Unverified Commit 2331a1fe authored by Bharath Ramsundar's avatar Bharath Ramsundar Committed by GitHub
Browse files

Merge pull request #2212 from deepchem/interaction 

Interaction Fingerprint Addition
parents ff137c65 35288b8f

datasets/.gitignore

0 → 100644
+11 −0
Original line number Diff line number Diff line 
PPB.csv

SAMPL.csv

bace.csv

bace_c-featurized/

chembl-featurized/

clintox-featurized/

clintox.csv.gz

core_grid.json

ppb-featurized/

sampl-featurized/

atom_init.json

deepchem/feat/__init__.py

+10 −0
Original line number Diff line number Diff line
@@ -37,6 +37,16 @@ from deepchem.feat.complex_featurizers import RdkitGridFeaturizer 
from deepchem.feat.complex_featurizers import NeighborListAtomicCoordinates

from deepchem.feat.complex_featurizers import NeighborListComplexAtomicCoordinates

from deepchem.feat.complex_featurizers import ComplexNeighborListFragmentAtomicCoordinates

from deepchem.feat.complex_featurizers import ContactCircularFingerprint

from deepchem.feat.complex_featurizers import ContactCircularVoxelizer

from deepchem.feat.complex_featurizers import SplifFingerprint

from deepchem.feat.complex_featurizers import SplifVoxelizer

from deepchem.feat.complex_featurizers import ChargeVoxelizer

from deepchem.feat.complex_featurizers import SaltBridgeVoxelizer

from deepchem.feat.complex_featurizers import CationPiVoxelizer

from deepchem.feat.complex_featurizers import PiStackVoxelizer

from deepchem.feat.complex_featurizers import HydrogenBondVoxelizer

from deepchem.feat.complex_featurizers import HydrogenBondCounter



# material featurizers

from deepchem.feat.material_featurizers import ElementPropertyFingerprint

deepchem/feat/complex_featurizers/__init__.py

+10 −0
Original line number Diff line number Diff line
@@ -6,3 +6,13 @@ from deepchem.feat.complex_featurizers.rdkit_grid_featurizer import RdkitGridFea 
from deepchem.feat.complex_featurizers.complex_atomic_coordinates import NeighborListAtomicCoordinates

from deepchem.feat.complex_featurizers.complex_atomic_coordinates import NeighborListComplexAtomicCoordinates

from deepchem.feat.complex_featurizers.complex_atomic_coordinates import ComplexNeighborListFragmentAtomicCoordinates

from deepchem.feat.complex_featurizers.contact_fingerprints import ContactCircularFingerprint

from deepchem.feat.complex_featurizers.contact_fingerprints import ContactCircularVoxelizer

from deepchem.feat.complex_featurizers.grid_featurizers import ChargeVoxelizer

from deepchem.feat.complex_featurizers.grid_featurizers import SaltBridgeVoxelizer

from deepchem.feat.complex_featurizers.grid_featurizers import CationPiVoxelizer

from deepchem.feat.complex_featurizers.grid_featurizers import PiStackVoxelizer

from deepchem.feat.complex_featurizers.grid_featurizers import HydrogenBondVoxelizer

from deepchem.feat.complex_featurizers.grid_featurizers import HydrogenBondCounter

from deepchem.feat.complex_featurizers.splif_fingerprints import SplifFingerprint

from deepchem.feat.complex_featurizers.splif_fingerprints import SplifVoxelizer

deepchem/feat/complex_featurizers/contact_fingerprints.py

0 → 100644
+235 −0
Original line number Diff line number Diff line 
"""

Topological fingerprints for macromolecular structures.

"""

import numpy as np

import logging

import itertools

from deepchem.utils.hash_utils import hash_ecfp

from deepchem.feat import ComplexFeaturizer

from deepchem.utils.rdkit_utils import load_complex

from deepchem.utils.hash_utils import vectorize

from deepchem.utils.voxel_utils import voxelize

from deepchem.utils.voxel_utils import convert_atom_to_voxel

from deepchem.utils.rdkit_utils import compute_all_ecfp

from deepchem.utils.rdkit_utils import compute_contact_centroid

from deepchem.utils.rdkit_utils import MoleculeLoadException

from deepchem.utils.geometry_utils import compute_pairwise_distances

from deepchem.utils.geometry_utils import subtract_centroid



from typing import Tuple, Dict, List



logger = logging.getLogger(__name__)





def featurize_contacts_ecfp(

    frag1: Tuple,

    frag2: Tuple,

    pairwise_distances: np.ndarray = None,

    cutoff: float = 4.5,

    ecfp_degree: int = 2) -> Tuple[Dict[int, str], Dict[int, str]]:

  """Computes ECFP dicts for pairwise interaction between two molecular fragments.



  Parameters

  ----------

  frag1: Tuple

    A tuple of (coords, mol) returned by `load_molecule`.

  frag2: Tuple

    A tuple of (coords, mol) returned by `load_molecule`.

  pairwise_distances: np.ndarray

    Array of pairwise fragment-fragment distances (Angstroms)

  cutoff: float

    Cutoff distance for contact consideration

  ecfp_degree: int

    ECFP radius



  Returns

  -------

  Tuple of dictionaries of ECFP contact fragments

  """

  if pairwise_distances is None:

    pairwise_distances = compute_pairwise_distances(frag1[0], frag2[0])

  # contacts is of form (x_coords, y_coords), a tuple of 2 lists

  contacts = np.nonzero((pairwise_distances < cutoff))

  # contacts[0] is the x_coords, that is the frag1 atoms that have

  # nonzero contact.

  frag1_atoms = set([int(c) for c in contacts[0].tolist()])

  # contacts[1] is the y_coords, the frag2 atoms with nonzero contacts

  frag2_atoms = set([int(c) for c in contacts[1].tolist()])



  frag1_ecfp_dict = compute_all_ecfp(

      frag1[1], indices=frag1_atoms, degree=ecfp_degree)

  frag2_ecfp_dict = compute_all_ecfp(

      frag2[1], indices=frag2_atoms, degree=ecfp_degree)



  return (frag1_ecfp_dict, frag2_ecfp_dict)





class ContactCircularFingerprint(ComplexFeaturizer):

  """Compute (Morgan) fingerprints near contact points of macromolecular complexes.



  Given a macromolecular complex made up of multiple

  constituent molecules, first compute the contact points where

  atoms from different molecules come close to one another. For

  atoms within "contact regions," compute radial "ECFP"

  fragments which are sub-molecules centered at atoms in the

  contact region.



  For a macromolecular complex, returns a vector of shape

  `(2*size,)`

  """



  def __init__(self, cutoff: float = 4.5, radius: int = 2, size: int = 8):

    """

    Parameters

    ----------

    cutoff: float (default 4.5)

      Distance cutoff in angstroms for molecules in complex.

    radius: int, optional (default 2)

      Fingerprint radius.

    size: int, optional (default 8)

      Length of generated bit vector.

    """

    self.cutoff = cutoff

    self.radius = radius

    self.size = size



  def _featurize(self, mol_pdb: str, protein_pdb: str):

    """

    Compute featurization for a molecular complex



    Parameters

    ----------

    mol_pdb: str

      Filename for ligand molecule

    protein_pdb: str

      Filename for protein molecule

    """

    try:

      fragments = load_complex((mol_pdb, protein_pdb), add_hydrogens=False)



    except MoleculeLoadException:

      logger.warning("This molecule cannot be loaded by Rdkit. Returning None")

      return None

    pairwise_features = []

    # We compute pairwise contact fingerprints

    for (frag1, frag2) in itertools.combinations(fragments, 2):

      # Get coordinates

      distances = compute_pairwise_distances(frag1[0], frag2[0])

      vector = [

          vectorize(hash_ecfp, feature_dict=ecfp_dict, size=self.size)

          for ecfp_dict in featurize_contacts_ecfp(

              frag1,

              frag2,

              distances,

              cutoff=self.cutoff,

              ecfp_degree=self.radius)

      ]

      pairwise_features += vector



    pairwise_features = np.concatenate(pairwise_features)

    return pairwise_features





class ContactCircularVoxelizer(ComplexFeaturizer):

  """Computes ECFP fingerprints on a voxel grid.



  Given a macromolecular complex made up of multiple

  constituent molecules, first compute the contact points where

  atoms from different molecules come close to one another. For

  atoms within "contact regions," compute radial "ECFP"

  fragments which are sub-molecules centered at atoms in the

  contact region. Localize these ECFP fingeprints at the voxel

  in which they originated.



  Featurizes a macromolecular complex into a tensor of shape

  `(voxels_per_edge, voxels_per_edge, voxels_per_edge, size)` where

  `voxels_per_edge = int(box_width/voxel_width)`. If `flatten==True`,

  then returns a flattened version of this tensor of length

  `size*voxels_per_edge**3`

  """



  def __init__(self,

               cutoff: float = 4.5,

               radius: int = 2,

               size: int = 8,

               box_width: float = 16.0,

               voxel_width: float = 1.0,

               flatten: bool = False):

    """

    Parameters

    ----------

    cutoff: float (default 4.5)

      Distance cutoff in angstroms for molecules in complex.

    radius : int, optional (default 2)

      Fingerprint radius.

    size : int, optional (default 8)

      Length of generated bit vector.

    box_width: float, optional (default 16.0)

      Size of a box in which voxel features are calculated. Box

      is centered on a ligand centroid.

    voxel_width: float, optional (default 1.0)

      Size of a 3D voxel in a grid.

    flatten: bool, optional (default False)

      If True, then returns a flat feature vector rather than voxel grid. This

      feature vector is constructed by flattening the usual voxel grid.

    """

    self.cutoff = cutoff

    self.radius = radius

    self.size = size

    self.box_width = box_width

    self.voxel_width = voxel_width

    self.voxels_per_edge = int(self.box_width / self.voxel_width)

    self.flatten = flatten



  def _featurize(self, mol_pdb: str, protein_pdb: str):

    """

    Compute featurization for a molecular complex



    Parameters

    ----------

    mol_pdb: str

      Filename for ligand molecule

    protein_pdb: str

      Filename for protein molecule

    """

    molecular_complex = (mol_pdb, protein_pdb)

    try:

      fragments = load_complex(molecular_complex, add_hydrogens=False)



    except MoleculeLoadException:

      logger.warning("This molecule cannot be loaded by Rdkit. Returning None")

      return None

    pairwise_features: List[np.ndarray] = []

    # We compute pairwise contact fingerprints

    centroid = compute_contact_centroid(fragments, cutoff=self.cutoff)

    for (frag1, frag2) in itertools.combinations(fragments, 2):

      distances = compute_pairwise_distances(frag1[0], frag2[0])

      frag1_xyz = subtract_centroid(frag1[0], centroid)

      frag2_xyz = subtract_centroid(frag2[0], centroid)

      xyzs = [frag1_xyz, frag2_xyz]

      pairwise_features.append(

          sum([

              voxelize(

                  convert_atom_to_voxel,

                  xyz,

                  self.box_width,

                  self.voxel_width,

                  hash_function=hash_ecfp,

                  feature_dict=ecfp_dict,

                  nb_channel=self.size) for xyz, ecfp_dict in zip(

                      xyzs,

                      featurize_contacts_ecfp(

                          frag1,

                          frag2,

                          distances,

                          cutoff=self.cutoff,

                          ecfp_degree=self.radius))

          ]))

    if self.flatten:

      return np.concatenate(

          [features.flatten() for features in pairwise_features])

    else:

      # Features are of shape (voxels_per_edge, voxels_per_edge,

      # voxels_per_edge, num_feat) so we should concatenate on the last

      # axis.

      return np.concatenate(pairwise_features, axis=-1)

deepchem/feat/complex_featurizers/grid_featurizers.py

0 → 100644
+633 −0

File added.

Preview size limit exceeded, changes collapsed.

CRA Git | Maintained and supported by SUSTech CRA and CCSE