update max_edge_length and influence_radius

previously `max_edge_distance` and `interaction_radius`, respectively

deeprank2/query.py

@@ -49,9 +49,9 @@ class Query:
             Note that this does not limit the structure to residues from this/these chain(s).
         pssm_paths (dict[str, str]): the name of the chain(s) (key) and path to the pssm file(s) (value).
         targets (dict[str, float]) = Name(s) (key) and target value(s) (value) associated with this query.
-        interaction_radius (float | None): all residues within this radius from the variant residue or interacting interfaces
+        influence_radius (float | None): all residues within this radius from the variant residue or interacting interfaces
             will be included in the graph, irrespective of the chain they are on.
-        max_edge_distance (float | None): the maximum distance between two nodes to generate an edge connecting them.
+        max_edge_length (float | None): the maximum distance between two nodes to generate an edge connecting them.
         suppress_pssm_errors (bool): Whether or not to suppress the error raised if the .pssm files do not
             match the .pdb files. If True, a warning is returned instead.
     """
@@ -61,20 +61,20 @@ class Query:
     chain_ids: list[str] | str
     pssm_paths: dict[str, str] = field(default_factory=dict)
     targets: dict[str, float] = field(default_factory=dict)
-    interaction_radius: float | None = None
-    max_edge_distance: float | None = None
+    influence_radius: float | None = None
+    max_edge_length: float | None = None
     suppress_pssm_errors: bool = False
 
     def __post_init__(self):
         self._model_id = os.path.splitext(os.path.basename(self.pdb_path))[0]
         self.variant = None  # not used for PPI, overwritten for SRV
 
         if self.resolution == 'residue':
-            self.max_edge_distance = 10 if not self.max_edge_distance else self.max_edge_distance
-            self.interaction_radius = 10 if not self.interaction_radius else self.interaction_radius
+            self.max_edge_length = 10 if not self.max_edge_length else self.max_edge_length
+            self.influence_radius = 10 if not self.influence_radius else self.influence_radius
         elif self.resolution == 'atom':
-            self.max_edge_distance = 4.5 if not self.max_edge_distance else self.max_edge_distance
-            self.interaction_radius = 4.5 if not self.interaction_radius else self.interaction_radius
+            self.max_edge_length = 4.5 if not self.max_edge_length else self.max_edge_length
+            self.influence_radius = 4.5 if not self.influence_radius else self.influence_radius
         else:
             raise ValueError(f"Invalid resolution given ({self.resolution}). Must be one of {VALID_RESOLUTIONS}")
 
@@ -228,9 +228,9 @@ class SingleResidueVariantQuery(Query):
             Note that this does not limit the structure to residues from this chain.
         pssm_paths (dict[str, str]): the name of the chain(s) (key) and path to the pssm file(s) (value).
         targets (dict[str, float]) = Name(s) (key) and target value(s) (value) associated with this query.
-        interaction_radius (float | None): all residues within this radius from the variant residue
+        influence_radius (float | None): all residues within this radius from the variant residue
             will be included in the graph, irrespective of the chain they are on.
-        max_edge_distance (float | None): the maximum distance between two nodes to generate an edge connecting them.
+        max_edge_length (float | None): the maximum distance between two nodes to generate an edge connecting them.
 
         suppress_pssm_errors (bool): Whether or not to suppress the error raised if the .pssm files do not
             match the .pdb files. If True, a warning is returned instead.
@@ -294,11 +294,11 @@ def _build_helper(self) -> Graph:
                 f"Residue not found in {self.pdb_path}: {self.variant_chain_id} {self.residue_id}"
             )
         self.variant = SingleResidueVariant(variant_residue, self.variant_amino_acid)
-        residues = get_surrounding_residues(structure, variant_residue, self.interaction_radius)
+        residues = get_surrounding_residues(structure, variant_residue, self.influence_radius)
 
         # build the graph
         if self.resolution == 'residue':
-            graph = build_residue_graph(residues, self.get_query_id(), self.max_edge_distance)
+            graph = build_residue_graph(residues, self.get_query_id(), self.max_edge_length)
         elif self.resolution == 'atom':
             residues.append(variant_residue)
             atoms = set([])
@@ -308,7 +308,7 @@ def _build_helper(self) -> Graph:
                         atoms.add(atom)
             atoms = list(atoms)
 
-            graph = build_atomic_graph(atoms, self.get_query_id(), self.max_edge_distance)
+            graph = build_atomic_graph(atoms, self.get_query_id(), self.max_edge_length)
 
         else:
             raise NotImplementedError(f"No function exists to build graphs with resolution of {self.resolution}.")
@@ -328,9 +328,9 @@ class ProteinProteinInterfaceQuery(Query):
             Note that this does not limit the structure to residues from these chains.
         pssm_paths (dict[str, str]): the name of the chain(s) (key) and path to the pssm file(s) (value).
         targets (dict[str, float]) = Name(s) (key) and target value(s) (value) associated with this query.
-        interaction_radius (float | None): all residues within this radius from the interacting interfaces
+        influence_radius (float | None): all residues within this radius from the interacting interface
             will be included in the graph, irrespective of the chain they are on.
-        max_edge_distance (float | None): the maximum distance between two nodes to generate an edge connecting them.
+        max_edge_length (float | None): the maximum distance between two nodes to generate an edge connecting them.
         suppress_pssm_errors (bool): Whether or not to suppress the error raised if the .pssm files do not
             match the .pdb files. If True, a warning is returned instead.
     """
@@ -360,17 +360,17 @@ def _build_helper(self) -> Graph:
         contact_atoms = get_contact_atoms(
             self.pdb_path,
             self.chain_ids,
-            self.interaction_radius
+            self.influence_radius
         )
         if len(contact_atoms) == 0:
             raise ValueError("no contact atoms found")
 
         # build the graph
         if self.resolution == 'atom':
-            graph = build_atomic_graph(contact_atoms, self.get_query_id(), self.max_edge_distance)
+            graph = build_atomic_graph(contact_atoms, self.get_query_id(), self.max_edge_length)
         elif self.resolution == 'residue':
             residues_selected = list({atom.residue for atom in contact_atoms})
-            graph = build_residue_graph(residues_selected, self.get_query_id(), self.max_edge_distance)
+            graph = build_residue_graph(residues_selected, self.get_query_id(), self.max_edge_length)
 
         graph.center = np.mean([atom.position for atom in contact_atoms], axis=0)
         structure = contact_atoms[0].residue.chain.model

deeprank2/utils/buildgraph.py

@@ -155,14 +155,14 @@ def get_structure(pdb, id_: str) -> PDBStructure:
 def get_contact_atoms( # pylint: disable=too-many-locals
     pdb_path: str,
     chain_ids: list[str],
-    interaction_radius: float
+    influence_radius: float
 ) -> list[Atom]:
     """Gets the contact atoms from pdb2sql and wraps them in python objects."""
 
     interface = get_interface(pdb_path)
     try:
         atom_indexes = interface.get_contact_atoms(
-            cutoff=interaction_radius,
+            cutoff=influence_radius,
             chain1=chain_ids[0],
             chain2=chain_ids[1],
         )
@@ -208,7 +208,7 @@ def get_residue_contact_pairs( # pylint: disable=too-many-locals
     structure: PDBStructure,
     chain_id1: str,
     chain_id2: str,
-    interaction_radius: float,
+    influence_radius: float,
 ) -> list[Pair]:
     """Find all residue pairs that may influence each other.
 
@@ -217,7 +217,7 @@ def get_residue_contact_pairs( # pylint: disable=too-many-locals
         structure (:class:`PDBStructure`): From which to take the residues.
         chain_id1 (str): First protein chain identifier.
         chain_id2 (str): Second protein chain identifier.
-        interaction_radius (float): Maximum distance between residues to consider them as interacting.
+        influence_radius (float): Maximum distance between residues to consider them as interacting.
 
     Returns:
         list[Pair]: The pairs of contacting residues.
@@ -227,7 +227,7 @@ def get_residue_contact_pairs( # pylint: disable=too-many-locals
     interface = get_interface(pdb_path)
     try:
         contact_residues = interface.get_contact_residues(
-            cutoff=interaction_radius,
+            cutoff=influence_radius,
             chain1=chain_id1,
             chain2=chain_id2,
             return_contact_pairs=True,

deeprank2/utils/graph.py

@@ -320,7 +320,7 @@ def get_all_chains(self) -> list[str]:
 
 
 def build_atomic_graph( # pylint: disable=too-many-locals
-    atoms: list[Atom], graph_id: str, max_edge_distance: float
+    atoms: list[Atom], graph_id: str, max_edge_length: float
 ) -> Graph:
     """Builds a graph, using the atoms as nodes.
 
@@ -332,7 +332,7 @@ def build_atomic_graph( # pylint: disable=too-many-locals
         positions[atom_index] = atom.position
 
     distances = distance_matrix(positions, positions, p=2)
-    neighbours = distances < max_edge_distance
+    neighbours = distances < max_edge_length
 
     graph = Graph(graph_id)
     for atom1_index, atom2_index in np.transpose(np.nonzero(neighbours)):
@@ -355,7 +355,7 @@ def build_atomic_graph( # pylint: disable=too-many-locals
 
 
 def build_residue_graph( # pylint: disable=too-many-locals
-    residues: list[Residue], graph_id: str, max_edge_distance: float
+    residues: list[Residue], graph_id: str, max_edge_length: float
 ) -> Graph:
     """Builds a graph, using the residues as nodes.
 
@@ -381,7 +381,7 @@ def build_residue_graph( # pylint: disable=too-many-locals
     distances = distance_matrix(positions, positions, p=2)
 
     # determine which atoms are close enough
-    neighbours = distances < max_edge_distance
+    neighbours = distances < max_edge_length
 
     atom_index_pairs = np.transpose(np.nonzero(neighbours))
 

tests/data/hdf5/_generate_testdata.ipynb

@@ -102,8 +102,8 @@
     "models_folder_name = 'exp_nmers_all_HLA_quantitative'\n",
     "data = 'pMHCI'\n",
     "resolution = 'residue' # either 'residue' or 'atom'\n",
-    "interaction_radius = 15 # max distance in Å between two interacting residues/atoms of two proteins\n",
-    "max_edge_distance = 15 # max distance in Å between to create an edge\n",
+    "influence_radius = 15 # max distance in Å between two interacting residues/atoms of two proteins\n",
+    "max_edge_length = 15 # max distance in Å between to create an edge\n",
     "\n",
     "csv_file_path = f'{project_folder}data/external/processed/I/{csv_file_name}'\n",
     "models_folder_path = f'{project_folder}data/{data}/features_input_folder/{models_folder_name}'\n",
@@ -131,8 +131,8 @@
     "            pdb_path = pdb_files[i],\n",
     "            resolution = \"residue\",\n",
     "            chain_ids = [\"M\", \"P\"],\n",
-    "            interaction_radius = interaction_radius,\n",
-    "            max_edge_distance = max_edge_distance,\n",
+    "            influence_radius = influence_radius,\n",
+    "            max_edge_length = max_edge_length,\n",
     "            targets = {\n",
     "                'binary': int(float(bas[i]) <= 500), # binary target value\n",
     "                'BA': bas[i], # continuous target value\n",

tests/features/__init__.py

@@ -26,8 +26,8 @@ def _get_residue(chain: Chain, number: int) -> Residue:
 def build_testgraph( # pylint: disable=too-many-locals, too-many-arguments # noqa:MC0001
     pdb_path: str,
     detail: Literal['atomic', 'residue'],
-    interaction_radius: float,
-    max_edge_distance: float,
+    influence_radius: float,
+    max_edge_length: float,
     central_res: int | None = None,
     variant: AminoAcid |None = None,
     chain_ids: str | tuple[str, str] | None = None,
@@ -38,8 +38,8 @@ def build_testgraph( # pylint: disable=too-many-locals, too-many-arguments # noq
     Args:
         pdb_path (str): Path of pdb file.
         detail (Literal['atomic', 'residue']): Level of detail.
-        interaction_radius (float): max distance to include in graph.
-        max_edge_distance (float): max distance to create an edge.
+        influence_radius (float): max distance to include in graph.
+        max_edge_length (float): max distance to create an edge.
         central_res (int | None, optional): Residue to center a single-chain graph around.
             Use None to create a 2-chain graph, or any value for a single-chain graph
             Defaults to None.
@@ -71,7 +71,7 @@ def build_testgraph( # pylint: disable=too-many-locals, too-many-arguments # noq
         for residue1, residue2 in get_residue_contact_pairs(
             pdb_path, structure,
             chains[0], chains[1],
-            interaction_radius
+            influence_radius
         ):
             if detail == 'residue':
                 nodes.add(residue1)
@@ -84,9 +84,9 @@ def build_testgraph( # pylint: disable=too-many-locals, too-many-arguments # noq
                     nodes.add(atom)
 
         if detail == 'residue':
-            return build_residue_graph(list(nodes), structure.id, max_edge_distance), None
+            return build_residue_graph(list(nodes), structure.id, max_edge_length), None
         if detail == 'atom':
-            return build_atomic_graph(list(nodes), structure.id, max_edge_distance), None
+            return build_atomic_graph(list(nodes), structure.id, max_edge_length), None
         raise TypeError('detail must be "atom" or "residue"')
 
     else:
@@ -95,7 +95,7 @@ def build_testgraph( # pylint: disable=too-many-locals, too-many-arguments # noq
         else:
             chain = structure.get_chain(chain_ids)
         residue = _get_residue(chain, central_res)
-        surrounding_residues = list(get_surrounding_residues(structure, residue, interaction_radius))
+        surrounding_residues = list(get_surrounding_residues(structure, residue, influence_radius))
 
         try:
             with open(f"tests/data/pssm/{structure.id}/{structure.id}.{chain.id}.pdb.pssm", "rt", encoding="utf-8") as f:
@@ -104,8 +104,8 @@ def build_testgraph( # pylint: disable=too-many-locals, too-many-arguments # noq
             pass
 
         if detail == 'residue':
-            return build_residue_graph(surrounding_residues, structure.id, max_edge_distance), SingleResidueVariant(residue, variant)
+            return build_residue_graph(surrounding_residues, structure.id, max_edge_length), SingleResidueVariant(residue, variant)
         if detail == 'atom':
             atoms = set(atom for residue in surrounding_residues for atom in residue.atoms)
-            return build_atomic_graph(list(atoms), structure.id, max_edge_distance), SingleResidueVariant(residue, variant)
+            return build_atomic_graph(list(atoms), structure.id, max_edge_length), SingleResidueVariant(residue, variant)
         raise TypeError('detail must be "atom" or "residue"')

tests/features/test_components.py

@@ -12,8 +12,8 @@ def test_atom_features():
     graph, _ = build_testgraph(
         pdb_path=pdb_path,
         detail='atom',
-        interaction_radius=10,
-        max_edge_distance=10,
+        influence_radius=10,
+        max_edge_length=10,
         central_res=25,
     )
     add_features(pdb_path, graph)
@@ -26,8 +26,8 @@ def test_aminoacid_features():
     graph, variant = build_testgraph(
         pdb_path=pdb_path,
         detail='residue',
-        interaction_radius=10,
-        max_edge_distance=10,
+        influence_radius=10,
+        max_edge_length=10,
         central_res=25,
         variant=serine,
     )

tests/features/test_conservation.py

@@ -13,8 +13,8 @@ def test_conservation_residue():
     graph, variant = build_testgraph(
         pdb_path=pdb_path,
         detail='residue',
-        interaction_radius=10,
-        max_edge_distance=10,
+        influence_radius=10,
+        max_edge_length=10,
         central_res=25,
         variant=alanine,
     )
@@ -34,8 +34,8 @@ def test_conservation_atom():
     graph, variant = build_testgraph(
         pdb_path=pdb_path,
         detail='atom',
-        interaction_radius=10,
-        max_edge_distance=10,
+        influence_radius=10,
+        max_edge_length=10,
         central_res=25,
         variant=alanine,
     )
@@ -55,8 +55,8 @@ def test_no_pssm_file_error():
     graph, variant = build_testgraph(
         pdb_path=pdb_path,
         detail='residue',
-        interaction_radius=10,
-        max_edge_distance=10,
+        influence_radius=10,
+        max_edge_length=10,
         central_res=17,
         variant=alanine,
     )

tests/features/test_exposure.py

@@ -22,8 +22,8 @@ def test_exposure_residue():
     graph, _ = build_testgraph(
         pdb_path=pdb_path,
         detail='residue',
-        interaction_radius=8.5,
-        max_edge_distance=8.5,
+        influence_radius=8.5,
+        max_edge_length=8.5,
     )
     add_features(pdb_path, graph)
     _run_assertions(graph)
@@ -34,8 +34,8 @@ def test_exposure_atom():
     graph, _ = build_testgraph(
         pdb_path=pdb_path,
         detail='atom',
-        interaction_radius=4.5,
-        max_edge_distance=4.5,
+        influence_radius=4.5,
+        max_edge_length=4.5,
     )
     add_features(pdb_path, graph)
     _run_assertions(graph)

tests/features/test_irc.py

@@ -28,8 +28,8 @@ def test_irc_residue():
     graph, _ = build_testgraph(
         pdb_path=pdb_path,
         detail='residue',
-        interaction_radius=8.5,
-        max_edge_distance=8.5,
+        influence_radius=8.5,
+        max_edge_length=8.5,
     )
     add_features(pdb_path, graph)
     _run_assertions(graph)
@@ -40,8 +40,8 @@ def test_irc_atom():
     graph, _ = build_testgraph(
         pdb_path=pdb_path,
         detail='residue',
-        interaction_radius=4.5,
-        max_edge_distance=4.5,
+        influence_radius=4.5,
+        max_edge_length=4.5,
     )
     add_features(pdb_path, graph)
     _run_assertions(graph)

tests/features/test_secondary_structure.py

@@ -14,8 +14,8 @@ def test_secondary_structure_residue():
     graph, _ = build_testgraph(
         pdb_path=pdb_path,
         detail='residue',
-        interaction_radius=10,
-        max_edge_distance=10,
+        influence_radius=10,
+        max_edge_length=10,
     )
     add_features(pdb_path, graph)
 
@@ -61,8 +61,8 @@ def test_secondary_structure_atom():
     graph, _ = build_testgraph(
         pdb_path=pdb_path,
         detail='atom',
-        interaction_radius=4.5,
-        max_edge_distance=4.5,
+        influence_radius=4.5,
+        max_edge_length=4.5,
     )
     add_features(pdb_path, graph)