dcatoolkit 0.1.6__tar.gz → 0.1.8__tar.gz

{dcatoolkit-0.1.6/src/dcatoolkit.egg-info → dcatoolkit-0.1.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dcatoolkit
-Version: 0.1.6
+Version: 0.1.8
 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-0.1.6 → dcatoolkit-0.1.8}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "dcatoolkit"
-version = "0.1.6"
+version = "0.1.8"
 description = "Collection of useful modules and representations for managing DCA output data."
 keywords = ["dca", "toolkit", "DI", "coevolution"]
 

{dcatoolkit-0.1.6 → dcatoolkit-0.1.8}/src/dcatoolkit/__init__.py

@@ -1,4 +1,4 @@
 
-__version__ = "0.1.6"
+__version__ = "0.1.8"
 from .representation import Pairs, DirectInformationData, StructureInformation, ResidueAlignment
 from .analytics import MSATools

{dcatoolkit-0.1.6 → dcatoolkit-0.1.8}/src/dcatoolkit/analytics.py

@@ -1,7 +1,7 @@
 import re
 from collections import Counter
-from typing import Optional
-import string
+from typing import Optional, Union
+import string, io
 
 class MSATools:
     """
@@ -16,23 +16,31 @@ class MSATools:
         self.MSA = MSA
     
     @staticmethod
-    def load_from_file(msa_filepath: str) -> 'MSATools':
+    def load_from_file(msa_source: Union[str, io.IOBase]) -> 'MSATools':
         """
         Generates MSATools object from an MSA file in ".afa" format.
 
         Parameters
         ----------
-        msa_filepath : str
-            Filepath of the MSA in ".afa" format that is provided.
+        msa_source : str or io.IOBase
+            Filepath or IOBase of the MSA in ".afa" format that is provided.
         
         Returns
         -------
         MSATools
             An MSATools instance with the appropriate list of (header, sequence) tuples where sequences are simplified and converted to single line format.
         """
+        data = ""
         msa_entries: list[tuple[str, str]] = []
-        with open(msa_filepath, 'r') as fs:
-            data = fs.read()
+        if isinstance(msa_source, str):
+            with open(msa_source, 'r') as fs:
+                data = fs.read()
+        elif isinstance(msa_source, io.BytesIO):
+            data = msa_source.getvalue().decode()
+        elif isinstance(msa_source, io.StringIO):
+            data = msa_source.getvalue()
+        else:
+            raise Exception("msa_file is not bytesIO, stringIO, or a filepath.")
         split_data = data.split(">")[1:]
         for entry in split_data:
             line_split_entry = entry.split("\n")
@@ -113,25 +121,32 @@ class MSATools:
                     kept_entries.append((header, sequence))
         return kept_entries
 
-    def write(self, filepath: str) -> None:
+    def write(self, destination: Union[str, io.IOBase]) -> None:
         """
-        Writes this MSA's headers and sequences to the filepath specified.
+        Writes this MSA's headers and sequences to the destination specified.
         
         Parameters
         ----------
-        filepath : str
-            Filepath to write the MSA supplied to.
+        destination : str or io.IOBase
+            Filepath or IO to write the MSA supplied to.
 
         Returns
         -------
         None
         """
-        with open(filepath, 'w') as fs:
+        if isinstance(destination, str):
+            with open(destination, 'w') as fs:
+                for header, sequence in self.MSA:
+                    fs.write(header)
+                    fs.write("\n")
+                    fs.write(sequence)
+                    fs.write("\n")
+        elif isinstance(destination, io.IOBase):
             for header, sequence in self.MSA:
-                fs.write(header)
-                fs.write("\n")
-                fs.write(sequence)
-                fs.write("\n")
+                destination.write(header)
+                destination.write("\n")
+                destination.write(sequence)
+                destination.write("\n")
 
     def __len__(self):
         """

{dcatoolkit-0.1.6 → dcatoolkit-0.1.8}/src/dcatoolkit/representation.py

@@ -641,7 +641,9 @@ class StructureInformation:
     self.unique_chains : numpy.ndarray, optional
         Array of unique asym_id entries which corresponds to unique chain IDs.
     self.chain_auth_dict : dict of str, str, optional
-        Uses chain id as a key and provides auth chain id as a value. 
+        Uses chain id as a key and provides auth chain id as a value.
+    self.auth_chain_dict : dict of str, str, optional
+        Uses auth chain id as a key and provides original/label chain id as a value. 
     self.res_auth_dict : dict of str, tuple of int, int or optional 
         Uses chain id as a key and an array of residue index and auth residue index as a value.
     """
@@ -670,6 +672,7 @@ class StructureInformation:
             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 = {}
             if self.atom_site_category:
                 group_pdbs = []
@@ -700,6 +703,7 @@ class StructureInformation:
                 for unique_chain in self.unique_chains:
                     unique_entry = self.atom_data[self.atom_data[:,2] == unique_chain][0]
                     self.chain_auth_dict[unique_entry[2]] = unique_entry[4]
+                    self.auth_chain_dict[unique_entry[4]] = unique_entry[2]
                     self.res_auth_dict[unique_entry[2]] = unique_entry[[1,3]].astype('int')
         else:
             self.atom_site_category = None
@@ -775,7 +779,6 @@ class StructureInformation:
         else:
             return str(self.full_sequences[self.chain_auth_dict[chain_id]])
         
-    
     def get_non_missing_sequence(self, chain_id: str, auth_chain_id_supplied: bool=False) -> str:
         """
         Get sequence, including only non-missing residues, from the specified chain off of RCSB.
@@ -793,15 +796,10 @@ class StructureInformation:
             The full sequence, including only non-missing residues, of the chain specified.
         """
         if auth_chain_id_supplied:
-            original_chain_id = None
-            for key in self.chain_auth_dict.keys():
-                if self.chain_auth_dict[key] == chain_id:
-                    original_chain_id = key
-            if original_chain_id is None:
-                raise Exception("Auth chain id supplied not found in chain_auth_dict.")
-            else:
-                return self.non_missing_sequences[original_chain_id]
-        return self.non_missing_sequences[chain_id]
+            original_chain_id = self.auth_chain_dict[chain_id]
+            return self.non_missing_sequences[original_chain_id]
+        else:
+            return self.non_missing_sequences[chain_id]
         
     def get_chain_specific_structure(self, ca_only: bool, chain1: str, chain2: str, remove_hetero=True) -> tuple:
         """

{dcatoolkit-0.1.6 → dcatoolkit-0.1.8/src/dcatoolkit.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dcatoolkit
-Version: 0.1.6
+Version: 0.1.8
 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>