dcatoolkit 0.2.0__tar.gz → 0.2.2__tar.gz

{dcatoolkit-0.2.0/src/dcatoolkit.egg-info → dcatoolkit-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: dcatoolkit
-Version: 0.2.0
+Version: 0.2.2
 Summary: Collection of useful modules and representations for managing DCA output data.
 Author-email: Raheel Syed Ahmed <raheelsyedahmed@gmail.com>
 Maintainer-email: Raheel Syed Ahmed <raheelsyedahmed@gmail.com>

{dcatoolkit-0.2.0 → dcatoolkit-0.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "dcatoolkit"
-version = "0.2.0"
+version = "0.2.2"
 description = "Collection of useful modules and representations for managing DCA output data."
 keywords = ["dca", "toolkit", "DI", "coevolution"]
 

{dcatoolkit-0.2.0 → dcatoolkit-0.2.2}/src/dcatoolkit/__init__.py

@@ -1,5 +1,5 @@
 
-__version__ = "0.1.9"
+__version__ = "0.2.2"
 from .representation import Pairs, DirectInformationData, StructureInformation, ResidueAlignment, MMCIFInformation, PDBInformation
 from .analytics import MSATools
 

{dcatoolkit-0.2.0 → dcatoolkit-0.2.2}/src/dcatoolkit/representation.py

@@ -546,7 +546,7 @@ class DirectInformationData:
         return results
 
     @staticmethod
-    def get_dist_commands(model1: str | int, model2: str | int, chain1: str, chain2: str, pairs: npt.NDArray, ca_only: bool=True, auth_res_ids=False) -> list[str]:
+    def get_dist_commands(model1: str | int, model2: str | int, chain1: str, chain2: str, pairs: npt.NDArray, ca_only: bool=True, auth_res_ids: bool=False) -> list[str]:
         """
         Get UCSF Chimera commands for displaying distance commands for usage in displaying distances between residue pairs. Options are present for alpha-carbon to alpha-carbon distance or for specified atom to specified atom distance.
         
@@ -624,7 +624,7 @@ class StructureInformation:
     """
     @overload
     @staticmethod
-    def fetch_pdb(pdb_id: str, struc_format: Literal["mmcif"]="mmcif", model_num: int=1) -> 'MMCIFInformation':
+    def fetch_pdb(pdb_id: str, struc_format: Literal["mmcif"], model_num: int=1) -> 'MMCIFInformation':
         ...
 
     @overload
@@ -787,32 +787,15 @@ class MMCIFInformation(StructureInformation):
         if len(self.pdbx_file.keys()) > 0:
             self.first_block = list(self.pdbx_file)[0]
             self.atom_site_category = self.pdbx_file[self.first_block].get('atom_site')
-            self.chain_auth_dict = {}
-            self.auth_chain_dict = {}
-            self.res_auth_dict = {}
+            self.chain_auth_dict: dict[str, str] = {}
+            self.auth_chain_dict: dict[str, str] = {}
+            self.res_auth_dict: dict[str, tuple[int, int]] = {}
+            
             if self.atom_site_category:
-                group_pdbs = []
-                seq_ids = []
-                asym_ids = []
-                auth_seq_ids = []
-                auth_asym_ids = []
-                model_nums = []
-                for col_name, col in self.atom_site_category.items():
-                    if col_name == 'group_PDB':
-                        group_pdbs = col.as_array()
-                    elif col_name == 'label_seq_id':
-                        seq_ids = col.as_array()
-                    elif col_name == 'label_asym_id':
-                        asym_ids = col.as_array()
-                    elif col_name == 'auth_seq_id':
-                        auth_seq_ids = col.as_array()
-                    elif col_name == 'auth_asym_id':
-                        auth_asym_ids = col.as_array()
-                    elif col_name == 'pdbx_PDB_model_num':
-                        model_nums = col.as_array()
-
-                atom_site_data = np.unique(np.column_stack((group_pdbs, seq_ids, asym_ids, auth_seq_ids, auth_asym_ids, model_nums)), axis=0)
-                atom_site_data = atom_site_data[atom_site_data[:,5] == str(self.model_num)]
+                categories = ['group_PDB', 'label_seq_id', 'label_asym_id', 'auth_seq_id', 'auth_asym_id', 'pdbx_PDB_model_num']
+                atom_site_data = np.column_stack([self.atom_site_category[category].as_array() for category in categories])
+                _, idx = np.unique(atom_site_data, axis=0, return_index=True)
+                atom_site_data = atom_site_data[np.sort(idx)]
                 self.atom_data = atom_site_data[atom_site_data[:,0] == "ATOM"]
                 self.het_atom_data = atom_site_data[atom_site_data[:,0] == "HETATM"]
                 self.unique_chains = np.unique(self.atom_data[:,2])
@@ -824,6 +807,31 @@ class MMCIFInformation(StructureInformation):
         else:
             self.atom_site_category = None
     
+    def get_start_res_id(self, chain_id: str, auth_res_ids: bool=False, auth_chain_id_supplied: bool=False) -> int:
+        """
+        Gets starting residue id of the specified chain excluding heteroatom group entries.
+
+        Parameters
+        ----------
+        chain_id : str
+            The chain id supplied and selected for from the structure.
+        auth_res_ids : bool
+            True if you want alt_ids for residues indices, False if cif residue indexing is needed.
+        auth_chain_id_supplied : bool
+            If True, the chain_id supplied is the auth chain id found on the RCSB website.            
+
+        Returns
+        -------
+        int
+            The residue id of the first atom in the chain provided.
+        """
+        if auth_chain_id_supplied:
+            chain_id = self.auth_chain_dict[chain_id]
+        if auth_res_ids:
+            return self.res_auth_dict[chain_id][1]
+        else:
+            return self.res_auth_dict[chain_id][0]
+
     def get_full_sequence(self, chain_id: str, auth_chain_id_supplied: bool=False) -> str:
         """
         Get full sequence, including missing residues, from the specified chain off of RCSB.
@@ -1067,6 +1075,26 @@ class PDBInformation(StructureInformation):
         self.non_missing_sequences = {str(chain): str(sequence) for (chain, sequence) in list(zip(struc.get_chains(non_hetero_structure), struc.to_sequence(non_hetero_structure)[0]))}
         self.unique_chains = struc.get_chains(non_hetero_structure)
 
+    def get_start_res_id(self, chain_id: str) -> int:
+        """
+        Gets starting residue id of the specified chain excluding heteroatom group entries.
+
+        Parameters
+        ----------
+        chain_id : str
+            The chain id supplied and selected for from the structure.
+
+        Returns
+        -------
+        int
+            The residue id of the first atom in the chain provided.
+        """
+        non_hetero_structure = self.structure[self.structure.hetero == False]
+        if chain_id in self.unique_chains:
+            return non_hetero_structure[non_hetero_structure.chain_id == chain_id][0].res_id
+        else:
+            raise ValueError("Chain supplied not found in structure.")
+
     def get_non_missing_sequence(self, chain_id: str) -> str:
         """
         Get sequence, including only non-missing residues, from the specified chain.
@@ -1159,6 +1187,8 @@ class PDBInformation(StructureInformation):
         if chain1 in self.unique_chains and chain2 in self.unique_chains:
             shift1 = non_hetero_structure[non_hetero_structure.chain_id == chain1][0].res_id - 1
             shift2 = non_hetero_structure[non_hetero_structure.chain_id == chain2][0].res_id - 1
+            shift1 *= -1
+            shift2 *= -1
             return shift1, shift2
         else:
             return shift1, shift2
@@ -1195,8 +1225,8 @@ class PDBInformation(StructureInformation):
             ind = np.unravel_index(np.argmin(dist_matrix), dist_matrix.shape)
             # Use the indices to access the atom in the atom array and get the correct atom name.
             # Generate the auth ids of the residues in the pairs ndarray
-            orig_res_id1 = row['residue1'] - shift1
-            orig_res_id2 = row['residue2'] - shift2
+            orig_res_id1 = row['residue1'] + shift1
+            orig_res_id2 = row['residue2'] + shift2
             min_dist_pairs_atoms.append((orig_res_id1, orig_res_id2, row['residue1'], row['residue2'], chain1_res1_structure[ind[0]].atom_name, chain2_res2_structure[ind[1]].atom_name))
         min_dist_pairs_atoms_arr = np.array(min_dist_pairs_atoms, dtype={'names': ['residue1','residue2','auth_residue1','auth_residue2','atom_name1','atom_name2'], 'formats': [int,int,int,int,'<U10','<U10']})
         return min_dist_pairs_atoms_arr    
@@ -1235,7 +1265,7 @@ class PDBInformation(StructureInformation):
             if not(chain1==chain2 and res1 >= res2):
                 if not auth_contacts:
                     shift1, shift2 = self.get_shift_values(chain1, chain2)
-                    contacts_set.add((res1 - shift1, res2 - shift2))
+                    contacts_set.add((res1 + shift1, res2 + shift2))
                 else:
                     contacts_set.add((res1, res2))
         return contacts_set

{dcatoolkit-0.2.0 → dcatoolkit-0.2.2/src/dcatoolkit.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: dcatoolkit
-Version: 0.2.0
+Version: 0.2.2
 Summary: Collection of useful modules and representations for managing DCA output data.
 Author-email: Raheel Syed Ahmed <raheelsyedahmed@gmail.com>
 Maintainer-email: Raheel Syed Ahmed <raheelsyedahmed@gmail.com>

{dcatoolkit-0.2.0 → dcatoolkit-0.2.2}/tests/test_contacts.py

@@ -59,9 +59,9 @@ def check_contacts(test_CA: bool, threshold: float):
         
         cif_file_contacts = read_contacts(corresponding_file)
         chain1, auth_chain1, chain2, auth_chain2 = pdb_id_chain_map[pdb_id]
-        fetch_cif_contacts = {(int(x[0]), int(x[1])) for x in MMCIFInformation.fetch_pdb(pdb_id).get_contacts(test_CA, threshold, chain1, chain2, auth_contacts=True)}
+        fetch_cif_contacts = {(int(x[0]), int(x[1])) for x in MMCIFInformation.fetch_pdb(pdb_id, 'mmcif').get_contacts(test_CA, threshold, chain1, chain2, auth_contacts=True)}
         read_cif_contacts = {(int(x[0]), int(x[1])) for x in MMCIFInformation.read_mmCIF_file(str(cif_file)).get_contacts(test_CA, threshold, chain1, chain2, auth_contacts=True)}
-        fetch_authchain_cif_contacts = {(int(x[0]), int(x[1])) for x in MMCIFInformation.fetch_pdb(pdb_id).get_contacts(test_CA, threshold, auth_chain1, auth_chain2, auth_contacts=True, auth_chain_id_supplied=True)}
+        fetch_authchain_cif_contacts = {(int(x[0]), int(x[1])) for x in MMCIFInformation.fetch_pdb(pdb_id, 'mmcif').get_contacts(test_CA, threshold, auth_chain1, auth_chain2, auth_contacts=True, auth_chain_id_supplied=True)}
         read_authchain_cif_contacts = {(int(x[0]), int(x[1])) for x in MMCIFInformation.read_mmCIF_file(str(cif_file)).get_contacts(test_CA, threshold, auth_chain1, auth_chain2, auth_contacts=True, auth_chain_id_supplied=True)}
         fetch_pdb_contacts = {(int(x[0]), int(x[1])) for x in PDBInformation.fetch_pdb(pdb_id, struc_format="pdb").get_contacts(test_CA, threshold, auth_chain1, auth_chain2, auth_contacts=True)}
         read_pdb_contacts = {(int(x[0]), int(x[1])) for x in PDBInformation.read_pdb_file(f"tests/pdb_info/{pdb_id.lower()}.pdb").get_contacts(test_CA, threshold, auth_chain1, auth_chain2, auth_contacts=True)}