(center=center, steepness=steepness)
logistics = logisticcontactfeaturizer.transform(trajectories)
for n in range(10):
i = np.random.randint(0, contacts[0].shape[0] - 1)
j = np.random.randint(0, contacts[0].shape[1] - 1)
x = contacts[0][i][j]
y = logistics[0][i][j]
if x > center:
assert y < 0.5
if x < center:
assert y > 0.5
def test_soft_min_contact_featurizer():
# just get one frame for now
traj = MinimalFsPeptide().get_cached().trajectories[0][0]
soft_min_beta = 20
ri, rj = np.random.choice(
np.arange(traj.top.n_residues), size=2, replace=False)
aind_i = [i.index for i in traj.top.residue(ri).atoms]
aind_j = [i.index for i in traj.top.residue(rj).atoms]
atom_pairs = [i for i in itertools.product(aind_i, aind_j)]
featuizer = ContactFeaturizer(contacts=[[ri, rj]], scheme='closest', soft_min=True,
soft_min_beta=soft_min_beta)
features = featuizer.transform(([traj]))[0]
distances = md.compute_distances(traj, atom_pairs)
distances = soft_min_beta / \
np.log(np.sum(np.exp(soft_min_beta / distances), axis=1))
np.allclose(features, distances)
def test_distance_to_logistic():
trajectories = MinimalFsPeptide().get_cached().trajectories
steepness = np.absolute(10 * np.random.randn())
center = np.absolute(np.random.randn())
contactfeaturizer = ContactFeaturizer()
contacts = contactfeaturizer.transform(trajectories)
logisticcontactfeaturizer = LogisticContactFeaturizer(center=center,
steepness=steepness)
logistics = logisticcontactfeaturizer.transform(trajectories)
for n in range(10):
i = np.random.randint(0, contacts[0].shape[0] - 1)
j = np.random.randint(0, contacts[0].shape[1] - 1)
x = contacts[0][i][j]
y = logistics[0][i][j]
if (x > center):
assert y < 0.5
if (x < center):
assert y > 0.5
def test_FeatureSelector_describe_features():
rnd_traj = np.random.randint(len(trajectories))
f_ca = ContactFeaturizer(scheme='CA', ignore_nonprotein=True)
f1 = f_ca.transform([trajectories[rnd_traj]])
df1 = pd.DataFrame(f_ca.describe_features(trajectories[rnd_traj]))
f_dih = DihedralFeaturizer()
f2 = f_dih.transform([trajectories[rnd_traj]])
df2 = pd.DataFrame(f_dih.describe_features(trajectories[rnd_traj]))
df_dict = {}
df_dict["ca"] = df1
df_dict["dih"] = df2
f_comb = FeatureSelector([('ca', f_ca), ('dih', f_dih)])
f3 = f_comb.transform([trajectories[rnd_traj]])
df3 = pd.DataFrame(f_comb.describe_features(trajectories[rnd_traj]))
assert len(df3) == len(df1) + len(df2)
df4 = pd.concat([df_dict[i] for i in f_comb.feat_list])
# lets randomly compare 40 features
for i in np.random.choice(range(len(df3)), 40):
for j in df3.columns:
assert eq(df3.iloc[i][j], df4.iloc[i][j])
def test_FeatureSelector_describe_features():
rnd_traj = np.random.randint(len(trajectories))
f_ca = ContactFeaturizer(scheme='CA', ignore_nonprotein=True)
f1 = f_ca.transform([trajectories[rnd_traj]])
df1 = pd.DataFrame(f_ca.describe_features(trajectories[rnd_traj]))
f_dih = DihedralFeaturizer()
f2 = f_dih.transform([trajectories[rnd_traj]])
df2 = pd.DataFrame(f_dih.describe_features(trajectories[rnd_traj]))
df_dict = {}
df_dict["ca"] = df1
df_dict["dih"] = df2
f_comb = FeatureSelector([('ca', f_ca), ('dih', f_dih)])
f3 = f_comb.transform([trajectories[rnd_traj]])
df3 = pd.DataFrame(f_comb.describe_features(trajectories[rnd_traj]))
assert len(df3) == len(df1) + len(df2)
df4 = pd.concat([df_dict[i] for i in f_comb.feat_list])
# lets randomly compare 40 features
for i in np.random.choice(range(len(df3)), 40):
for j in df3.columns:
assert eq(df3.iloc[i][j], df4.iloc[i][j])
def test_soft_min_contact_featurizer():
# just get one frame for now
traj = MinimalFsPeptide().get_cached().trajectories[0][0]
soft_min_beta = 20
ri, rj = np.random.choice(np.arange(traj.top.n_residues),
size=2,
replace=False)
aind_i = [i.index for i in traj.top.residue(ri).atoms]
aind_j = [i.index for i in traj.top.residue(rj).atoms]
atom_pairs = [i for i in itertools.product(aind_i, aind_j)]
featuizer = ContactFeaturizer(contacts=[[ri, rj]],
scheme='closest',
soft_min=True,
soft_min_beta=soft_min_beta)
features = featuizer.transform(([traj]))[0]
distances = md.compute_distances(traj, atom_pairs)
distances = soft_min_beta / \
np.log(np.sum(np.exp(soft_min_beta / distances), axis=1))
np.allclose(features, distances)
def test_contacts():
trajectories = MinimalFsPeptide().get_cached().trajectories
contactfeaturizer = ContactFeaturizer()
contacts = contactfeaturizer.transform(trajectories)
assert contacts[0].shape[1] == 171
def test_contacts():
trajectories = MinimalFsPeptide().get_cached().trajectories
contactfeaturizer = ContactFeaturizer()
contacts = contactfeaturizer.transform(trajectories)
assert contacts[0].shape[1] == 171
