Commit ff1b21f3 authored by arunppsg's avatar arunppsg
Browse files

updated docs

parent a650b1d0

deepchem/feat/atomic_conformation.py

+11 −8
Original line number Diff line number Diff line
@@ -131,19 +131,22 @@ class AtomicConformationFeaturizer(Featurizer): 
  >>> import deepchem as dc

  >>> smiles = ['CCC']

  >>> featurizer = dc.feat.AtomicConformationFeaturizer()

  >>> features = featurizer.featurize()

  >>> features = featurizer.featurize(smiles)

  >>> features[0].num_atoms

  11

  >>> sum(features[0].atomic_number == 6)

  3

  >>> sum(features[0].atmoic_number == 1)

  >>> sum(features[0].atomic_number == 1)

  8

  >>> features[0].formal_charge

  array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], dtype=float32)

  >>> features[0].partial_charge

  array([-0.06564544, -0.06564544, -0.05903836,  0.02302528,  0.02302528,

        0.02302528,  0.02302528,  0.02302528,  0.02302528,  0.0260888 ,

        0.0260888 ], dtype=float32)

  >>> type(features[0].formal_charge)

  <class 'numpy.ndarray'>

  >>> features[0].formal_charge.shape

  (11,)

  >>> type(features[0].partial_charge)

  <class 'numpy.ndarray'>

  >>> features[0].partial_charge.shape

  (11,)



  """



  def _featurize(self, datapoint: str) -> AtomicConformation:

deepchem/feat/graph_features.py

+52 −20
Original line number Diff line number Diff line
@@ -54,6 +54,7 @@ def one_of_k_encoding_unk(x, allowable_set): 
  --------

  >>> dc.feat.graph_features.one_of_k_encoding_unk("s", ["a", "b", "c"])

  [False, False, True]



  """

  if x not in allowable_set:

    x = allowable_set[-1]
@@ -78,6 +79,7 @@ def get_intervals(l): 


  >>> dc.feat.graph_features.get_intervals([[1], [], [1, 2], [1, 2, 3]])

  [1, 1, 3, 12]



  """

  intervals = len(l) * [0]

  # Initalize with 1
@@ -104,6 +106,7 @@ def safe_index(l, e): 
  0

  >>> dc.feat.graph_features.safe_index([1, 2, 3], 7)

  3



  """

  try:

    return l.index(e)
@@ -157,8 +160,11 @@ def get_feature_list(atom): 
  >>> from rdkit import Chem

  >>> mol = Chem.MolFromSmiles("C")

  >>> atom = mol.GetAtoms()[0]

  >>> dc.feat.graph_features.get_feature_list(atom)

  [0, 4, 4, 3, 0, 2]

  >>> features = dc.feat.graph_features.get_feature_list(atom)

  >>> type(features)

  <class 'list'>

  >>> len(features)

  6



  Note

  ----
@@ -290,6 +296,11 @@ def atom_features(atom, 
  use_chirality: bool, optional

    If true, use chirality information.



  Returns

  -------

  features: np.ndarray 

    An array of per-atom features.



  Examples

  --------

  >>> from rdkit import Chem
@@ -297,13 +308,10 @@ def atom_features(atom, 
  >>> atom = mol.GetAtoms()[0]

  >>> features = dc.feat.graph_features.atom_features(atom)

  >>> type(features)

  numpy.ndarray

  <class 'numpy.ndarray'>

  >>> features.shape

  (75,)



  Returns

  -------

  np.ndarray of per-atom features.

  """

  if bool_id_feat:

    return np.array([atom_to_id(atom)])
@@ -394,24 +402,31 @@ def bond_features(bond, use_chirality=False): 
  use_chirality: bool, optional

    If true, use chirality information.

  

  Note

  ----

  This method requires RDKit to be installed.



  Returns

  -------

  bond_feats: np.ndarray

    Array of bond features. This is a 1-D array of length 6 if `use_chirality`

    is `False` else of length 10 with chirality encoded.



  Examples

  --------

  >>> from rdkit import Chem

  >>> mol = Chem.MolFromSmiles('CCC')

  >>> bond = mol.GetBonds()[0]

  >>> bond_features = dc.feat.graph_features.bond_features(bond)

  >>> bond_features

  array([ True, False, False, False, False, False])

  >>> type(bond_features)

  <class 'numpy.ndarray'>

  >>> bond_features.shape

  (6,)



  Note

  ----

  This method requires RDKit to be installed.



  Returns

  -------

  bond_feats: np.ndarray

    Array of bond features. This is a 1-D array of length 6 if `use_chirality`

    is `False` else of length 10 with chirality encoded.

  """

  try:

    from rdkit import Chem
@@ -430,8 +445,8 @@ def bond_features(bond, use_chirality=False): 
  return np.array(bond_feats)





def max_pair_distance_pairs(mol: RDKitMol,

                            max_pair_distance: Optional[int] = None) -> np.ndarray:

def max_pair_distance_pairs(

    mol: RDKitMol, max_pair_distance: Optional[int] = None) -> np.ndarray:

  """Helper method which finds atom pairs within max_pair_distance graph distance.



  This helper method is used to find atoms which are within max_pair_distance
@@ -462,9 +477,11 @@ def max_pair_distance_pairs(mol: RDKitMol, 
  --------

  >>> from rdkit import Chem

  >>> mol = Chem.MolFromSmiles('CCC')

  >>> dc.feat.graph_features.max_pair_distance_pairs(mol, 1)

  array([[0, 0, 1, 1, 1, 2, 2],

       [0, 1, 0, 1, 2, 1, 2]])

  >>> features = dc.feat.graph_features.max_pair_distance_pairs(mol, 1)

  >>> type(features)

  <class 'numpy.ndarray'>

  >>> features.shape  # (2, num_pairs)

  (2, 7)



  Returns

  -------
@@ -893,9 +910,24 @@ class WeaveFeaturizer(MolecularFeaturizer): 
  Examples

  --------

  >>> import deepchem as dc

  >>> mols = ["C", "CCC"]

  >>> mols = ["CCC"]

  >>> featurizer = dc.feat.WeaveFeaturizer()

  >>> X = featurizer.featurize(mols)

  >>> features = featurizer.featurize(mols)

  >>> type(features[0])

  <class 'deepchem.feat.mol_graphs.WeaveMol'>

  >>> features[0].get_num_atoms() # 3 atoms in compound

  3

  >>> features[0].get_num_features() # feature size

  75

  >>> type(features[0].get_atom_features())

  <class 'numpy.ndarray'>

  >>> features[0].get_atom_features().shape

  (3, 75)

  >>> type(features[0].get_pair_features())

  <class 'numpy.ndarray'>

  >>> features[0].get_pair_features().shape

  (9, 14)





  References

  ----------

deepchem/feat/molecule_featurizers/atomic_coordinates.py

+16 −0
Original line number Diff line number Diff line
@@ -10,6 +10,22 @@ from deepchem.utils.typing import RDKitMol 
class AtomicCoordinates(MolecularFeaturizer):

  """Calculate atomic coordinates.



  Examples

  --------

  >>> import deepchem as dc

  >>> from rdkit import Chem

  >>> mol = Chem.MolFromSmiles('C1C=CC=CC=1')

  >>> n_atoms = len(mol.GetAtoms())

  >>> n_atoms

  6

  >>> featurizer = dc.feat.AtomicCoordinates(use_bohr=False)

  >>> features = featurizer.featurize([mol])

  >>> type(features[0])

  <class 'numpy.ndarray'>

  >>> features[0].shape # (n_atoms, 3)

  (6, 3)





  Note

  ----

  This class requires RDKit to be installed.

deepchem/feat/molecule_featurizers/bp_symmetry_function_input.py

+12 −1
Original line number Diff line number Diff line
@@ -9,7 +9,18 @@ from deepchem.feat.molecule_featurizers.atomic_coordinates import AtomicCoordina 
class BPSymmetryFunctionInput(MolecularFeaturizer):

  """Calculate symmetry function for each atom in the molecules



  This method is described in [1]_

  This method is described in [1]_.



  Standalone usage:



  >>> import deepchem as dc

  >>> smiles = ['C1C=CC=CC=1']

  >>> featurizer = dc.feat.BPSymmetryFunctionInput(max_atoms=10)

  >>> features = featurizer.featurize(smiles)

  >>> type(features[0])

  <class 'numpy.ndarray'>

  >>> features[0].shape  # (max_atoms, 4)

  (10, 4)



  References

  ----------

deepchem/feat/molecule_featurizers/circular_fingerprint.py

+11 −10
Original line number Diff line number Diff line
@@ -30,22 +30,23 @@ class CircularFingerprint(MolecularFeaturizer): 
  --------

  >>> import deepchem as dc

  >>> from rdkit import Chem

  >>> smiles = 'C1=CC=CC=C1'

  >>> mol = Chem.MolFromSmiles(smiles)

  >>> smiles = ['C1=CC=CC=C1']

  

  >>> # Example 1: (size = 2048, radius = 4)

  >>> featurizer = dc.feat.CircularFingerprint(size=2048, radius=4)

  >>> fingerprint = featurizer([mol])

  >>> fingerprint.shape

  (1, 2048)

  >>> features = featurizer.featurize(smiles)

  >>> type(features[0])

  <class 'numpy.ndarray'>

  >>> features[0].shape

  (2048,)



  >>> # Example 2: (size = 2048, radius = 4, sparse = True, smiles = True)

  >>> featurizer = dc.feat.CircularFingerprint(size=2048, radius=8,

  ...                                          sparse=True, smiles=True)

  >>> featurizer([mol])

  array([{98513984: {'smiles': 'ccc', 'count': 6}, 2763854213: {'smiles':

    'ccccc', 'count': 6}, 3218693969: {'smiles': '', 'count': 6}, 3741631696:

    {'smiles': 'c1ccccc1', 'count': 1}}], dtype=object)

  >>> features = featurizer.featurize(smiles)

  >>> type(features[0]) # dict containing fingerprints

  <class 'dict'>



  """



  def __init__(self,

CRA Git | Maintained and supported by SUSTech CRA and CCSE