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 _extract_data(self, traj):
contact = ContactFeaturizer(
contacts=self.contacts, scheme=self.scheme, ignore_nonprotein=self.ignore_nonprotein
)
distances = contact.partial_transform(traj)
summary = contact.describe_features(traj)
pairs = [item["resids"] for item in summary]
resids = np.unique(pairs)
data = []
for resid in resids:
idx = list(list(set(pair) - {resid})[0] for pair in pairs if resid in pair)
mapping = np.array([True if resid in pair else False for pair in pairs])
data.append(pd.DataFrame(distances[:, mapping], columns=[idx, len(idx) * [resid]]))
return pd.concat(data, axis=1)
def Get_contacts_features_villin():
import os
import shutil
import mdtraj as md
os.chdir('/homes/anuginueni/traj_villin')
if(os.path.isdir('./contacts')):
shutil.rmtree('./contacts')
from msmbuilder.dataset import dataset
xyz = dataset( "/homes/anuginueni/traj_villin/*.xtc",topology='/homes/anuginueni/traj_villin/filtered.pdb',stride=5)
t=md.load( "/homes/anuginueni/traj_villin/trajectory-331.xtc",top='/homes/anuginueni/traj_villin/filtered.pdb',stride=5)
from msmbuilder.featurizer import ContactFeaturizer #for contacts
featurizer = ContactFeaturizer(scheme='ca') #for contacts
des_feat=featurizer.describe_features(t)
res = [ sub['resids'] for sub in des_feat ]
print(str(res))
contacts = xyz.fit_transform_with(featurizer, 'contacts/', fmt='dir-npy') #for contacts
return contacts
def _extract_data(self, traj):
contact = ContactFeaturizer(contacts=self.contacts,
scheme=self.scheme,
ignore_nonprotein=self.ignore_nonprotein)
distances = contact.partial_transform(traj)
summary = contact.describe_features(traj)
pairs = [item['resids'] for item in summary]
resids = np.unique(pairs)
data = []
for resid in resids:
idx = list(
list(set(pair) - {resid})[0] for pair in pairs
if resid in pair)
mapping = np.array(
[True if resid in pair else False for pair in pairs])
data.append(
pd.DataFrame(distances[:, mapping],
columns=[idx, len(idx) * [resid]]))
return pd.concat(data, axis=1)
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])
