Commit f1ded1be authored by nd-02110114's avatar nd-02110114
Browse files

🚧 wip commit

parent ca579061

deepchem/feat/molecule_featurizers/one_hot_featurizer.py→contrib/autoencoder_models/one_hot_featurizer.py

+51 −57
Original line number Diff line number Diff line 
import numpy as np

from typing import List



from deepchem.utils.typing import RDKitMol

from deepchem.feat.base_classes import MolecularFeaturizer



ZINC_CHARSET = [

zinc_charset = [

    ' ', '#', ')', '(', '+', '-', '/', '1', '3', '2', '5', '4', '7', '6', '8',

    '=', '@', 'C', 'B', 'F', 'I', 'H', 'O', 'N', 'S', '[', ']', '\\', 'c', 'l',

    'o', 'n', 'p', 's', 'r'
@@ -14,52 +11,52 @@ ZINC_CHARSET = [ 
class OneHotFeaturizer(MolecularFeaturizer):

  """Encodes a molecule as a one-hot array.



  This featurizer takes a molecule and encodes its SMILES string

  as a one-hot array.

  This featurizer takes a molecule and encodes its Smiles string as a one-hot

  array.



  Notes

  -----

  This class requires RDKit to be installed.

  Note that this featurizer is not thread safe in initialization of charset.

  Note

  ----

  This class requires RDKit to be installed. Note that this featurizer is not

  Thread Safe in initialization of charset

  """



  def __init__(self, charset: List[str] = ZINC_CHARSET, padlength: int = 120):

  def __init__(self, charset=None, padlength=120):

    """Initialize featurizer.



    Parameters

    ----------

    charset: List[str]

    charset: list of str, optional (default None)

      A list of strings, where each string is length 1.

    padlength: int, optional (default 120)

      length to pad the smile strings to.

    """

    try:

      from rdkit import Chem

    except ModuleNotFoundError:

      raise ValueError("This class requires RDKit to be installed.")

    self.charset = charset

    self.pad_length = padlength



  def _featurize(self, mol: RDKitMol) -> np.ndarray:

  def _featurize(self, mol):

    """Compute one-hot featurization of this molecule.



    Parameters

    ----------

    mol: rdkit.Chem.rdchem.Mol

      RDKit Mol object

    mol : RDKit Mol

        Molecule.



    Returns

    -------

    np.ndarray

      The one hot encoded arrays for each character in SMILES

    rval: np.ndarray

      Vector of RDKit descriptors for `mol`

    """

    try:

    from rdkit import Chem

    except ModuleNotFoundError:

      raise ValueError("This class requires RDKit to be installed.")



    smiles = Chem.MolToSmiles(mol)

    if self.charset is None:

      self.charset = self._create_charset(smiles)

    return np.array([self.one_hot_encoded(smile) for smile in smiles])



  def one_hot_array(self, i: int) -> List[int]:

  def one_hot_array(self, i):

    """Create a one hot array with bit i set to 1



    Parameters
@@ -69,93 +66,90 @@ class OneHotFeaturizer(MolecularFeaturizer): 


    Returns

    -------

    List[int]

      The one hot list of bit i. The length is len(self.charset)

    obj:`list` of obj:`int`

      length len(self.charset)

    """

    return [int(x) for x in [ix == i for ix in range(len(self.charset))]]



  def one_hot_index(self, c: str) -> int:

  def one_hot_index(self, c):

    """Compute one-hot index of charater.



    Parameters

    ----------

    c: str

    c: char

      character whose index we want



    Returns

    -------

    int

    index of c in self.charset

    """

    return self.charset.index(c)



  def pad_smile(self, smile: str) -> str:

    """Pad a SMILES string to `self.pad_length`

  def pad_smile(self, smile):

    """Pad a smile string to `self.pad_length`



    Parameters

    ----------

    smile: str

      The SMILES string to be padded.

      The smiles string to be padded.



    Returns

    -------

    str

      SMILES string padded to self.pad_length

      smile string space padded to self.pad_length

    """



    return smile.ljust(self.pad_length)



  def one_hot_encoded(self, smile: str) -> np.ndarray:

    """One Hot Encode an entire SMILES string

  def one_hot_encoded(self, smile):

    """One Hot Encode an entire SMILE string

    

    Parameters

    ----------

    smile: str

      SMILES string to encode

      smile string to encode



    Returns

    -------

    np.ndarray

      The one hot encoded arrays for each character in SMILES

    np.array of one hot encoded arrays for each character in smile

    """

    return np.array([

        self.one_hot_array(self.one_hot_index(x)) for x in self.pad_smile(smile)

    ])



  def untransform(self, one_hot: np.ndarray) -> List[str]:

    """Convert from one hot representation back to SMILES

  def untransform(self, z):

    """Convert from one hot representation back to SMILE



    Parameters

    ----------

    one_hot: np.ndarray

      A numpy array of one hot encoded features

    z: obj:`list`

      list of one hot encoded features



    Returns

    -------

    List[str]

      The List SMILES strings picking MAX for each one hot encoded array

    Smile Strings picking MAX for each one hot encoded array

    """

    smiles_list = []

    for i in range(len(one_hot)):

      smiles = ""

      for j in range(len(one_hot[i])):

        char_bit = np.argmax(one_hot[i][j])

        smiles += self.charset[char_bit]

      smiles_list.append(smiles.strip())

    return smiles_list



  def _create_charset(self, smiles: List[str]) -> List[str]:

    """Create the charset from SMILES

    z1 = []

    for i in range(len(z)):

      s = ""

      for j in range(len(z[i])):

        oh = np.argmax(z[i][j])

        s += self.charset[oh]

      z1.append([s.strip()])

    return z1



  def _create_charset(self, smiles):

    """Create the charset from smiles



    Parameters

    ----------

    smiles: List[str]

      List of SMILES strings

    smiles: obj:`list` of obj:`str`

      list of smile strings



    Returns

    -------

    List[str]

      List of length one strings that are characters in SMILES. No duplicates

    obj:`list` of obj:`str`

      List of length one strings that are characters in smiles.  No duplicates

    """

    s = set()

    for smile in smiles:

deepchem/feat/molecule_featurizers/adjacency_fingerprint.py→contrib/torch/adjacency_fingerprint.py

+11 −0
Original line number Diff line number Diff line 
from collections import deque



import sys

import tensorflow as tf

import pickle



import os

import fnmatch

import numpy as np

from scipy.spatial.distance import pdist, squareform

import pandas as pd



from deepchem.feat.base_classes import Featurizer

from deepchem.feat.graph_features import atom_features

from scipy.sparse import csr_matrix





def get_atom_type(atom):

deepchem/feat/__init__.py

+0 −2
Original line number Diff line number Diff line
@@ -20,11 +20,9 @@ from deepchem.feat.atomic_coordinates import NeighborListComplexAtomicCoordinate 


# molecule featurizers

from deepchem.feat.molecule_featurizers import MolGraphConvFeaturizer

from deepchem.feat.molecule_featurizers import AdjacencyFingerprint

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 OneHotFeaturizer

from deepchem.feat.molecule_featurizers import RawFeaturizer

from deepchem.feat.molecule_featurizers import RDKitDescriptors

from deepchem.feat.molecule_featurizers import SmilesToImage

deepchem/feat/base_classes.py

+4 −4
Original line number Diff line number Diff line
@@ -5,7 +5,7 @@ import inspect 
import logging

import numpy as np

import multiprocessing

from typing import Any, Dict, List, Iterable, Sequence, Tuple

from typing import Any, Dict, List, Iterable, Sequence, Tuple, Union



from deepchem.utils.typing import PymatgenStructure
@@ -214,7 +214,7 @@ class MolecularFeaturizer(Featurizer): 
  The subclasses of this class require RDKit to be installed.

  """



  def featurize(self, molecules, log_every_n=1000, canonical=False):

  def featurize(self, molecules, log_every_n=1000):

    """Calculate features for molecules.



    Parameters
@@ -224,8 +224,6 @@ class MolecularFeaturizer(Featurizer): 
      strings.

    log_every_n: int, default 1000

      Logging messages reported every `log_every_n` samples.

    canonical: bool, default False

      Whether to use a canonical order of atoms returned by RDKit



    Returns

    -------
@@ -235,6 +233,8 @@ class MolecularFeaturizer(Featurizer): 
    try:

      from rdkit import Chem

      from rdkit.Chem.rdchem import Mol

      from rdkit.Chem import rdmolfiles

      from rdkit.Chem import rdmolops

    except ModuleNotFoundError:

      raise ValueError("This class requires RDKit to be installed.")

deepchem/feat/molecule_featurizers/__init__.py

+0 −2
Original line number Diff line number Diff line 
# flake8: noqa

from deepchem.feat.molecule_featurizers.adjacency_fingerprint import AdjacencyFingerprint

from deepchem.feat.molecule_featurizers.bp_symmetry_function_input import BPSymmetryFunctionInput

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.one_hot_featurizer import OneHotFeaturizer

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

CRA Git | Maintained and supported by SUSTech CRA and CCSE