Commit a650b1d0 authored by arunppsg's avatar arunppsg
Browse files

Added examples in documentation for featurizers 

Added examples for MACCSKeysFingerprint, PubChemFingerprint
functions in graph_features.py.
parent c52454c8

deepchem/feat/graph_features.py

+34 −3
Original line number Diff line number Diff line
@@ -149,7 +149,7 @@ def get_feature_list(atom): 


  Parameters

  ----------

  atom: RDKit.rdchem.Atom

  atom: RDKit.Chem.rdchem.Atom

    Atom to get features for



  Examples
@@ -259,7 +259,7 @@ def atom_to_id(atom): 


  Parameters

  ----------

  atom: RDKit.rdchem.Atom

  atom: RDKit.Chem.rdchem.Atom

    Atom to convert to ids.



  Returns
@@ -281,6 +281,8 @@ def atom_features(atom, 


  Parameters

  ----------

  atom: RDKit.Chem.rdchem.Atom

    Atom to compute features on.

  bool_id_feat: bool, optional

    Return an array of unique identifiers corresponding to atom type.

  explicit_H: bool, optional
@@ -288,6 +290,17 @@ def atom_features(atom, 
  use_chirality: bool, optional

    If true, use chirality information.



  Examples

  --------

  >>> from rdkit import Chem

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

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

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

  >>> type(features)

  numpy.ndarray

  >>> features.shape

  (75,)



  Returns

  -------

  np.ndarray of per-atom features.
@@ -376,9 +389,20 @@ def bond_features(bond, use_chirality=False): 


  Parameters

  ----------

  bond: rdkit.Chem.rdchem.Bond

    Bond to compute features on.

  use_chirality: bool, optional

    If true, use chirality information.



  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])



  Note

  ----

  This method requires RDKit to be installed.
@@ -407,7 +431,7 @@ def bond_features(bond, use_chirality=False): 




def max_pair_distance_pairs(mol: RDKitMol,

                            max_pair_distance: Optional[int]) -> np.ndarray:

                            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
@@ -434,6 +458,13 @@ def max_pair_distance_pairs(mol: RDKitMol, 
    distance 2 apart. If `max_pair_distance` is `None`, all pairs are

    considered (effectively infinite `max_pair_distance`)



  Examples

  --------

  >>> 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]])



  Returns

  -------

deepchem/feat/molecule_featurizers/maccs_keys_fingerprint.py

+10 −0
Original line number Diff line number Diff line
@@ -19,6 +19,16 @@ class MACCSKeysFingerprint(MolecularFeaturizer): 
  Note

  ----

  This class requires RDKit to be installed.



  Examples

  --------

  >>> import deepchem as dc

  >>> smiles = 'CC(=O)OC1=CC=CC=C1C(=O)O'

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

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

  >>> features.shape

  (1, 167)



  """



  def __init__(self):

deepchem/feat/molecule_featurizers/pubchem_fingerprint.py

+11 −0
Original line number Diff line number Diff line
@@ -19,6 +19,17 @@ class PubChemFingerprint(MolecularFeaturizer): 
  -----

  This class requires RDKit and PubChemPy to be installed.

  PubChemPy use REST API to get the fingerprint, so you need the internet access.



  Examples

  --------

  >>> import deepchem as dc

  >>> smiles = 'CCC'

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

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

  >>> features.shape

  (1, 881)

  >>> type(features)

  numpy.ndarray

  """



  def __init__(self):

CRA Git | Maintained and supported by SUSTech CRA and CCSE