Merge pull request #2090 from nd-02110114/fix-base-classes-feat

Add canonicalize option to MolecularFeaturizer
deepchem · Aug 18, 2020 · ab91135 · ab91135
2 parents 9c879e4 + c94fa0b
commit ab91135
Show file tree

Hide file tree

Showing 20 changed files with 232 additions and 251 deletions.
diff --git a/deepchem/dock/binding_pocket.py b/deepchem/dock/binding_pocket.py
@@ -22,11 +22,11 @@ def extract_active_site(protein_file: str,
 
   Parameters
   ----------
-  protein_file : str
+  protein_file: str
     Location of protein PDB
-  ligand_file : str
+  ligand_file: str
     Location of ligand input file
-  cutoff : float, optional (default 4.0)
+  cutoff: float, optional (default 4.0)
     The distance in angstroms from the protein pocket to
     consider for featurization.
 
@@ -73,7 +73,7 @@ def find_pockets(self, molecule: Any):
 
     Parameters
     ----------
-    molecule : object
+    molecule: object
       Some representation of a molecule.
     """
     raise NotImplementedError
@@ -90,9 +90,9 @@ def __init__(self, scoring_model: Optional[Model] = None, pad: float = 5.0):
 
     Parameters
     ----------
-    scoring_model : Model, optional (default None)
+    scoring_model: Model, optional (default None)
       If specified, use this model to prune pockets.
-    pad : float, optional (default 5.0)
+    pad: float, optional (default 5.0)
       The number of angstroms to pad around a binding pocket's atoms
       to get a binding pocket box.
     """
@@ -104,7 +104,7 @@ def find_all_pockets(self, protein_file: str) -> List[CoordinateBox]:
 
     Parameters
     ----------
-    protein_file : str
+    protein_file: str
       Protein to load in.
 
     Returns
@@ -125,7 +125,7 @@ def find_pockets(self, macromolecule_file: str) -> List[CoordinateBox]:
 
     Parameters
     ----------
-    macromolecule_file : str
+    macromolecule_file: str
       Location of the macromolecule file to load
 
     Returns

diff --git a/deepchem/dock/docking.py b/deepchem/dock/docking.py
@@ -38,11 +38,11 @@ def __init__(self,
 
     Parameters
     ----------
-    pose_generator : PoseGenerator
+    pose_generator: PoseGenerator
       The pose generator to use for this model
-    featurizer : ComplexFeaturizer, optional (default None)
+    featurizer: ComplexFeaturizer, optional (default None)
       Featurizer associated with `scoring_model`
-    scoring_model : Model, optional (default None)
+    scoring_model: Model, optional (default None)
       Should make predictions on molecular complex.
     """
     if ((featurizer is not None and scoring_model is None) or
@@ -73,27 +73,27 @@ def dock(self,
 
     Parameters
     ----------
-    molecular_complex : Tuple[str, str]
+    molecular_complex: Tuple[str, str]
       A representation of a molecular complex. This tuple is
       (protein_file, ligand_file).
-    centroid : np.ndarray, optional (default None)
+    centroid: np.ndarray, optional (default None)
       The centroid to dock against. Is computed if not specified.
-    box_dims : np.ndarray, optional (default None)
+    box_dims: np.ndarray, optional (default None)
       A numpy array of shape `(3,)` holding the size of the box to dock. If not
       specified is set to size of molecular complex plus 5 angstroms.
-    exhaustiveness : int, optional (default 10)
+    exhaustiveness: int, optional (default 10)
       Tells pose generator how exhaustive it should be with pose
       generation.
-    num_modes : int, optional (default 9)
+    num_modes: int, optional (default 9)
       Tells pose generator how many binding modes it should generate at
       each invocation.
-    num_pockets : int, optional (default None)
+    num_pockets: int, optional (default None)
       If specified, `self.pocket_finder` must be set. Will only
       generate poses for the first `num_pockets` returned by
       `self.pocket_finder`.
-    out_dir : str, optional (default None)
+    out_dir: str, optional (default None)
       If specified, write generated poses to this directory.
-    use_pose_generator_scores : bool, optional (default False)
+    use_pose_generator_scores: bool, optional (default False)
       If `True`, ask pose generator to generate scores. This cannot be
       `True` if `self.featurizer` and `self.scoring_model` are set
       since those will be used to generate scores in that case.

diff --git a/deepchem/dock/pose_generation.py b/deepchem/dock/pose_generation.py
@@ -47,27 +47,27 @@ def generate_poses(self,
 
     Parameters
     ----------
-    molecular_complexes : Tuple[str, str]
+    molecular_complexes: Tuple[str, str]
       A representation of a molecular complex. This tuple is
       (protein_file, ligand_file).
-    centroid : np.ndarray, optional (default None)
+    centroid: np.ndarray, optional (default None)
       The centroid to dock against. Is computed if not specified.
-    box_dims : np.ndarray, optional (default None)
+    box_dims: np.ndarray, optional (default None)
       A numpy array of shape `(3,)` holding the size of the box to dock. If not
       specified is set to size of molecular complex plus 5 angstroms.
-    exhaustiveness : int, optional (default 10)
+    exhaustiveness: int, optional (default 10)
       Tells pose generator how exhaustive it should be with pose
       generation.
-    num_modes : int, optional (default 9)
+    num_modes: int, optional (default 9)
       Tells pose generator how many binding modes it should generate at
       each invocation.
-    num_pockets : int, optional (default None)
+    num_pockets: int, optional (default None)
       If specified, `self.pocket_finder` must be set. Will only
       generate poses for the first `num_pockets` returned by
       `self.pocket_finder`.
-    out_dir : str, optional (default None)
+    out_dir: str, optional (default None)
       If specified, write generated poses to this directory.
-    generate_score : bool, optional (default False)
+    generate_score: bool, optional (default False)
       If `True`, the pose generator will return scores for complexes.
       This is used typically when invoking external docking programs
       that compute scores.
@@ -88,8 +88,8 @@ class VinaPoseGenerator(PoseGenerator):
   is an environment variable you set) and invokes the executable
   to perform pose generation for you.
 
-  Notes
-  -----
+  Note
+  ----
   This class requires RDKit to be installed.
   """
 

diff --git a/deepchem/dock/pose_scoring.py b/deepchem/dock/pose_scoring.py
@@ -9,9 +9,9 @@ def pairwise_distances(coords1: np.ndarray, coords2: np.ndarray) -> np.ndarray:
 
   Parameters
   ----------
-  coords1 : np.ndarray
+  coords1: np.ndarray
     A numpy array of shape `(N, 3)`
-  coords2 : np.ndarray
+  coords2: np.ndarray
     A numpy array of shape `(M, 3)`
 
   Returns
@@ -27,11 +27,11 @@ def cutoff_filter(d: np.ndarray, x: np.ndarray, cutoff=8.0) -> np.ndarray:
 
   Parameters
   ----------
-  d : np.ndarray
+  d: np.ndarray
     Pairwise distances matrix. A numpy array of shape `(N, M)`
-  x : np.ndarray
+  x: np.ndarray
     Matrix of shape `(N, M)`
-  cutoff : float, optional (default 8)
+  cutoff: float, optional (default 8)
     Cutoff for selection in Angstroms
 
   Returns
@@ -47,11 +47,11 @@ def vina_nonlinearity(c: np.ndarray, w: float, Nrot: int) -> np.ndarray:
 
   Parameters
   ----------
-  c : np.ndarray
+  c: np.ndarray
     A numpy array of shape `(N, M)`
-  w : float
+  w: float
     Weighting term
-  Nrot : int
+  Nrot: int
     Number of rotatable bonds in this molecule
 
   Returns
@@ -68,7 +68,7 @@ def vina_repulsion(d: np.ndarray) -> np.ndarray:
 
   Parameters
   ----------
-  d : np.ndarray
+  d: np.ndarray
     A numpy array of shape `(N, M)`.
 
   Returns
@@ -86,7 +86,7 @@ def vina_hydrophobic(d: np.ndarray) -> np.ndarray:
 
   Parameters
   ----------
-  d : np.ndarray
+  d: np.ndarray
     A numpy array of shape `(N, M)`.
 
   Returns
@@ -112,7 +112,7 @@ def vina_hbond(d: np.ndarray) -> np.ndarray:
 
   Parameters
   ----------
-  d : np.ndarray
+  d: np.ndarray
     A numpy array of shape `(N, M)`.
 
   Returns
@@ -139,7 +139,7 @@ def vina_gaussian_first(d: np.ndarray) -> np.ndarray:
 
   Parameters
   ----------
-  d : np.ndarray
+  d: np.ndarray
     A numpy array of shape `(N, M)`.
 
   Returns
@@ -164,7 +164,7 @@ def vina_gaussian_second(d: np.ndarray) -> np.ndarray:
 
   Parameters
   ----------
-  d : np.ndarray
+  d: np.ndarray
     A numpy array of shape `(N, M)`.
 
   Returns
@@ -187,9 +187,9 @@ def weighted_linear_sum(w: np.ndarray, x: np.ndarray) -> np.ndarray:
 
   Parameters
   ----------
-  w : np.ndarray
+  w: np.ndarray
     A numpy array of shape `(N,)`
-  x : np.ndarray
+  x: np.ndarray
     A numpy array of shape `(N,)`
 
   Returns
@@ -206,15 +206,15 @@ def vina_energy_term(coords1: np.ndarray, coords2: np.ndarray,
 
   Parameters
   ----------
-  coords1 : np.ndarray
+  coords1: np.ndarray
     Molecular coordinates of shape `(N, 3)`
-  coords2 : np.ndarray
+  coords2: np.ndarray
     Molecular coordinates of shape `(M, 3)`
-  weights : np.ndarray
+  weights: np.ndarray
     A numpy array of shape `(5,)`
-  wrot : float
+  wrot: float
     The scaling factor for nonlinearity
-  Nrot : int
+  Nrot: int
     Number of rotatable bonds in this calculation
 
   Returns