improve type hinting throughout

deeprank2/domain/aminoacidlist.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from deeprank2.molstruct.aminoacid import AminoAcid, Polarity
 
 # All info below sourced from above websites in December 2022 and summarized in deeprank2/domain/aminoacid_summary.xlsx
@@ -352,7 +350,7 @@
     # pyrrolysine,
     ]
 
-def convert_aa_nomenclature(aa: str, output_type: Optional[int] = None):
+def convert_aa_nomenclature(aa: str, output_type: int | None = None):
     try:
         if len(aa) == 1:
             aa: AminoAcid = [entry for entry in amino_acids if entry.one_letter_code.lower() == aa.lower()][0]

deeprank2/features/components.py

@@ -1,5 +1,4 @@
 import logging
-from typing import Optional
 
 import numpy as np
 
@@ -12,9 +11,10 @@
 _log = logging.getLogger(__name__)
 
 def add_features( # pylint: disable=unused-argument
-    pdb_path: str, graph: Graph,
-    single_amino_acid_variant: Optional[SingleResidueVariant] = None
-    ):
+    pdb_path: str,
+    graph: Graph,
+    single_amino_acid_variant: SingleResidueVariant | None = None
+):
 
     for node in graph.nodes:
         if isinstance(node.id, Residue):

deeprank2/features/conservation.py

@@ -1,4 +1,3 @@
-from typing import Optional
 
 import numpy as np
 
@@ -10,9 +9,10 @@
 
 
 def add_features( # pylint: disable=unused-argument
-    pdb_path: str, graph: Graph,
-    single_amino_acid_variant: Optional[SingleResidueVariant] = None
-    ):
+    pdb_path: str,
+    graph: Graph,
+    single_amino_acid_variant: SingleResidueVariant | None = None
+):
 
     profile_amino_acid_order = sorted(amino_acids, key=lambda aa: aa.three_letter_code)
 

deeprank2/features/contact.py

@@ -1,9 +1,8 @@
 import logging
 import warnings
-from typing import List, Optional, Tuple
 
 import numpy as np
-import numpy.typing as npt
+from numpy.typing import NDArray
 from scipy.spatial import distance_matrix
 
 from deeprank2.domain import edgestorage as Efeat
@@ -21,21 +20,21 @@
 cutoff_14 = 4.2
 
 def _get_nonbonded_energy( #pylint: disable=too-many-locals
-    atoms: List[Atom],
-    distances: npt.NDArray[np.float64],
-    ) -> Tuple [npt.NDArray[np.float64], npt.NDArray[np.float64]]:
+    atoms: list[Atom],
+    distances: NDArray[np.float64],
+    ) -> tuple [NDArray[np.float64], NDArray[np.float64]]:
     """Calculates all pairwise electrostatic (Coulomb) and Van der Waals (Lennard Jones) potential energies between all atoms in the structure.
 
     Warning: there's no distance cutoff here. The radius of influence is assumed to infinite.
     However, the potential tends to 0 at large distance.
 
     Args:
-        atoms (List[Atom]): list of all atoms in the structure
-        distances (npt.NDArray[np.float64]): matrix of pairwise distances between all atoms in the structure
+        atoms (list[Atom]): list of all atoms in the structure
+        distances (NDArray[np.float64]): matrix of pairwise distances between all atoms in the structure
             in the format that is the output of scipy.spatial's distance_matrix (i.e. a diagonally symmetric matrix)
 
     Returns:
-        Tuple [npt.NDArray[np.float64], npt.NDArray[np.float64]]: matrices in same format as `distances` containing
+        Tuple [NDArray[np.float64], NDArray[np.float64]]: matrices in same format as `distances` containing
             all pairwise electrostatic potential energies and all pairwise Van der Waals potential energies
     """
 
@@ -76,9 +75,10 @@ def _get_nonbonded_energy( #pylint: disable=too-many-locals
 
 
 def add_features( # pylint: disable=unused-argument, too-many-locals
-    pdb_path: str, graph: Graph,
-    single_amino_acid_variant: Optional[SingleResidueVariant] = None
-    ):
+    pdb_path: str,
+    graph: Graph,
+    single_amino_acid_variant: SingleResidueVariant | None = None
+):
 
     # assign each atoms (from all edges) a unique index
     all_atoms = set()

deeprank2/features/exposure.py

@@ -2,7 +2,6 @@
 import signal
 import sys
 import warnings
-from typing import Optional
 
 import numpy as np
 from Bio.PDB.Atom import PDBConstructionWarning
@@ -34,9 +33,10 @@ def space_if_none(value):
 
 
 def add_features( # pylint: disable=unused-argument
-    pdb_path: str, graph: Graph,
-    single_amino_acid_variant: Optional[SingleResidueVariant] = None
-    ):
+    pdb_path: str,
+    graph: Graph,
+    single_amino_acid_variant: SingleResidueVariant | None = None
+):
 
     signal.signal(signal.SIGINT, handle_sigint)
     signal.signal(signal.SIGALRM, handle_timeout)

deeprank2/features/irc.py

@@ -1,6 +1,5 @@
 import logging
 from itertools import combinations_with_replacement as combinations
-from typing import Dict, List, Optional, Tuple
 
 import pdb2sql
 
@@ -14,7 +13,7 @@
 _log = logging.getLogger(__name__)
 
 
-def _id_from_residue(residue: Tuple[str, int, str]) -> str:
+def _id_from_residue(residue: tuple[str, int, str]) -> str:
     """Create and id from pdb2sql rendered residues that is similar to the id of residue nodes
 
     Args:
@@ -32,7 +31,7 @@ class _ContactDensity:
     """Internal class that holds contact density information for a given residue.
     """
 
-    def __init__(self, residue: Tuple[str, int, str], polarity: Polarity):
+    def __init__(self, residue: tuple[str, int, str], polarity: Polarity):
         self.res = residue
         self.polarity = polarity
         self.id = _id_from_residue(self.res)
@@ -42,12 +41,12 @@ def __init__(self, residue: Tuple[str, int, str], polarity: Polarity):
         self.connections['all'] = []
 
 
-def get_IRCs(pdb_path: str, chains: List[str], cutoff: float = 5.5) -> Dict[str, _ContactDensity]:
+def get_IRCs(pdb_path: str, chains: list[str], cutoff: float = 5.5) -> dict[str, _ContactDensity]:
     """Get all close contact residues from the opposite chain.
 
     Args:
         pdb_path (str): Path to pdb file to read molecular information from.
-        chains (Sequence[str]): List (or list-like object) containing strings of the chains to be considered.
+        chains (Sequence[str]): list (or list-like object) containing strings of the chains to be considered.
         cutoff (float, optional): Cutoff distance (in Ångström) to be considered a close contact. Defaults to 10.
 
     Returns:
@@ -56,7 +55,7 @@ def get_IRCs(pdb_path: str, chains: List[str], cutoff: float = 5.5) -> Dict[str,
             items: _ContactDensity objects, containing all contact density information for the residue.
     """
 
-    residue_contacts: Dict[str, _ContactDensity] = {}
+    residue_contacts: dict[str, _ContactDensity] = {}
 
     sql = pdb2sql.interface(pdb_path)
     pdb2sql_contacts = sql.get_contact_residues(
@@ -104,11 +103,12 @@ def get_IRCs(pdb_path: str, chains: List[str], cutoff: float = 5.5) -> Dict[str,
 
 
 def add_features(
-    pdb_path: str, graph: Graph,
-    single_amino_acid_variant: Optional[SingleResidueVariant] = None
-    ):
+    pdb_path: str,
+    graph: Graph,
+    single_amino_acid_variant: SingleResidueVariant | None = None
+):
 
-    if not single_amino_acid_variant: # VariantQueries do not use this feature
+    if not single_amino_acid_variant:  # VariantQueries do not use this feature
         polarity_pairs = list(combinations(Polarity, 2))
         polarity_pair_string = [f'irc_{x[0].name.lower()}_{x[1].name.lower()}' for x in polarity_pairs]
 

deeprank2/features/secondary_structure.py

@@ -1,6 +1,5 @@
 from enum import Enum
 from pathlib import Path
-from typing import Dict, List, Optional
 
 import numpy as np
 from Bio.PDB import PDBParser
@@ -31,7 +30,7 @@ def onehot(self):
         return t
 
 
-def _get_records(lines: List[str]):
+def _get_records(lines: list[str]):
     seen = set()
     seen_add = seen.add
     return [x.split()[0] for x in lines if not (x in seen or seen_add(x))]
@@ -82,7 +81,7 @@ def _classify_secstructure(subtype: str):
     return None
 
 
-def _get_secstructure(pdb_path: str) -> Dict:
+def _get_secstructure(pdb_path: str) -> dict:
     """Process the DSSP output to extract secondary structure information.
 
     Args:
@@ -124,8 +123,8 @@ def _get_secstructure(pdb_path: str) -> Dict:
 def add_features( # pylint: disable=unused-argument
     pdb_path: str,
     graph: Graph,
-    single_amino_acid_variant: Optional[SingleResidueVariant] = None
-    ):
+    single_amino_acid_variant: SingleResidueVariant | None = None
+):
 
     sec_structure_features = _get_secstructure(pdb_path)
 

deeprank2/features/surfacearea.py

@@ -1,5 +1,4 @@
 import logging
-from typing import Optional
 
 import freesasa
 import numpy as np
@@ -105,9 +104,10 @@ def add_bsa(graph: Graph):
 
 
 def add_features( # pylint: disable=unused-argument
-    pdb_path: str, graph: Graph,
-    single_amino_acid_variant: Optional[SingleResidueVariant] = None
-    ):
+    pdb_path: str,
+    graph: Graph,
+    single_amino_acid_variant: SingleResidueVariant | None = None
+):
 
     """calculates the Buried Surface Area (BSA) and the Solvent Accessible Surface Area (SASA):
     BSA: the area of the protein, that only gets exposed in monomeric state"""

deeprank2/molstruct/atom.py

@@ -3,6 +3,7 @@
 from enum import Enum
 
 import numpy as np
+from numpy.typing import NDArray
 
 from deeprank2.molstruct.residue import Residue
 
@@ -31,7 +32,7 @@ def __init__( # pylint: disable=too-many-arguments
         residue: Residue,
         name: str,
         element: AtomicElement,
-        position: np.array,
+        position: NDArray,
         occupancy: float,
     ):
         """
@@ -81,7 +82,7 @@ def occupancy(self) -> float:
         return self._occupancy
 
     @property
-    def position(self) -> np.array:
+    def position(self) -> NDArray:
         return self._position
 
     @property

deeprank2/molstruct/residue.py

@@ -1,8 +1,9 @@
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Optional
+from typing import TYPE_CHECKING
 
 import numpy as np
+from numpy.typing import NDArray
 
 from deeprank2.molstruct.aminoacid import AminoAcid
 from deeprank2.molstruct.structure import Chain
@@ -25,8 +26,8 @@ def __init__(
         self,
         chain: Chain,
         number: int,
-        amino_acid: Optional[AminoAcid] = None,
-        insertion_code: Optional[str] = None,
+        amino_acid: AminoAcid | None = None,
+        insertion_code: str | None = None,
     ):
         """
         Args:
@@ -98,7 +99,7 @@ def __repr__(self) -> str:
     def position(self) -> np.array:
         return np.mean([atom.position for atom in self._atoms], axis=0)
 
-    def get_center(self) -> np.ndarray:
+    def get_center(self) -> NDArray:
         """Find the center position of a `Residue`.
 
         Center position is found as follows:

deeprank2/molstruct/structure.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Optional
+from typing import TYPE_CHECKING
 
 from deeprank2.utils.pssmdata import PssmRow
 
@@ -18,7 +18,7 @@ class PDBStructure:
     particular `AminoAcid` type and in turn consists of a number of `Atom`s.
     """
 
-    def __init__(self, id_: Optional[str] = None):
+    def __init__(self, id_: str | None = None):
         """
         Args:
             id_ (str, optional): An unique identifier for this structure, can be the pdb accession code.
@@ -72,7 +72,7 @@ class Chain:
     In other words: each `Chain` in a `PDBStructure` is a separate molecule.
     """
 
-    def __init__(self, model: PDBStructure, id_: Optional[str]):
+    def __init__(self, model: PDBStructure, id_: str | None):
         """One chain of a PDBStructure.
 
             Args:
@@ -99,10 +99,10 @@ def pssm(self, pssm: PssmRow):
     def add_residue(self, residue: Residue):
         self._residues[(residue.number, residue.insertion_code)] = residue
 
-    def has_residue(self, residue_number: int, insertion_code: Optional[str] = None) -> bool:
+    def has_residue(self, residue_number: int, insertion_code: str | None = None) -> bool:
         return (residue_number, insertion_code) in self._residues
 
-    def get_residue(self, residue_number: int, insertion_code: Optional[str] = None) -> Residue:
+    def get_residue(self, residue_number: int, insertion_code: str | None = None) -> Residue:
         return self._residues[(residue_number, insertion_code)]
 
     @property

deeprank2/neuralnets/cnn/model3d.py

@@ -1,5 +1,3 @@
-from typing import Tuple
-
 import torch
 import torch.nn
 import torch.nn.functional as F
@@ -25,7 +23,7 @@
 
 class CnnRegression(torch.nn.Module):
 
-    def __init__(self, num_features: int, box_shape: Tuple[int]):
+    def __init__(self, num_features: int, box_shape: tuple[int]):
         super().__init__()
 
         self.convlayer_000 = torch.nn.Conv3d(num_features, 4, kernel_size=2)
@@ -38,7 +36,7 @@ def __init__(self, num_features: int, box_shape: Tuple[int]):
         self.fclayer_000 = torch.nn.Linear(size, 84)
         self.fclayer_001 = torch.nn.Linear(84, 1)
 
-    def _get_conv_output(self, num_features: int, shape: Tuple[int]):
+    def _get_conv_output(self, num_features: int, shape: tuple[int]):
         num_data_points = 2
         input_ = Variable(torch.rand(num_data_points, num_features, *shape))
         output = self._forward_features(input_)