fix linting according to ruff

DeepRank · Jan 15, 2024 · 3343756 · 3343756
1 parent 68ee7a6
commit 3343756
Show file tree

Hide file tree

Showing 60 changed files with 529 additions and 1,583 deletions.
diff --git a/deeprank2/dataset.py b/deeprank2/dataset.py
diff --git a/deeprank2/domain/aminoacidlist.py b/deeprank2/domain/aminoacidlist.py
@@ -372,33 +372,19 @@
     # pyrrolysine,
 ]
 
-amino_acids_by_code = {
-    amino_acid.three_letter_code: amino_acid for amino_acid in amino_acids
-}
-amino_acids_by_letter = {
-    amino_acid.one_letter_code: amino_acid for amino_acid in amino_acids
-}
+amino_acids_by_code = {amino_acid.three_letter_code: amino_acid for amino_acid in amino_acids}
+amino_acids_by_letter = {amino_acid.one_letter_code: amino_acid for amino_acid in amino_acids}
 amino_acids_by_name = {amino_acid.name: amino_acid for amino_acid in amino_acids}
 
 
 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]
+            aa: AminoAcid = [entry for entry in amino_acids if entry.one_letter_code.lower() == aa.lower()][0]
         elif len(aa) == 3:
-            aa: AminoAcid = [
-                entry
-                for entry in amino_acids
-                if entry.three_letter_code.lower() == aa.lower()
-            ][0]
+            aa: AminoAcid = [entry for entry in amino_acids if entry.three_letter_code.lower() == aa.lower()][0]
         else:
-            aa: AminoAcid = [
-                entry for entry in amino_acids if entry.name.lower() == aa.lower()
-            ][0]
+            aa: AminoAcid = [entry for entry in amino_acids if entry.name.lower() == aa.lower()][0]
     except IndexError as e:
         raise ValueError(f"{aa} is not a valid amino acid.") from e
 
@@ -408,6 +394,4 @@ def convert_aa_nomenclature(aa: str, output_type: int | None = None):
         return aa.three_letter_code
     if output_type == 1:
         return aa.one_letter_code
-    raise ValueError(
-        f"output_type {output_type} not recognized. Must be set to None (amino acid name), 1 (one letter code), or 3 (three letter code)."
-    )
+    raise ValueError(f"output_type {output_type} not recognized. Must be set to None (amino acid name), 1 (one letter code), or 3 (three letter code).")
diff --git a/deeprank2/domain/nodestorage.py b/deeprank2/domain/nodestorage.py
@@ -29,9 +29,7 @@
 DIFFPI = "diff_pI"
 DIFFPOLARITY = "diff_polarity"  # [type?]; former FEATURENAME_POLARITYDIFFERENCE
 DIFFHBDONORS = "diff_hb_donors"  # int; former FEATURENAME_HYDROGENBONDDONORSDIFFERENCE
-DIFFHBACCEPTORS = (
-    "diff_hb_acceptors"  # int; former FEATURENAME_HYDROGENBONDACCEPTORSDIFFERENCE
-)
+DIFFHBACCEPTORS = "diff_hb_acceptors"  # int; former FEATURENAME_HYDROGENBONDACCEPTORSDIFFERENCE
 
 ## conservation features
 PSSM = "pssm"  # list[20xint]; former FEATURENAME_PSSM

diff --git a/deeprank2/features/components.py b/deeprank2/features/components.py
@@ -45,24 +45,16 @@ def add_features(  # pylint: disable=unused-argument
             if residue == single_amino_acid_variant.residue:
                 node.features[Nfeat.VARIANTRES] = variant.onehot
                 node.features[Nfeat.DIFFCHARGE] = variant.charge - wildtype.charge
-                node.features[Nfeat.DIFFPOLARITY] = (
-                    variant.polarity.onehot - wildtype.polarity.onehot
-                )
+                node.features[Nfeat.DIFFPOLARITY] = variant.polarity.onehot - wildtype.polarity.onehot
                 node.features[Nfeat.DIFFSIZE] = variant.size - wildtype.size
                 node.features[Nfeat.DIFFMASS] = variant.mass - wildtype.mass
                 node.features[Nfeat.DIFFPI] = variant.pI - wildtype.pI
-                node.features[Nfeat.DIFFHBDONORS] = (
-                    variant.hydrogen_bond_donors - wildtype.hydrogen_bond_donors
-                )
-                node.features[Nfeat.DIFFHBACCEPTORS] = (
-                    variant.hydrogen_bond_acceptors - wildtype.hydrogen_bond_acceptors
-                )
+                node.features[Nfeat.DIFFHBDONORS] = variant.hydrogen_bond_donors - wildtype.hydrogen_bond_donors
+                node.features[Nfeat.DIFFHBACCEPTORS] = variant.hydrogen_bond_acceptors - wildtype.hydrogen_bond_acceptors
             else:
                 node.features[Nfeat.VARIANTRES] = residue.amino_acid.onehot
                 node.features[Nfeat.DIFFCHARGE] = 0
-                node.features[Nfeat.DIFFPOLARITY] = np.zeros(
-                    residue.amino_acid.polarity.onehot.shape
-                )
+                node.features[Nfeat.DIFFPOLARITY] = np.zeros(residue.amino_acid.polarity.onehot.shape)
                 node.features[Nfeat.DIFFSIZE] = 0
                 node.features[Nfeat.DIFFMASS] = 0
                 node.features[Nfeat.DIFFPI] = 0

diff --git a/deeprank2/features/conservation.py b/deeprank2/features/conservation.py
@@ -24,28 +24,17 @@ def add_features(  # pylint: disable=unused-argument
             raise TypeError(f"Unexpected node type: {type(node.id)}")
 
         pssm_row = residue.get_pssm()
-        profile = np.array(
-            [
-                pssm_row.get_conservation(amino_acid)
-                for amino_acid in profile_amino_acid_order
-            ]
-        )
+        profile = np.array([pssm_row.get_conservation(amino_acid) for amino_acid in profile_amino_acid_order])
         node.features[Nfeat.PSSM] = profile
         node.features[Nfeat.INFOCONTENT] = pssm_row.information_content
 
         if single_amino_acid_variant is not None:
             if residue == single_amino_acid_variant.residue:
                 # only the variant residue can have a variant and wildtype amino acid
-                conservation_wildtype = pssm_row.get_conservation(
-                    single_amino_acid_variant.wildtype_amino_acid
-                )
-                conservation_variant = pssm_row.get_conservation(
-                    single_amino_acid_variant.variant_amino_acid
-                )
+                conservation_wildtype = pssm_row.get_conservation(single_amino_acid_variant.wildtype_amino_acid)
+                conservation_variant = pssm_row.get_conservation(single_amino_acid_variant.variant_amino_acid)
                 node.features[Nfeat.CONSERVATION] = conservation_wildtype
-                node.features[Nfeat.DIFFCONSERVATION] = (
-                    conservation_variant - conservation_wildtype
-                )
+                node.features[Nfeat.DIFFCONSERVATION] = conservation_variant - conservation_wildtype
             else:
                 # all nodes must have the same features, so set them to zero here
                 node.features[Nfeat.CONSERVATION] = 0.0

diff --git a/deeprank2/features/contact.py b/deeprank2/features/contact.py
@@ -38,49 +38,26 @@ def _get_nonbonded_energy(  # pylint: disable=too-many-locals
         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
     """
-
     # ELECTROSTATIC POTENTIAL
     EPSILON0 = 1.0
     COULOMB_CONSTANT = 332.0636
     charges = [atomic_forcefield.get_charge(atom) for atom in atoms]
-    E_elec = (
-        np.expand_dims(charges, axis=1)
-        * np.expand_dims(charges, axis=0)
-        * COULOMB_CONSTANT
-        / (EPSILON0 * distances)
-    )
+    E_elec = np.expand_dims(charges, axis=1) * np.expand_dims(charges, axis=0) * COULOMB_CONSTANT / (EPSILON0 * distances)
 
     # VAN DER WAALS POTENTIAL
     # calculate main vdw energies
-    sigmas = [
-        atomic_forcefield.get_vanderwaals_parameters(atom).sigma_main for atom in atoms
-    ]
-    epsilons = [
-        atomic_forcefield.get_vanderwaals_parameters(atom).epsilon_main
-        for atom in atoms
-    ]
+    sigmas = [atomic_forcefield.get_vanderwaals_parameters(atom).sigma_main for atom in atoms]
+    epsilons = [atomic_forcefield.get_vanderwaals_parameters(atom).epsilon_main for atom in atoms]
     mean_sigmas = 0.5 * np.add.outer(sigmas, sigmas)
     geomean_eps = np.sqrt(np.multiply.outer(epsilons, epsilons))  # sqrt(eps1*eps2)
-    E_vdw = (
-        4.0
-        * geomean_eps
-        * ((mean_sigmas / distances) ** 12 - (mean_sigmas / distances) ** 6)
-    )
+    E_vdw = 4.0 * geomean_eps * ((mean_sigmas / distances) ** 12 - (mean_sigmas / distances) ** 6)
 
     # calculate vdw energies for 1-4 pairs
-    sigmas = [
-        atomic_forcefield.get_vanderwaals_parameters(atom).sigma_14 for atom in atoms
-    ]
-    epsilons = [
-        atomic_forcefield.get_vanderwaals_parameters(atom).epsilon_14 for atom in atoms
-    ]
+    sigmas = [atomic_forcefield.get_vanderwaals_parameters(atom).sigma_14 for atom in atoms]
+    epsilons = [atomic_forcefield.get_vanderwaals_parameters(atom).epsilon_14 for atom in atoms]
     mean_sigmas = 0.5 * np.add.outer(sigmas, sigmas)
     geomean_eps = np.sqrt(np.multiply.outer(epsilons, epsilons))  # sqrt(eps1*eps2)
-    E_vdw_14pairs = (
-        4.0
-        * geomean_eps
-        * ((mean_sigmas / distances) ** 12 - (mean_sigmas / distances) ** 6)
-    )
+    E_vdw_14pairs = 4.0 * geomean_eps * ((mean_sigmas / distances) ** 12 - (mean_sigmas / distances) ** 6)
 
     # Fix energies for close contacts on same chain
     chains = [atom.residue.chain.id for atom in atoms]
@@ -137,51 +114,21 @@ def add_features(  # pylint: disable=unused-argument, too-many-locals
             atom1_index = atom_dict[contact.atom1]
             atom2_index = atom_dict[contact.atom2]
             ## set features
-            edge.features[Efeat.SAMERES] = float(
-                contact.atom1.residue == contact.atom2.residue
-            )
-            edge.features[Efeat.SAMECHAIN] = float(
-                contact.atom1.residue.chain == contact.atom1.residue.chain
-            )
-            edge.features[Efeat.DISTANCE] = interatomic_distances[
-                atom1_index, atom2_index
-            ]
-            edge.features[Efeat.ELEC] = interatomic_electrostatic_energy[
-                atom1_index, atom2_index
-            ]
-            edge.features[Efeat.VDW] = interatomic_vanderwaals_energy[
-                atom1_index, atom2_index
-            ]
+            edge.features[Efeat.SAMERES] = float(contact.atom1.residue == contact.atom2.residue)
+            edge.features[Efeat.SAMECHAIN] = float(contact.atom1.residue.chain == contact.atom1.residue.chain)
+            edge.features[Efeat.DISTANCE] = interatomic_distances[atom1_index, atom2_index]
+            edge.features[Efeat.ELEC] = interatomic_electrostatic_energy[atom1_index, atom2_index]
+            edge.features[Efeat.VDW] = interatomic_vanderwaals_energy[atom1_index, atom2_index]
 
         elif isinstance(contact, ResidueContact):
             ## find the indices
             atom1_indices = [atom_dict[atom] for atom in contact.residue1.atoms]
             atom2_indices = [atom_dict[atom] for atom in contact.residue2.atoms]
             ## set features
-            edge.features[Efeat.SAMECHAIN] = float(
-                contact.residue1.chain == contact.residue2.chain
-            )
-            edge.features[Efeat.DISTANCE] = np.min(
-                [
-                    [interatomic_distances[a1, a2] for a1 in atom1_indices]
-                    for a2 in atom2_indices
-                ]
-            )
-            edge.features[Efeat.ELEC] = np.sum(
-                [
-                    [interatomic_electrostatic_energy[a1, a2] for a1 in atom1_indices]
-                    for a2 in atom2_indices
-                ]
-            )
-            edge.features[Efeat.VDW] = np.sum(
-                [
-                    [interatomic_vanderwaals_energy[a1, a2] for a1 in atom1_indices]
-                    for a2 in atom2_indices
-                ]
-            )
+            edge.features[Efeat.SAMECHAIN] = float(contact.residue1.chain == contact.residue2.chain)
+            edge.features[Efeat.DISTANCE] = np.min([[interatomic_distances[a1, a2] for a1 in atom1_indices] for a2 in atom2_indices])
+            edge.features[Efeat.ELEC] = np.sum([[interatomic_electrostatic_energy[a1, a2] for a1 in atom1_indices] for a2 in atom2_indices])
+            edge.features[Efeat.VDW] = np.sum([[interatomic_vanderwaals_energy[a1, a2] for a1 in atom1_indices] for a2 in atom2_indices])
 
         # Calculate irrespective of node type
-        edge.features[Efeat.COVALENT] = float(
-            edge.features[Efeat.DISTANCE] < covalent_cutoff
-            and edge.features[Efeat.SAMECHAIN]
-        )
+        edge.features[Efeat.COVALENT] = float(edge.features[Efeat.DISTANCE] < covalent_cutoff and edge.features[Efeat.SAMECHAIN])
diff --git a/deeprank2/features/irc.py b/deeprank2/features/irc.py
@@ -14,7 +14,7 @@
 
 
 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
+    """Create and id from pdb2sql rendered residues that is similar to the id of residue nodes.
 
     Args:
         residue (tuple): Input residue as rendered by pdb2sql: ( str(<chain>), int(<residue_number>), str(<three_letter_code> )
@@ -23,7 +23,6 @@ def _id_from_residue(residue: tuple[str, int, str]) -> str:
     Returns:
         str: Output id in form of '<chain><residue_number>'. For example: 'A27'.
     """
-
     return residue[0] + str(residue[1])
 
 
@@ -40,9 +39,7 @@ 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:
@@ -55,7 +52,6 @@ def get_IRCs(
             keys: ids of residues in form returned by id_from_residue.
             items: _ContactDensity objects, containing all contact density information for the residue.
     """
-
     residue_contacts: dict[str, _ContactDensity] = {}
 
     sql = pdb2sql.interface(pdb_path)
@@ -93,9 +89,7 @@ def get_IRCs(
             # add chain2_res to residue_contact dict if it doesn't exist yet
             contact2_id = _id_from_residue(chain2_res)
             if contact2_id not in residue_contacts:
-                residue_contacts[contact2_id] = _ContactDensity(
-                    chain2_res, aa2.polarity
-                )
+                residue_contacts[contact2_id] = _ContactDensity(chain2_res, aa2.polarity)
 
             # populate densities and connections for chain2_res
             residue_contacts[contact2_id].densities["total"] += 1
@@ -113,9 +107,7 @@ def add_features(
 ):
     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
-        ]
+        polarity_pair_string = [f"irc_{x[0].name.lower()}_{x[1].name.lower()}" for x in polarity_pairs]
 
         total_contacts = 0
         residue_contacts = get_IRCs(pdb_path, graph.get_all_chains())
@@ -129,28 +121,20 @@ def add_features(
             else:
                 raise TypeError(f"Unexpected node type: {type(node.id)}")
 
-            contact_id = (
-                residue.chain.id + residue.number_string
-            )  # reformat id to be in line with residue_contacts keys
+            contact_id = residue.chain.id + residue.number_string  # reformat id to be in line with residue_contacts keys
 
             # initialize all IRC features to 0
             for IRC_type in Nfeat.IRC_FEATURES:
                 node.features[IRC_type] = 0
 
             # load correct values to IRC features
             try:
-                node.features[Nfeat.IRCTOTAL] = residue_contacts[contact_id].densities[
-                    "total"
-                ]
+                node.features[Nfeat.IRCTOTAL] = residue_contacts[contact_id].densities["total"]
                 for i, pair in enumerate(polarity_pairs):
                     if residue_contacts[contact_id].polarity == pair[0]:
-                        node.features[polarity_pair_string[i]] = residue_contacts[
-                            contact_id
-                        ].densities[pair[1]]
+                        node.features[polarity_pair_string[i]] = residue_contacts[contact_id].densities[pair[1]]
                     elif residue_contacts[contact_id].polarity == pair[1]:
-                        node.features[polarity_pair_string[i]] = residue_contacts[
-                            contact_id
-                        ].densities[pair[0]]
+                        node.features[polarity_pair_string[i]] = residue_contacts[contact_id].densities[pair[0]]
                 total_contacts += 1
             except KeyError:  # node has no contact residues and all counts remain 0
                 pass

diff --git a/deeprank2/features/secondary_structure.py b/deeprank2/features/secondary_structure.py
@@ -12,11 +12,11 @@
 
 
 class DSSPError(Exception):
-    "Raised if DSSP fails to produce an output"
+    """Raised if DSSP fails to produce an output."""
 
 
 class SecondarySctructure(Enum):
-    "a value to express a secondary a residue's secondary structure type"
+    """Value to express a secondary a residue's secondary structure type."""
 
     HELIX = 0  # 'GHI'
     STRAND = 1  # 'BE'
@@ -54,9 +54,7 @@ def _check_pdb(pdb_path: str):
     existing_records = _get_records(lines)
     if "CRYST1" not in existing_records:
         fix_pdb = True
-        dummy_CRYST1 = (
-            "CRYST1   00.000   00.000   00.000  00.00  00.00  00.00 X 00 00 0    00\n"
-        )
+        dummy_CRYST1 = "CRYST1   00.000   00.000   00.000  00.00  00.00  00.00 X 00 00 0    00\n"
         lines = [lines[0]] + [dummy_CRYST1] + lines[1:]
 
     # check for unnumbered REMARK lines
@@ -92,7 +90,6 @@ def _get_secstructure(pdb_path: str) -> dict:
     Returns:
         dict: A dictionary containing secondary structure information for each chain and residue.
     """
-
     # Execute DSSP and read the output
     _check_pdb(pdb_path)
     p = PDBParser(QUIET=True)
@@ -108,7 +105,7 @@ def _get_secstructure(pdb_path: str) -> dict:
             \nThis is likely due to an improrperly formatted pdb file: {pdb_path}.\
             \nSee {pdb_format_link} for guidance on how to format your pdb files.\
             \nAlternatively, turn off secondary_structure feature module during QueryCollection.process()."
-        )
+        ) from e
 
     chain_ids = [dssp_key[0] for dssp_key in dssp.property_keys]
     res_numbers = [dssp_key[1][1] for dssp_key in dssp.property_keys]
@@ -145,11 +142,8 @@ def add_features(  # pylint: disable=unused-argument
 
         # pylint: disable=raise-missing-from
         try:
-            node.features[Nfeat.SECSTRUCT] = _classify_secstructure(
-                sec_structure_features[chain_id][res_num]
-            ).onehot
-        except AttributeError:
+            node.features[Nfeat.SECSTRUCT] = _classify_secstructure(sec_structure_features[chain_id][res_num]).onehot
+        except AttributeError as e:
             raise ValueError(
-                f"Unknown secondary structure type ({sec_structure_features[chain_id][res_num]}) "
-                + f"detected on chain {chain_id} residues {res_num}."
-            )
+                f"Unknown secondary structure type ({sec_structure_features[chain_id][res_num]}) " + f"detected on chain {chain_id} residues {res_num}."
+            ) from e