Merge 6ef4c4b into 0fcc6b4

deepchem/feat/__init__.py

@@ -21,10 +21,12 @@
 from deepchem.feat.molecule_featurizers import CircularFingerprint
 from deepchem.feat.molecule_featurizers import CoulombMatrix
 from deepchem.feat.molecule_featurizers import CoulombMatrixEig
+from deepchem.feat.molecule_featurizers import MACCSKeysFingerprint
 from deepchem.feat.molecule_featurizers import MordredDescriptors
 from deepchem.feat.molecule_featurizers import Mol2VecFingerprint
 from deepchem.feat.molecule_featurizers import MolGraphConvFeaturizer
 from deepchem.feat.molecule_featurizers import OneHotFeaturizer
+from deepchem.feat.molecule_featurizers import PubChemFingerprint
 from deepchem.feat.molecule_featurizers import RawFeaturizer
 from deepchem.feat.molecule_featurizers import RDKitDescriptors
 from deepchem.feat.molecule_featurizers import SmilesToImage

deepchem/feat/molecule_featurizers/__init__.py

@@ -4,9 +4,11 @@
 from deepchem.feat.molecule_featurizers.circular_fingerprint import CircularFingerprint
 from deepchem.feat.molecule_featurizers.coulomb_matrices import CoulombMatrix
 from deepchem.feat.molecule_featurizers.coulomb_matrices import CoulombMatrixEig
+from deepchem.feat.molecule_featurizers.maccs_keys_fingerprint import MACCSKeysFingerprint
 from deepchem.feat.molecule_featurizers.mordred_descriptors import MordredDescriptors
 from deepchem.feat.molecule_featurizers.mol2vec_fingerprint import Mol2VecFingerprint
 from deepchem.feat.molecule_featurizers.one_hot_featurizer import OneHotFeaturizer
+from deepchem.feat.molecule_featurizers.pubchem_fingerprint import PubChemFingerprint
 from deepchem.feat.molecule_featurizers.raw_featurizer import RawFeaturizer
 from deepchem.feat.molecule_featurizers.rdkit_descriptors import RDKitDescriptors
 from deepchem.feat.molecule_featurizers.smiles_to_image import SmilesToImage

deepchem/feat/molecule_featurizers/maccs_keys_fingerprint.py

@@ -0,0 +1,47 @@
+import numpy as np
+
+from deepchem.utils.typing import RDKitMol
+from deepchem.feat.base_classes import MolecularFeaturizer
+
+
+class MACCSKeysFingerprint(MolecularFeaturizer):
+  """MACCS Keys Fingerprint.
+
+  The MACCS (Molecular ACCess System) keys are one of the most commonly used structural keys.
+  Please confirm the details in [1]_, [2]_.
+
+  References
+  ----------
+  .. [1] Durant, Joseph L., et al. "Reoptimization of MDL keys for use in drug discovery."
+     Journal of chemical information and computer sciences 42.6 (2002): 1273-1280.
+  .. [2] https://github.com/rdkit/rdkit/blob/master/rdkit/Chem/MACCSkeys.py
+
+  Notes
+  -----
+  This class requires RDKit to be installed.
+  """
+
+  def __init__(self):
+    """Initialize this featurizer."""
+    try:
+      from rdkit.Chem.AllChem import GetMACCSKeysFingerprint  # noqa
+    except ModuleNotFoundError:
+      raise ValueError("This class requires RDKit to be installed.")
+
+    self.calculator = GetMACCSKeysFingerprint
+
+  def _featurize(self, mol: RDKitMol) -> np.ndarray:
+    """
+    Calculate MACCS keys fingerprint.
+
+    Parameters
+    ----------
+    mol: rdkit.Chem.rdchem.Mol
+      RDKit Mol object
+
+    Returns
+    -------
+    np.ndarray
+      1D array of RDKit descriptors for `mol`. The length is 167.
+    """
+    return self.calculator(mol)

deepchem/feat/molecule_featurizers/pubchem_fingerprint.py

@@ -0,0 +1,52 @@
+import numpy as np
+
+from deepchem.utils.typing import RDKitMol
+from deepchem.feat.base_classes import MolecularFeaturizer
+
+
+class PubChemFingerprint(MolecularFeaturizer):
+  """PubChem Fingerprint.
+
+  The PubChem fingerprint is a 881 bit structural key,
+  which is used by PubChem for similarity searching.
+  Please confirm the details in [1]_.
+
+  References
+  ----------
+  .. [1] ftp://ftp.ncbi.nlm.nih.gov/pubchem/specifications/pubchem_fingerprints.pdf
+
+  Notes
+  -----
+  This class requires RDKit and PubChemPy to be installed.
+  PubChemPy use REST API to get the fingerprint, so you need the internet access.
+  """
+
+  def __init__(self):
+    """Initialize this featurizer."""
+    try:
+      from rdkit import Chem  # noqa
+      import pubchempy as pcp  # noqa
+    except ModuleNotFoundError:
+      raise ValueError("This class requires PubChemPy to be installed.")
+
+    self.get_pubchem_compounds = pcp.get_compounds
+
+  def _featurize(self, mol: RDKitMol) -> np.ndarray:
+    """
+    Calculate PubChem fingerprint.
+
+    Parameters
+    ----------
+    mol: rdkit.Chem.rdchem.Mol
+      RDKit Mol object
+
+    Returns
+    -------
+    np.ndarray
+      1D array of RDKit descriptors for `mol`. The length is 881.
+    """
+    from rdkit import Chem
+    smiles = Chem.MolToSmiles(mol)
+    pubchem_compound = self.get_pubchem_compounds(smiles, 'smiles')[0]
+    feature = [int(bit) for bit in pubchem_compound.cactvs_fingerprint]
+    return np.asarray(feature)

deepchem/feat/tests/test_maccs_keys_finerprint.py

@@ -0,0 +1,25 @@
+import unittest
+
+from deepchem.feat import MACCSKeysFingerprint
+
+
+class TestMACCSKeysFingerprint(unittest.TestCase):
+  """
+  Test MACCSKeyFingerprint.
+  """
+
+  def setUp(self):
+    """
+    Set up tests.
+    """
+    from rdkit import Chem
+    smiles = 'CC(=O)OC1=CC=CC=C1C(=O)O'
+    self.mol = Chem.MolFromSmiles(smiles)
+
+  def test_maccs_key_fingerprint(self):
+    """
+    Test simple fingerprint.
+    """
+    featurizer = MACCSKeysFingerprint()
+    feature_sum = featurizer([self.mol])
+    assert feature_sum.shape == (1, 167)

deepchem/feat/tests/test_puchem_fingerprint.py

@@ -0,0 +1,25 @@
+import unittest
+
+from deepchem.feat import PubChemFingerprint
+
+
+class TestPubChemFingerprint(unittest.TestCase):
+  """
+  Test PubChemFingerprint.
+  """
+
+  def setUp(self):
+    """
+    Set up tests.
+    """
+    from rdkit import Chem
+    smiles = 'CC(=O)OC1=CC=CC=C1C(=O)O'
+    self.mol = Chem.MolFromSmiles(smiles)
+
+  def test_pubchem_fingerprint(self):
+    """
+    Test simple fingerprint.
+    """
+    featurizer = PubChemFingerprint()
+    feature_sum = featurizer([self.mol])
+    assert feature_sum.shape == (1, 881)

docs/featurizers.rst

@@ -92,12 +92,24 @@ WeaveFeaturizer
 .. autoclass:: deepchem.feat.WeaveFeaturizer
   :members:
 
+MACCSKeysFingerprint
+^^^^^^^^^^^^^^^^^^^
+
+.. autoclass:: deepchem.feat.MACCSKeysFingerprint
+  :members:
+
 CircularFingerprint
 ^^^^^^^^^^^^^^^^^^^
 
 .. autoclass:: deepchem.feat.CircularFingerprint
   :members:
 
+PubChemFingerprint
+^^^^^^^^^^^^^^^^^^^
+
+.. autoclass:: deepchem.feat.PubChemFingerprint
+  :members:
+
 Mol2VecFingerprint
 ^^^^^^^^^^^^^^^^^^^
 

docs/requirements.rst

@@ -78,6 +78,10 @@ DeepChem has a number of "soft" requirements.
 |                                |               | :code:`dc.trans.transformers`                     |
 |                                |               |                                                   |
 +--------------------------------+---------------+---------------------------------------------------+
+| `PubChemPy`_                   | latest        | :code:`dc.feat.molecule_featurizers`              |
+|                                |               |                                                   |
+|                                |               |                                                   |
++--------------------------------+---------------+---------------------------------------------------+
 | `pyGPGO`_                      | latest        | :code:`dc.hyper.gaussian_process`                 |
 |                                |               |                                                   |
 |                                |               |                                                   |
@@ -134,6 +138,7 @@ DeepChem has a number of "soft" requirements.
 .. _`OpenMM`: http://openmm.org/
 .. _`PDBFixer`: https://github.com/pandegroup/pdbfixer
 .. _`Pillow`: https://pypi.org/project/Pillow/
+.. _`PubChemPy`: https://pubchempy.readthedocs.io/en/latest/
 .. _`pyGPGO`: https://pygpgo.readthedocs.io/en/latest/
 .. _`Pymatgen`: https://pymatgen.org/
 .. _`PyTorch`: https://pytorch.org/

requirements.yml

@@ -16,6 +16,7 @@ dependencies:
     - mordred
     - networkx
     - pillow
+    - pubchempy
     - pyGPGO
     - pymatgen
     - simdna